Article
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Aim of the presented research is the development of a cognitive driver assistance system, which can capture the traffic situation, analyse it, and warn the driver in case a pedestrian is a potential hazard. Hence parameters have to be identified by which the intention of the pedestrian can be unambiguously predicted. Two approaches to the topic are addressed. First, the pedestrian’s perspective was taken. The question was how crossing decisions were influenced by the parameters distance and velocity of the car. Following a signal, participants had to choose to cross the road in front of or behind the car. The data analysis showed that pedestrians relied on the distance of the car rather than the time to collision for their decision. In the second experiment the observer’s perspective raised the question what parameters humans use to predict pedestrians’ intentions. Videos of natural traffic scenes were presented. Participants had to make statements about whether the shown pedestrian would cross the street during the next moment. In a baseline and four experimental conditions, certain information was masked in the videos. Just the condition in which only the trajectory information of the pedestrian was available produced a higher error rate.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Not only does it affect pedestrians, but also it affects drivers. Schmidt and Färber 2009 suggested that drivers driving at high speed will tend to receive more dangerous crossings from pedestrians, potentially resulting in more accidents. However, few studies have studied the potential decision-making mechanism of this unsafe crossing behaviour specifically. ...
... These can be roughly categorised as external and internal attributes. External attributes which may affect pedestrian gap acceptance behaviour include vehicle speed (Schmidt and Färber, 2009), time to arrival (TTA) (Avinash et al., 2019;Pawar and Patil, 2016), distance (Lobjois and Cavallo, 2007;Schmidt and Färber, 2009), number of lanes (Chandra et al., 2014), and vehicle size (Beggiato et al., 2017;Lee and Sheppard, 2017). Internal attributes which may have an impact include gender, age (Hulse et al., 2018;Kalatian and Farooq, 2021) and group size (Pawar and Patil, 2015;Avinash et al., 2019). ...
... These can be roughly categorised as external and internal attributes. External attributes which may affect pedestrian gap acceptance behaviour include vehicle speed (Schmidt and Färber, 2009), time to arrival (TTA) (Avinash et al., 2019;Pawar and Patil, 2016), distance (Lobjois and Cavallo, 2007;Schmidt and Färber, 2009), number of lanes (Chandra et al., 2014), and vehicle size (Beggiato et al., 2017;Lee and Sheppard, 2017). Internal attributes which may have an impact include gender, age (Hulse et al., 2018;Kalatian and Farooq, 2021) and group size (Pawar and Patil, 2015;Avinash et al., 2019). ...
Article
Full-text available
Accidents involving pedestrians are particularly common at unsignalised intersections and mid-block crosswalks, where vehicles often do not yield to them. Analysing and understanding pedestrian crossing behaviour at such locations is vital for improving road safety. Previous studies have repeatedly shown that pedestrians tend to accept smaller time gaps in conditions with higher vehicle speeds and thus potentially less safe. This has prompted the hypothesis that pedestrians rely on spatial distance to make crossing decisions. However, few studies have investigated the mechanism underpinning this phenomenon. We propose a novel approach to characterise pedestrian crossing behaviour: a psychophysics-based gap acceptance (PGA) model based on visual looming cues and binary choice logit method. Road crossing data collected in a simulated experiment were used to analyse pedestrian behaviour and test the model. Our analysis indicates that, in line with previous studies, higher vehicle speed increased the tendency of gap acceptance, leading to a higher rate of unsafe crossings. Crucially, the PGA model could accurately account for these crossing decisions across experimental scenarios, more parsimoniously than a conventional model. These results explain the speed-induced unsafe behaviour by suggesting that pedestrians apply visual looming, which depends on vehicle speed and distance, to make crossing decisions. This study reinforces the notion that for two vehicles with the same time gap, the one with higher speed can elicit more risky crossing behaviour from pedestrians, potentially resulting in more severe accidents. The practical implications of the results for traffic safety management, modelling and development of automated vehicles are discussed.
... To the best of our knowledge, there are no comparative studies to date between Japan and Germany that systematically examine pedestrians' subjective risk perception. In different studies, it was reported that Japanese pedestrians [44] require a longer time-gap (16s) to consider a crossing safe compared to German pedestrians (5-6s) [10], [56] These findings are consistent with the higher risk aversion in Japan and correspond to the gap acceptance (see section IV-C). The frequency and duration of uncertainty behavior (freezing, abandoning, accelerating) during crossing at red is also more pronounced in Japan compared to France (10%, 1.5s vs. 5%, 1.22s) [57]. ...
... To decide whether a gap in traffic to the next car is large enough to cross the street safely, distance and velocity cues can be used. Slower vehicles can increase the time gap due to their larger distance [56], [59]. In addition, there are indications that with reduced cognitive resources (e.g. ...
... In Japan, female pedestrians required larger gaps (19s) compared to male pedestrians (11s) [44]. In Germany, different studies show that pedestrians require a time gap of 5-6s to decide for a safe crossing, both in a real environment [10], [56], as well as in a simulated environment [59] with a speed limit of 50 km/h. ...
Conference Paper
The prediction of pedestrian behavior remains a major objective for the development of autonomous vehicles. Pedestrians do not merely represent the most vulnerable traffic participants, but are also a challenge in the prediction process, since their behavior entails a large number of options for possible paths, velocities, and motions. In addition, autonomous vehicles should be able to operate safely in different countries, and thus the incorporation of cultural differences in the training and evaluation of the relevant AI systems is required. This paper provides the first review of Japanese and German pedestrians’ behavior in urban traffic. In particular, cultural behavior differences of pedestrians in risk avoidance, compliance, gap acceptance, and walking velocity together with different environmental factors like pedestrian facilities in both countries are addressed.
... A number of behavioral studies analyze the human ability of predicting the intentions or actions of others and what factors guide these decisions. The majority of studies are conducted in a lab setting where participants view naturalistic videos of pedestrians [16], [17], [10] or bicyclists [18] and predict their future actions from a set of predefined answers. Some experiments are also conducted under realistic driving conditions. ...
... The results of human experiments confirm that people are good at predicting future behaviors of pedestrians and cyclists, selecting the correct answer in 75-90% of cases which is significantly above chance [16], [18], [10]. It has been shown that prediction accuracy improves when videos are terminated closer to the decision point [18] and when drivers have a longer time to analyze the scene [10]. ...
... In addition to evaluating prediction accuracy, some studies also required participants to provide the reasoning behind their decisions. Named among important predictors for the next action was pedestrian's body language (e.g. head orientation, leg position, etc.) [16], gaze and reaction to the driver's actions [19]. This agrees with the fact that pedestrians report looking for eye contact with the driver and vehicle speed reduction [19], [20]. ...
... These can be roughly categorized as external and internal attributes. External attributes which may affect pedestrians' gap acceptance behaviour include vehicle speed (Schmidt and Färber, 2009), time to arrival (TTA) (Velasco et al., 2019), distance (Lobjois and Cavallo, 2007;Schmidt and Färber, 2009), lane quantity (Chandra et al., 2014), and vehicle size (Beggiato et al., 2017;Lee and Sheppard, 2017;Petzoldt, 2016). Internal attributes which may have an impact include gender, age (Hulse et al., 2018;Kalatian and Farooq, 2021), culture (Lee et al., 2020b) and group size (Pawar and Patil, 2015;Wang et al., 2010). ...
... These can be roughly categorized as external and internal attributes. External attributes which may affect pedestrians' gap acceptance behaviour include vehicle speed (Schmidt and Färber, 2009), time to arrival (TTA) (Velasco et al., 2019), distance (Lobjois and Cavallo, 2007;Schmidt and Färber, 2009), lane quantity (Chandra et al., 2014), and vehicle size (Beggiato et al., 2017;Lee and Sheppard, 2017;Petzoldt, 2016). Internal attributes which may have an impact include gender, age (Hulse et al., 2018;Kalatian and Farooq, 2021), culture (Lee et al., 2020b) and group size (Pawar and Patil, 2015;Wang et al., 2010). ...
... However, previous studies have repeatedly shown that higher vehicle speeds can affect pedestrians, causing them to make risky decisions. Under constant time gaps, pedestrians tend to accept a smaller time gap for higher vehicle speed conditions (Beggiato et al., 2017;Lobjois and Cavallo, 2007;Oxley et al., 2005;Petzoldt, 2016;Schmidt and Färber, 2009). This risky behaviour also manifested as a greater proportion of pedestrians crossing the road, under the same time gap condition, when a vehicle is approaching at a higher speed, which means that drivers who travel at high speeds tend to receive more pedestrian crossing responses (Schmidt and Färber, 2009). ...
... However, it should be noted that conflicts or sudden 11 motions of pedestrians often occur in an unusual context. In 12 [20], a random walk model was utilized to predict the future 13 trajectory of a pedestrian, while [21] predicted the trajectory 14 by matching the obtained motion cues from the vision sensor 15 with previously learned trajectories. It is noteworthy that 16 these previous studies into the prediction of future motion 17 states usually relied on currently recognized sensor infor-18 mation, and did not use motion cues for prediction. ...
... 18 Furthermore, for the acquisition of motion cues, three 19 physical measuring points were defined. First, the stride 12 Based on the discussion in the previous section, we propose 13 a prediction model to infer the steady-state walking speed 14 using the motion cues obtained during the first gait cycle 15 after heel-off. In the prediction model, stride length, leg 16 velocity, and upper-body inclination were used as the inputs. ...
... in Section IV were obtained through the harmonization of 10 statistical and empirical methods. The core of input fuzzy 11 set for stride length and leg velocity was set to the mean 12 value of each linguistic level as presented in Table 4, and 13 the support of them was fixed to the core of adjacent fuzzy 14 set as depicted in Fig. 5(a) and 5(b). Moreover, the core 15 of two input fuzzy sets for upper-body inclination was set 16 to the values of the first and third level, and the support Table 5. ...
Article
Full-text available
As the motion of pedestrians is largely unpredictable, situational awareness presents a challenge for safe autonomous driving in urban areas. In particular, conventional sensor information about the dynamic states involved in determining and predicting pedestrian motion, including the walking speed, is significantly affected by latency when pedestrians suddenly increase their pace. In this paper, we propose a framework for predicting the steady-state walking speed of sudden pedestrian movement at the early stage of walking after heel-off. Based on the analysis that some motion cues during gait initiation are related to the steady-state walking speed, a fuzzy inference framework for predicting the steady-state walking speed, where the related motion cues are input to the inference model, is developed. The proposed framework can accurately predict the steady-state walking speed, even at the end of the first gait cycle. Moreover, the future trajectory of the pedestrian can be predicted using the piecewise linear speed model. Using the proposed framework, installed on the edge server of the cooperative-intelligent transportation system (C-ITS), this study aims to ensure the safety of autonomous vehicles by enabling them to successfully navigate the danger caused by sudden pedestrian movement. Experimental results obtained from testing the system at a real urban intersection verify the value offered by the proposed framework.
... In general, the time-to-collision (TTC) value is a key indicator [9]. A typical limit is a TTC value of less than 3 s, which makes it unlikely for pedestrians to attempt a crossing [10]. While this property is often used to model pedestrian behaviour, it is necessary to also consider the social aspects of AD. ...
... B. Pedestrian Models 1) Level-1: To resemble a basic but rational human crossing behavior [10], we define a pedestrian policy which evaluates the TTC value at each time step t according to ...
... See Section III-B.2 for a description of these components. The AV's action space U AV is equivalent to (10). Similar to (8), the AV's reward function R AV with reward r AV t+1 is described by ...
Preprint
Full-text available
Reliable pedestrian crash avoidance mitigation (PCAM) systems are crucial components of safe autonomous vehicles (AVs). The nature of the vehicle-pedestrian interaction where decisions of one agent directly affect the other agent's optimal behavior, and vice versa, is a challenging yet often neglected aspect of such systems. We address this issue by defining a Markov decision process (MDP) for a simulated driving scenario in which an AV driving along an urban street faces a pedestrian trying to cross an unmarked crosswalk. The AV's PCAM decision policy is learned through deep reinforcement learning (DRL). Since modeling pedestrians realistically is challenging, we compare two levels of intelligent pedestrian behavior. While the baseline model follows a predefined strategy, our advanced pedestrian model is defined as a second DRL agent. This model captures continuous learning and the uncertainty inherent in human behavior, making the vehicle-pedestrian interaction a deep multi-agent reinforcement learning (DMARL) problem. We benchmark the developed PCAM systems according to the agents' collision rate and the resulting traffic flow efficiency with a focus on the influence of observation uncertainty or noise on the decision-making of the agents. The results show that the AV is able to completely mitigate collisions under the majority of the investigated conditions, and that the DRL pedestrian model indeed learns a more intelligent crossing behavior.
... The effect of lane width is in line with (Rasouli et al., 2017), where authors, using real video data from urban and suburban roads, report pedestrians paying more attention before crossing wider streets. The reported effects of traffic parameters on pedestrian behaviour in previous studies also confirm the negative effect of traffic density on waiting time (Schmidt and Faerber, 2009;Ishaque and Noland, 2008). Schmidt and Faerber (2009), for instance, suggest speed and density as important parameters for pedestrians crossing decision, with pedestrians using distance of the vehicles for making crossing decisions. ...
... The reported effects of traffic parameters on pedestrian behaviour in previous studies also confirm the negative effect of traffic density on waiting time (Schmidt and Faerber, 2009;Ishaque and Noland, 2008). Schmidt and Faerber (2009), for instance, suggest speed and density as important parameters for pedestrians crossing decision, with pedestrians using distance of the vehicles for making crossing decisions. Six of the used covariates are relevant to walking habits: Walk to work and shopping, main transportation mode of cars and active modes, having driving licence and having more than 1 car in the house. ...
... Several studies both in the automated environments (Rasouli and Tsotsos, 2019) and human-driven environments (Sun et al., 2015) have investigated the effect of environmental variable, with which our results are in line. The effect of traffic parameters, in various forms, has also been explored in traditional studies of pedestrians (Schmidt and Faerber, 2009;Ishaque and Noland, 2008), and we show the same pattern exists in the new context. Wider and more comfortable sidewalks, narrower lane widths, enhanced lighting equipment, and incorporation of pedestrian-to-vehicle communication technologies are some of the solutions that can be implemented before diving into future automated urban areas. ...
Article
To ensure pedestrian-friendly streets in the era of automated vehicles, reassessment of current policies, practices, design, rules and regulations of urban areas is of importance. This study investigates pedestrian crossing behaviour which, as an important element of urban dynamics, is expected to be affected by the presence of automated vehicles. For this purpose, an interpretable machine learning framework is proposed to explore factors affecting pedestrians’ wait time before crossing mid-block crosswalks in the presence of automated vehicles. To collect rich behavioural data, we developed a dynamic and immersive virtual reality experiment, with 180 participants from a heterogeneous population in 4 different locations in the Greater Toronto Area (GTA). Pedestrian wait time behaviour is then analysed using a data-driven Cox Proportional Hazards (CPH) model, in which the linear combination of the covariates is replaced by a flexible non-linear deep neural network. The proposed model achieved a 5% improvement in goodness of fit, but more importantly, enabled us to incorporate a richer set of covariates. A game theoretic based interpretability method is used to understand the contribution of different covariates to the time pedestrians wait before crossing. Results show that the presence of automated vehicles on roads, wider lane widths, high density on roads, limited sight distance, and lack of walking habits are the main contributing factors to longer wait times. Our study suggested that, to move towards pedestrian-friendly urban areas, educational programs for children, enhanced safety measures for seniors, promotion of active modes of transportation, and revised traffic rules and regulations should be considered.
... Not only does it affect pedestrians, but also it affects drivers. Schmidt and Färber 2009 suggested that drivers driving at high speed will tend to receive more dangerous crossings from pedestrians, potentially resulting in more accidents. However, few studies have studied the potential decision-making mechanism of this unsafe crossing behaviour specifically. ...
... These can be roughly categorised as external and internal attributes. External attributes which may affect pedestrian gap acceptance behaviour include vehicle speed (Schmidt and Färber, 2009), time to arrival (TTA) (Avinash et al., 2019;Pawar and Patil, 2016), distance (Lobjois and Cavallo, 2007;Schmidt and Färber, 2009), number of lanes (Chandra et al., 2014), and vehicle size (Beggiato et al., 2017;Lee and Sheppard, 2017). Internal attributes which may have an impact include gender, age (Hulse et al., 2018;Kalatian and Farooq, 2021) and group size (Pawar and Patil, 2015;Avinash et al., 2019). ...
... These can be roughly categorised as external and internal attributes. External attributes which may affect pedestrian gap acceptance behaviour include vehicle speed (Schmidt and Färber, 2009), time to arrival (TTA) (Avinash et al., 2019;Pawar and Patil, 2016), distance (Lobjois and Cavallo, 2007;Schmidt and Färber, 2009), number of lanes (Chandra et al., 2014), and vehicle size (Beggiato et al., 2017;Lee and Sheppard, 2017). Internal attributes which may have an impact include gender, age (Hulse et al., 2018;Kalatian and Farooq, 2021) and group size (Pawar and Patil, 2015;Avinash et al., 2019). ...
Preprint
Full-text available
Accidents involving pedestrians are particularly common at unsignalised intersections and mid-block crosswalks, where vehicles often do not yield to them. Analysing and understanding pedestrian crossing behaviour at such locations is vital for improving road safety. Previous studies have repeatedly shown that pedestrians tend to accept smaller time gaps in conditions with higher vehicle speeds and thus potentially less safe. This has prompted the hypothesis that pedestrians rely on spatial distance to make crossing decisions. However, few studies have investigated the mechanism underpinning this phenomenon. We propose a novel approach to characterise pedestrian crossing behaviour: a psychophysics-based gap acceptance (PGA) model based on visual looming cues and binary choice logit method. Road crossing data collected in a simulated experiment were used to analyse pedestrian behaviour and test the model. Our analysis indicates that, in line with previous studies, higher vehicle speed increased the tendency of gap acceptance, leading to a higher rate of unsafe crossings. Crucially, the PGA model could accurately account for these crossing decisions across experimental scenarios, more parsimoniously than a conventional model. These results explain the speed-induced unsafe behaviour by suggesting that pedestrians apply visual looming, which depends on vehicle speed and distance, to make crossing decisions. This study reinforces the notion that for two vehicles with the same time gap, the one with higher speed can elicit more risky crossing behaviour from pedestrians, potentially resulting in more severe accidents. The practical implications of the results for traffic safety management, modelling and development of automated vehicles are discussed.
... Through interviews and on-site observations [6,7] and recordings of natural driving scenes [7][8][9], it has been shown that a sizeable percentage of pedestrians use eye contact to negotiate right of way when crossing the road. Additionally, studies have investigated pedestrians' responses to automated vehicles without a driver making eye contact (typically using a Wizard of Oz approach [5,10,11]. ...
... More recently, in a field study measuring car speed profiles as a function of eye contact, Ren et al. [22] found that drivers braked earlier for staged pedestrians who attempted to make eye contact than for those who did not. That said, Schmidt and Färber [9] found that participants looking at videos of traffic scenes from a driver's perspective were able to make accurate predictions of pedestrians' crossing intentions even when the pedestrians' heads were occluded, suggesting that eye contact is not essential in traffic. ...
Article
Full-text available
Non-verbal communication, such as eye contact between drivers and pedestrians, has been regarded as one way to reduce accident risk. So far, studies have assumed rather than objectively measured the occurrence of eye contact. We address this research gap by developing an eye contact detection method and testing it in an indoor experiment with scripted driver-pedestrian interactions at a pedestrian crossing. Thirty participants acted as a pedestrian either standing on an imaginary curb or crossing an imaginary one-lane road in front of a stationary vehicle with an experimenter in the driver’s seat. In half of the trials, pedestrians were instructed to make eye contact with the driver; in the other half, they were prohibited from doing so. Both parties’ gaze was recorded using eye trackers. An in-vehicle stereo camera recorded the car’s point of view, a head-mounted camera recorded the pedestrian’s point of view, and the location of the driver’s and pedestrian’s eyes was estimated using image recognition. We demonstrate that eye contact can be detected by measuring the angles between the vector joining the estimated location of the driver’s and pedestrian’s eyes, and the pedestrian’s and driver’s instantaneous gaze directions, respectively, and identifying whether these angles fall below a threshold of 4°. We achieved 100% correct classification of the trials involving eye contact and those without eye contact, based on measured eye contact duration. The proposed eye contact detection method may be useful for future research into eye contact.
... Prior work has shown that pedestrian non-verbal actions (e.g., body posture) play a key role in influencing driving behavior [11,43]. Many studies investigated different aspects of pedestrian actions at crosswalks such as eye contact before crossing [10,40,45], including how often and when they typically occurred [5]. Pedestrian conditions like standing or walking before crossings were also studied [33,41]. ...
... Pedestrian conditions like standing or walking before crossings were also studied [33,41]. Researchers demonstrated that body language like hand, leg, and head movements are important cues of pedestrian actions [18,40,42] and often help drivers to yield [10,36], thereby generating a positive or negative interaction [9,16]. ...
... Pedestrian intention recognition until now was investigated mainly from a technological standpoint [3,7,48,52]. Therefore, we propose to include visualizations of pedestrian intention recognition to calibrate trust for passengers of AVs and, therefore, to increase usage [19]. ...
... The combination of the dynamics of pedestrians, their 3D pose and awareness (meaning head orientation towards the vehicle), and obstacles lead to the best prediction results. Other factors were included as focusing on trajectories and dynamic factors alone is insufficient [48]: awareness [6], social forces [37] (i.e., repulsion and attraction), or structure of the street [49]. Rasouli and Tsotsos [46] summarize: "intention estimation algorithms are used in very limited traffic scenarios [...] Ideally, these algorithms should be universal" [46, p. 915]. ...
... For instance, it was found that pedestrians who want to cross the street without a crossing aid often use eye contact to ensure that an approaching driver sees them [36]. If the driver returns the eye contact, pedestrians assume that they have been seen and that the driver will act accordingly [87]. This assumption is supported by studies showing that a pedestrian's direct stare towards an oncoming driver invokes more compliant and yielding behavior [40,41]. ...
... Variations in traffic culture exist not only between different countries but also within the same country, such as between urban and rural areas or between different cities [9]. Culture has been shown to have an effect on gap acceptance [87], perceptions of traffic problems such as speeding or jaywalking [60], and the assessment of traffic situations [16]. Besides culture, past experience may also play an important role in crossing behavior. ...
Chapter
As the control of driving tasks is increasingly transferred from the human driver to the on-board sensor and computer systems, a potential gap in communication is created between the car as an entity, and other road users. How can pedestrians, cyclists, and other drivers be certain that an automated vehicle is aware of the different road users in its environment and will do the ‘right thing’? In the need for creating a sense of optimal trust in automated vehicles, particularly in the nascent stages of their development and introduction to traffic, this communication gap needs to be filled. This chapter looks at the state of the art of the research that tries to answer this question, and lays out some common considerations and recommendations for the design of such systems.
... The pedestrian observes the traffic in order to make a decision. If an approaching vehicle drives at constant speed in an urban scenario, the velocity seems to play no role in the decision making [2]. However, it does play a role if the driver is slowing down to waive the right of way. ...
... It is possible to recognize this by tracking the position of a pedestrian. It has been shown that object tracking alone is not sufficient if the pedestrian is still on the pavement [2]. However, if the pedestrian has not stepped onto the road yet, the reason for his trajectory is not always about crossing the road. ...
Preprint
Full-text available
State-of-the-art motor vehicles are able to break for pedestrians in an emergency. We investigate what it would take to issue an early warning to the driver so he/she has time to react. We have identified that predicting the intention of a pedestrian reliably by position is a particularly hard challenge. This paper describes an early pedestrian warning demonstration system.
... As can be seen from the previous work, traditional interactions between motorized vehicles and pedestrians play a fundamental role in infuencing the pedestrian's crossing decision, which relies on the vehicle's speed and distance to estimate both the awareness and the intent of the driver [48,53,55]. Although pedestrians and cyclists receive additional information about what a car intends to do with an introduction of on-vehicle displays, they still heavily rely on the drivers' behavior inside the vehicles. ...
... To safely cross a street, people usually rely on a distance to a vehicle and its speed [8,48,53,55]. These factors play an essential role (2) Countdown -depicts the remaining time the intersection is safe to cross (right). ...
Conference Paper
Full-text available
Cycling has become increasingly popular as a means of transportation. However, cyclists remain a highly vulnerable group of road users. According to accident reports, one of the most dangerous situations for cyclists are uncontrolled intersections, where cars approach from both directions. To address this issue and assist cyclists in crossing decision-making at uncontrolled intersections, we designed two visualizations that: (1) highlight occluded cars through an X-ray vision and (2) depict the remaining time the intersection is safe to cross via a Countdown. To investigate the efficiency of these visualizations, we proposed an Augmented Reality simulation as a novel evaluation method, in which the above visualizations are represented as AR, and conducted a controlled experiment with 24 participants indoors. We found that the X-ray ensures a fast selection of shorter gaps between cars, while the Countdown facilitates a feeling of safety and provides a better intersection overview.
... Furthermore, the pedestrian's behavior is more flexible than other road user's behavior, as they can quickly switch from one state to another (walking, running, stepping back, stopping, etc.). Also, pedestrians can change suddenly their direction (Schmidt and Faerber, 2009), and they do not have a flashing lights or horn to warn other road users. This diversity may lead to unexpected behavior, as viewed from automated vehicle, and thus to accidents. ...
... This may help the experimenter implementing virtual reality experiments with non-normative pedestrians in order to study drivers or passengers of automated vehicles facing unexpected pedestrian crossings. Furthermore, by improving our model, it might help to improve driver assistants (Schmidt and Faerber, 2009) for a better anticipation of the pedestrian crossing decision. ...
Conference Paper
Automated vehicle driving raises the challenge of producing vehicle behaviors similar to those produced by human drivers. Automated vehicles could then be accepted more easily. Among the many different behaviors to be simulated, one is particularly important from a road safety point of view: the interaction between automated vehicles and pedestrians during a street crossing. More particularly, pedestrians non-normative and unexpected behaviors should be taken into account by automated vehicles. Studying the behaviors of drivers or passengers in these situations becomes a major stake for the acceptance of automated vehicles. Thus, in this contribution, we aim to develop a new model of pedestrian street crossing at a red light for virtual pedestrians in order to facilitate the scenario development. This model will allow virtual pedestrians to cross the street illegally, and to influence other pedestrians to follow them. Thus, some among the waiting pedestrians will also illegally cross the street. The model is able to manage in a very simple manner a group of pedestrians with only few parameters. These parameters allow to coordinate the pedestrians in the group for street crossing, and experimenters will keep the control on their studies in ceteris paribus conditions. The model is based on three hypotheses. The first one concerns the time that each pedestrian accepts to wait at the red light. The second and third hypotheses are related to social influence: the actions made by others influence the pedestrian street crossing decisions. Based on the works of Rosenbloom (2009), we assume that: i) waiting pedestrians encourage the others to wait too, and: ii) crossing pedestrians at a red light shows the others there is an opportunity to cross, and thus encourages them to cross. The simulation results illustrate our method and show different pedestrians group behaviour of street crossings. Our method allows experimenters to coordinate the pedestrians in the group with only few parameters.
... For instance, Schmidt et al. found that pedestrians who want to cross a street tend to look at the approaching vehicle to get acknowledgement from the driver; if the driver returns their eye contact, pedestrians assume that they have been seen and that they have achieved a mutual understanding (Schmidt et al., 2009). Similarly, Sucha et al. found that pedestrian's decision to cross, as well as their feeling of safety, are directly impacted by various signals provided by the driver, like eye contact, postures, waving hand, or flashing lights (Sucha et al., 2017). ...
Conference Paper
Full-text available
The importance of informal communication between manual vehicles drivers and pedestrians in order to prevent misinterpretation, and thus accidents, in road-crossing situations has been widely shown in the literature. Such crucial communication consequently raises the issue of the introduction of automated vehicles (AVs) on the roads, in which case the status of the driver becomes less obvious. In this paper, we present a novel simulation platform, the V-HCD, allowing the conduct of immersive experimentations, both from the pedestrian's and the driver's point of view. This platform will be used to study the acceptance of the automated vehicle for the European SUaaVE project, and further to support the human-centred design of a future empathic AV.
... There is a wide variety of situations where humans need to process visual sensory input to 23 determine whether or not they are on a collision course with objects in their surroundings, 24 ...
Preprint
Full-text available
Detection of impending collision is fundamental to many human activities, and is widely assumed to be limited by a ‘looming threshold’. Evidence accumulation models explain decision-making in abstract paradigms, but have not been shown to remain valid for continuously time-varying, ecologically relevant stimuli. Here, we record behavioural and EEG responses in a collision detection task, disprove the conventional looming threshold assumption, and instead provide stringent evidence for a looming accumulation model. Generalising existing model assumptions from stationary to time-varying evidence, we show that our model accounts for previously unexplained observations and full distributions of detection. We replicate a centroparietal pre-decision positivity in scalp potentials, and show that our model explains its onset rather than its buildup, suggesting that neural evidence accumulation is implemented differently, possibly in distinct brain regions, in collision detection compared to previous paradigms. Our findings illustrate the value of connecting basic and applied research on human behaviour.
... AVs need to detect and recognize other road users, automated or non-automated, to interact safely with them. Multiple studies have been performed from the point of view of AVs regarding their ability to recognize other road users [4,5]. Also, smart infrastructure is proposed to create a safer environment in which cyclists can interact with AVs. ...
Article
Full-text available
Most of cyclists’ fatalities originate from collisions with motorized vehicles. It is expected that automated vehicles (AV) will be safer than human-driven vehicles, but this depends on the nature of interactions between non-automated road users, among them cyclists. Little research on the interactions between cyclists and AVs exists. This study aims to determine the main factors influencing cyclists’ crossing intentions when interacting with an automated vehicle as compared to a conventional vehicle (CV) using a 360° video-based virtual reality (VR) method. The considered factors in this study included vehicle type, gap size between cyclist and vehicle, vehicle speed, and right of way. Each factor had two levels. In addition, cyclist’s self-reported behavior and trust in automated vehicles were also measured. Forty-seven participants experienced 16 different crossing scenarios in a repeated measures study using VR. These scenarios are the result of combinations of the studied factors at different levels. In total, the experiment lasted 60 min. The results show that the gap size and the right of way were the primary factors affecting the crossing intentions of the individuals. The vehicle type and vehicle speed did not have a significant effect on the crossing intentions. Finally, the 360° video-based VR method scored relatively high as a research method and comparable with the results of a previous study investigating pedestrians’ crossing intentions confirming its suitability as a research methodology to study cyclists’ crossing intentions.
... In order to obtain the cognitive annotations, a video experiment was conducted for all the recruited 24 video annotators. Previous studies have used video experiments to study human neural and cognitive mechanisms in the activity segmentation process [37], investigate the driver's decision-making process in predicting pedestrian's behaviors [11], [38], and explain the driving behaviors with text descriptions [25]. Furthermore, a recent study [35] adopted a similar video experiment process to annotate pedestrians' intent to cross the street. ...
Preprint
Prediction of pedestrian behavior is critical for fully autonomous vehicles to drive in busy city streets safely and efficiently. The future autonomous cars need to fit into mixed conditions with not only technical but also social capabilities. As more algorithms and datasets have been developed to predict pedestrian behaviors, these efforts lack the benchmark labels and the capability to estimate the temporal-dynamic intent changes of the pedestrians, provide explanations of the interaction scenes, and support algorithms with social intelligence. This paper proposes and shares another benchmark dataset called the IUPUI-CSRC Pedestrian Situated Intent (PSI) data with two innovative labels besides comprehensive computer vision labels. The first novel label is the dynamic intent changes for the pedestrians to cross in front of the ego-vehicle, achieved from 24 drivers with diverse backgrounds. The second one is the text-based explanations of the driver reasoning process when estimating pedestrian intents and predicting their behaviors during the interaction period. These innovative labels can enable several computer vision tasks, including pedestrian intent/behavior prediction, vehicle-pedestrian interaction segmentation, and video-to-language mapping for explainable algorithms. The released dataset can fundamentally improve the development of pedestrian behavior prediction models and develop socially intelligent autonomous cars to interact with pedestrians efficiently. The dataset has been evaluated with different tasks and is released to the public to access.
... Research into vehicle automation has focused on the technological challenges, such as pedestrian recognition and trajectory tracking, as well as intention prediction (Koehler et al., 2013;Quintero et al., 2014;Rasouli et al., 2018), which emphasize functioning of the automation. Besides, pedestrians also rely on implicit cues from the vehicles to make a decision, such as distance and velocity of the vehicle (Domeyer et al., 2019;Risto et al., 2017), as well as vehicle platoon size (Himanen & Kulmala, 1988;Schmidt & Färber, 2009). If AV slows down for pedestrians, it should be decelerated as soon as possible (Fuest et al., 2020). ...
Article
Automated Vehicles (AVs) are being developed rapidly and tested on public roads, but pedestrians’ interaction with AV is not comprehensively understood or thoroughly investigated to ensure safe operations and the public’s trust of AVs. In this study, we aimed to provide another research evidence to enhance such understanding with the use of external interfaces for facilitating the interaction between pedestrians and AVs. We developed five external interfaces, including text, symbol, animated-eye, a combination of text and symbol, and speed. These interfaces communicated five types of information, including (1) intent of AV; 2) advice to pedestrians of what to do, (3) AV’s awareness of pedestrians, (4) combination of intent and advice, and (5) vehicle movement (i.e., speed). We tested the interfaces through two field studies at uncontrolled intersections with crosswalks. The Wizard of Oz method was used, in which an experimenter worked as a driver in an instrumented vehicle and wore an outfit to be invisible to the pedestrians, thus rendering the set-up to simulate an AV interacting with a pedestrian. The interfaces were displayed on an LED panel mounted on the AV. Results showed that the AV’s external interface did not change pedestrians’ response time in comparison with the baseline without any interface. There was no statistically significant difference in response time among the external interfaces either. According to the post-experimental interview, vehicle movement pattern (e.g., vehicle speed) continued to be a significant cue for pedestrians to decide when to cross the intersections. Participants perceived the communication of the AV’s intent and vehicle speed as more beneficial than the communication of AV’s awareness. The subjective ratings showed positive effects of those interfaces that were easy to understand (e.g., text interface and speed interface), which also helped pedestrians feel safer when interacting with the AV.
... First, pedestrians examine vehicle cues such as lights (e.g., turn indicators, headlights flashing), audible signals (e.g., horn) and, foremost, vehicle dynamics. Pedestrians particularly rely on the distance of the vehicle (Liu & Tung, 2014;Schmidt & Färber, 2009) and the vehicle's speed (Beggiato et al., 2017;Himanen & Kulmala, 1998;Šucha et al., 2017;Varhelyi, 1998). For example, pedestrians feel safe to cross a street if a vehicle is braking, while accelerating or maintaining speed is an indicator that the driver does not intend to yield to pedestrians. ...
Article
With self-driving vehicles (SDVs), pedestrians lose the possibility of making eye contact with an attentive driver. This study investigated whether an external human-machine interface (eHMI) displaying the automated driving mode (a. without eHMI vs. b. with eHMI) affects how pedestrians respond to different driver's states: (1) attentive driver, (2) tinted windshield, (3) distracted driver (within-subject design). At a test site, N = 65 pedestrians crossed a pedestrian crossing while a Wizard-of-Oz SDV approached. We assessed perceived safety and crossing onset times after each trial. Findings reveal that without an eHMI, pedestrians felt significantly less safe if the windshield was tinted or the driver was distracted as compared to an attentive driver. With an eHMI, pedestrians did not differ in perceived safety with regard to the driver's state. We observed no significant differences in pedestrians' crossing onset times. We conclude that an eHMI helps pedestrians to not consider the driver's state.
... Driver cues are informal and are particularly important to coordinate actions in ambiguous traffic situations with unclear or few regulations such as in a parking lot (Färber, 2016;Fildes et al., 2014;Witzlack et al., 2016). For instance, pedestrians ensure with eye contact that a driver is aware of their presence (Guéguen et al., 2015;Rasouli et al., 2017;Schmidt and Färber, 2009). Prior studies showed that the lack of a driver makes pedestrians feel stressed (Faas et al., 2020a;Lagström and Lundgren, 2015;Lundgren et al., 2017). ...
Article
Pedestrians rely on vehicle dynamics, engine sound, and driver cues. The lack of engine sound now constitutes an addressed pedestrian safety issue for (hybrid) electric vehicles ((H)EVs). Analogously, lacking driver cues may constitute a pedestrian safety issue for self-driving vehicles (SDVs). The purpose of this study was to systematically compare the relevance of substituting driver cues with an external human-machine interface among SDVs (no eHMI vs. eHMI) with the relevance of substituting engine sound with artificial sound among (H)EVs (no engine sound vs. engine sound). In a within-subject design, twenty-nine participants acting as pedestrians encountered a simulated SDV in a parking lot. The results revealed that both informational cues have equally large effects on subjective measures such as perceived safety. In semi-structured interviews, participants stated that it is equally crucial to equip SDVs with an eHMI as equipping (H)EVs with an artificial sound generator. We conclude that an eHMI for SDVs seems to be as relevant as an artificial sound for (H)EVs.
... From the perspective of physical modality, the movement of driverless vehicles, such as approach speed, plays a fundamental role on the safety of pedestrians on the road. In traditional interactions between pedestrians and vehicles, the former relies on approach speed and gap to judge both the awareness and the intent of the driver [21,44,45]. Our findings indicate that physical modality, including vehicle movement patterns, will continue to be a significant cue in driverless vehicle and pedestrian interactions, even in the presence of eHMIs. ...
Article
Full-text available
With the development and promotion of driverless technology, researchers are focusing on designing varied types of external interfaces to induce trust in road users towards this new technology. In this paper, we investigated the effectiveness of a multimodal external human–machine interface (eHMI) for driverless vehicles in virtual environment, focusing on a two-way road scenario. Three phases of identifying, decelerating, and parking were taken into account in the driverless vehicles to pedestrian interaction process. Twelve eHMIs are proposed, which consist of three visual features (smile, arrow and none), three audible features (human voice, warning sound and none) and two physical features (yielding and not yielding). We conducted a study to gain a more efficient and safer eHMI for driverless vehicles when they interact with pedestrians. Based on study outcomes, in the case of yielding, the interaction efficiency and pedestrian safety in multimodal eHMI design was satisfactory compared to the single-modal system. The visual modality in the eHMI of driverless vehicles has the greatest impact on pedestrian safety. In addition, the “arrow” was more intuitive to identify than the “smile” in terms of visual modality.
... Instead of using eHMIs that communicate explicitly, it may prove fruitful to let AVs communicate implicitly via adjustments in their approach speed and distance. Research has shown that speed and distance, and the composite measure time-to-arrival (TTA, i.e., the time gap), strongly affect the likelihood that a road user will cross (De Winter et al. 2009;Oxley et al. 2005;Schmidt and F€ arber 2009;Simpson, Johnston, and Richardson 2003). Dietrich et al. (2019) investigated the effect of different deceleration patterns (baseline: constant deceleration, defensive: braking hard and early, and aggressive: braking hard and later) coupled with different values of vehicle pitch (none, normal pitch proportional to vehicle deceleration, boosted normal pitch, and premature pitch which preceded vehicle deceleration) on the crossing behaviour of pedestrians. ...
Article
Full-text available
It may be necessary to introduce new modes of communication between automated vehicles (AVs) and pedestrians. This research proposes using the AV’s lateral deviation within the lane to communicate if the AV will yield to the pedestrian. In an online experiment, animated video clips depicting an approaching AV were shown to participants. Each of 1104 participants viewed 28 videos twice in random order. The videos differed in deviation magnitude, deviation onset, turn indicator usage, and deviation-yielding mapping. Participants had to press and hold a key as long as they felt safe to cross, and report the perceived intuitiveness of the AV’s behaviour after each trial. The results showed that the AV moving towards the pedestrian to indicate yielding and away to indicate continuing driving was more effective than the opposite combination. Furthermore, the turn indicator was regarded as intuitive for signalling that the AV will yield. Practitioner summary: Future automated vehicles (AVs) may have to communicate with vulnerable road users. Many researchers have explored explicit communication via text messages and led strips on the outside of the AV. The present study examines the viability of implicit communication via the lateral movement of the AV.
... fact, when a motorcycle can be seen only by its central headlight at nighttime, the angular velocity of the headlight's visual expansion can be very low and difficult to assess, or may even be under the motionperception threshold, which is about 0.17 deg/s (Hoffmann and Mortimer, 1994;Schmidt and Färber, 2009). For instance, a motorcycle seen by its standard light only and approaching at 60 km/h from a distance of 67 m (arrival time: 4.5 s), has an angular velocity of 0.04deg/s, i.e., under the threshold, whereas the same motorcycle equipped with the vertical configuration has an angular velocity of 0.30 deg/s, i.e., clearly above the threshold. ...
Article
Many motorcycle accidents occur at intersections and are caused by other vehicle drivers who misperceive the speed and time-to-arrival of an approaching motorcycle. The two experiments reported here tested different motorcycle headlight configurations likely to counteract this perceptual failure. In the first experiment, conducted on a driving simulator, car drivers turned left in front of cars and motorcycles approaching an intersection under nighttime lighting conditions. The motorcycles were equipped with either a standard white central light, or one of three vertical configurations of white and yellow lights. The results showed that the standard configuration led to significantly more unsafe accepted gaps than the vertical configurations. In the second experiment, conducted on a test track using a similar task, the most promising motorcycle headlight configuration, i.e., the vertical yellow-white light arrangement (one central white light, plus one yellow light on the helmet and two yellow lights on the fork) was evaluated and compared to a standard configuration and a car. The vertical yellow-white headlight configuration again provided significant safety benefits as compared to the standard configuration. These findings demonstrate that motorcycle safety can be improved by headlight ergonomics that accentuate the vertical dimension of motorcycles. They also suggest that the driving simulator is a valid tool for conducting research on motorcycle headlight design.
... In today's trafc, to decide whether it is safe to cross a street, pedestrians rely on two established means of communication when a vehicle approaches: (1) Vehicle cues such as the distance, speed, and deceleration of the vehicle [21,67,87,88,91] and (2) driver cues such as eye contact, posture and gestures [43,82,91]. While in well-defned situations, pedestrians largely rely on vehicle cues [2,23,91], driver cues become particularly prominent as a subsequent form of communication in ambiguous, low-speed urban scenarios [24,66,72]. ...
Conference Paper
Policymakers recommend that automated vehicles (AVs) display their automated driving status using an external human-machine interface (eHMI). However, previous studies suggest that a status eHMI is associated with overtrust, which might be overcome by an additional yielding intent message. We conducted a video-based laboratory study (N = 67) to investigate pedestrians’ trust and crossing behavior in repeated encounters with AVs. In a 2x2 between-subjects design, we investigated (1) the occurrence of a malfunction (AV failing to yield) and (2) system transparency (status eHMI vs. status+intent eHMI). Results show that during initial encounters, trust gradually increases and crossing onset time decreases. After a malfunction, trust declines but recovers quickly. In the status eHMI group, trust was reduced more, and participants showed 7.3 times higher odds of colliding with the AV as compared to the status+intent group. We conclude that a status eHMI can cause pedestrians to overtrust AVs and advocate additional intent messages.
... It is reasonable to assume that this is not always a deliberate act but that pedestrians may simply be overlooked due to restrictions of vision [7,8] and lack of lighting [9]. A misinterpretation of the pedestrians' intentions would also be possible [10]. In view of their high risk of injury or death, it is therefore appropriate to improve the situation of pedestrians. ...
Article
Full-text available
Recent research shows that braking of vehicles equipped with a front brake light is identified significantly earlier than braking of vehicles without front brake lights. Moreover, the absence of front brake lights leads to more conservative road crossing decisions. These results suggest that front brake lights are able to facilitate the pedestrians' anticipation of dangerous traffic situations, thereby increasing road safety. The present research investigated the effects of front brake lights in the real traffic of the Berlin Tegel Airport airside. A total of 102 vehicles were equipped with front brake lights and circulated in airport traffic for a period of three and a half months. Before and after this test period, 197 staff members were asked about their experiences with and their attitude towards front brake lights. The results show that front brake lights rarely led to misunderstandings, whereas they were significantly more often perceived to facilitate communication avoiding dangerous situations. The attitude towards front brake lights was already positive at the first interview and improved significantly during the measurement period. Overall, a great majority of participants stated that front brake lights improve communication between road users and thus increase road safety.
... Through interviews and on-site observations (Lee et al., 2021;Sucha, Dostal, & Risser, 2017) and recordings of natural driving scenes (Rasouli, Kotseruba, & Tsotsos, 2017;Schmidt & Färber, 2009;Sucha et al., 2017), it has been shown that a sizeable percentage of pedestrians use eye contact to negotiate right of way when crossing the road. Additionally, studies have investigated pedestrians' responses to automated vehicles without a driver making eye contact (typically using a Wizard of Oz approach; Habibovic et al., or recorded via cameras inside or outside of the vehicle, can be used to infer eye-contact seeking (Kotseruba, Rasouli, & Tsotsos, 2016;Rasouli et al., 2017;Schneemann & Gohl, 2016;Roth, Flohr, & Gavrila, 2016;Sucha et al., 2017). ...
Preprint
Full-text available
Non-verbal communication, such as eye contact between drivers and pedestrians, has been regarded as one way to reduce accident risk. So far, studies have assumed rather than objectively measured the occurrence of eye contact. We address this research gap by developing an eye contact detection method and testing it in an indoor experiment with scripted driver-pedestrian interactions at a pedestrian crossing. Thirty participants acted as a pedestrian either standing on an imaginary curb or crossing an imaginary one-lane road in front of a stationary vehicle with an experimenter in the driver’s seat. In half of the trials, pedestrians were instructed to make eye contact with the driver; in the other half, they were prohibited from doing so. Both parties’ gaze was recorded using eye trackers. An in-vehicle stereo camera recorded the car’s point of view, a head-mounted camera recorded the pedestrian’s point of view, and the location of the driver’s and pedestrian’s eyes was estimated using image recognition. We demonstrate that eye contact can be detected by measuring the angles between the vector joining the estimated location of the driver’s and pedestrian’s eyes, and the pedestrian’s and driver’s instantaneous gaze directions, respectively, and identifying whether these angles fall below a threshold of 4°. We achieved 100% correct classification of the trials involving eye contact and those without eye contact, based on measured eye contact duration. The proposed eye contact detection method may be useful for future research into eye contact.
... Behavioral research shows that some parts of the pedestrians or scene may be more informative than others for predicting the likelihood of crossing [50,12]. Likely, computational models are similarly affected by occlusion (e.g. ...
... Data-driven approaches had a major share in the used methods as they can combine our knowledge about human behavior with other visual and spatial information, such as the works in [Has+15; Völ+16; Ras+19; CMF19; AA20]. According to [SF09] a visual information of the pedestrian such as gaze or body movement detection is imperative to predict the intention. While a more recent study in [DT17b] argues that the detection of explicit body or gaze communication between the pedestrian and the vehicle is not significant in the intention prediction process. ...
Thesis
Application of deep learning to geometric 3D data poses various challenges for researchers. The complex nature of geometric 3D data allows to represent it in different forms: occupancy grids, point clouds, meshes, implicit functions, etc. Each of those representations has already spawned streams of deep neural network models, capable of processing and predicting according data samples for further use in various data recognition, generation, and modification tasks.Modern deep learning models force researchers to make various design choices, associated with their architectures, learning algorithms and other specific aspects of the chosen applications. Often, these choices are made with the help of various heuristics and best practice methods discovered through numerous costly experimental evaluations. Probabilistic modeling provides an alternative to these methods that allows to formalize machine learning tasks in a meaningful manner and develop probability-based training objectives. This thesis explores combinations of deep learning based methods and probabilistic modeling in application to geometric 3D data.The first contribution explores how probabilistic modeling could be applied in the context of single-view 3D shape inference task. We propose a family of probabilistic models, Probabilistic Reconstruction Networks (PRNs),which treats the task as image conditioned generation and introduces a global latent variable, encoding shape geometry information. We explore different image conditioning options, and two different training objectives based on Monte Carlo and variational approximations of the model likelihood. Parameters of every distribution are predicted by multi-layered convolutional and fully-connected neural networks from the input images. All the options in the family of models are evaluated in the single-view 3D occupancy grid inference task on synthetic shapes and according image renderings from randomized viewpoints. We show that conditioning the latent variable prior on the input images is sufficient to achieve competitive and state-of-the-art single-view 3D shape inference performance for point cloud based and voxel based metrics, respectively. We additionally demonstrate that probabilistic objective based on variational approximation of the likelihood allows the model to obtain better results compared to Monte Carlo based approximation.The second contribution proposes a probabilistic model for 3D point cloud generation. It treats point clouds as distributions over exchangeable variables and use de Finetti’s representation theorem to define a global latent variable model with conditionally independent distributions for coordinates of each point. To model these point distributions a novel type of conditional normalizing flows is proposed, based on discrete coupling of point coordinate dimensions. These flows update the coordinates of each point sample multiple times by dividing them in two groups and inferring the updates for one group of coordinates from another group and, additionally, global latent variable sample by the means of multi-layered fully-connected neural networks with parameters shared for all the points. We also extend our Discrete Point Flow Networks (DPFNs) from generation to single-view inference task by conditioning the global latent variable prior in a manner similar to PRNs from the first contribution. Resulting generative performance demonstrates that DPFNs produce sets of samples of similar quality and diversity compared to state of the art based on continuous normalizing flows, but are approximately 30 times faster both in training and sampling. Results in autoencoding and single-view inference tasks show competitive and state-of-the-art performance for Chamfer distance, F-score and earth mover’s distance similarity metrics for point clouds.
... The label of a video sequence (transition or no-transition) is determined by the TTE tag of its last frame. As crossing-related cases are arguably the most critical for stop and go forecasting, we set the prediction time horizon λ to be 2 seconds, which is the minimum time within which pedestrians make crossing decisions [51]. We choose a relatively large sampling rate of 5fps in the hope of reducing overfitting and speeding up training. ...
Preprint
Full-text available
Forecasting pedestrians' future motions is essential for autonomous driving systems to safely navigate in urban areas. However, existing prediction algorithms often overly rely on past observed trajectories and tend to fail around abrupt dynamic changes, such as when pedestrians suddenly start or stop walking. We suggest that predicting these highly non-linear transitions should form a core component to improve the robustness of motion prediction algorithms. In this paper, we introduce the new task of pedestrian stop and go forecasting. Considering the lack of suitable existing datasets for it, we release TRANS, a benchmark for explicitly studying the stop and go behaviors of pedestrians in urban traffic. We build it from several existing datasets annotated with pedestrians' walking motions, in order to have various scenarios and behaviors. We also propose a novel hybrid model that leverages pedestrian-specific and scene features from several modalities, both video sequences and high-level attributes, and gradually fuses them to integrate multiple levels of context. We evaluate our model and several baselines on TRANS, and set a new benchmark for the community to work on pedestrian stop and go forecasting.
... The narrower the road, the smaller the gap. When a pedestrian sees that he or she will have a clearer path a little later, he or she usually waits and does not take an unnecessary risk (Schmidt & Färber, 2009). ...
Article
Full-text available
The article deals with the behaviour of pedestrians using a smartphone. The work aims to describe the behaviour of pedestrians using a smartphone while walking and to survey the factors that lead pedestrians to this behaviour. The data gathering was performed at a marked pedestrian crossing without signals in Olomouc. The statistics in question were collected via observation and interviews. A total of 2689 pedestrians were observed and 90 people took part in a structured interview. We observed that 15% of pedestrians use their smartphone while walking. We found out that pedestrians who are holding a smartphone in their hand walk safely across a pedestrian crossing less often, rely on others more often when they are walking in a group, and step into the road more often when cars are supposed to give way to them. Furthermore, we found that pedestrians who were walking in a group and at the same time were on the phone or had on headsets were more likely to be guided by their companions than pedestrians who were not distracted.
... Some studies have investigated the shift of the pedestrians' ride at a high speed, resulting in abrupt stops and the speed variation in gender and age groups [34]. Some researchers focused their experiments for discovering the parameters that most influence the pedestrians' decision to cross a street and the factors that human drivers take into consideration when predicting movement of pedestrian [35]. The streets with narrow width, older people, young adults with a high-speed fall into these categories. ...
Article
Walking is the special mode of transportation that comprises 60% of the World’s population. This population includes the pedestrians as the focus of sight, because they are considered as the road users. Understanding the behavior of road users is a difficult task as people have complex mindsets. When people are crossing the road, they have been subjected to various attitude issues and other psychological issues. The prediction of the pedestrian’s motion is very ridiculous, because their motions has to be predicted related to the traffic parameter. A prediction algorithm always uses the past experiences to anticipate the future events. These algorithms use the set of sample data from a sample collected over a period. This makes prediction algorithms more ideal to use within smart environments. So as a part of this study, we have compared various algorithms, for their accurateness of the prediction on pedestrians’ movements. This paper also focuses on the various pedestrian’s data set, pedestrian behavior estimation and the various algorithms used to predict the behavior of the people. As a part of our research on pedestrian safety prediction would be done by providing an efficient prediction algorithm based on their movements, ecological factors, pedestrians’ psychological factors, other outreaches.
... Instead of using eHMIs that communicate explicitly, it may prove fruitful to let the AV communicate implicitly via adjustments in approach speed and distance. Research has shown that speed and distance, and the composite measure time-to-arrival (TTA, i.e., the time gap), strongly affect the likelihood that a road user will cross (De Winter, Spek, De Groot, & Wieringa, 2009;Oxley, Ihsen, Fildes, Charlton, & Day, 2005;Schmidt & Färber, 2009;Simpson, Johnston, & Richardson, 2003). Dietrich, Maruhn, Schwarze, and Bengler (2019) investigated the effect of different deceleration patterns (baseline: constant deceleration, defensive: braking hard and early, and aggressive: braking hard and later) coupled with different values of vehicle pitch (none, normal pitch proportional to vehicle deceleration, boosted normal pitch, and premature pitch which preceded vehicle deceleration) on the crossing behaviour of pedestrians. ...
Preprint
Full-text available
It may be necessary to introduce new modes of communication between automated vehicles (AVs) and pedestrians. This research proposes using the AV’s lateral deviation within the lane to communicate if the AV will yield to the pedestrian. In an online experiment, animated video clips depicting an approaching AV were shown to participants. Each of 1104 participants viewed 28 videos twice in random order. The videos differed in deviation magnitude, deviation onset, turn indicator usage, and deviation-yielding mapping. Participants had to press and hold a key as long as they felt safe to cross, and report the perceived intuitiveness of the AV’s behaviour after each trial. The results showed that the AV moving towards the pedestrian to indicate yielding and away to indicate continuing driving was more effective than the opposite combination. Furthermore, the turn indicator was regarded as intuitive for signalling that the AV will yield.
... This conclusion is in line with the results of recent studies that explore the role of vehicle movement as a mean of communication and coordination between drivers and pedestrians. Deceleration is normally interpreted by pedestrians as an indication that the driver has seen them and will yield the passage (Ackermann et al., 2018;Dey et al., 2019;Mahadevan et al., 2018;Schmidt & Färber, 2009;Várhelyi, 1998). Drivers, in turn, may deliberately use anticipated braking as a way to signal their yielding intention, encouraging the pedestrian to cross with the vehicle still moving, speeding up the encounter and eventually preventing the need for a full stop (Risto, Emmenegger, Vinkhuyzen, Cefkin, & Hollan, 2017). ...
Article
Full-text available
The controlled study of pedestrians’ crossing decision-making is relevant to the search for better safety conditions for this class of vulnerable road users. Several risk factors have been identified in the literature related to the crosswalks’ surrounding environment, the socio-demographic characteristics of the pedestrians crossing the road and the place where the crosswalks are inserted, as well as situational variables, such as speed and distance of the approaching vehicle during the crossing. In this work, the roles of visual and auditory cues in crossing decisions were analysed, comparing different speeds and distances, and taking into consideration different speed patterns of the approaching vehicle, aiming to identify what can affect pedestrians’ crossing behaviour. Experiments were performed in a virtual environment. Participants were presented with 10 different stimuli featuring a vehicle approaching with different speeds and movement patterns, combined with 2 auditory conditions: one concerning a vehicle with a gasoline combustion engine and another one with no sound cues. Participants were tasked with indicating the moment they decided to cross the street when they thought it was safe to do so by pressing a response button. Percentage of crossings, response time (RT), and time-to-passage (TTP) were recorded and subsequently analysed. The results showed that lower speeds and higher distances lead to higher percentages of crossings and RTs. The auditory condition did not significantly affect participants’ responses, leading to the conclusion that participants’ crossing decision was especially based on their visual perception of the movement characteristics of the approaching vehicle, particularly its speed and distance. These results may have relevance for the development of communication strategies between the vehicles, especially the automated ones, and pedestrians.
... Beside using static environment for predictions, also the interaction of traffic participants is modeled in literature. In Schmidt and Faerber (2009), Schmidt analyzed the gap acceptance of pedestrians to cross the street, based on time to collision which is an important information for predicting the crossing behavior. Rasouli Rasouli et al. (2017) analyzed the typical behavior of traffic participants before crossing a road on zebra crossings or other situations. ...
Article
Full-text available
Ensuring a safe journey with an autonomous vehicle, the surrounding has to be sensed and understood. Especially human intuition about the plans and intentions of traffic participants is hard to model for machines. In literature, there are already several prediction techniques existing for pedestrians, which are based on different features. Some models are very complex, whereas others only rely on the considered person’s motion. The goal of this work is to analyze the importance of different classes of context knowledge for the prediction performance, derive features to remove this lack of information and prove this by an improved prediction algorithm. In order to judge the lack of context knowledge, we analyze the prediction performance and error cases of a long short-term memory (LSTM) Neural Network as State-of-the-Art prediction algorithm, only based on motion data. The Network is trained and evaluated on a benchmark dataset, to make the results comparable to other approaches. Analyzing the most error-prone predictions, the missing context shall be identified, which could improve the prediction results. Since the data was generated by video, we can evaluate the whole scenario and identify the influencing factors. The found influences were classified in categories and their importance for the prediction model estimated. We prove the necessity of additional context knowledge by retraining a neural network with additional context knowledge. In a literature research we compare our found results to existing approaches.
... Mean pedestrian walking speeds for different pedestrian types are set based on the field study by Knoblauch et al. [23]. Since pedestrian gap acceptance can differ widely depending on the country and environment [3], we set the default gap acceptance range following the study conducted by Schmidt et al. [24] in Europe, which is in agreement with an earlier European study by Ashworth [25] and North American one by Brewer et al. [16]. ...
Preprint
In this paper, we present a microscopic agent-based pedestrian behavior model Intend-Wait-Cross. The model is comprised of rules representing behaviors of pedestrians as a series of decisions that depend on their individual characteristics (e.g. demographics, walking speed, law obedience) and environmental conditions (e.g. traffic flow, road structure). The model's main focus is on generating realistic crossing decision-model, which incorporates an improved formulation of time-to-collision (TTC) computation accounting for context, vehicle dynamics, and perceptual noise. Our model generates a diverse population of agents acting in a highly configurable environment. All model components, including individual characteristics of pedestrians, types of decisions they make, and environmental factors, are motivated by studies on pedestrian traffic behavior. Model parameters are calibrated using a combination of naturalistic driving data and estimates from the literature to maximize the realism of the simulated behaviors. A number of experiments validate various aspects of the model, such as pedestrian crossing patterns, and individual characteristics of pedestrians.
... Data-driven approaches had a major share in the used methods as they can combine our knowledge about human behavior with other visual and spatial information, such as the works in [Has+15; Völ+16; Ras+19; CMF19; AA20]. According to [SF09] a visual information of the pedestrian such as gaze or body movement detection is imperative to predict the intention. While a more recent study in [DT17b] argues that the detection of explicit body or gaze communication between the pedestrian and the vehicle is not significant in the intention prediction process. ...
Thesis
Full-text available
The current trend in electric autonomous vehicles design is based on pre-existing models of cities which have been built for cars. The carbon footprint of cities cannot be reduced until the overall requirement for vehicles is reduced and more green and pedestrianized zones are created for better livability. However, such green zones cannot be scaled without providing autonomous mobility solutions, accessible to people with reduced mobility. Such solutions need to be capable of operating in spaces shared with pedestrians, which makes this a much harder problem to solve as compared to traditional autonomous driving. This thesis serves as a starting point to develop such autonomous mobility solutions. The work is focused on developing a navigation system for autonomous vehicles operating around pedestrians. The suggested solution is a proactive framework capable of anticipating pedestrian reactions and exploiting their cooperation to optimize the performance while ensuring pedestrians safety andcomfort.A cooperation-based model for pedestrian behaviors around a vehicle is proposed. The model starts by evaluating the pedestrian tendency to cooperate with the vehicle by a time-varying factor. This factor is then used in combination with the space measurements to predict the future trajectory. The model is based on social rules and cognitive studies by using the concept of the social zones and then applying the deformable virtual zone concept (DVZ) to measure the resulting influence in each zone. Both parts of the model are learnt using a data-set of pedestrians to vehicle interactions by manually annotating the behaviors in the data-set.Moreover, the model is exploited in the navigation system to control both the velocity and the local steering of the vehicle. Firstly, the longitudinal velocity is proactively controlled. Two criteria are considered to control the longitudinal velocity. The first is a safety criterion using the minimum distance between an agent and the vehicle’s body. The second is proactive criterion using the cooperation measure of the surroundingagents. The latter is essential to exploit any cooperative behavior and avoid the freezing of the vehicle in dense scenarios. Finally, the optimal control is derived using the gradient of a cost function combining the two previous criteria. This is possible thanks to a suggested formulation of the cooperation model using a non-central chi distribution for the distance between the vehicle and an agent.A smooth steering is derived using a proactive dynamic channel method for the space exploration. The method depends on evaluating the navigation cost in a channel (sub-space) using a fuzzy cost model. The channel with the minimum cost is selected, and a human-like steering is affected using a Quintic spline candidate path between channels. Finally, the local steering is derived using a sliding mode path follower.The navigation is evaluated using PedSim simulator under ROS in pedestrian-vehicle interaction scenarios. The navigation is tested with different pedestrian density and sparsity. The proactive framework managed to navigate the vehicle producing smooth trajectories while maintaining the pedestrians’ safety and reducing the travel time in comparison with traditional reactive methods (Risk-RRT).
Chapter
The full-scale deployment of autonomous driving demands successful interaction with pedestrians and other vulnerable road users, which requires an understanding of their dynamic behavior and intention. Current research achieves this by estimating pedestrian’s trajectory mainly based on the gait and movement information in the past as well as other relevant scene information. However, the autonomous vehicles still struggle with such interactions since the visual features alone may not supply subtle details required to attain a superior understanding. The decision-making ability of the system can improve by incorporating human knowledge to guide the vision-based algorithms. In this paper, we adopt a novel approach to retrieve human knowledge from the natural text descriptions about the pedestrian-vehicle encounters, which is crucial to anticipate the pedestrian intention and is difficult for computer vision (CV) algorithms to capture automatically. We applied natural language processing (NLP) techniques on the aggregated description from different annotators to generate a temporal knowledge graph, which can achieve the changes of intention and the corresponding reasoning processes in a better resolution. In future work, we plan to show that in combination with video processing algorithms, the knowledge graph has the potential to aid the decision-making process to be more accurate by passively integrating the reasoning ability of humans.
Chapter
Estimating and reshaping human intentions are among the most significant topics of research in the field of human-robot interaction. This chapter provides an overview of intention estimation literature on human-robot interaction, and introduces an approach on how robots can voluntarily reshape estimated intentions. The reshaping of the human intention is achieved by the robots moving in certain directions that have been a priori observed from the interactions of humans with the objects in the scene. Being among the only few studies on intention reshaping, the authors of this chapter exploit spatial information by learning a Hidden Markov Model (HMM) of motion, which is tailored for intelligent robotic interaction. The algorithmic design consists of two phases. At first, the approach detects and tracks human to estimate the current intention. Later, this information is used by autonomous robots that interact with detected human to change the estimated intention. In the tracking and intention estimation phase, postures and locations of the human are monitored by applying low-level video processing methods. In the latter phase, learned HMM models are used to reshape the estimated human intention. This two-phase system is tested on video frames taken from a real human-robot environment. The results obtained using the proposed approach shows promising performance in reshaping of detected intentions.
Article
The successful deployment of automated vehicles (AVs) will depend on their capacity to travel within a mixed traffic environment, adopting appropriate interaction strategies across different scenarios. Thus, it is important to gain a detailed understanding of the specific types of interactions that are most likely to arise. The overall purpose of this paper was to present a methodology designed to facilitate the systematic observation of pedestrian-vehicle interactions, and to validate its use for both onsite and video based observations. A detailed observation protocol was developed to capture pedestrian and vehicle movement and communication patterns across four interaction phases. Onsite coders completed field observations of 50 pedestrian-vehicle interactions at a UK intersection, while video coders observed the same interactions recorded through a wireless camera mounted on a nearby rooftop. Results show that the observation protocol provides a reliable methodology for capturing patterns of pedestrian-vehicle interactions, with high levels of inter-coder consistency emerging across all categories of codes. A detailed examination of the specific descriptors selected suggests that onsite coding may be particularly beneficial in situations where the aim is to capture any explicit, and perhaps subtle, communication cues, whereas video based coding may be more appropriate in situations where exact sequences of behaviours or measurements of timings are desired. It is anticipated that this type of observation tool will be beneficial for AV developers to increase their understanding of how to interpret the movements of road users, along with increasing knowledge of when implicit and explicit communication techniques should be used.
Preprint
Full-text available
The successful deployment of automated vehicles (AVs) will depend on their capacity to travel within a mixed traffic environment, adopting appropriate interaction strategies across different scenarios. Thus, it is important to gain a detailed understanding of the specific types of interactions that are most likely to arise. The overall purpose of this paper was to present a methodology designed to facilitate the systematic observation of pedestrian-vehicle interactions, and to validate its use for both onsite and video based observations. A detailed observation protocol was developed to capture pedestrian and vehicle movement and communication patterns across four interaction phases. Onsite coders completed field observations of 50 pedestrian-vehicle interactions at a UK intersection, while video coders observed the same interactions recorded through a wireless camera mounted on a nearby rooftop. Results show that the observation protocol provides a reliable methodology for capturing patterns of pedestrian-vehicle interactions, with high levels of inter-coder consistency emerging across all categories of codes. A detailed examination of the specific descriptors selected suggests that onsite coding may be particularly beneficial in situations where the aim is to capture any explicit, and perhaps subtle, communication cues, whereas video based coding may be more appropriate in situations where exact sequences of behaviours or measurements of timings are desired. It is anticipated that this type of observation tool will be beneficial for AV developers to increase their understanding of how to interpret the movements of road users, along with increasing knowledge of when implicit and explicit communication techniques should be used.
Article
Full-text available
Evidence accumulation models provide a dominant account of human decision-making, and have been particularly successful at explaining behavioral and neural data in laboratory paradigms using abstract, stationary stimuli. It has been proposed, but with limited in-depth investigation so far, that similar decision-making mechanisms are involved in tasks of a more embodied nature, such as movement and locomotion, by directly accumulating externally measurable sensory quantities of which the precise, typically continuously time-varying, magnitudes are important for successful behavior. Here, we leverage collision threat detection as a task which is ecologically relevant in this sense, but which can also be rigorously observed and modelled in a laboratory setting. Conventionally, it is assumed that humans are limited in this task by a perceptual threshold on the optical expansion rate–the visual looming–of the obstacle. Using concurrent recordings of EEG and behavioral responses, we disprove this conventional assumption, and instead provide strong evidence that humans detect collision threats by accumulating the continuously time-varying visual looming signal. Generalizing existing accumulator model assumptions from stationary to time-varying sensory evidence, we show that our model accounts for previously unexplained empirical observations and full distributions of detection response. We replicate a pre-response centroparietal positivity (CPP) in scalp potentials, which has previously been found to correlate with accumulated decision evidence. In contrast with these existing findings, we show that our model is capable of predicting the onset of the CPP signature rather than its buildup, suggesting that neural evidence accumulation is implemented differently, possibly in distinct brain regions, in collision detection compared to previously studied paradigms.
Chapter
The most frequent justification for implementing automated vehicles is the claim that they will increase road safety by removing human involvement in driving. This, however, introduces emerging Human Factors (HFs) issues, since regardless of the level of automation, the human being will continue to play a crucial role in interacting with vehicle automation. In the medium-low levels, the driver will have to play a supervisory role which will introduce out-of-the-loop problems, in the driver-vehicle interaction during the transition of control. At the higher level, new forms of accidents may occur associated with the need for automated vehicles to interact with other road users. The chapter is a thorough literature review of the HFs for both of these interactions, mainly those relating to the medium-low level of automation. Such review is aimed at understanding the influences of HFs on road safety and the role played by infrastructures.
Article
Full-text available
The importance of investigating pedestrian safety has been evaluated repeatedly in safety studies. The present study attempts to evaluate the various methods used by previous researchers in a hierarchical process, to determine the characteristics, advantages, and limitations of each method. Two general analysis approaches (passive and active) were taken into account to categorize 169 previous types of research. In the passive approach, the studied methods were those based on crash databases, questionnaires, and post-crash field observation data; while, in the active approach, the studied methods were those based on driving simulations and videography. The result of the passive approach reveals that road users’ features and road characteristics (crash database studies), and error, lapses, intentional and unintentional violations (questionnaire studies) by them were among the most important causes of crashes and conflicts. Furthermore, road users’ distractions also reported a set of factors affecting the possibility of conflicts and crashes based on post-crash field observation studies. Also, results of the active approach showed that risky behaviors are the most important factor in threatening pedestrian safety such as unauthorized speeding, non-compliance with traffic law, unauthorized overtaking by drivers, and illegal crossing. Furthermore, risk perception and decision-making processes are the most important bond between the attitude and behavior of road users in dangerous driving situations. Examining studies through passive approach would lead to identifying the causes of crashes, recognizing the attitude of road users towards safety, and determining road users' behavioral patterns in certain situations, while the active approach has led to a more detailed understanding of behaviors and attitudes of road users. The inference of the findings obtained in this study will lead to a better understanding of the behavior of road users for studies on advanced driving assistance systems (ADAS).
Preprint
Full-text available
This distributed simulator study investigated pedestrians’ head-turning behaviour during a series of road crossings in a CAVE-based pedestrian simulator. Pedestrians were required to cross the road in front of an approaching vehicle, the kinematic behaviour of which was either programmed by the simulation to depict an automated vehicle (AV) or controlled by a human driver (HD), via a connected (hidden) desktop driving simulator. A within-participant experimental design was used with twenty-five pairs of participants (a pedestrian and a driver). For each trial, pedestrians had to decide whether to cross in front of the HD/AV, which was instructed (or programmed) to yield (or not) to the pedestrian. For the AV trials, two braking patterns were included: a hard-braking AV (AVHB, deceleration rate = 3.2 m/s2, stopping distance = 12 m from pedestrian) and soft-braking (AVSB, deceleration rate = 2.5 m/s2, stopping distance = 4 m from pedestrian). Pedestrians’ head-turning frequency and the change in head-turning angle, were calculated for each condition, both before a crossing was initiated, and during the actual road crossing. Results showed a significant increase in head-turning behaviour in the last 2 seconds before a crossing initiation in the yielding trials, in line with a ‘last-second check’ reported in observations of real-world crossings (Hassan, Geruschat, & Turano, 2005). The vehicle’s braking behaviour and stopping distance were the most important factors affecting pedestrians’ head-turning patterns during the crossing, with the least head-turning behaviour seen in the AVSB condition, compared with AVHB and HDB trials. This suggests that a closer stopping distance for the AV was associated with less confusion for the pedestrian, although this condition was also associated with the longest crossing initiation time. In contrast, the highest number of head-turnings were seen for the human-driven vehicle, which, on average, yielded about 40 m away from the participants, enabling a much faster crossing initiation. Overall, the shortest crossing initiation time (~ 1 sec) and highest head-turning behaviour were seen in the non-braking conditions, where participants crossed as quickly as the circumstances allowed. These results provide new insights about the use of VR simulators for understanding pedestrians’ crossing behaviour in response to different vehicle kinematics. They also extend our knowledge of pedestrian cues for the development of suitable sensors in future automated vehicles, which should help with providing a more seamless interaction between AVs and other road users in mixed traffic settings.
Conference Paper
Full-text available
Road traffic is a social situation where participants heavily interact with each other. Consequently, communication plays an important role. Typically, the communication between pedestrians and drivers is nonverbal and consists of a combination of gestures, eye contact, and body movement. However, when vehicles become automated, this will change. Previous work has investigated the design and effectiveness of additional communication cues between pedestrians and automated vehicles. It remains unclear, though, how this impacts the perceptions of the quality of communication and impressions of mindfulness and prosociality. In this paper, we report an online experiment, where we evaluated the perception of communication cues in the form of on-road light projections, across different traffic scenarios and roles. Our results indicate that, while the cues can improve communication, their effect is dependent on traffic scenarios. These results provide preliminary implications for the design of communication cues that consider their prosocial aspects.
Article
Full-text available
Two time-to-contact (T c) experiments are reported that manipulated the manner in which a visually simulated target vehicle disappeared from the screen. In both experiments, one condition featured the traditional, spontaneous disappearance of the vehicle. A contrasting condition featured the occlusion of the vehicle behind a natural object. The available visual information was essentially equivalent in each condition. If T c is specified by information in the expanding optic array alone, the two conditions should produce equivalent estimates of T c. Results of each experiment, however, showed estimates with 14% and 12% greater accuracy in the occlusion condition compared to the disappearance condition. This implies that T c judgments depend on more than the rate of optical expansion. In addition to the occlusion manipulation, factors influencing the accuracy of T c estimates included both the sex and age of the participant. In an effort to compare T c estimates with time-judgment ability, participants also performed a time-production task with the same temporal structure as the T c task but with no graphic scene representation. A positive relation was found but further clarification is still needed between these two capabilities.
Conference Paper
Full-text available
This paper describes a system for pedestrian detection in infrared im- ages implemented and tested on an experimental vehicle. A specific stabilization procedure is applied after image acquisition and before processing to cope with vehicle movements affecting the camera calibration. The localization of pedestri- ans is based on the search for warm symmetrical objects with specific size and aspect ratio. A set of filters is used to reduce false detections. The final validation process relies on the human shape's morphological characteristics.
Article
Full-text available
Theories in motor control suggest that the parameters specified during the planning of goal-directed hand movements to a visual target are defined in spatial parameters like direction and amplitude. Recent findings in the visual attention literature, however, argue widely for early object-based selection processes. The present experiments were designed to examine the contributions of object-based and space-based selection processes to the preparation time of goal-directed pointing movements. Therefore, a cue was presented at a specific location. The question addressed was whether the initiation of responses to uncued target stimuli could benefit from being either within the same object (object based) or presented at the same direction (space based). Experiment 1 replicated earlier findings of object-based benefits for non-goal-directed responses. Experiment 2 confirmed earlier findings of space-based benefits for goal-directed hand pointing movements. In Experiments 3 and 4, space-based and object-based manipulations were combined while requiring goal-directed hand pointing movements. The results clearly favour the notion that the selection processes for goal-directed pointing movements are primarily object based. Implications for theories on selective attention and action planning are discussed.
Article
Full-text available
Three gender-balanced groups of 16 school children (5-6 years, 8-9 years, 11-12 years) participated in individual pretests of vision, hearing, and time to walk across a 12-m wide urban street and back. Each child then completed 10 roadside trials requiring judgement of the threshold point at which they would no longer cross in front of traffic approaching from their right. The judgements were made from a site immediately in front of a parked car at a point 2 m from the kerb and 4 m from the centre of the road. Traffic speeds and distances were measured using a laser speed and distance detector. The results indicated that, overall, distance gap thresholds remained constant regardless of vehicle approach speeds. Analysis of the thresholds for distance gap judgements for the 4-m half-street crossing showed that some of the older children could be expected to make safe decisions, but this was not so for the 5-6- and 8-9-year-olds at vehicle approach speeds above 60 kph. Almost two-thirds of the children reported using distance to judge gaps, which proved the least adequate strategy in terms of proportion of resultant safe decisions. The findings are discussed in relation to developing effective child pedestrian safety strategies.
Article
Full-text available
A category of stimuli of great importance for primates, humans in particular, is that formed by actions done by other individuals. If we want to survive, we must understand the actions of others. Furthermore, without action understanding, social organization is impossible. In the case of humans, there is another faculty that depends on the observation of others' actions: imitation learning. Unlike most species, we are able to learn by imitation, and this faculty is at the basis of human culture. In this review we present data on a neurophysiological mechanism--the mirror-neuron mechanism--that appears to play a fundamental role in both action understanding and imitation. We describe first the functional properties of mirror neurons in monkeys. We review next the characteristics of the mirror-neuron system in humans. We stress, in particular, those properties specific to the human mirror-neuron system that might explain the human capacity to learn by imitation. We conclude by discussing the relationship between the mirror-neuron system and language.
Article
Full-text available
Understanding the intentions of others while watching their actions is a fundamental building block of social behavior. The neural and functional mechanisms underlying this ability are still poorly understood. To investigate these mechanisms we used functional magnetic resonance imaging. Twenty-three subjects watched three kinds of stimuli: grasping hand actions without a context, context only (scenes containing objects), and grasping hand actions performed in two different contexts. In the latter condition the context suggested the intention associated with the grasping action (either drinking or cleaning). Actions embedded in contexts, compared with the other two conditions, yielded a significant signal increase in the posterior part of the inferior frontal gyrus and the adjacent sector of the ventral premotor cortex where hand actions are represented. Thus, premotor mirror neuron areas-areas active during the execution and the observation of an action-previously thought to be involved only in action recognition are actually also involved in understanding the intentions of others. To ascribe an intention is to infer a forthcoming new goal, and this is an operation that the motor system does automatically.
Article
This paper summarises a Presidential Address to the Division of Traffic and Transportation Psychology at the 2002 International Congress of Applied Psychology. It considers whether traffic psychology is a distinct area of psychology, and concludes that the range of psychological approaches that understanding drivers and traffic requires is too pervasive for it to be so. The difficulties and shortcomings of various attempts to apply cognitive psychology to driving and traffic are explored, with respect to perceptual, motor and skilled aspects of the driving task. Examples are given of how ‘understanding driving’ poses theoretical challenges to mainstream cognitive psychology that have yet to be satisfactorily resolved.
Article
This paper reports the first phase of a research program on visual perception of motion patterns characteristic of living organisms in locomotion. Such motion patterns in animals and men are termed here as biological motion. They are characterized by a far higher degree of complexity than the patterns of simple mechanical motions usually studied in our laboratories. In everyday perceptions, the visual information from biological motion and from the corresponding figurative contour patterns (the shape of the body) are intermingled. A method for studying information from the motion pattern per se without interference with the form aspect was devised. In short, the motion of the living body was represented by a few bright spots describing the motions of the main joints. It is found that 10–12 such elements in adequate motion combinations in proximal stimulus evoke a compelling impression of human walking, running, dancing, etc. The kinetic-geometric model for visual vector analysis originally developed in the study of perception of motion combinations of the mechanical type was applied to these biological motion patterns. The validity of this model in the present context was experimentally tested and the results turned out to be highly positive.
Article
A multinomial logit model is used to examine pedestrian and driver reaction to “encounters” occurring on pedestrian crossings. The probabilities of a driver braking or weaving, and of a pedestrian continuing to cross in response to an encounter are identified for a variety of pedestrian, environmental, and traffic conditions. Results indicate that the most important explanatory variables included pedestrian distance from kerb, city size, number of pedestrians simultaneously crossing, vehicle speed, and vehicle platoon size. It is felt that the model performed well, should be applied in further studies, and could be a useful technique for identifying the most hazardous situations and locations within an area, for planning relevant safety measures, and for national research for developing traffic legislation.
Article
Four questions concerning the perceptual source of information about time to contact (tc) are addressed: (a) What conditions are required for the optic variable tau to play a role in the perception of tc? (b) When these conditions are met, does tau alone provide sufficient information for accurate timing of interceptive actions? (c) Does a distance divided by velocity account of tc perception provide a convincing alternative to an account that is based on tau? (d) Is there any empirical evidence that distinguishes the two accounts? A "global" type of tau variable and a "local" type of tau variable are distinguished, each with different limitations. The discussion is largely concerned with local tau variables, 2 versions of which are identified. It is concluded that tau alone cannot provide sufficient information for skilled timing. An extended tau-based account presented in an earlier article (Tresilan, 1990) is discussed. It is argued that no extant empirical data can distinguish the extended account from the distance divided by velocity account.
Article
Subjects estimated time of vehicle arrival while viewing twenty-four film clips of an approaching vehicle, half with a constant viewing time of 4.2 s and half with a constant vehicle-movement distance of 40 m. The distances from the subject at which the film ended were 20, 60, and 100 m. Speeds of approach varied between 7.45 and 15.44 m s-1. Performance was strongly dependent on age of the subject. Subjects in the 5-6-year-old group made estimates based on the distance of the vehicle; at 7-8 years an interaction between the effects of distance and velocity appeared and for 9-10-year-olds there was a main effect of the vehicle velocity. Only for adults was the information from distance and velocity fully integrated. There was no significant difference between males and females for any of the age groups. Performance of adults was very similar to that reported by other authors in that subjects underestimated the time to arrival of the vehicle, with estimated times about 60% of the actual times. Standard deviations of the estimated times were such that a small percentage of subjects overestimated times and hence would have caused a collision if they had proceeded with a crossing. The mechanism of time estimation was strongly dependent on the angular velocity of the vehicle subtended at the eye of the observer. This must exceed a threshold value of about 0.002 rad s-1 (adults) if a linear relationship between estimated and actual times is to be obtained.
Article
Drivers' estimates of time to collision were determined in a laboratory simulation using film segments made from a following vehicle approaching a lead vehicle, which was also in motion. Headway, approach speed, and viewing time were varied to make a total of 48 conditions. It was found that, provided the angular velocity subtended by the lead vehicle was above a threshold value of about .003 radians/sec, the driver was able to give reasonable estimates of time to collision. The standard deviation of the estimates varied linearly with the time to collision. Although drivers underestimated the time to collision when it was small, the large standard deviation shows the possibility of rear-end collisions due to poor estimation of time to collision, especially when the times for control action and vehicle deceleration are considered.
Article
The over-representation of older pedestrians in serious injury and fatal crashes compared to younger adults may be due, in part, to age-related diminished ability to select gaps in oncoming traffic for safe road-crossing. Two experiments are described that examine age differences in gap selection decisions in a simulated road-crossing environment. Three groups of participants were tested, younger (30-45 years), young-old (60-69 years) and old-old (>75 years). The results showed that, for all age groups, gap selection was primarily based on vehicle distance and less so on time-of-arrival. Despite the apparent ability to process the distance and speed of oncoming traffic when given enough time to do so, many of the old-old adults appeared to select insufficiently large gaps. These results are discussed in terms of age-related physical, perceptual and cognitive limitations and the ability to compensate for these limitations. Practical implications for road safety countermeasures are also highlighted, particularly the provision of safe road environments and development of behavioural and training packages.
Article
Two experiments were conducted to study how age affects street-crossing decisions in an estimation task, with particular emphasis on how oncoming vehicle speed and a time constraint influence the time gap deemed acceptable for crossing. Experiment 1 showed that when there was a time constraint, all age groups selected a shorter time gap for the higher speed. This was associated with a large number of missed opportunities for the low speed and many unsafe decisions for the high speed. In the second experiment, which had no time constraint, young pedestrians operated in a constant-time mode regardless of speed, whereas older pedestrians accepted shorter and shorter time gaps as speed increased. The results seem to indicate that the effect of speed is due to a mixed operating mode of participants, whose decisions may be based on either time or vehicle distance, depending on the task requirements and on the participant's own ability to meet those requirements.
Article
We examine the behaviour of pedestrians wishing to cross a stream of traffic at signalized intersections. We model each pedestrian as making a discrete crossing choice by comparing the gaps between vehicles in traffic to an individual-specific 'critical gap' that characterizes the individual's minimal acceptable gap. We propose both parametric and nonparametric approaches to estimate the distribution of critical gaps in the population of pedestrians. To estimate the model, we gather field data on crossing decisions and vehicle flows at three intersections in New Delhi. The estimates provide information about heterogeneity in critical gaps across pedestrians and intersections, and permit simulation of the effect of changes in traffic light sequences on pedestrian crossing behaviour and waiting times. Copyright © 2005 John Wiley & Sons, Ltd.
Article
This paper presents a method for pedestrian detection and tracking using a single night-vision video camera installed on the vehicle. To deal with the nonrigid nature of human appearance on the road, a two-step detection/tracking method is proposed. The detection phase is performed by a support vector machine (SVM) with size-normalized pedestrian candidates and the tracking phase is a combination of Kalman filter prediction and mean shift tracking. The detection phase is further strengthened by information obtained by a road-detection module that provides key information for pedestrian validation. Experimental comparisons (e.g., grayscale SVM recognition versus binary SVM recognition and entire-body detection versus upper-body detection) have been carried out to illustrate the feasibility of our approach.
Article
Intelligent vehicles and unattended driving systems ofthefuturewillneedtheabilitytorecognizerelevant tra#c participants (such as other vehicles, pedestrians, bicyclists, etc.) and detect dangerous situations ahead of time. An important component of these systems is one that is able to distinguish pedestrians and track their motion to make intelligent driving decisions. The associated computer vision problem that needs to be solved is detection and tracking of pedestrians from a moving camera, which is extremely challenging. Robust pedestrian tracking performance can be achieved by temporal integration of the data in a probabilistic setting. Weemployashapemodelforpedestriansand an e#cient variant of the Condensation tracker to achieve these objectives. The tracking is performed in the high-dimensional space of shape model parameters which consists of Euclidean transformation parameters and deformation parameters. Our Condensation tracker employs sampling on quasirandom points, improving its asymptotic complexity and robustness, and making it amenable to realtime implementation.
Unfallgeschehen im Straßenverkehr
  • Statistik Bundesamt Für
Bundesamt für Statistik (2007). Unfallgeschehen im Straßenverkehr 2006. Fachserie 8 Reihe 7, Wiesbaden.
Visual perception of biological motion and a model for its analysis
  • Johannson
Johannson, G. (1973). Visual perception of biological motion and a model for its analysis. Perception and Psychophysics, 14(2), 201-211.
Pedestrian tracking from a moving vehicle
  • V Philomin
  • R Duraiswami
  • L Davis
Philomin, V., Duraiswami, R. & Davis, L. (2000). Pedestrian tracking from a moving vehicle. In Proceedings of the IEEE intelligent vehicles symposium. Vol. IV, pp. 350-355.
Development, analysis and testing of a pedestrian alert system (PAS)
  • C Rodgers
  • D Greenlee
  • R Blomberg
Rodgers, C., Greenlee, D., & Blomberg, R. (2002). Development, analysis and testing of a pedestrian alert system (PAS). In Proceedings of the ION GPS, September 2002.
System and method for providing pedestrian alerts
  • C E Rodgers
  • D F Greenlee
  • R D Blomberg
Rodgers, C. E., Greenlee, D. F., & Blomberg, R. D. (2006). System and method for providing pedestrian alerts. US-Patent 7,095,336; 25 pp.
Geht er oder geht er nicht? - Ein FAS zur Vorhersage von Fußgängerabsichten
  • S Schmidt
  • B Färber
  • A Grassi
Schmidt, S., Färber, B., & Pérez Grassi, A. (2008). Geht er oder geht er nicht? -Ein FAS zur Vorhersage von Fußgängerabsichten. In M. Maurer & C. Stiller (Eds.), Workshop Fahrerassistenzsysteme, Freundeskreis Mess -und Regelungstechnik Karlsruhe e.V., Walting, 2-4 April 2008.
Fusion von MIR-Bildern und Lidardaten zur Klassifikation menschlicher Verkehrsteilnehmer
  • M Thuy
  • A Pérez Grassi
  • V A Frolov
  • F Puente León
Thuy, M., Pérez Grassi, A., Frolov, V. A., & Puente León, F. (2008). Fusion von MIR-Bildern und Lidardaten zur Klassifikation menschlicher Verkehrsteilnehmer. In M. Maurer & C. Stiller (Eds.), Workshop Fahrerassistenzsysteme, Freundeskreis Mess -und Regelungstechnik Karlsruhe e.V., Walting, 2-4 April 2008.
Klassifikation menschlicher Verkehrsteilnehmer in MIR-Bildern: eine erste Annäherung
  • Pérez Grassi
Grasping the intentions of others with one’s own mirror neuron system
  • Iacobini