No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Measuring People-Flow through Doorways Using Easy-to-Install IR Array Sensors
... ESP8266 has a large community of developers, which created and integrated specifics of this board into Arduino IDE. During initialization we will take background temperature for later processing optimization as is mentioned [24]. This will be important in the separation of objects, background and will help recognize background in various conditions (temperatures) [11]. ...
... Determining direction is a demanding task, requiring analysis of more pictures. Based on paper [24], we expect that it is not possible to extract direction from a single picture, because of the resolution. ...
... From this point we used a Gaussian filter for smoothing the image in next experiments. We performed an experiment for comparison with paper [24] with one man walking through doors in a controlled manner (Table 2). A participant was asked to walk through doors 150 times, 75 times out and 75 times into the room. ...
This paper is elaborating on problems in public transport in the context of Smart Cities and Internet of Things (IoT). The means of public transport are commonly overcrowded and on the other hand some lines could be designed inefficiently. This affects passengers’ comfort and also the financial site of public transport companies. The field of counting people in public transport is specific with its variety and limitations regarding setup in vehicles, which we took into account while designing the embedded system. We propose a solution—an embedded system with an array of infrared sensors. Approach uses image processing means (gauss filter, sliding average, and thresholding) for object detection, followed by the detection of direction by correspondence of objects positions across images. We performed controlled experiments with one and four participants in different scenarios which were compared to other similar solutions. We have achieved satisfying results up to 95%.KeywordsCountingPublic transportInfrared sensorsSmart citiesEmbedded systems
... However, their method is case sensitive and people with different heights might be missed easily since their detected blob areas may lie beyond the predefined range. In [10][11][12], an 8 × 8 IR array by Panasonic, called Grid-EYE [13], is used to record the bird's eye view of AoI. Due to the computational complexity of the proposed supervised learning based methods in [10,11] and the amount of data to be transferred via wireless networks, they are not feasible for an IoT-based WSN. ...
... Based on the deployment height and the size of AoI, one may need several sensors to cover a desired zone which makes counting more challenging due to overlapping FoVs. By using 8 × 8 Grid-EYE, the authors in [12] proposed a method to count the number of people who passed the doorway by leveraging a combination of Otsu's thresholding and modeling thermal noise distribution. For tracking the body(s) over series of frames, they have defined three features: spatial distance, temperature distance, and temporal distance. ...
... Among the mentioned constraints, the range of target's height is a key parameter to define the detection parameters and sensor deployment. When the target is too short, its detection is challenging since it is far from the sensor and measured temperature level lies within a lower thermal range [12]. On the other hand, when the target is very tall, it can be easily detected but the number of consecutive frames in which the target appears might be reduced depending on its body temperature, cloths, and walking speed. ...
Knowledge about the indoor occupancy is one of the important sources of information to design smart buildings. In some applications, the number of occupants in each zone is required. However, there are many challenges such as user privacy, communication limit, and sensor’s computational capability in development of the occupancy monitoring systems. In this work, a people flow counting algorithm has been developed which uses low-resolution thermal images to avoid any privacy concern. Moreover, the proposed scheme is designed to be applicable for wireless sensor networks based on the internet-of-things platform. Simple low-complexity image processing techniques are considered to detect possible objects in sensor’s field of view. To tackle the noisy detection measurements, a multi-Bernoulli target tracking approach is used to track and finally to count the number of people passing the area of interest in different directions. Based on the sensor node’s processing capability, one can consider either a centralized or a full in situ people flow counting system. By performing the tracking part either in sensor node or in a fusion center, there would be a trade off between the computational complexity and the transmission rate. Therefore, the developed system can be performed in a wide range of applications with different processing and transmission constraints. The accuracy and robustness of the proposed method are also evaluated with real measurements from different conducted trials and open-source dataset.
... They also presented an active pixel detection algorithm that is based on background subtraction and simple thresholding methods. As discussed in [10], such an approach is ineffective in certain scenarios as it may over-filter a frame, leading to the loss of useful information and thus ineffective feature vectors. The features used in the paper include total active points, number of connected components, and size of the largest component. ...
... In the paper [10], the authors proposed an occupancy estimation technique based on entry and exit events through doors by placing the GridEye sensor on the doorway. The accuracy achieved therein is around 92%. ...
... F b is extracted from F with L (i) as mask 9: T b ← T + δ b increase the threshold 10: 11: record all blobs in L b as valid blobs 12: frame. Fig. 9 demonstrates the intermediate stages of filtering process proposed in the paper, where frame (a) is the original sensor data frame, frame (b) is the active pixels frame using the proposed pixel level thresholding method, frame (c) is the result of the first level of filtering, with the threshold that is increased by δ b , when applied to the active pixels frame, frame (d) is the result of the second level of filtering, with a threshold that is increased by 2δ b , when applied to the blobs that is larger than s 1,max . ...
Occupancy estimation has a broad range of applications in security, surveillance, traffic and resource management in smart building environments. Low-resolution thermal imaging sensors can be used for real-time non-intrusive occupancy estimation. Such sensors have a resolution that is too low to identify occupants, but it may provide sufficient data for real-time occupancy estimation. In this paper, we present a systematic study of three thermal imaging sensors with different resolutions, with a focus on sensor characterization, estimation algorithms, and comparative analysis of occupancy estimation performance. A unified processing algorithms pipeline for occupancy estimation is presented and the performance of three sensors are compared side-by-side. A number of specific algorithms are proposed for pre-processing of sensor data, feature extraction, and fine-tuning of the occupancy estimation algorithms. Our results show that it is possible to achieve about 99% accuracy for occupancy estimation with our proposed approach, which might be sufficient for many practical smart building applications.
... GridEye AMG88xx (Panasonic), 8 x 8 pixels infrared array is a widely known component and has been used previous human occupancy detection, counting or tracking studies [1] [4][5][6][7][8][9][10][11][12][13]. IR-arrays with the same amount of pixels as GridEye, but in different dimensions, are available. ...
... A doorway counter has 96% accuracy in indicating whether a room is occupied or not, 91 % accuracy in showing the time a room has been occupied and 87% accuracy in showing times a person has entered in or exited from a room. [9] presents a doorway counter which is a single sensor located on the side of a doorway at a height between 125 cm to 140 cm. Its operation has been verified with a door width of 90 cm and 180 cm. ...
... In previous studies GridEye has shown surprisingly good accuracy in occupant counting. According to [9], accuracy in estimating the number of occupants in a room was 93%. As a doorway sensor, mounted on the side at height of 140 cm, the accuracy was 89-92%. ...
A doorway counter, which detects a person underpass at a room
entry/exit, may be the most accurate type of occupancy counters used in buildings. An occupancy counter, which uses a low-resolution IR-imager and Raspberry Pi board has been constructed. The imager provides only 8 x 8 pixels initial resolution, but it has been enhanced using two-dimensional interpolation. Due to the low absolute accuracy in temperature measurements, the imager is set to measure temperature difference between a target and background. Signal-to noise ratio is also increased using discrete two-dimensional convolution filtering. The blob detection and tracking algorithm deduces the direction of an occupant and finally increments or decrements the counter. A heat signature varies between people and depends on person’s clothing. An on-board server on Raspberry Pi
distributes the data via Wi-Fi to any client device in the net. The complete system includes also wireless PIR-sensors. The low-resolution IR occupancy counter has been compared with counters based on different technologies. The benefits of a low-resolution IR-imager are privacy preservation, operation capability in total
darkness, energy-efficient passive operation and a low price.
... where, σ is the standard deviation of the Gaussian distribution with mean of 0 [43]. The 3 × 3 filter mask for Gaussian is given as: ...
... From this, the segmented binary image is obtained. In a binary thermal image, all the foreground object temperature values are binary ones and the background are binary zero [43], [44]. The foreground image shows the occupancy of humans. ...
Low-Resolution Thermopile Array Sensors are widely used in several indoor applications such as security, intelligent surveillance, robotics, military, and health monitoring systems. It is compact, cost-effective, and offers a low-resolution thermal image of the environment, attracting its use in privacy-focused applications. Many industries migrating towards Industry 4.0 are facing challenges in using sensors and automating the systems. One of the areas in which automation could be implemented is by using sensors to operate the systems smartly based on occupancy. The major challenge in such applications is maintaining privacy; conventional imaging mechanisms using optical camera systems fail to achieve it. The same could be achieved by using thermopile sensors which provide thermal data of the desired region. This generates the possibility to identify the number of people in a specified area without revealing their identity. This paper proposes various approaches to detect human occupancy using a low-resolution infrared thermopile array sensor to keep their identity safe and avoid privacy issues. The proposed system detects IR-emitting objects using a low-resolution thermopile array Grid-EYE sensor (AMG8833). The sensor acquires
pixels of thermal distribution. These thermal distribution data are subjected to interpolation, filtering, adaptive thresholding, and background suppression to attain the set goal of human detection.
... Thermal imaging sensors have shown promising performance in many smart building and Internet of Things (IoT) applications such as human object localization, occupancy detection and estimation, activity recognition, security, surveillance, traffic and resource management, etc. [1][2][3][4][5][6][7][8][9][10][11][12][13][14]. In particular, low-5 resolution thermal imaging sensors are gaining more and more traction in occupancy estimation applications due to a number of advantages as compared to the more traditional object detection and object counting sensors. ...
... There are a number of infrared (IR) thermal imaging sensors readily avail- 15 able in the market with varying price, resolution, and various technical characteristics, including for example, GridEye, MLX90640, and Lepton [14]. A number of recent studies demonstrated promising use cases and performance results of low-resolution thermal imaging sensors, see for example [1][2][3][4][5][6][7][8][9][10][11][12][13][14] and the references therein. The focuses of the existing studies vary in terms of the 20 sensors employed, deployment structures, estimation and detection algorithms, and application scenarios. ...
Thermal imaging sensors have been increasingly integrated in a wide range of smart building and Internet of Things systems. Low-resolution thermal imaging sensors are especially suitable for applications that require non-intrusive monitoring with proper privacy protection. In this paper, we present an in-depth investigation of a low-resolution thermal imaging sensor (i.e., Melexis MLX90640) focusing on algorithm design issues and solutions when detecting moving objects. This type of sensors are designed to operate with a two-subpage chessboard reading pattern, which gives rise to blob displacements across two subpages when target objects are in motion. We have conducted systematic characterization of the sensor and demonstrated issues through experimental measurements and analysis. We have also proposed a subpage bilinear interpolation method and an enhanced sensor data preprocessing method for occupancy estimation with moving objects. The performance of the proposed method is analyzed by training and testing classification algorithms using two datasets collected with objects of different moving speeds. Our performance results indicate that the proposed method could be used for occupancy estimation in various smart building and Internet of Things applications.
... In a smart campus context, integrating sensing applications with official and public open data (such as lectures time tables, enrolment data, number of students attending lectures in classrooms and activities in labs, etc.), so as to count people who are in a room, can be effective in improving management activities. In order to get sufficiently precise information in this context, using a movement sensor or a presence sensor is not enough, because they are not adequate to count and return the number of occupants, since they are not sufficiently precise and accurate [25]. To face this issue, solutions providing more accuracy are those ones based on using pictures and video-camera [25]. ...
... In order to get sufficiently precise information in this context, using a movement sensor or a presence sensor is not enough, because they are not adequate to count and return the number of occupants, since they are not sufficiently precise and accurate [25]. To face this issue, solutions providing more accuracy are those ones based on using pictures and video-camera [25]. In this context, identifying lowbudget technological solutions (in terms of hardware and software) is necessary, so as to limit installation costs in all the smart campus environments (in particular, in classrooms and in labs). ...
The wide diffusion of smart objects and Internet of Things (IoT) is making available sensing applications that can support citizens' smart moving in outdoor contexts, as well as indoor ones. Detecting people presence and monitoring their flows could be strategic in public buildings, including shopping centers, administration offices, schools and universities. Having information about the actual occupancy of rooms in specific hours could provide useful insights for smart buildings management, that could be exploited in adequately setting the Heat, Ventilation and Air Conditioning (HVAC), the alarm, the lighting systems, and also other management issues (such as classrooms or labs assignment for different didactic activities, on the basis of the students frequency, in a smart campus). In this context, different approaches can be adopted, different technologies and sensors equipment can be installed, implying different requirements (in terms of budget), with different accuracy.
In this paper, we present a preliminary experiment aiming to detect and count people in small indoor crowded environments (such as students in a classroom). The paper describes a prototype we have designed and developed, by exploiting two different low-budget cameras. The results of an evaluation assessment are reported, by comparing the two cameras outcomes and discussing the obtained accuracy.
... Similarly, sensor site adaptation issues were presented in other research [36]- [39]. Aloulou et al. [40] presented an adaptable method for motion sensor plug-and-play systems utilized for older people's ambient assistive living. ...
Daily activity monitoring systems used in households provide vital information for health status, particularly with aging residents. Multiple approaches have been introduced to achieve such goals, typically obtrusive and non-obtrusive. Amongst the obtrusive approaches are the wearable devices, and among the non-obtrusive approaches are the movement detection systems, including motion sensors and thermal sensor arrays (TSAs). TSA systems are advantageous when preserving a person's privacy and picking his precise spatial location. In this study, human daily living activities were monitored day and night, constructing the corresponding activity time series and spatial probability distribution and employing a TSA system. The monitored activities are classified into two categories: sleeping and daily activity. Results showed the possibility of distinguishing between classes regardless of day and night. The obtained sleep activity duration was compared with previous research using the same raw data. Results showed that the duration of sleep activity, on average, was 9 hours/day, and daily life activity was 7 hours/day. The person's spatial probability distribution was determined using the bivariate distribution for the monitored location. In conclusion, the results showed that sleeping activity was dominant. Our study showed that TSAs were the optimum choice when monitoring human activity. Our proposed approach tackled limitations encountered by previous human activity monitoring systems, such as preserving human privacy while knowing his precise spatial location.
... However, in all the developments, the analysis is done on the offline data. The MLX90640 sensor detects and monitors workers' activity in an office and predicts the range between humans and the sensor [9][10][11][12][13]. Machine learning algorithms were used to analyze the activity of workers. ...
... Among deterministic approaches, [11] implemented a novel real-time pattern recognition algorithm to process data sensed from doorway-mounted low-resolution IR array sensors to determine the number of people in a room. Similarly, [26] also takes advantage of a doorway-mounted sensor, combined with a body extraction and localization algorithm, and background determination. [27] proposed a similar lightweight deterministic solution based on a single array sensor positioned on a (*) These entries refer to our deployment of the method described in [25]. ...
Ultra-low-resolution Infrared (IR) array sensors offer a low-cost, energy-efficient, and privacy-preserving solution for people counting, with applications such as occupancy monitoring. Previous work has shown that Deep Learning (DL) can yield superior performance on this task. However, the literature was missing an extensive comparative analysis of various efficient DL architectures for IR array-based people counting, that considers not only their accuracy, but also the cost of deploying them on memory- and energy-constrained Internet of Things (IoT) edge nodes. In this work, we address this need by comparing 6 different DL architectures on a novel dataset composed of IR images collected from a commercial 8x8 array, which we made openly available. With a wide architectural exploration of each model type, we obtain a rich set of Pareto-optimal solutions, spanning cross-validated balanced accuracy scores in the 55.70-82.70% range. When deployed on a commercial Microcontroller (MCU) by STMicroelectronics, the STM32L4A6ZG, these models occupy 0.41-9.28kB of memory, and require 1.10-7.74ms per inference, while consuming 17.18-120.43 J of energy. Our models are significantly more accurate than a previous deterministic method (up to +39.9%), while being up to 3.53x faster and more energy efficient. Further, our models' accuracy is comparable to state-of-the-art DL solutions on similar resolution sensors, despite a much lower complexity. All our models enable continuous, real-time inference on a MCU-based IoT node, with years of autonomous operation without battery recharging.
... Among deterministic approaches, [11] implemented a novel real-time pattern recognition algorithm to process data sensed from doorway-mounted low-resolution IR array sensors to determine the number of people in a room. Similarly, [26] also takes advantage of a doorway-mounted sensor, combined with a body extraction and localization algorithm, and background determination. [27] proposed a similar lightweight deterministic solution based on a single array sensor positioned on a This article has been accepted for publication in IEEE Internet of Things Journal. ...
Ultra-low-resolution Infrared (IR) array sensors offer a low-cost, energy-efficient, and privacy-preserving solution for people counting, with applications such as occupancy monitoring and visitor flow analysis in private and public spaces. Previous work has shown that Deep Learning (DL) can yield superior performance on this task. However, the literature was missing an extensive comparative analysis of various efficient DL architectures for IR array-based people counting, that considers not only their accuracy, but also the cost of deploying them on memory-and energy-constrained Internet of Things (IoT) edge nodes. Such analysis is key for system designers, since it helps them select the most appropriate DL model given the constraints of their target hardware. In this work, we address this need by comparing 6 different DL architectures on a novel dataset composed of IR images collected from a commercial 8x8 array, which we made openly available. With a wide architectural exploration of each model type, we obtain a rich set of Pareto-optimal solutions, spanning cross-validated balanced accuracy scores in the 55.70-82.70% range. When deployed on a commercial Microcontroller (MCU) by STMicroelectronics, the STM32L4A6ZG, these models occupy 0.41-9.28kB of memory, and require 1.10-7.74ms per inference, while consuming 17.18-120.43 of energy. Our models are significantly more accurate than a previous deterministic method (up to +39.9%), while being up to 3.53x faster and more energy efficient. So, our work serves also as a demonstration that DL can not only achieve higher accuracy, but also higher efficiency compared to classic algorithms for this type of task. Further, our models accuracy is comparable to state-of-the-art DL solutions on similar resolution sensors, despite a much lower complexity. All our models enable continuous, real-time inference on a MCU-based IoT node, with years of autonomous operation without battery recharging.
... For the ride-hailing application, the vehicle needs to detect the presence of the rider and identify him/her before localizing him/her. Humans can be detected using cameras [48,54], depth sensors [10,11,20,21,26,[28][29][30], IRarray sensors [27], mmWave radars [5,52], Wi-Fi [4,[7][8][9], and using other sensors for various purposes [14,33,34]. ...
With the rise of hailing services, people are increasingly relying on shared mobility (e.g., Uber, Lyft) drivers to pick up for transportation. However, such drivers and riders have difficulties finding each other in urban areas as GPS signals get blocked by skyscrapers, in crowded environments (e.g., in stadiums, airports, and bars), at night, and in bad weather. It wastes their time, creates a bad user experience, and causes more CO2 emissions due to idle driving. In this work, we explore the potential of Wi-Fi to help drivers to determine the street side of the riders. Our proposed system is called CarFi that uses Wi-Fi CSI from two antennas placed inside a moving vehicle and a data-driven technique to determine the street side of the rider. By collecting real-world data in realistic and challenging settings by blocking the signal with other people and other parked cars, we see that CarFi is 95.44% accurate in rider-side determination in both line of sight (LoS) and non-line of sight (nLoS) conditions, and can be run on an embedded GPU in real-time.
... The low-resolution thermal imaging sensors make the object association in specific more challenging in the scenarios where multiple people enter or leave the frame simultaneously. A minimum distance and temperature difference-based tracking algorithm are implemented in [16] with an accuracy of 89-92% in counting people at doorways. However, given the noise level in thermal sensors, low resolution, and the dynamic walking speeds of humans, it is extremely challenging to distinguish one human object from other human objects. ...
The sensor systems are growing daily in terms of their complexity and getting more sophisticated from an application perspective. Smart cities and intelligent buildings are critical driving factors in designing and improving sensor systems. However, there is always a big concern about invading people’s privacy and finding the right balance between privacy and sensing accuracy. In our previous work, we demonstrated how thermal imaging sensors could estimate occupancy effectively in a non-intrusive way. This paper presents an efficient sensor system design of a non-intrusive occupancy monitoring system (OMS). It uses state-of-the-art open-source software elements such as the FastAPI web framework, Raspberry Pi, low-resolution IR thermal sensor, temperature, humidity, and motion sensors. We also present our data collection methods in detail and show valuable insights and experimental results to demonstrate that our OMS can accurately estimate the occupancy in a designated area or a room level to meet various demanding real-time occupancy monitoring applications.
... The cost of ultrasonic transponders increases with their ability to produce higher frequency signals, which increases accuracy. [18][19][20] The main concept is to put IR array sensors and monitor the temperature pattern of the room in search of rapid changes caused by a person's presence. [21] The use of RGB cameras is a relatively common method for tracking and counting people [22]. ...
... erefore, to classify the brain tumor images in this proposed research, ANFIS is employed. e neuro-fuzzy classifier is a hybrid of ANN and fuzzy logic, with the neural network determining the fuzzy system parameters [27,28]. e neurofuzzy classifier is used in this study to detect anomalies in brain magnetic resonance imaging, where the hybrid intelligent system is the product of the neurofuzzy hybridization. ...
A neurological disorder is a problem with the neural system of the body, as a brain tumor is one of the deadliest neurological conditions and it requires an early and effective detection procedure. The existing detection and diagnosis methods for image evaluation are based on the judgment of the radiologist and neurospecialist, where a risk of human mistakes can be found. Therefore, a new flanged method and methodology for detecting brain tumors using magnetic resonance imaging and the artificial neural network (ANN) technique are applied. The research is based on an artificial neural network-based behavioral examination of neurological disorders. In this study, an artificial neural network is used to detect a brain tumor as early as possible. The current work develops an effective approach for detecting cancer from a given brain MRI and recognizing the retrieved data for further use. To obtain the desired result, the following three procedures are used: preprocessing, feature extraction, training, and detection or classification. A Gaussian filter is also incorporated to eliminate noise from the image, and for texture feature extraction, GLCM is considered in this study. Further entropy, contrast, energy, homogeneity, and other GLCM texture properties of tumor categorization are measured using the ANFIS approach, which determines if the tumor is normal, benign, or malignant. Future research will focus on applying advanced texture analysis to classify brain tumors into distinct classes in order to improve the accuracy of brain tumor diagnosis. In the future, MRI brain imaging will be used to classify metastatic brain tumors.
... The emergence of thermal vision sensors is an excellent non-invasive and privacyfriendly approach to monitor people in their homes [8]; [21]. However, most work in the scientific literature makes use of visible-spectrum sensors, due to the encouraging performance of deep learning in multimedia data analysis using IoT [12]. ...
In this work, we propose the use of thermal vision sensors to estimate the frontal body landmarks of an inhabitant. The use of thermal sensors is being promoted to collect human patterns while protecting inhabitants’ privacy in smart environments. On the other hand, deep learning approaches have provided encouraging results in estimating body, hand and facial landmarks. Here, we present a residual neural network which produces body landmarks from images collected by a low cost thermal sensor. In order to solve the problems of capturing and labeling data, which hinder learning in deep learning models, we propose an auto-labeling approach with dual visible-spectrum and thermal cameras, including the recognition of keypoints by the OpenPose model. A case study developed with four inhabitants in different poses shows encouraging results.
... In fact, such activities are able to provide information that can be useful and can be exploited for different purposes [1]. A few examples from the context of smart building management include the configuration settings of heat, ventilation and air conditioning (HVAC), alarms, lighting and building security systems [2]. ...
Studies and systems that are aimed at the identification of the presence of people within an indoor environment and the monitoring of their activities and flows have been receiving more attention in recent years, specifically since the beginning of the COVID-19 pandemic. This paper proposes an approach for people counting that is based on the use of cameras and Raspberry Pi platforms, together with an edge-based transfer learning framework that is enriched with specific image processing strategies, with the aim of this approach being adopted in different indoor environments without the need for tailored training phases. The system was deployed on a university campus, which was chosen as the case study. The proposed system was able to work in classrooms with different characteristics. This paper reports a proposed architecture that could make the system scalable and privacy compliant and the evaluation tests that were conducted in different types of classrooms, which demonstrate the feasibility of this approach. Overall, the system was able to count the number of people in classrooms with a maximum mean absolute error of 1.23.
... Similarly, there are also other systems in [36], [56]- [60] which also faces sensor adaptation issues where TS cannot achieve the occupancy estimation well. The experimental setup of the occupancy estimation can be seen in the figure 2, where it shows how it can be used for the HVAC systems in smart buildings. ...
The use of thermal sensors is increasing in response to dealing with the problems of the visible light spectrum. These sensors measure the temperature of the object and convert it to some readable output. There is a diverse range of temperature sensors, and different sensors are used for different purposes. The choice of the sensor depends on the cost of the sensor, resolution, and level of accuracy. For instance, an IR camera combined with the RGB sensor can produce better human activity recognition. However, increase the cost of the machine. For some applications, a high resolution is not required and a low-cost sensor can satisfy the need. In this survey, we discuss the employment of thermal sensors in HVAC systems, vehicle, and manufacturing industries as they are heavily used in these industries. We reported the types of available thermal sensors and the sensors commonly used in each industry. This is followed by a comprehensive review of the application-specific methods. In the end, we may say that the selection of the thermal sensor has much importance as well as the choice of the suitable algorithms according to the given conditions to avail the maximum accuracy in our results.
... Trofimova et al. [5], have employed the noise rеmоvаl technique bаsеd оn Kаlmаn filter (KF) tо detect human presence in indoor environment and reported improved accuracy in human detection up to 97%. Mohammadmoradi et al. [6], have utilized a threshold-based technique and temperature filtering technique to estimate the flow of people through doorways using a low-resolution IR sensor array. They have reported an average accuracy of 93%. ...
... Diraco et al. [38] evaluate the performance of two depth sensors for occupancy estimation, namely the MESA SR4000 and Kinect sensors, and subsequently apply this information to energy management. Apart from depth sensors, other literature has investigated the use of passive infrared sensors (PIRs) [39] and infrared arrays [40] for occupancy estimation. However, none of the existing approaches have leveraged the use of both depth and infrared sensors for occupancy estimation. ...
The planning of public transport operations is an essential component of urban transport management systems that aims to provide the most efficient, safe and effective way to support movement of people. Improving the customer journey experience is a key focus, as cities grow and sustainable public transport becomes more critical. This has led to an increased interest in Automatic Passenger Counting (APC) technologies that provide real-time estimates of occupancy in order to support better planning and customer information. The proliferation of sensors and power-efficient miniaturised computing capabilities offer a range of low-cost and versatile APC choices. However, it is important to understand the various design and implementation considerations and trade-offs of the APC technologies in the context of transport operation scenarios they are deployed in. In this paper, we present outcomes of a field study that evaluated the four APC solutions video, floor-based sensing, WiFi and Infrared sensing. We present an evaluations methodology that authentically captures operating conditions while providing a robust way to assess APC solutions. While most technologies achieve over 70% accuracy in some settings, the differences between weekend trips with longer legs and weekday services with short distances between stops lead to stark variations in the performances.
... Basu and Rowe, in [16], developed a low-cost method to estimate the direction of human motion (with 80% accuracy) using a 64 pixels IR sensor array and using a support vector machine algorithm. Mohammadmoradi et al.,in [17], employed a threshold-based technique (Otsu's binarization) to estimate the people flow (with an average 93% accuracy) through doorways using a low-resolution IR sensor array. ...
We propose a device for monitoring the number of people who are physically present inside indoor environments. The device performs local processing of infrared array sensor data detecting people’s direction, which allows monitoring users’ occupancy in any space of the building and also respects people privacy. The device implements a novel real-time pattern recognition algorithm for processing data sensed by a low-cost infrared (IR) array sensor. The computed information is transferred through a Z-Wave network. On-field evaluation of the algorithm has been conducted by placing the device on top of doorways in offices and laboratory rooms. To evaluate the performance of the algorithm in varying ambient temperatures, two groups of stress tests have been designed and performed. These tests established the detection limits linked to the difference between the average ambient temperature and perturbation. For an in-depth analysis of the accuracy of the algorithm, synthetic data have been generated considering temperature ranges typical of a residential environment, different human walking speeds (normal, brisk, running), and distance between the person and the sensor (1.5 m, 5 m, 7.5 m). The algorithm performed with high accuracy for routine human passage detection through a doorway, considering indoor ambient conditions of 21–30 °C.
... As a preliminary study in this field, we have investigated two different approaches and hardware low-cost equipment, to detect and count people who are occupying a classroom in a smart building, within a University campus 9 . In fact, having information about the occupancy of an indoor environment can provide insights for smart building management, letting it adequately configure settings like Heat, Ventilation and Air Conditioning (HVAC), the alarm, the lighting, and the building security systems, just to cite the most commonly used and important ones 10 . We have set up a prototype that iteratively repeats the following steps: (i) takes a picture of the people in the room employing a camera, (ii) predicts the number of occupants on the basis of already conducted training (such a computation is based on YOLOv3 11 , and in its first version it was conducted on a Raspberry Pi 2 Model B), (iii) deletes the picture. ...
... Compared with commonly used sensors such as cameras and microphones, infrared-based sensors have their own advantages [6]. Some researchers use a group of infrared array sensors to monitor the movement of pedestrians by detecting human existence and create trajectories of pedestrians [7], while other researchers use a long short-term memory and gated recurrent unit models to construct a fall detection system based on infrared array sensors [8]. Besides, location [9] and bedexit detection [10] have also been attempted with infrared array sensors. ...
Nowadays, with the development of automotive driving technologies, more and more functions and devices with control systems based on tactile, optical, and acoustic sensors are assembled into cars. However, these systems are faced with environmental limitations such as environmental noise and illumination conditions. Moreover, operations of these systems will cause lack of concentration on driving, which is a major cause of car accidents. In order to overcome these limitations, in this paper, an infrared array sensor is applied to construct a hand posture recognition system for in-vehicle device control. In the system, 10 kinds of target hand postures and posture movements toward four directions are combined to achieve the aim of the device selection and operations. The input images are separated into images with objects and without objects. Then, images in which object appears in boundary areas as well as blurred images are removed to improve the accuracy of the system. A convolutional neural network is applied as a classifier in order to realize the recognition of the 10 target hand postures and non-target postures for the in-vehicle device selection. After that, a detection method of the posture movement directions is applied for the device operations. Both indoor and in-vehicle experiments are conducted to verify the robustness of this system, and the results show that the proposed system can overcome the disadvantages of other systems and has a wide application with high accuracy.
... Request permissions from permissions@acm.org. [10], infrared array sensors [8], depth sensors [9], millimeter wave radar [12], radio [3], and thermal images. While each sensing solution has its strength and weakness, with the rapid drop of price, depth sensors have the potential to provide very accurate occupancy estimation in a non-privacy invasive way [9] [7]. ...
Occupancy detection, tracking, and estimation has a wide range of applications including improving building energy efficiency, safety, and security of the occupants. As depth sensors are getting cheaper, they offer a viable solution to estimate occupancy accurately in a non-privacy invasive manner. Even though there are publicly available depth datasets, they do not consider placing the sensor in the ceiling looking downwards to estimate occupancy. We deployed four Kinect for XBOX One in four CMU classrooms and conference rooms for a period of four weeks in 2017 and collected over 6 TB of depth data. We annotate this huge dataset by labelling bounding boxes around occupants and release the annotated dataset.
... HVAC systems can also be controlled in an inexpensive way by making use of 8X8 IR array. These sensors are deployed at doorways and [7]. ...
Deprem gibi felaketlerde can kaybını önlemek için hızlı ve etkili bir şekilde bilgi sağlama yeteneği,
yaşamsal öneme sahiptir. Acil durumlarda apartmanda bulunan kişi sayısı hızlı bir şekilde tespit
edebilmesi çok önemlidir. Özellikle deprem gibi afet durumlarında, apartmanda veya binalarda bulunan
kişi sayısı bilgilerinin ilgili kurtarma ekiplerine iletilerek, kişilere etkili bir yardım sağlanabilir. Bu
proje ile apartman güvenliğini artırmak ve deprem gibi acil durumlarda can kaybını önlemek amacıyla
Arduino tabanlı bir sistem geliştirilmiştir. Arduino programlama dili olarak C++ kullanılmış ve
projenin prototipi yapılmıştır. Sistem, IR sensörleri kullanılarak apartmana giren ve apartmandan çıkan
kişilerin sayısının takibini gerçekleştirilebilmektedir. Algılanan veriler, anlık olarak LCD panel
üzerinde görüntülenmekte ve aynı anda Bluetooth modülü aracılığıyla mobil uygulamaya üzerinden
ilgili kurum, kuruluş ve kişilere iletilebilmektedir. Bu sayede kullanıcılar, uzaktan erişim sağlayarak
apartmandaki kişi sayısını takip edilebilmektedir. Bu proje ile apartman güvenliği ve acil durum
yönetimi konularında önemli bir adım niteliği taşımaktadır. Ayrıca apartman sakinlerine güvenli bir
ortam sağlamanın yanı sıra, acil durum yönetimi konusunda da önemli bir katkı sunmaktadır.
In dynamic environments, robots require instantaneous detection of moving events with microseconds of latency. This task, known as moving event detection, is typically achieved using event cameras. While light detection and ranging (LiDAR) sensors are essential for robots due to their dense and accurate depth measurements, their use in event detection has not been thoroughly explored. Current approaches involve accumulating LiDAR points into frames and detecting object-level motions, resulting in a latency of tens to hundreds of milliseconds. We present a different approach called M-detector, which determines if a point is moving immediately after its arrival, resulting in a point-by-point detection with a latency of just several microseconds. M-detector is designed based on occlusion principles and can be used in different environments with various types of LiDAR sensors. Our experiments demonstrate the effectiveness of M-detector on various datasets and applications, showcasing its superior accuracy, computational efficiency, detection latency, and generalization ability.
The report illustrates the state of the art of the most successful AAL applications and functions based on audio and video data, namely (i) lifelogging and self-monitoring, (ii) remote monitoring of vital signs, (iii) emotional state recognition, (iv) food intake monitoring, activity and behaviour recognition, (v) activity and personal assistance, (vi) gesture recognition, (vii) fall detection and prevention, (viii) mobility assessment and frailty recognition, and (ix) cognitive and motor rehabilitation. For these application scenarios, the report illustrates the state of play in terms of scientific advances, available products and research project. The open challenges are also highlighted.
One of the main objectives of smart homes is to facilitate daily life by increasing user comfort, with the potential to play a key role in revolutionizing healthcare for the elderly, the disabled and people with functional limitations. To achieve this end, smart homes will have to be able to distinguish the identity of users, their location and the activities they are performing, while also being implemented in a non-invasive way that protects the privacy of these users. Computer vision is one of the main technologies included in smart homes. However, there are drawbacks to traditional cameras, given their dependence on light and privacy-related concerns. Thermal cameras provide a solution, as they operate regardless of light conditions (e.g. at night) while respecting users’ privacy. In this work, image reconstruction and identification of inhabitants from facial images collected by low-resolution thermal sensors has been carried out by using Conditional Generative Adversarial Neural Networks (CGANs). The system has been implemented through an IoT device with raspberry Pi and dual-vision thermal and visible-spectrum sensors installed in a real smart home to automatically collect paired visible-spectrum and thermal images. Thus, different configurations of CGANs have been implemented and analyzed to achieve the following outcomes: (1) inhabitant identification (normal and masked face) with enhanced user privacy and (2) transfer from thermal to colour images in the visible spectrum. Results show that the proposed CGAN achieves a recognition rate of 95% and 94% for uncovered and masked faces. This enables user identification without registering accurate facial expressions in the color image reconstruction, protecting user privacy. Furthermore, the developed system outperformed similar approaches using low-resolution datasets and has demonstrated that the accuracy of image reconstruction depends on the resolution of the input visible-spectrum images. In addition, a contribution to high-performance computing has been made by designing a CGAN that runs efficiently on multiple GPUs, achieving increased performance and response speed of the network, as well as applicability to larger problems.
It is a matter of fact that Europe is facing more and more crucial challenges regarding health and social care due to the demographic change and the current economic context. The recent COVID-19 pandemic has stressed this situation even further, thus highlighting the need for taking action. Active and Assisted Living (AAL) technologies come as a viable approach to help facing these challenges, thanks to the high potential they have in enabling remote care and support. Broadly speaking, AAL can be referred to as the use of innovative and advanced Information and Communication Technologies to create supportive, inclusive and empowering applications and environments that enable older, impaired or frail people to live independently and stay active longer in society. AAL capitalizes on the growing pervasiveness and effectiveness of sensing and computing facilities to supply the persons in need with smart assistance, by responding to their necessities of autonomy, independence, comfort, security and safety. The application scenarios addressed by AAL are complex, due to the inherent heterogeneity of the end-user population, their living arrangements, and their physical conditions or impairment. Despite aiming at diverse goals, AAL systems should share some common characteristics. They are designed to provide support in daily life in an invisible, unobtrusive and user-friendly manner. Moreover, they are conceived to be intelligent, to be able to learn and adapt to the requirements and requests of the assisted people, and to synchronise with their specific needs. Nevertheless, to ensure the uptake of AAL in society, potential users must be willing to use AAL applications and to integrate them in their daily environments and lives. In this respect, video- and audio-based AAL applications have several advantages, in terms of unobtrusiveness and information richness. Indeed, cameras and microphones are far less obtrusive with respect to the hindrance other wearable sensors may cause to one's activities. In addition, a single camera placed in a room can record most of the activities performed in the room, thus replacing many other non-visual sensors. Currently, video-based applications are effective in recognising and monitoring the activities, the movements, and the overall conditions of the assisted individuals as well as to assess their vital parameters (e.g., heart rate, respiratory rate). Similarly, audio sensors have the potential to become one of the most important modalities for interaction with AAL systems, as they can have a large range of sensing, do not require physical presence at a particular location and are physically intangible. Moreover, relevant information about individuals' activities and health status can derive from processing audio signals (e.g., speech recordings). Nevertheless, as the other side of the coin, cameras and microphones are often perceived as the most intrusive technologies from the viewpoint of the privacy of the monitored individuals. This is due to the richness of the information these technologies convey and the intimate setting where they may be deployed. Solutions able to ensure privacy preservation by context and by design, as well as to ensure high legal and ethical standards are in high demand. After the review of the current state of play and the discussion in GoodBrother, we may claim that the first solutions in this direction are starting to appear in the literature. A multidisciplinary debate among experts and stakeholders is paving the way towards AAL ensuring ergonomics, usability, acceptance and privacy preservation. The DIANA, PAAL, and VisuAAL projects are examples of this fresh approach.
This report provides the reader with a review of the most recent advances in audio- and video-based monitoring technologies for AAL. It has been drafted as a collective effort of WG3 to supply an introduction to AAL, its evolution over time and its main functional and technological underpinnings. In this respect, the report contributes to the field with the outline of a new generation of ethical-aware AAL technologies and a proposal for a novel comprehensive taxonomy of AAL systems and applications. Moreover, the report allows non-technical readers to gather an overview of the main components of an AAL system and how these function and interact with the end-users.
The report illustrates the state of the art of the most successful AAL applications and functions based on audio and video data, namely (i) lifelogging and self-monitoring, (ii) remote monitoring of vital signs, (iii) emotional state recognition, (iv) food intake monitoring, activity and behaviour recognition, (v) activity and personal assistance, (vi) gesture recognition, (vii) fall detection and prevention, (viii) mobility assessment and frailty recognition, and (ix) cognitive and motor rehabilitation. For these application scenarios, the report illustrates the state of play in terms of scientific advances, available products and research project. The open challenges are also highlighted.
The report ends with an overview of the challenges, the hindrances and the opportunities posed by the uptake in real world settings of AAL technologies. In this respect, the report illustrates the current procedural and technological approaches to cope with acceptability, usability and trust in the AAL technology, by surveying strategies and approaches to co-design, to privacy preservation in video and audio data, to transparency and explainability in data processing, and to data transmission and communication. User acceptance and ethical considerations are also debated. Finally, the potentials coming from the silver economy are overviewed.
Detection of human presence can be used for intelligently switching on and off devices. This will save a lot of electricity as well as help in building an intuitive experience for smart homeowners. In the future, technologies like artificial intelligence may also benefit from this information by taking smart decisions and providing more contextual responses. One can find many research proposals and commercial products for efficiently counting humans. However, these systems are very costly, extremely difficult to install, and many a time obstructs people. It is the reason why they have still not made it to residential homes yet. In this paper, we have discussed some of the most cutting-edge technologies that can be used for sensing humans. We analyze them based on six factors and determine how economic and easy to deploy they are. Some of the solutions deliver promising results and have the potential of becoming a mass-market product. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Steganography is the oldest technique that is been used from century, steganography purpose has not changed, i.e., all these techniques aim at hiding data or protecting data. With the help of steganalysis, the media can be analyzed to check for the presence of any secret information. Nowadays, attackers are making the use of advanced steganography approaches to conceal the secret information and communicate in a stealth manner. In this paper, the authors have discussed about the novel approach to hide malicious payload into image metadata. Therefore, metadata is a data that describes about the image rights and its administration. Hacker generally uses this metadata to perform various malicious attacks such embedding malicious script inside the image metadata and many more.
Monitoring indoor activities of daily living (ADLs) of a person is subjected to dependency on sensor type, power supply stability, and connectivity stability without mentioning artifacts introduced by the person himself. Multiple challenges have to be overcome in this field, such as; detecting the precise spatial location of the person, and estimating vital signs like an individual's average temperature. Privacy is another domain of the problem to be thought of with care. Identifying the person's posture without a camera is another challenge. Posture identification is a key in assisting detection of a person's fall. Thermal imaging could be a proper solution for most of the mentioned challenges. It provides monitoring both the person's average temperature and spatial location while maintaining privacy. In this research, an IoT system for monitoring an indoor ADL using thermal sensor array (TSA) is proposed. Three classes of ADLs are introduced, which are daily activity, sleeping activity and no-activity respectively. Estimating person average temperature using TSAs is introduced as well in this paper. Results have shown that the three activity classes can be identified as well as the person's average temperature during day and night. The person's spatial location can be determined while his/her privacy is maintained as well.
—Monitoring indoor activities of daily living (ADLs)
of a person is neither an easy nor an accurate process. It is
subjected to dependency on sensor type, power supply
stability, and connectivity stability without mentioning
artifacts introduced by the person himself. Multiple
challenges have to be overcome in this field, such as;
monitoring the precise spatial location of the person, and
estimating vital signs like an individual’s average
temperature. Privacy is another domain of the problem to be
thought of with care. Identifying the person’s posture without
a camera is another challenge. Posture identification assists in
the person’s fall detection. Thermal imaging could be a
proper solution for most of the mentioned challenges. It
provides monitoring both the person’s average temperature
and spatial location while maintaining privacy. In this
research, we propose an IoT system for monitoring an indoor
ADL using thermal sensor array (TSA). Three classes of
ADLs are introduced, which are daily activity, sleeping
activity and no-activity respectively. Estimating person
average temperature using TSAs is introduced as well in this
paper. Results have shown that the three activity classes can
be identified as well as the person’s average temperature
during day and night. The person’s spatial location can be
determined while his/her privacy is maintained as well.
Monitoring indoor activities of daily living (ADLs) of a person is neither an easy nor an accurate process. It is subjected to dependency on sensor type, power supply stability, and connectivity stability without mentioning artifacts introduced by the person himself. Multiple challenges have to be overcome in this field, such as; monitoring the precise spatial location of the person, and estimating vital signs like an individuals average temperature. Privacy is another domain of the problem to be thought of with care. Identifying the persons posture without a camera is another challenge. Posture identification assists in the persons fall detection. Thermal imaging could be a proper solution for most of the mentioned challenges. It provides monitoring both the persons average temperature and spatial location while maintaining privacy. In this research, we propose an IoT system for monitoring an indoor ADL using thermal sensor array (TSA). Three classes of ADLs are introduced, which are daily activity, sleeping activity and no-activity respectively. Estimating person average temperature using TSAs is introduced as well in this paper. Results have shown that the three activity classes can be identified as well as the persons average temperature during day and night. The persons spatial location can be determined while his/her privacy is maintained as well.
In this paper, we propose a novel people counting algorithm exploiting convolutional neural network (CNN) using a low radiation impulse radio ultra-wide bandwith (IR-UWB) radar. Because of the ever-changing signals caused by the various cases of human motion scales, superposition and obstruction of signals as well as the attenuate of signal’s strength along the distance and the angle, it is not easy to handle the people counting task by directly detecting targets for each range bin. Thus, we hope to excavate the information of targets’ patterns, including their densities and forms of patterns’ distributions in the detecting region to execute the counting task. To achieve this, the multi-scale range-time maps are extracted from the received data and further used to classify the number of people using the CNN. Finally, the experiments are conducted to show the priority of the proposed algorithm.
Thermal sensor array (TSA) offers privacy-preserving, low-cost, and non-invasive features, which makes it suitable for various indoor applications such as anomaly detection, health monitoring, home security, and monitoring energy efficiency applications. Previous approaches to human-centred applications using the TSA usually relied on the use of a fixed sensor location to make the human-sensor distance and the human presence shape fixed. However, placing this sensor in different locations and new indoor environments can pose a significant challenge. In this paper, a novel framework based on a deep convolutional encoder-decoder network is proposed to address this challenge in real-life deployment. The framework presents a semantic segmentation of the human presence and estimates the occupancy in indoor-environment. It is also capable to segment the human presence and counts the number of people from different sensor locations, indoor environments, and human to sensor distance. Furthermore, the impact of the distance on the human presence using the TSA is investigated. The framework is evaluated to estimate the occupancy in different sensor locations, the number of occupants, environments, and human distance with classification and regression machine learning approaches. This paper shows that the classification approach using the adaptive boosting algorithm is an accurate approach which has achieves an accuracy of 98.43% and 100% from vertical and overhead sensor locations respectively.
Accurate estimation of localized occupancy related informa- tion in real time enables a broad range of intelligent smart environment applications. A large number of studies using heterogeneous sensor arrays reflect the myriad requirements of various emerging pervasive, ubiquitous and participatory sensing applications. In this paper, we introduce a zero- configuration and infrastructure-less smartphone based lo- cation specific occupancy estimation model. We opportunis- tically exploit smartphone’s acoustic sensors in a conversing environment and motion sensors in absence of any conver- sational data. We demonstrate a novel speaker estimation algorithm based on unsupervised clustering of overlapped and non-overlapped conversational data and a change point detection algorithm for locomotive motion of the users to infer the occupancy. We augment our occupancy detection model with a fingerprinting based methodology using smart- phone’s magnetometer sensor to accurately assimilate loca- tion information of any gathering. We postulate a novel crowdsourcing-based approach to annotate the semantic lo- cation of the occupancy. We evaluate our algorithms in dif- ferent contexts; conversational, silence and mixed in pres- ence of 10 domestic users. Our experimental results on real-life data traces in natural settings show that using this hybrid approach, we can achieve approximately 0.76 error count distance for occupancy detection accuracy on aver- age.
Understanding occupant-building interactions helps in personalized energy and comfort management. However, occupant identification using affordable infrastructure, remains unresolved. Our analysis of existing solutions revealed that for a building to have real-time view of occupancy state and use it intelligently, there needs to be a smart fusion of affordable, not-necessarily-smart, yet accurate enough sensors. Such a sensor fusion should aim for minimalistic user intervention while providing accurate building occupancy data. We describe an occupant detection system that accurately monitors the occupants’ count and identities in a shared office space, which can be scaled up for a building. Incorporating aspects from data analytics and sensor fusion with intuition, we have built a Smart-Door using inexpensive sensors to tackle this problem. It is a scalable, plug-and-play software architecture for flexibly realizing smart-doors using different sensors to monitor buildings with varied occupancy profiles. Further, we show various smart-energy applications of this occupancy information: detecting anomalous device behaviour and load forecasting of plug-level loads.
Contemporary office buildings commonly experience changes in occupancy patterns and needs due to changes in business practice and personal churns. Hence, it is important to understand and accurately capture the information of such trends for applications in building design and subsequent building operations. Detection of occupant presence has been used extensively in built environments for applications such as demand-controlled ventilation and security, and occupancy profiles are widely used in building simulations. However, the ability to discern the actual number of people in a space is often beyond the scope of current sensing techniques. This paper presents a study to develop algorithms for occupancy number detection based on the analysis of environmental data captured from existing sensors and ambient sensing networks. Both wireless and wired sensor networks are deployed in the Robert L. Preger Intelligent Workplace (IW) at Carnegie Mellon University, comprising six different types of sensors. An average of 80% accuracy on the occupancy number detection was achieved by Hidden Markov Models during testing periods. The findings also offer encouraging possibilities for incorporating the algorithms into building management systems for optimizing energy use while maintaining occupant comfort.
This paper describes an implementation method for the people counting system which detects and tracks moving people using a fixed single camera. This system counts the number of moving objects (peo-ple) entering the security door. Moreover, the detected objects are tracked by the proposed tracking algorithm before entering the door. The proposed system with In-tel Pentium IV operates at an average rate of 10 frames a second on real world scenes where up to 6 persons come into the view of a vertically mounted camera.
Vision-based people counting systems have wide potential applications including video surveillance and public resources management. Most works in the literature rely on moving object detection and tracking, assuming that all moving objects are people. In this paper, we present our people counting approach based on face detection, tracking and trajectory classification. While we have used a standard face detector, we achieve face tracking combining a new scale invariant Kalman filter with kernel based tracking algorithm. From each potential face trajectory an angle histogram of neighboring points is then extracted. Finally, an Earth Mover's Distance-based K-NN classification discriminates true face trajectories from the false ones. Experimented on a video dataset of more than 160 potential people trajectories, our approach displays an accuracy rate up to 93%.
A novel real-time people counting system is presented in this paper. Using a single overhead mounted camera, the system counts the number of people going in and out of an observed area. Counting is performed by analyzing an image zone composed by a set of virtual counting lines. The system runs on a commercial PC, does not need a special background and is easily adjustable to different camera height requirements. We have tested the performance of the system, achieving a correct people counting rate of 95%.
Estimating the number of people in a crowded environment is a central task in civilian surveillance. Most vision-based counting techniques depend on detecting individuals in order to count, an unrealistic proposition in crowded settings. We propose an alternative approach that directly estimates the number of people. In our system, groups of image sensors segment foreground objects from the background, aggregate the resulting silhouettes over a network, and compute a planar projection of the scene's visual hull. We introduce a geometric algorithm that calculates bounds on the number of persons in each region of the projection, after phantom regions have been eliminated. The computational requirements scale well with the number of sensors and the number of people, and only limited amounts of data are transmitted over the network. Because of these properties, our system runs in real-time and can be deployed as an untethered wireless sensor network. We describe the major components of our system, and report preliminary experiments with our first prototype implementation.
Estimating the number of people within a room is important for a wide variety of applications including: HVAC load management, scheduling room allocations and guiding first responders to areas with trapped people. In this paper, we present an active sensing technique that uses changes in a room's acoustic properties to estimate the number of occupants. Frequency dependent models of reverberation and room capacity are often used when designing auditoriums and concert halls. We leverage this property by using measured changes in the ultrasonic spectrum reflected back from a wide-band transmitter to estimate occupancy. A centrally located beacon transmits an ultrasonic chirp and then records how the signal dissipates over time. By analyzing the frequency response over the chirp's bandwidth at a few known occupancy levels, we are able to extrapolate the response as the number of people in the room changes. We explore the design of an excitation signal that best senses the environment with the fewest number of training samples. Through experimentation, we show that our approach is able to capture the number of people in a wide-variety of room configurations with people counting accuracy below 10% of the maximum room capacity count with as few as two training points. Finally, we provide a simple mechanism that allows our system to recalibrate when we know the room is empty so that it can adapt dynamically over time.
In this paper, we present a room-level building occupancy estimation system (BOES) utilizing low-resolution
vibration sensors that are sparsely distributed. Many ubiquitous computing and building maintenance systems
require fine-grained occupancy knowledge to enable occupant centric services and optimize space and energy
utilization. The sensing infrastructure support for current occupancy estimation systems often requires multiple
intrusive sensors per room, resulting in systems that are both costly to deploy and difficult to maintain. To
address these shortcomings, we developed BOES. BOES utilizes sparse vibration sensors to track occupancy
levels and activities. Our system has three major components. 1) It extracts features that distinguish occupant
activities from noise prone ambient vibrations and detects human footsteps. 2) Using a sequence of footsteps, the
system localizes and tracks individuals by observing changes in the sequences. It uses this tracking information to
identify when an occupant leaves or enters a room. 3) The entering and leaving room information are combined
with detected individual location information to update the room-level occupancy state of the building. Through
validation experiments in two different buildings, our system was able to achieve 99.55% accuracy for event
detection, less than three feet average error for localization, and 85% accuracy in occupancy counting.
Indoor tracking systems will be an essential part of the home of the future, enabling location-aware and individually-tailored services. However, today there are no tracking solutions that are practical for "every day" use in the home. In this paper, we introduce the Doorjamb track-ing system that uses ultrasonic range finders mounted above each doorway, pointed downward to sense people as they walk through the doorway. The system differentiates peo-ple by measuring their heights, infers their walking direc-tion using signal processing, and identifies their room lo-cations based on the sequence of doorways through which they pass. Doorjamb provides room-level tracking without requiring any user participation, wearable devices, privacy-intrusive sensors, or high-cost sensors. We create a proof-of-concept implementation and empirically evaluate Doorjamb with experiments that include over 3000 manually-recorded doorway crossings. Results indicate that the system can per-form room-level tracking with 90% accuracy on average.
In order to achieve sustainability, steps must be taken to reduce energy consumption. In particular, heating, cooling, and ventilation systems, which account for 42% of the energy consumed by US buildings in 2010 [8], must be made more efficient. In this paper, we demonstrate ThermoSense, a new system for estimating occupancy. Using this system we are able to condition rooms based on usage. Rather than fully conditioning empty or partially filled spaces, we can control ventilation based on near real-time estimates of occupancy and temperature using conditioning schedules learned from occupant usage patterns. ThermoSense uses a novel multisensor node that utilizes a low-cost, low-power thermal sensor array along with a passive infrared sensor. By using a novel processing pipeline and sensor fusion, we show that our system is able measure occupancy with a RMSE of only ≈0.35 persons. By conditioning spaces based on occupancy, we show that we can save 25% energy annually while maintaining room temperature effectiveness.
Through accurate and dynamic occupancy detection, building actuation systems can fine tune the targets of their actions to better fit the patterns of usage in modern buildings. We outline a method for achieving this through existing wireless infrastructure and present a demonstration of its viability in a corporate environment.
Detecting when a household is occupied by its residents is fundamental to enable a number of home automation applications. Current systems for occupancy detection usually require the installation of dedicated sensors, like passive infrared sensors, magnetic reed switches, or cameras. In this paper, we investigate the suitability of digital electricity meters -- which are already available in millions of households worldwide -- to be used as occupancy sensors. To this end, we have collected fine-grained electricity consumption data along with ground-truth occupancy information for 5 households during a period of about 8 months. Our results show that using common classification methods it is possible to achieve occupancy detection accuracies of more than 80%.
This broad overview of energy programs of the Office of Conservation and Renewable Energy of the U.S. DOE emphasizes means of promoting energy efficiency for the next generation. Current research goals to reduce energy consumption in industry, buildings, and the transportation sector are presented. A doubling of economic growth without depleting fossil fuels by the year 2030 is conceivable.
The development of a system able to detect and track moving people
is described. Given a sequence of time-varying images, the goal is to
count the number of people crossing a counting line. A motion detection
module first determines whether any person has entered the scene; a
tracking module combining prediction and matching then follows people
until they reach the counting line. The efficiency of the proposed
approach is illustrated and assessed using sequences of images taken in
a real environment
Based on color image processing, an automatic bidirectional counting method of pedestrians through a gate is proposed. In the developed technique, one color video camera is hung from the ceiling of the gate with a directly downward view so that the passing people will be observed from just overhead. Firstly, the passing people is roughly counted with the area of people in an image. The moving direction of the pedestrian can be oriented by tracking each people pattern through analyzing its HSI histogram. With features extracted from the quantized histograms of I (intensity) or H (hue), the first counting can be refined. Experimental results show that an 100% accuracy of bidirectional counting can be achieved in the case of multiple isolated one-person patterns and the same accuracy can be also obtained unless the people number of a multiple-person pattern is over five.
Buildingsherlock: Fault management framework for hvac systems in commercial buildings
- H Teraoka
- B Balaji
- R Zhang
- A Nwokafor
- B Narayanaswamy
- Y Agarwal
H. Teraoka, B. Balaji, R. Zhang, A. Nwokafor, B. Narayanaswamy, and
Y. Agarwal. Buildingsherlock: Fault management framework for hvac
systems in commercial buildings. Technical report, Technical Report,
CSE, UCSD, 2014.
A people counting system based on face detection and tracking in a video
- X Zhao
- E Delleandrea
- L Chen
Energy efficiency and renewable energy. US department of energy
- B E D Book
B. E. D. Book. Energy efficiency and renewable energy. US department
of energy, 2011.