No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Measurement and analysis of visitors' trajectories in crowded museums
Abstract
We tackle the issue of measuring and ana- lyzing the visitors’ dynamics in crowded museums. We propose an IoT-based system – supported by artificial intelligence models – to reconstruct the visitors’ tra- jectories throughout the museum spaces. Thanks to this tool, we are able to gather wide ensembles of vis- itors’ trajectories, allowing useful insights for the facil- ity management and the preservation of the art pieces. Our contribution comes with one successful use case: the Galleria Borghese in Rome, Italy.
... Given the captured RSSi from a single beacon, the output of this resampling procedure is a A × T matrix R (where T is the duration of the visit divided by ∆t). In [6,5] we proposed two methodologies to process such a matrix to estimate individual trajectories, the most effective of which was based on an MLP neural network operating on R after a row-normalisation (average over time = 0, standard deviation over time = 1), resulting in acc = 85% localisation accuracy. Specifically, our MLP was 3-layers deep, its input was a two-minutes long symmetric time window (i.e. ...
... We report here the distance matrices D in the case of the fictitious museum floor plan in Figure 2(a) and for Galleria Borghese, respectively in Table 2 and Table 3. r0 r1 r2 r3 r4 r5 r6 r7 r8 r9 r10 r11 r12 r0 0 11.5 10.5 11.5 12.5 12.5 11.5 10. 5 Table 2: Distance matrix D from the total-coloured graph in Figure 2(a). We weight '1' the door connections (↔), '10' the staircase links (↔) and +0.5 the distance between two rooms not sharing the same room-colour. ...
Individual tracking of museum visitors based on portable radio beacons, an asset for behavioural analyses and comfort/performance improvements, is seeing increasing diffusion. Conceptually, this approach enables room-level localisation based on a network of small antennas (thus, without invasive modification of the existent structures). The antennas measure the intensity (RSSi) of self-advertising signals broadcasted by beacons individually assigned to the visitors. The signal intensity provides a proxy for the distance to the antennas and thus indicative positioning. However, RSSi signals are well-known to be noisy, even in ideal conditions (high antenna density, absence of obstacles, absence of crowd, ...). In this contribution, we present a method to perform accurate RSSi-based visitor tracking when the density of antennas is relatively low, e.g. due to technical constraints imposed by historic buildings. We combine an ensemble of "simple" localisers, trained based on ground-truth, with an encoding of the museum topology in terms of a total-coloured graph. This turns the localisation problem into a cascade process, from large to small scales, in space and in time. Our use case is visitors tracking in Galleria Borghese, Rome (Italy), for which our method manages >96% localisation accuracy, significantly improving on our previous work (J. Comput. Sci. 101357, 2021).
... In signal terms, the visitor appears to perform extremely rapid and unrealistic room changes. Building upon [7], we consider two data refinement methods: one based on a neural network and another, more standard, relying on a sliding window approach. 4.1. ...
... In Figure 17 we finally report the representative trajectories of the two most numerous clusters obtained by gathering real and simulated trajectories. 7. Museum control and optimization. ...
We present an all-around study of the visitors flow in crowded museums: a combination of Lagrangian field measurements and statistical analyses enable us to create stochastic digital-twins of the guests dynamics, unlocking comfort- and safety-driven optimizations. Our case study is the Galleria Borghese museum in Rome (Italy), in which we performed a real-life data acquisition campaign. We specifically employ a Lagrangian IoT-based visitor tracking system based on Raspberry Pi receivers, displaced in fixed positions throughout the museum rooms, and on portable Bluetooth Low Energy beacons handed over to the visitors. Thanks to two algorithms: a sliding window-based statistical analysis and an MLP neural network, we filter the beacons RSSI and accurately reconstruct visitor trajectories at room-scale. Via a clustering analysis, hinged on an original Wasserstein-like trajectory-space metric, we analyze the visitor paths to get behavioral insights, including the most common flow patterns. On these bases, we build the transition matrix describing, in probability, the room-scale visitor flows. Such a matrix is the cornerstone of a stochastic model capable of generating visitor trajectories in silico. We conclude by employing the simulator to increase the number of daily visitors while respecting numerous logistic and safety constraints. This is possible thanks to optimized ticketing and new entrance/exit management.
... Crowd management in museums and exhibitions has been approached by various methods which re-route the visitor or try to provide additional information. The use of IoT for visitor tracking [7] and Neural Networks for path planning and reconstructing visitor trajectories [6] is an example scenario of such implementation. Other studies include the installation of a robotic system [9] to deliver content and perform crowd counting. ...
... Museum managers are constantly challenged by the need to maximize the number of visitors (Kontarinis et al. 2017). Yet, this involves highly complex issues, such as continuous and reliable data acquisition, complexity reduction, and modelling physical and psychological aspects of crowd movement (Centorrino et al. 2019). ...
Museum studies is an academic and practical field of research that provides new challenges and opportunities
to researchers thanks to the extraordinary growth of museums worldwide in the last 20 years
(McCarthy and Brown 2022). There is, however, a need for more research on museum economics, including
tourism (Silberberg and Lord 2015). The tourism industry has become the cornerstone of the economy
for most of the world’s tourist destinations thanks to the aviation industry, especially in the capital cities of
developed countries where large airports are localized, as well as providing a high level of connectivity in
the rest of the country. Tourism is highly dependent on the aviation sector (Florido-Benítez 2022a; 2022b).
The World Tourism Organization (UNWTO) indicates that air travel is the most popular choice of travel
for leisure tourism (UNWTO 2020; 2021), and inside the tourism industry, museums represent a growing
attraction for international tourists (Nowacki and Kruczek 2021). They help drive the tourism and aviation
sectors, and play a cultural and economic role in their communities (Florido-Benítez
2023; Maxim 2017).
City museums around the world empower their visitors to consider their roles as active city comakers
(Grincheva 2022). “Superstar museums,” which are a “must see” for tourists and have achieved cult status
(Frey 1998), depend on digital and physical positioning in the media (Plaza et al. 2022).
... Centorrino et al. used Bluetooth beacons for this purpose. Visitors are given the beacons upon entrance, while stationed receivers capture the trajectory of the visitors (can also be called pedestrians) as they move within the museum [15]. Similar techniques are also used in large events to keep track of visitors or recognize returning ones, and monitor passengers' movements in a train station [16,19]. ...
Beyond the many advantages which Smart City brings, the issue of security and privacy remain very important concerns. As things get more interconnected, cyber orchestrated crimes such as cyberterror-ism may become more prevalent. For example, an autonomous vehicle or drone may be used to commit acts of terrorism, such as driving or flying into a crowd. Responses to such incidents need to be swift and likewise smart. Law enforcement needs to be equipped with the necessary tools to respond speedily and even automatically, equally taking advantage of the Internet of Things (IoT). We propose a Sensor-Based Crime and Incident Watch for Smart Cities (SBCI-Watch), leveraging Human Activity Recognition (HAR). SBCI-Watch may be used to automatically detect and possibly report occurrences of public disturbances (likely caused by acts of terrorism or similar crimes) to foster swift response. Slightly similar reports exist, but they are focused on different topics, such as helping law enforcement to pick suitable officers to respond to crime scenes based on proximity, but without attempting to automatically detect crimes. We are using the sensor-based approach; it is less privacy intrusive compared to the vision-based method, which is dominant in the public surveillance area but also more privacy intrusive and more expensive. To the best of our knowledge, our work is the first to address the problem in this fashion, and the results illustrate the viability of the SBCI-Watch.
... In [26], different evacuation scenarios are considered and recommendations for faster and safer evacuation of museum visitors (arrangement of expositions, increase or transfer of passages) are offered. In [27,28], the trajectories of visitors to the Galleria Borghese museum (Rome, Italy) were studied in order to develop strategies of occupancy and visits to the museum during the day by means of mathematical simulation of the movement of people. In [29], the dynamics of visitors in a crowded museum (Rome, Italy) were examined in order to create a mathematical model that can be used as a tool for the management and optimization of the work of this museum. ...
The manuscript is focused on the problems of evacuation in case of fire from the buildings of museums as places with a mass presence of people. Features specific to museums and how they affect safe evacuation conditions are discussed. Most attention is paid to evacuation management, since the vast majority of museum visitors are not familiar with the layout of the building. In this case, the actions of staff in evacuation management are decisive. The paper considers the development of evacuation schemes, taking into account the spread of fire hazards in the building and the development of instructions on their basis for the staff. Using the example of the Winter Palace of the State Hermitage Museum, the solution of the marked tasks with the use of computer simulation of evacuation during a fire is given. The analysis of the simulation results showed the vulnerabilities of the museum. In this work, the evacuation schemes for the scenarios are considered. The maximum number of visitors at a single time in the Winter Palace has been set at 4000. The principles of making evacuation schemes are formulated, including taking into account the peculiarities of space-planning solutions inherent in museums, such as enfilades and the connections of rooms.
... Given the captured RSSi from a single beacon, the output of this resampling procedure is a A × T matrix R (where T is the duration of the visit divided by ∆t). In [4,22] we proposed two methodologies to process such a matrix to estimate individual trajectories, the most effective of which was based on an MLP neural network operating on R after a row-normalisation (average over time = 0, standard deviation over time = 1), resulting in acc = 85% localisation accuracy. Specifically, our MLP was 3-layers deep, its input was a two-minutes long symmetric time window (i.e. ...
Individual tracking of museum visitors based on portable radio beacons, an asset for behavioural analyses and comfort/performance improvements, is seeing increasing diffusion. Conceptually, this approach enables room-level localisation based on a network of small antennas (thus, without invasive modification of the existent structures). The antennas measure the intensity (RSSi) of self-advertising signals broadcasted by beacons individually assigned to the visitors. The signal intensity provides a proxy for the distance to the antennas and thus indicative positioning. However, RSSi signals are well-known to be noisy, even in ideal conditions (high antenna density, absence of obstacles, absence of crowd, ...). In this contribution, we present a method to perform accurate RSSi-based visitor tracking when the density of antennas is relatively low, e.g. due to technical constraints imposed by historic buildings. We combine an ensemble of "simple" localisers, trained based on ground-truth, with an encoding of the museum topology in terms of a total-coloured graph. This turns the localisation problem into a cascade process, from large to small scales, in space and in time. Our use case is visitors tracking in Galleria Borghese, Rome (Italy), for which our method manages >96% localisation accuracy, significantly improving on our previous work (J. Comput. Sci. 101357, 2021).
... They track groups of visitors at the National Museum of Emerging Science and Innovation (Miraikan) in Tokyo, Japan, to identify the leader and study their dynamics. In [12], the authors present an IoT-(Internet of Things) based system to measure and understand visitor dynamics at the Galleria Borghese museum in Rome, Italy. A similar approach is described in [5], in which the authors report the results of a case study conducted at the CoBrA Museum of Modem Art in Amstelveen, the Netherlands. ...
Nowadays, technology makes it possible to admire objects and artworks exhibited all over the world remotely. We have been able to appreciate this convenience even more in the last period, in which the pandemic has forced us into our homes for a long time. However, visiting art sites in person remains a truly unique experience. Even during on-site visits, technology can help make them much more satisfactory, by assisting visitors during the fruition of cultural and artistic resources. To this aim, it is necessary to monitor the active user for acquiring information about their behavior. We, therefore, need systems able to monitor and analyze visitor behavior. The literature proposes several techniques for the timing and tracking of museum visitors. In this article, we propose a novel approach to indoor tracking that can represent a promising and non-expensive solution for some of the critical issues that remain. In particular, the system we propose relies on low-cost equipment (i.e., simple badges and off-the-shelf RGB cameras) and harnesses one of the most recent deep neural networks (i.e., Faster R-CNN) for detecting specific objects in an image or a video sequence with high accuracy. An experimental evaluation performed in a real scenario, namely, the “Exhibition of Fake Art” at Roma Tre University, allowed us to test our system on site. The collected data has proven to be accurate and helpful for gathering insightful information on visitor behavior.
... Building upon [8], we consider two data refinement methods: the first one relying on a sliding window approach and the second one based on a neural network. ...
We present an all-around study of the visitors flow in crowded museums: a combination of Lagrangian field measurements and statistical analyses enable us to create stochastic digital-twins of the guest dynamics, unlocking comfort- and safety-driven optimizations. Our case study is the Galleria Borghese museum in Rome (Italy), in which we performed a real-life data acquisition campaign.
We specifically employ a Lagrangian IoT-based visitor tracking system based on Raspberry Pi receivers, displaced in fixed positions throughout the museum rooms, and on portable Bluetooth Low Energy beacons handed over to the visitors. Thanks to two algorithms: a sliding window-based statistical analysis and an MLP neural network, we filter the beacons RSSI and accurately reconstruct visitor trajectories at room-scale. Via a clustering analysis, hinged on an original Wasserstein-like trajectory-space metric, we analyze the visitors paths to get behavioral insights, including the most common flow patterns. On these bases, we build the transition matrix describing, in probability, the room-scale visitor flows. Such a matrix is the cornerstone of a stochastic model capable of generating visitor trajectories in silico. We conclude by employing the simulator to enhance the museum fruition while respecting numerous logistic and safety constraints. This is possible thanks to optimized ticketing and new entrance/exit management.
... The second group of studies featured Wi-Fi and Bluetooth sensors (e. g., Centorrino et al. [67]; Danalet et al. [68]; Ton et al. [69]; Versichele et al. [70]; Yoshimura et al. [71,72]). These researchers adopted this type of sensor to study pedestrian activity location and route choice behaviour in, respectively, a museum, a university campus, a train station, a festival, and a museum. ...
Collecting pedestrian behaviour data is vital to understand pedestrian behaviour. This systematic review of 145 studies aims to determine the capability of contemporary data collection methods in collecting different pedestrian behavioural data, identify research gaps and discuss the possibilities of using new technologies to study pedestrian behaviour. The review finds that there is an imbalance in the number of studies that feature various aspects of pedestrian behaviour, most importantly (1) pedestrian behaviour in large complex scenarios, and (2) pedestrian behaviour during new types of high-risk situations. Additionally, three issues are identified regarding current pedestrian behaviour studies, namely (3) little comprehensive data sets featuring multi-dimensional behaviour data simultaneously, (4) generalizability of most collected data sets is limited, and (5) costs of pedestrian behaviour experiments are relatively high. A set of new technologies offers opportunities to overcome some of these limitations. This review identifies three types of technologies that can become a valuable addition to pedestrian behaviour research methods, namely (1) applying VR experiments to study pedestrian behaviour in the environments that are difficult or cannot be mimicked in real-life, repeat experiments to determine the impact of factors on pedestrian behaviour and collect more accurate behavioural data to understand the decision-making process of pedestrian behaviour deeply, (2) applying large-scale crowd monitoring to study pedestrian movements in large complex environments and incident situations, and (3) utilising the Internet of Things to track pedestrian movements at various locations that are difficult to investigate at the moment.
... Recent developments reported in [3] brought us to study drafting effects via the dynamics of mixed active-passive pedestrian populations in confined domains with obstacles and exit doors, which mimicks a built complex environment. 2 Museums in highly touristic cities are examples of crowded areas; compare, e.g., with the situation of Galleria Borghese in Rome as described in [9]. ...
Stochastic particle–based models are useful tools for describing the collective movement of large crowds of pedestrians in crowded confined environments. Using descriptions based on the simple exclusion process, two populations of particles, mimicking pedestrians walking in a built environment, enter a room from two opposite sides. One population is passive – being unaware of the local environment; particles belonging to this group perform a symmetric random walk. The other population has information on the local geometry in the sense that as soon as particles enter a visibility zone, a drift activates them. Their self–propulsion leads them towards the exit. This second type of species is referred here as active. The assumed crowdedness corresponds to a near–jammed scenario. The main question we ask in this paper is: Can we induce modifications of the dynamics of the active particles to improve the outgoing current of the passive particles? To address this question, we compute occupation number profiles and currents for both populations in selected parameter ranges. Besides observing the more classical faster–is–slower effect, new features appear as prominent like the non–monotonicity of currents, self–induced phase separation within the active population, as well as acceleration of passive particles for large–drift regimes of active particles.
... Museums in highly touristic cities are examples of crowded areas; compare, e.g., with the situation of Galleria Borghese in Rome as described in[9]. ...
Stochastic particle--based models are useful tools for describing
the collective movement of large crowds of pedestrians in crowded confined environments. Using descriptions based on the simple exclusion process, two populations of particles, mimicking pedestrians walking in a built environment, enter a room from two opposite sides. One population is {\em passive} -- being unaware of the local environment; particles belonging to this group perform a symmetric
random walk. The other population has information on the local geometry in the sense that as soon as particles enter a visibility zone, a drift activates them. Their self-propulsion leads them towards the exit. This second type of species is referred here as {\em active}. The assumed crowdedness corresponds
to a near--jammed scenario. The main question we ask in this paper is: {\em Can we induce modifications of the dynamics of the active particles to improve the outgoing current of the passive particles?}
To address this question, we compute
occupation number profiles and
currents for both populations in selected parameter ranges. Besides
observing the more classical faster--is--slower effect, new features
appear as prominent like the non--monotonicity of currents,
self--induced phase separation within the active population,
as well as acceleration
of passive particles for large--drift regimes of active particles.
Beyond the many advantages which Smart City brings, the issue of security and privacy remain very important concerns. As things get more interconnected, cyber orchestrated crimes such as cyberterrorism may become more prevalent. For example, an autonomous vehicle or drone may be used to commit acts of terrorism, such as driving or flying into a crowd. Responses to such incidents need to be swift and likewise smart. Law enforcement needs to be equipped with the necessary tools to respond speedily and even automatically, equally taking advantage of the Internet of Things (IoT). We propose a Sensor-Based Crime and Incident Watch for Smart Cities (SBCI-Watch), leveraging Human Activity Recognition (HAR). SBCI-Watch may be used to automatically detect and possibly report occurrences of public disturbances (likely caused by acts of terrorism or similar crimes) to foster swift response. Slightly similar reports exist, but they are focused on different topics, such as helping law enforcement to pick suitable officers to respond to crime scenes based on proximity, but without attempting to automatically detect crimes. We are using the sensor-based approach; it is less privacy intrusive compared to the vision-based method, which is dominant in the public surveillance area but also more privacy intrusive and more expensive. To the best of our knowledge, our work is the first to address the problem in this fashion, and the results illustrate the viability of the SBCI-Watch.KeywordsSmart CityHuman Activity Recognition (HAR)Incident watchCrime watchPrivacy
There are no scientific studies in the context of airports and museums relationship, which analyze the impact of airports for identifying the relationship between museums and air accessibility, as well as promotion campaigns to attract visitors and passengers at museums and airports. The main purpose of this study is to analyze the locations of US airports in the top 20 US museums, due to connectivity, accessibility, and technological change that aviation and museums activities are experiencing because of pandemic crisis. Moreover, this study evaluates promotion and travelling exhibitions factors, with the aim of attracting more visitors to museums and how these two variables can affect to airports. This research addresses this knowledge gap by providing discussions and justifications on how airports and museums should fortify their interaction and cooperation to develop joint marketing strategies. Results show how airports provide accessibility, connectivity, and frequencies of flights through airlines, and they have a direct impact of number of passengers’ arrivals on destinations and museums. Indeed, the findings revealed the need to implement joint strategies alliances by DMOs, airports, and museums, to increase the number of tourists in cities, particularly in this time of economic uncertainly. Airport and airlines operators could encourage to museum managers to incorporate customized travel packages and commercial discounts together through their official website and apps. These commercial strategies remove unnecessary intermediaries and increasing the profit margins.
In this dissertation, we study models for coupled active--passive pedestrian dynamics from mathematical analysis and simulation perspectives. The general aim is to contribute to a better understanding of complex pedestrian flows.
This work comes in three main parts, in which we adopt distinct perspectives and conceptually different tools from lattice gas models, partial differential equations, and stochastic differential equations, respectively.
In part one, we introduce two lattice models for active--passive pedestrian dynamics. In a first model, using descriptions based on the simple exclusion process, we study the dynamics of pedestrian escape from an obscure room in a lattice domain with two species of particles (pedestrians). The main observable is the evacuation time as a function of the parameters caracterizing the motion of the active pedestrians. Our Monte Carlo simulation results show that the presence of the active pedestrians can favor the evacuation of the passive ones. We interpret this phenomenon as a discrete space counterpart of the so-called drafting effect. In a second model, we consider again a microscopic approach based on a modification of the simple exclusion process formulated for active--passive populations of interacting pedestrians. The model describes a scenario where pedestrians are walking in a built environment and enter a room from two opposite sides. For such counterflow situation, we have found out that the motion of active particles improves the outgoing current of the passive particles.
In part two, we study a fluid-like driven system modeling active--passive pedestrian dynamics in a heterogenous domain. We prove the well-posedness of a nonlinear coupled parabolic system that models the evolution of the complex pedestrian flow by using special energy estimates, a Schauder's fixed point argument and the properties of the nonlinearity's structure.
In the third part, we describe via a coupled nonlinear system of Skorohod-like stochastic differential equations the dynamics of active--passive pedestrians dynamics through a heterogenous domain in the presence of fire and smoke. We prove the existence and uniqueness of strong solutions to our model when reflecting boundary conditions are imposed on the boundaries. To achieve this we used compactness methods and the Skorohod's representation of solutions to SDEs posed in bounded domains. Furthermore, we study an homogenization setting for a toy model (a semi-linear elliptic equation) where later on our pedestrian models can be studied.
Art museum professionals traditionally rely on observations and surveys to enhance their knowledge of visitor behavior and experience. However, these approaches often produce spatially and temporally limited empirical evidence and measurements. Only recently has the ubiquity of digital technologies revolutionized the ability to collect data about human behavior. Consequently, the greater availability of large-scale datasets based on quantifying visitors' behavior provides new opportunities to apply computational and comparative analytical techniques. In this article, the authors analyze visitor behavior in the Louvre Museum from anonymized longitudinal datasets collected from noninvasive Bluetooth sensors. They examine visitors' length of stay in the museum and consider this relationship with occupation density around artwork. This data analysis increases museum professionals' knowledge and understanding of the visitor experience. This article is part of a special issue on smart cities.
Nowadays, electronic museum guides have evolved to a point that can act as navigational and informational devices in the museum context; thus they also enable the collection of large volumes of spatiotemporal visitor movement data, from which individual visitor trajectories can be extracted and analyzed.
These trajectories have individual characteristics expressed through unique semantics in each museum context (based on the museum, its exhibits and its visitors) and they are restricted in an indoor environment that provides additional constraints. This work presents the benefits, the challenges, and a direction for studying museum visitor movements through context-aware indoor trajectory modeling, mining and analysis.
Museums often suffer from so-called ‘hypercongestion’, wherein the number of visitors exceeds the capacity of the physical space of the museum. This can potentially be detrimental to the quality of visitors’ experiences, through disturbance by the behavior and presence of other visitors. Although this situation can be mitigated by managing visitors’ flow between spaces, a detailed analysis of visitor movement is required to realize fully and apply a proper solution to the problem. In this paper we analyze visitors’ sequential movements, the spatial layout, and the relationship between them in a large- scale art museum-The Louvre Museum-using anonymized data collected through noninvasive Bluetooth sensors. This enables us to unveil some features of visitor behavior and spatial impact that shed some light on the mechanisms of museum overcrowding. The analysis reveals that the visiting styles of short-stay and long-stay visitors are not as significantly different as one might expect. Both types of visitors tend to visit a similar number of key locations in the museum while the longer-stay visitors just tend to do so more time extensively. In addition, we reveal that some ways of exploring the museum appear frequently for both types of visitors, although long-stay visitors might be expected to diversify much more, given the greater time spent in the museum. We suggest that these similarities and dissimilarities make for an uneven distribution of the number of visitors in the museum space. The findings increase the understanding of the unknown behaviors of visitors, which is key to improving the museum’s environment and visitor experience.
- T M Mitchell
T.M.Mitchell, "Machine Learning", 1st edition,
McGraw-Hill,New York, USA, 1997