arXiv subjects

Alessandro Corbetta

Publications and source records attributed to Alessandro Corbetta.

At least 37 records · Page 2Linked to original sources

arXiv2021

Managing Crowded Museums: Visitors Flow Measurement, Analysis, Modeling, 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.

physics.soc-ph↗

arXiv2020

Monitoring physical distancing for crowd management: real-time trajectory and group analysis

Physical distancing, as a measure to contain the spreading of Covid-19, is defining a "new normal". Unless belonging to a family, pedestrians in shared spaces are asked to observe a minimal (country-dependent) pairwise distance. Coherently, managers of public spaces may be tasked with the enforcement or monitoring of this constraint. As privacy-respectful real-time tracking of pedestrian dynamics in public spaces is a growing reality, it is natural to leverage on these tools to analyze the adherence to physical distancing and compare the effectiveness of crowd management measurements. Typical questions are: "in which conditions non-family members infringed social distancing?", "Are there repeated offenders?", and "How are new crowd management measures performing?". Notably, dealing with large crowds, e.g. in train stations, gets rapidly computationally challenging. In this work we have a two-fold aim: first, we propose an efficient and scalable analysis framework to process, offline or in real-time, pedestrian tracking data via a sparse graph. The framework tackles efficiently all the questions mentioned above, representing pedestrian-pedestrian interactions via vector-weighted graph connections. On this basis, we can disentangle distance offenders and family members in a privacy-compliant way. Second, we present a thorough analysis of mutual distances and exposure-times in a Dutch train platform, comparing pre-Covid and current data via physics observables as Radial Distribution Functions. The versatility and simplicity of this approach, developed to analyze crowd management measures in public transport facilities, enable to tackle issues beyond physical distancing, for instance the privacy-respectful detection of groups and the analysis of their motion patterns.

physics.soc-ph↗

arXiv2020

Controlling Rayleigh-Bénard convection via Reinforcement Learning

Thermal convection is ubiquitous in nature as well as in many industrial applications. The identification of effective control strategies to, e.g., suppress or enhance the convective heat exchange under fixed external thermal gradients is an outstanding fundamental and technological issue. In this work, we explore a novel approach, based on a state-of-the-art Reinforcement Learning (RL) algorithm, which is capable of significantly reducing the heat transport in a two-dimensional Rayleigh-Bénard system by applying small temperature fluctuations to the lower boundary of the system. By using numerical simulations, we show that our RL-based control is able to stabilize the conductive regime and bring the onset of convection up to a Rayleigh number $Ra_c \approx 3 \cdot 10^4$, whereas in the uncontrolled case it holds $Ra_{c}=1708$. Additionally, for $Ra > 3 \cdot 10^4$, our approach outperforms other state-of-the-art control algorithms reducing the heat flux by a factor of about $2.5$. In the last part of the manuscript, we address theoretical limits connected to controlling an unstable and chaotic dynamics as the one considered here. We show that controllability is hindered by observability and/or capabilities of actuating actions, which can be quantified in terms of characteristic time delays. When these delays become comparable with the Lyapunov time of the system, control becomes impossible.

physics.flu-dyn↗

arXiv2020

Pedestrian orientation dynamics from high-fidelity measurements

We investigate in real-life conditions and with very high accuracy the dynamics of body rotation, or yawing, of walking pedestrians - an highly complex task due to the wide variety in shapes, postures and walking gestures. We propose a novel measurement method based on a deep neural architecture that we train on the basis of generic physical properties of the motion of pedestrians. Specifically, we leverage on the strong statistical correlation between individual velocity and body orientation: the velocity direction is typically orthogonal with respect to the shoulder line. We make the reasonable assumption that this approximation, although instantaneously slightly imperfect, is correct on average. This enables us to use velocity data as training labels for a highly-accurate point-estimator of individual orientation, that we can train with no dedicated annotation labor. We discuss the measurement accuracy and show the error scaling, both on synthetic and real-life data: we show that our method is capable of estimating orientation with an error as low as 7.5 degrees. This tool opens up new possibilities in the studies of human crowd dynamics where orientation is key. By analyzing the dynamics of body rotation in real-life conditions, we show that the instantaneous velocity direction can be described by the combination of orientation and a random delay, where randomness is provided by an Ornstein-Uhlenbeck process centered on an average delay of 100ms. Quantifying these dynamics could have only been possible thanks to a tool as precise as that proposed.

physics.soc-ph↗

arXiv2019

High-statistics modeling of complex pedestrian avoidance scenarios

Quantitatively modeling the trajectories and behavior of pedestrians walking in crowds is an outstanding fundamental challenge deeply connected with the physics of flowing active matter, from a scientific point of view, and having societal applications entailing individual safety and comfort, from an application perspective. In this contribution, we review a pedestrian dynamics modeling approach, previously proposed by the authors, aimed at reproducing some of the statistical features of pedestrian motion. Comparing with high-statistics pedestrian dynamics measurements collected in real-life conditions (from hundreds of thousands to millions of trajectories), we modeled quantitatively the statistical features of the undisturbed motion (i.e. in absence of interactions with other pedestrians) as well as the avoidance dynamics triggered by a pedestrian incoming in the opposite direction. This was accomplished through (coupled) Langevin equations with potentials including multiple preferred velocity states and preferred paths. In this chapter we review this model, discussing some of its limitations, in view of its extension toward a more complex case: the avoidance dynamics of a single pedestrian walking through a crowd that is moving in the opposite direction. We analyze some of the challenges connected to this case and present extensions to the model capable of reproducing some features of the motion.

physics.soc-ph↗

arXiv2019

Measurement and analysis of visitors' trajectories in crowded museums

We tackle the issue of measuring and analyzing the visitors' dynamics in crowded museums. We propose an IoT-based system -- supported by artificial intelligence models -- to reconstruct the visitors' trajectories throughout the museum spaces. Thanks to this tool, we are able to gather wide ensembles of visitors' trajectories, allowing useful insights for the facility management and the preservation of the art pieces. Our contribution comes with one successful use case: the Galleria Borghese in Rome, Italy.

cs.HC↗

arXiv2019

Deep learning velocity signals allows to quantify turbulence intensity

Turbulence, the ubiquitous and chaotic state of fluid motions, is characterized by strong and statistically non-trivial fluctuations of the velocity field, over a wide range of length- and time-scales, and it can be quantitatively described only in terms of statistical averages. Strong non-stationarities hinder the possibility to achieve statistical convergence, making it impossible to define the turbulence intensity and, in particular, its basic dimensionless estimator, the Reynolds number. Here we show that by employing Deep Neural Networks (DNN) we can accurately estimate the Reynolds number within $15\%$ accuracy, from a statistical sample as small as two large-scale eddy-turnover times. In contrast, physics-based statistical estimators are limited by the rate of convergence of the central limit theorem, and provide, for the same statistical sample, an error at least $100$ times larger. Our findings open up new perspectives in the possibility to quantitatively define and, therefore, study highly non-stationary turbulent flows as ordinarily found in nature as well as in industrial processes.

physics.flu-dyn↗

arXiv2019

StampNet: unsupervised multi-class object discovery

Unsupervised object discovery in images involves uncovering recurring patterns that define objects and discriminates them against the background. This is more challenging than image clustering as the size and the location of the objects are not known: this adds additional degrees of freedom and increases the problem complexity. In this work, we propose StampNet, a novel autoencoding neural network that localizes shapes (objects) over a simple background in images and categorizes them simultaneously. StampNet consists of a discrete latent space that is used to categorize objects and to determine the location of the objects. The object categories are formed during the training, resulting in the discovery of a fixed set of objects. We present a set of experiments that demonstrate that StampNet is able to localize and cluster multiple overlapping shapes with varying complexity including the digits from the MNIST dataset. We also present an application of StampNet in the localization of pedestrians in overhead depth-maps.

cs.CV↗

arXiv2018

Physics-based modeling and data representation of pedestrian pairwise interactions

The possibility to understand and to quantitatively model the physics of the interactions between pedestrians walking in crowds has compelling relevant applications, e.g. related to the design and safety of civil infrastructures. In this work we study pedestrian-pedestrian interactions from observational experimental data in diluted crowds. While in motion, pedestrians adapt their walking paths trying to preserve mutual comfort distances and to avoid collisions. In mathematical models this behavior is typically modeled via "social" interaction forces. Leveraging on a high-quality, high-statistics dataset - composed of few millions of real-life trajectories acquired from state-of-the-art observational experiments - we develop a quantitative model capable of addressing interactions in the case of binary collision avoidance. We model interactions in terms of both long- and short-range forces, which we superimpose to our Langevin model for non-interacting pedestrian motion [Corbetta et al. Phys.Rev.E 95, 032316, 2017]. The new model that we propose here features a Langevin dynamics with "fast" random velocity fluctuations that are superimposed to the "slow" dynamics of a hidden model variable: the "intended" walking path. The model is capable of reproducing relevant statistics of the collision avoidance motion, such as the statistics of the side displacement and of the passing speed. Rare occurrences of bumping events are also recovered. Furthermore, comparing with large datasets of real-life tracks involves an additional challenge so far neglected: identifying, within a database containing very heterogeneous conditions, only the relevant events corresponding to binary avoidance interactions. To tackle this challenge, we propose a novel approach based on a graph representation of pedestrian trajectories, which allows us to operate complexity reduction for efficient data selection.

physics.soc-ph↗

arXiv2018

A large-scale real-life crowd steering experiment via arrow-like stimuli

We introduce "Moving Light": an unprecedented real-life crowd steering experiment that involved about 140.000 participants among the visitors of the Glow 2017 Light Festival (Eindhoven, NL). Moving Light targets one outstanding question of paramount societal and technological importance: "can we seamlessly and systematically influence routing decisions in pedestrian crowds?" Establishing effective crowd steering methods is extremely relevant in the context of crowd management, e.g. when it comes to keeping floor usage within safety limits (e.g. during public events with high attendance) or at designated comfort levels (e.g. in leisure areas). In the Moving Light setup, visitors walking in a corridor face a choice between two symmetric exits defined by a large central obstacle. Stimuli, such as arrows, alternate at random and perturb the symmetry of the environment to bias choices. While visitors move in the experiment, they are tracked with high space and time resolution, such that the efficiency of each stimulus at steering individual routing decisions can be accurately evaluated a posteriori. In this contribution, we first describe the measurement concept in the Moving Light experiment and then we investigate quantitatively the steering capability of arrow indications.

physics.soc-ph↗

arXiv2018

Accurate pedestrian localization in overhead depth images via Height-Augmented HOG

We tackle the challenge of reliably and automatically localizing pedestrians in real-life conditions through overhead depth imaging at unprecedented high-density conditions. Leveraging upon a combination of Histogram of Oriented Gradients-like feature descriptors, neural networks, data augmentation and custom data annotation strategies, this work contributes a robust and scalable machine learning-based localization algorithm, which delivers near-human localization performance in real-time, even with local pedestrian density of about 3 ped/m2, a case in which most state-of-the art algorithms degrade significantly in performance.

cs.CV↗

arXiv2018

Path-integral representation of diluted pedestrian dynamics

We frame the issue of pedestrian dynamics modeling in terms of path-integrals, a formalism originally introduced in quantum mechanics to account for the behavior of quantum particles, later extended to quantum field theories and to statistical physics. Path-integration enables a trajectory-centric representation of the pedestrian motion, directly providing the probability of observing a given trajectory. This appears as the most natural language to describe the statistical properties of pedestrian dynamics in generic settings. In a given venue, individual trajectories can belong to many possible usage patterns and, within each of them, they can display wide variability. We provide first a primer on path-integration, and we introduce and discuss the path-integral functional probability measure for pedestrian dynamics in the diluted limit. As an illustrative example, we connect the path-integral description to a Langevin model that we developed previously for a particular crowd flow condition (the flow in a narrow corridor). Building on our previous real-life measurements, we provide a quantitatively correct path-integral representation for this condition. Finally, we show how the path-integral formalism can be used to evaluate the probability of rare-events (in the case of the corridor, U-turns).

physics.soc-ph↗

arXiv2017

Weakly supervised training of deep convolutional neural networks for overhead pedestrian localization in depth fields

Overhead depth map measurements capture sufficient amount of information to enable human experts to track pedestrians accurately. However, fully automating this process using image analysis algorithms can be challenging. Even though hand-crafted image analysis algorithms are successful in many common cases, they fail frequently when there are complex interactions of multiple objects in the image. Many of the assumptions underpinning the hand-crafted solutions do not hold in these cases and the multitude of exceptions are hard to model precisely. Deep Learning (DL) algorithms, on the other hand, do not require hand crafted solutions and are the current state-of-the-art in object localization in images. However, they require exceeding amount of annotations to produce successful models. In the case of object localization these annotations are difficult and time consuming to produce. In this work we present an approach for developing pedestrian localization models using DL algorithms with efficient weak supervision from an expert. We circumvent the need for annotation of large corpus of data by annotating only small amount of patches and relying on synthetic data augmentation as a vehicle for injecting expert knowledge in the model training. This approach of weak supervision through expert selection of representative patches, suitable transformations and synthetic data augmentations enables us to successfully develop DL models for pedestrian localization efficiently.

cs.CV↗

arXiv2016

Fluctuations around mean walking behaviours in diluted pedestrian flows

Understanding and modeling the dynamics of pedestrian crowds can help with designing and increasing the safety of civil facilities. A key feature of crowds is its intrinsic stochasticity, appearing even under very diluted conditions, due to the variability in individual behaviours. Individual stochasticity becomes even more important under densely crowded conditions, since it can be nonlinearly magnified and may lead to potentially dangerous collective behaviours. To understand quantitatively crowd stochasticity, we study the real-life dynamics of a large ensemble of pedestrians walking undisturbed, and we perform a statistical analysis of the fully-resolved pedestrian trajectories obtained by a year-long high-resolution measurement campaign. Our measurements have been carried out in a corridor of the Eindhoven University of Technology via a combination of Microsoft Kinect 3D-range sensor and automatic head-tracking algorithms. The temporal homogeneity of our large database of trajectories allows us to robustly define and separate average walking behaviours from fluctuations parallel and orthogonal with respect to the average walking path. Fluctuations include rare events when individuals suddenly change their minds and invert their walking direction. Such tendency to invert direction has been poorly studied so far even if it may have important implications on the functioning and safety of facilities. We propose a novel model for the dynamics of undisturbed pedestrians, based on stochastic differential equations, that provides a good agreement with our experimental observations, including the occurrence of rare events.

physics.soc-ph↗

arXiv2016

Continuous measurements of real-life bidirectional pedestrian flows on a wide walkway

Employing partially overlapping overhead \kinectTMS sensors and automatic pedestrian tracking algorithms we recorded the crowd traffic in a rectilinear section of the main walkway of Eindhoven train station on a 24/7 basis. Beside giving access to the train platforms (it passes underneath the railways), the walkway plays an important connection role in the city. Several crowding scenarios occur during the day, including high- and low-density dynamics in uni- and bi-directional regimes. In this paper we discuss our recording technique and we illustrate preliminary data analyses. Via fundamental diagrams-like representations we report pedestrian velocities and fluxes vs. pedestrian density. Considering the density range $0$ - $1.1\,$ped/m$^2$, we find that at densities lower than $0.8\,$ped/m$^2$ pedestrians in unidirectional flows walk faster than in bidirectional regimes. On the opposite, velocities and fluxes for even bidirectional flows are higher above $0.8\,$ped/m$^2$.

physics.soc-ph↗

arXiv2016

Eulerian vs. Lagrangian analyses of pedestrian dynamics asymmetries in a staircase landing

Real-life, out-of-laboratory, measurements of pedestrian movements allow extensive and fully-resolved statistical analyses. However, data acquisition in real-life is subjected to the wide heterogeneity that characterizes crowd flows over time. Disparate flow conditions, such as co-flows and counter-flows at low and at high pedestrian densities, typically follow randomly one another. When analysing the data in order to study the dynamics and behaviour of pedestrians it is crucial to be able disentangle and to properly select (query) data from statistically homogeneous flow conditions in order to avoid spurious statistics and to enable qualitative comparisons. In this paper we extend our previous analysis on the asymmetric pedestrian dynamics on a staircase landing, where we collected a large statistical database of measurements from ad hoc continuous recordings. This contribution has a two-fold aim: first, method-wise, we discuss two possible approaches to query experimental datasets for homogeneous flow conditions. For given flow conditions, we can either agglomerate measurements on a time-frame basis (Eulerian queries) or on a trajectory basis (Lagrangian queries). Second, we employ these two different perspectives to further explore asymmetries in the pedestrian dynamics in our measurement site. We report cross-comparisons of statistics of pedestrian positions, velocities and accelerations vs. flow conditions as well as vs. Eulerian or Lagrangian approach.

physics.soc-ph↗

arXiv2016

From individual behaviour to an evaluation of the collective evolution of crowds along footbridges

This paper proposes a crowd dynamic macroscopic model grounded on microscopic phenomenological observations which are upscaled by means of a formal mathematical procedure. The actual applicability of the model to real world problems is tested by considering the pedestrian traffic along footbridges, of interest for Structural and Transportation Engineering. The genuinely macroscopic quantitative description of the crowd flow directly matches the engineering need of bulk results. However, three issues beyond the sole modelling are of primary importance: the pedestrian inflow conditions, the numerical approximation of the equations for non trivial footbridge geometries, and the calibration of the free parameters of the model on the basis of in situ measurements currently available. These issues are discussed and a solution strategy is proposed.

math-ph↗

arXiv2016

Comparing first order microscopic and macroscopic crowd models for an increasing number of massive agents

In this paper a comparison between first order microscopic and macroscopic differential models of crowd dynamics is established for an increasing number $N$ of pedestrians. The novelty is the fact of considering massive agents, namely particles whose individual mass does not become infinitesimal when $N$ grows. This implies that the total mass of the system is not constant but grows with $N$. The main result is that the two types of models approach one another in the limit $N\to\infty$, provided the strength and/or the domain of pedestrian interactions are properly modulated by $N$ at either scale. This is consistent with the idea that pedestrians may adapt their interpersonal attitudes according to the overall level of congestion.

math.AP↗