Abstract Urban environments face persistent challenges in managing mobility and public health, creating a growing demand for advanced simulation tools to support decision-making. Existing population-driven frameworks often require detailed individual data, raising privacy concerns and limiting scalability. Moreover, most approaches are constrained to a single modeling scale, making it difficult to capture both individual routines and collective urban dynamics within one framework. This paper introduces LodusPop, a flexible multi-scale simulation framework for urban population dynamics. LodusPop employs an environment-driven paradigm, where environments actively request population movements, reducing dependence on fine-grained, individual behavioral data. Populations are represented as blobs, aggregated groups of arbitrary size with defined characteristics, that can split, merge, and adapt to changing simulation conditions. This abstraction balances computational efficiency with behavioral expressiveness, enabling the study of diverse urban phenomena across scales ranging from neighborhoods to entire cities. We demonstrate LodusPop’s versatility through three case studies in Porto Alegre, Brazil, addressing everyday mobility, large-scale events, and epidemic control with vaccination policies. The results highlight LodusPop as a practical and extensible tool for urban planning, crisis management, and public health interventions, bridging the gap between data availability, computational scalability, and the ability to analyze population dynamics across multiple spatial and temporal scales.

As the quest for high-level realism in virtual environments continues, there is a growing demand for accurate representations of human characteristics in Virtual Humans (VHs), including gender and emotions.Although people assign gender to VHs even without explicit cues, it is still unknown whether this bias endures during interactive engagement rather than passive video observation.This study aims to address this issue by conducting a perceptual study involving the evaluation of a genderless Virtual Baby (VB) in an interactive web environment.This study advances the understanding of gender assignment in interactive environments.

Figure 1: An example of our model in action is shown from left to right: the agent (in a red shirt) first follows the direction of a crowd, then identifies an exit sign and moves toward it, and finally locates and evacuates through the exit, successfully leaving the scene.

ABSTRACT In this paper, we explore the usability of an explainable Artificial Neural Network (ANN) model to provide recommendations for architectural improvements aimed at enhancing crowd safety and comfort during emergency situations. We trained an ANN to predict the outcomes of crowd simulations without the need for direct simulation, while also generating recommendations for the studied space. Our dataset comprises approximately 36,000 simulations of diverse crowds evacuating rooms of different sizes, capturing data on room characteristics, crowd composition, evacuation densities, times, and velocities. To identify the most influential environmental factors affecting evacuation performance, we employ Shapley values. Based on these insights, we propose modifications to the architectural design of the space. Our results demonstrate that the proposed model effectively predicts crowd dynamics and provides meaningful recommendations for improving evacuation efficiency and safety.

Abstract Animating gaze behavior is crucial for creating believable virtual characters, providing insights into their perception and interaction with the environment. In this paper, we present an efficient yet natural‐looking gaze animation model applicable to real‐time walking characters exploring natural environments. We address the challenge of dynamic gaze adaptation by combining findings from neuroscience with a data‐driven saliency model. Specifically, our model determines gaze focus by considering the character's locomotion, environment stimuli, and terrain conditions. Our model is compatible with both automatic navigation through pre‐defined character trajectories and user‐guided interactive locomotion, and can be configured according to the desired degree of visual exploration of the environment. Our perceptual evaluation shows that our solution significantly improves the state‐of‐the‐art saliency‐based gaze animation with respect to the character's apparent awareness of the environment, the naturalness of the motion, and the elements to which it pays attention.

Crowd simulation is a research area widely used in diverse fields, including gaming and security, assessing virtual agent movements through metrics like time to reach their goals, speed, trajectories, and densities. This is relevant for security applications, for instance, as different crowd configurations can determine the time people spend in environments trying to evacuate them. In this work, we extend WebCrowds, an authoring tool for crowd simulation, to allow users to build scenarios and evaluate them through a set of metrics. The aim is to provide a quantitative metric that can, based on simulation data, select the best crowd configuration in a certain environment. We conduct experiments to validate our proposed metric in multiple crowd simulation scenarios and perform a comparison with another metric found in the literature. The results show that experts in the domain of crowd scenarios agree with our proposed quantitative metric.

The simulation of virtual humans organized in groups and crowds has been widely explored in the literature. Nevertheless, the simulation of virtual humans that interact with fluids is still incipient. Indeed it is easy to understand that human behavior is different from ordinary rigid bodies when affected by fluids, i.e., on the one hand, agents can try to walk, achieve their goals against fluid forces, trying to survive. On the other hand, humans can also be completely carried by the fluid, depending on the conditions, as a passive rigid body. A challenge in this area is that virtual agent simulation research often focuses on the realism of their trajectories and interaction with the environment, obstacles, and other agents, without considering that agents might evolve into an environment that can take control of their movements and trajectories in certain conditions. In this case, it is essential to note that, with proper integration between agents and fluids, we should be able to simulate agents who can continue walking despite an existing fluid (e.g., a weak fluid stream), walking with an effort to stay in the desired direction (e.g., medium stream), until they are partially or totally carried by a fluid, like a strong flow of water in a river or the sea. The main contribution of our model is to give the first step into simulating the steering behaviors of humans in environments with fluids. We integrate two published methodologies and available source codes in order to create our method. For the motion of virtual humans, we use BioCrowds; and SPlisHSPlasH as a fluid dynamics model. Results indicate that the proposed approach generates coherent behaviors regarding the influence of fluids on people in real events, even if this is not the objective of this paper, because other variables should be incorporated, in cases of serious simulations.

In crowds, one important aspect that has been studied in literature is the sociability of groups dealing with aspects based on personality and emotions. In this paper we contribute to the space design area while considering the cultural, personality and thermal aspects to provide spatial group distribution. Our method applies a thermal comfort method together with cultural and personality model to optimally distribute the groups in a virtual environment. Results indicate that obtained groups distribution are coherent with expected based on literature.

This work aims to evaluate people's perception regarding geometric features, personalities and emotions characteristics in virtual humans. For this, we use as a basis, a dataset containing the tracking files of pedestrians captured from spontaneous videos and visualized them as identical virtual humans. In addition to tracking files containing their positions, the dataset also contains pedestrian emotions and personalities detected using Computer Vision and Pattern Recognition techniques. We proceed with our analysis in order to answer the question if subjects can perceive geometric features as distances/speeds as well as emotions and personalities in video sequences when pedestrians are represented by virtual humans. Regarding the participants, an amount of 73 people volunteered for the experiment. The analysis was divided in two parts: i) evaluation on perception of geometric characteristics, such as density, angular variation, distances and speeds, and ii) evaluation on personality and emotion perceptions. Results indicate that, even without explaining to the participants the concepts of each personality or emotion and how they were calculated (considering geometric characteristics), in most of the cases, participants perceived the personality and emotion expressed by the virtual agents, in accordance with the available ground truth.

Abstract We present a system to generate a procedural environment that produces a desired crowd behaviour. Instead of altering the behavioural parameters of the crowd itself, we automatically alter the environment to yield such desired crowd behaviour. This novel inverse approach is useful both to crowd simulation in virtual environments and to urban crowd planning applications. Our approach tightly integrates and extends a space discretization crowd simulator with inverse procedural modelling. We extend crowd simulation by goal exploration (i.e. agents are initially unaware of the goal locations), variable‐appealing sign usage and several acceleration schemes. We use Markov chain Monte Carlo to quickly explore the solution space and yield interactive design. We have applied our method to a variety of virtual and real‐world locations, yielding one order of magnitude faster crowd simulation performance over related methods and several fold improvement of crowd indicators.

Abstract This paper presents a study, organized in two phases, regarding group behavior in a controlled experiment focused on differences in an important attribute that vary across cultures—personal spaces. First, we want to study and compare the spatial behavior different populations adopt with respect to their personal space. Second, we want to use simulation of virtual agents to artificially generate movements of people in similar situations and validate them using real video sequences. Our main goal is to be able to extract from video sequences and then simulate variations in populations in a coherent way with literature that studies cultural aspects. In addition to the cultural aspects, we also investigate the personality model in the studied videos using OCEAN (Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism). Finally, we propose a way to simulate the fundamental diagram experiment from other countries using the OCEAN psychological trait model as input. Results indicate that the simulated countries have consistent characteristics with the expected literature.

Most of the techniques available nowadays for crowd simulation are focused on a specific situation, like people evacuation. Even if one consider heterogeneous crowds, very few of existing methodologies consider the psychological traits of individuals in order to determine the behavior of agents. Therefore, this work aims to add psychological factor as input for agents simulation, which is going to determine their group behavior and, therefore, how individuals move and evolve in virtual environments. The proposed input is the individuals OCEAN attributes which are used to parametrize BioCrowds, a crowd simulation method. We implemented two different parameterizations to map from OCEAN to crowd parameters and compare results. Obtained results with both methods indicate a positive correlation, once they presented a similar behavior in both tested scenarios. In addition, we show how heterogeneous behaviors we can generate in comparison to original BioCrowds.

Crowd simulation has its greatest utility in the study of safety measures for crowded events. However, total evacuation time, which is the most important feature in crowd evacuation, can vary depending on the population, the environment, the adopted strategies to decide routes, but also because people can be panicked or not. This paper presents a model to parametrize crowd simulation allowing to increase or decrease the agents stress. We use BioCrowds model and proposed an extension to consider new parameters to deal with crowd relaxing and compression, as comfort and stress. These two new parameters impact the will to go to the goal and the individual panic in trying to save itself. Indeed, our model could be integrated in other crowd simulators. This work discusses some obtained results and also presents a case study regarding a real scenario. We simulate the Hillsborough Disaster happened in 1989 in order to discuss the reliability of our method. Results indicate that our method can simulate in a coherent way the densities observed in the real life event.

The area of crowd simulation has been widely explored in several contexts from entertainment to safety purposes. In this paper we present an approach to simulate the evacuation of crowds in facilities such as hospitals, geriatric clinics, orphanages and etc. We use Snook tables to parametrize the effort of people to push patients impacting the people speed when evacuating a specific environment. In addition, we compare our method with another simulation in a hospital.

• SBGames is the largest and most important scientific event for games and digital entertainment in Latin America. • It is attended by scientists, artists, designers, teachers and students from Colleges, Universities and the Game Industry. • It gathers around a thousand participants from different regions of Brazil and Countries as United States, England and Portugal. • SBGames is an In-Cooperation event of Eurographics and ACM SIGGRAPH and in 2018 it is held in the beautiful city of Foz do Iguaçu in a jointly conference.

Crowds arise in a variety of situations, such as public concerts and sporting matches. In typical conditions, the crowd moves in an orderly manner, but panic situations may lead to catastrophic results. We propose a computer vision method to identify motion pattern changes in human crowds that can be related to an unusual event. The proposed approach can identify global changes, by evaluating 2D motion histograms in time, and also local effects, by identifying clusters that present similar spatial locations and velocity vectors. The method is tested both on publicly available data sets involving crowded scenarios and on synthetic data produced by a crowd simulation algorithm, which allows the creation of controlled environments with known motion patterns that are particularly suitable for multicamera scenarios.

This paper presents a methodology to characterize information about groups of people with the main goal of detecting cultural aspects. Based on tracked pedestrians, groups are detected and characterized. Group information is then used to find out Cultural aspects in videos, based on the Hofstede cultural dimensions theory. The presented work was tested in videos of pedestrian groups recorded in different countries and results seem promising in order to identify cultural aspects in the filmed sequences.

Pedestrian segmentation is a problem of considerable practical interest. In this work we propose a shape-based model for pedestrian segmentation. Our model is initialized by a bounding-box of the person under analysis, which can be estimated by a person detector. The basic idea of the proposed model is to create a graph around the detected person, based on a scale invariant shape model and the estimated contour is given by a path in the graph that maximizes certain boundary energy. In practice, such energy should be large in the boundary between the foreground/background. To cope with pose/shape variations, the final estimate is given by a selection scheme, which takes into consideration the individual estimate given by different generated graphs. Experimental results indicated that the proposed technique works well in non trivial images, with comparable accuracy to the state-of-the-art.

In this work we propose a framework for group re-identification based on manually defined soft-biometric characteristics. Users are able to choose colors that describe the soft-biometric attributes of each person belonging to the searched group. Our technique matches these structured attributes against image databases using color distance metrics, a novel adaptive threshold selection and people's proximity high level feature. Experimental results show that the proposed approach is able to help the re-identification procedure ranking the most likely results without training data, and also being extensible to work without previous images.

In this paper we propose a head-shoulder contour estimation model for human figures in still images, captured in a frontal pose. The contour estimation is guided by a learned head-shoulder shape model, initialized automatically by a face detector. A graph is generated around the detected face with an omega-like shape, and the estimated head-shoulder contour is a path in the graph with maximal cost. A dataset with labeled data is used to create the head-shoulder shape model and to quantitatively analyze the results. The proposed model is scaled according to the detected face size to be scale invariant. Experimental results indicate that the proposed technique works well in non trivial images, effectively estimating the contour of the head-shoulder even under partial occlusions.

In this paper we propose a self-occlusion and 3D pose estimation model for human figures in still images based on a user-provided 2D skeleton. An initial segmentation model is used to capture labeled human body parts in a 2D image. Then, occluded body parts are detected when different body parts overlap, and are disambiguated by analyzing the energy of the corresponding contours around the intersection points. The estimated occlusion results feed the 3D pose estimation algorithm, which reconstructs a set of plausible 3D postures. Experimental results indicate that the proposed technique works well in non trivial images, effectively estimating the occluded body parts and reducing the number of possible 3D postures.

Adventure role playing games (RPGs) provide players with increasingly expansive worlds, compelling storylines, and meaningful fictional character interactions. Despite the fast-growing richness of these worlds, the majority of interactions between the player and non-player characters (NPCs) still remain scripted. In this paper we propose using an NPC's animations to reflect how they feel towards the player and as a proof of concept, investigate the potential for a straightforward gaze model to convey trust. Through two perceptual experiments, we find that viewers can distinguish between high and low trust animations, that viewers associate the gaze differences specifically with trust and not with an unrelated attitude (aggression), and that the effect can hold for different facial expressions and scene contexts, even when viewed by participants for a short (five second) clip length. With an additional experiment, we explore the extent that trust is uniquely conveyed over other attitudes associated with gaze, such as interest, unfriendliness, and admiration.

In this paper we propose a skeleton-based model for human segmentation in static images. Our approach explores edge information, orientation coherence and anthropometric-estimated parameters to generate a graph, and the desired contour is a path with maximal cost. Experimental results show that the proposed technique works well in non trivial images.

ABSTRACT In this paper, we propose a new model to quantitatively compare global flow characteristics of two crowds. The proposed approach explores a 4‐D histogram that contains information on the local velocity (speed and orientation) of each spatial position, and the comparison is made using histogram distances. The 4‐D histogram also allows the comparison of specific characteristics, such as distribution of orientations only, speed only, relative spatial occupancy only, and combinations of such features. Experimental results indicate that the proposed quantitative metric correlates with visual inspection. Copyright © 2012 John Wiley & Sons, Ltd.

Estimating human pose in static images is challenging due to the high dimensional state space, presence of image clutter and ambiguities of image observations. In this paper we propose a method to automatically segment human subjects in images, based on dominant colors, and given the face captured by a face detector. The posture is estimated using a 2D model combined with anthropometric data. Experimental results showed that the proposed technique performs well in non trivial images.

Understanding people attentional focus can be useful for several applications. One important challenge in this area is to determine the iris position in image/video in order to estimate gaze behavior. To this end, this paper presents a robust and non-intrusive method to locate human iris position in low resolution grayscale images, in real-time. The method requires the previous knowledge of the face location and provides iris position in a region of interest (ROI) estimated based on anthropometric parameters. We achieved good results, varying from 90% to 100% of accuracy on images and video sequences. In addition, we tested our algorithm with noisy images. The lowest levels of accuracy are mainly due to light reflection on spectacles and eyes occlusion by eyelids.

In this paper, we propose a framework for event detection based on trajectory clustering and 4-D histograms. In the training period, captured trajectories are grouped into coherent clusters according to global motion flows. Within each cluster, the position and instantaneous velocity of each tracked object are used to build a 4-D motion histogram for the cluster. In the test period, each new trajectory is compared against the 4-D histograms of all clusters, so that its coherence with previously tracked objects can be evaluated. Experimental results showed that these criteria can be effectively used to measure the coherence of test trajectories with those in the training stage, allowing a range of events to be detected in surveillance and traffic applications.

Abstract In this paper, we propose a new model to simulate the movement of virtual humans based on trajectories captured automatically from filmed video sequences. These trajectories are grouped into similar classes using an unsupervised clustering algorithm, and an extrapolated velocity field is generated for each class. A physically‐based simulator is then used to animate virtual humans, aiming to reproduce the trajectories fed to the algorithm and at the same time avoiding collisions with other agents. The proposed approach provides an automatic way to reproduce the motion of real people in a virtual environment, allowing the user to change the number of simulated agents while keeping the same goals observed in the filmed video. Copyright © 2007 John Wiley & Sons, Ltd.

This paper presents a new adaptive background model for grayscale video sequences, that includes shadows and highlight detection. In the training period, statistics are computed for each image pixel to obtain the initial background model and an estimate of the image global noise, even in the presence of several moving objects. Each new frame is then compared to this background model, and spatio-temporal features are used to obtain foreground pixels. Local statistics are then used to detect shadows and highlights, and pixels that are detected as either shadow or highlight for a certain number of frames are adapted to become part of the background. Experimental results indicate that the proposed algorithm can effectively detect shadows and highlights, adapting the background with respect to illumination changes.

This paper presents a new approach for real-time generation of 3D virtual cities. The main goal is to provide of a generic framework which support semi-automatic creation, manage-ment, and visualization of urban complex environments for virtual human simulation, called virtual urban life (VUL). It intends to minimize efforts of designers in the modeling of complex and huge environments. A versatile multi-level data model has been developed to support data management and visualization in an efficient way. Moreover, a polygon partitioning algorithm addresses the city allotment problem in an automatic way, according to input parameters and constraints. In addition, we discuss some results of virtual populated city simulations developed with proposed frame-work.

Crowd animation and simulation have been widely studied over the last decade for many purposes: populating collaborative virtual environments, entertainment and special effects industry and finally simulating behaviors and motion of people in emergency situations for safety systems. This last topic is addressed in this paper. We propose an original enhancement of a well known physics-based animation model which allows to consider influence of gaseous phenomena such as smoke or toxic gases in the behavior of the crowd. In order to get real time performances we also propose an implementation of this framework on modern graphics hardware, which allows to simulate crowds of thousands individuals at interactive framerate.

This paper presents the urban environment model (UEM), a novel approach through which a large number of virtual humans can populate a urban space by considering normal life situations. Using this model, the semantic is included in the virtual space considering normal life actions according to different agent profiles distributed in time and space. For instance, children going to the school and adults going to work at usual times. Leisure and shopping activities are also considered. Agent profiles and their actions are also described using UEM. Besides presenting the details of the model, we present its integration into a crowd simulator whose main goal is to provide realistic and coherent population behaviors into urban environments. The results show that urban environments can be populated in a more realistic way by using UEM, escaping from the normal impression we have in such kind of system that virtual people are walking in a random way by predefined paths in the virtual space.

This paper presents a novel approach to simulate virtual human crowds in emergency situations. Our model is based on two previous works, on a physical model proposed by Helbing, where individuals are represented by a particle system affected by "social forces" that impels them to go to a point-objective, while avoiding collisions with obstacles and other agents. As a new property, the virtual agents are endowed with different attributes and individualities as proposed by Braun et al. The main contributions of this paper are the treatment of complex environments and their implications on agents' movement, the management of alarms distributed in space, the virtual agents endowed with perception of emergency events and their consequent reaction as well as changes in their individualities. The prototype reads a XML file where different scenarios can be simulated, such as the characteristics of population, the virtual scene description, the alarm configuration and the properties of hazardous events. As output, the prototype generates information in order to measure the impact of parameters on saved, injured and dead agents. In addition, some results and validation are discussed.

This paper presents a model for studying the impact of individual agent characteristics in emergent groups, based on the evacuation efficiency as a result of local interactions. We used the physically based model of crowd simulation proposed by Helbing et al. (2000) and generalized it in order to deal with different individualities for agent and group behaviors. In addition, we present a framework to visualize the virtual agents and discuss the obtained results. A variety of simulations with different parameter sets shows significant impact on the evacuation scenario.

This paper presents a model for building agents' memories in virtual environments. This approach allows the generation of agents' memory during the simulation, without user intervention. Moreover the memory can be used to generate behavioural reactive rules. We use dynamic and hierarchical finite state machine (DHFSM) in order to represent the agents past experiences.

We describe a model for simulating crowds of humans in real time. We deal with a hierarchy composed of virtual crowds, groups, and individuals. The groups are the most complex structure that can be controlled in different degrees of autonomy. This autonomy refers to the extent to which the virtual agents are independent of user intervention and also the amount of information needed to simulate crowds. Thus, depending on the complexity of the simulation, simple behaviors can be sufficient to simulate crowds. Otherwise, more complicated behavioral rules can be necessary and, in this case, it can be included in the simulation data in order to improve the realism of the animation. We present three different ways for controlling crowd behaviors: by using innate and scripted behaviors; by defining behavioral rules, using events and reactions; and by providing an external control to guide crowd behaviors in real time. The two main contributions of our approach are: the possibility of increasing the complexity of group/agent behaviors according to the problem to be simulated and the hierarchical structure based on groups to compose a crowd.

This paper presents a crowd modelling method in Collaborative Virtual Environment (CVE) which aims to create a sense of group presence to provide a more realistic virtual world. An adaptive display is also presented as a key element to optimise the needed information to keep an acceptable frame rate during crowd visualisation. This system has been integrated in the several CVE platforms which will be presented at the end of this paper. 1.1 Keywords Autonomous agents, virtual crowds, virtual environments.