Data Driven Evaluation of Crowds

There are various techniques for simulating crowds, however, in most cases the quality of the simulation is measured by examining its "look-and-feel". Even if the aggregate movement of the crowd looks natural from afar, the behaviors of individuals might look odd when examined more closely. In this paper we present a data-driven approach for evaluating the behaviors of individuals within a simulated crowd. Each decision of an individual agent is expressed as a state-action pair, which stores a representation of the characteristics being evaluated and the factors that influence it. Based on video footage of a real crowd, a database of state-action examples is generated. Using a similarity measure, the queries are matched with the database of examples. The degree of similarity can be interpreted as the level of "naturalness" of the behavior. Essentially, this sort of evaluation offers an objective answer to the question of how similar are the simulated behaviors compared to real ones. By changing the input video we can change the context of evaluation.

[1]  Ming C. Lin,et al.  Real-time Path Planning for Virtual Agents in Dynamic Environments , 2007, 2007 IEEE Virtual Reality Conference.

[2]  Stephen Chenney,et al.  Flow tiles , 2004, SCA '04.

[3]  F. Porikli.  Trajectory Distance Metric Using Hidden Markov Model Based Representation , 2004 .

[4]  Stéphane Donikian,et al.  Crowd of Virtual Humans: a New Approach for Real Time Navigation in Complex and Structured Environments , 2004, Comput. Graph. Forum.

[5]  Norman I. Badler,et al.  Virtual Crowds: Methods, Simulation, and Control (Synthesis Lectures on Computer Graphics and Animation) , 2008 .

[6]  Nancy S. Pollard,et al.  Evaluating motion graphs for character navigation , 2004, SCA '04.

[7]  Dinesh Manocha,et al.  Real-time Path Planning for Virtual Agents in Dynamic Environments , 2007, VR.

[8]  R. Hughes.  The flow of human crowds , 2003 .

[9]  Dimitris N. Metaxas,et al.  Eurographics/ Acm Siggraph Symposium on Computer Animation (2007) Group Behavior from Video: a Data-driven Approach to Crowd Simulation , 2022 .

[10]  Norman I. Badler,et al.  Virtual Crowds: Methods, Simulation, and Control , 2008, Virtual Crowds: Methods, Simulation, and Control.

[11]  Sébastien Paris,et al.  Pedestrian Reactive Navigation for Crowd Simulation: a Predictive Approach , 2007, Comput. Graph. Forum.

[12]  Tieniu Tan,et al.  A system for learning statistical motion patterns , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Matthew Brand,et al.  Discovery and Segmentation of Activities in Video , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Dani Lischinski,et al.  Crowds by Example , 2007, Comput. Graph. Forum.

[15]  Norman I. Badler,et al.  Proceedings of the 2004 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, Grenoble, France, August 27-29, 2004 , 2004, Symposium on Computer Animation.

[16]  Norman I. Badler,et al.  Being a part of the crowd: towards validating VR crowds using presence , 2008, AAMAS.

[17]  Christopher E. Peters,et al.  Perceptual evaluation of position and orientation context rules for pedestrian formations , 2008, APGV '08.

[18]  Adrien Treuille,et al.  Continuum crowds , 2006, SIGGRAPH 2006.

[19]  Glenn Reinman,et al.  Watch Out! A Framework for Evaluating Steering Behaviors , 2008, MIG.

[20]  David C. Hogg,et al.  Learning the Distribution of Object Trajectories for Event Recognition , 1995, BMVC.

[21]  Fatih Murat Porikli,et al.  Event Detection by Eigenvector Decomposition Using Object and Frame Features , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.