Floor Fields for Tracking in High Density Crowd Scenes

This paper presents an algorithm for tracking individual targets in high density crowd scenes containing hundreds of people. Tracking in such a scene is extremely challenging due to the small number of pixels on the target, appearance ambiguity resulting from the dense packing, and severe inter-object occlusions. The novel tracking algorithm, which is outlined in this paper, will overcome these challenges using a scene structure based force model. In this force model an individual, when moving in a particular scene, is subjected to global and local forces that are functions of the layout of that scene and the locomotive behavior of other individuals in the scene. The key ingredients of the force model are three floor fields, which are inspired by the research in the field of evacuation dynamics, namely Static Floor Field (SFF), Dynamic Floor Field (DFF), and Boundary Floor Field (BFF). These fields determine the probability of move from one location to another by converting the long-range forces into local ones. The SFF specifies regions of the scene which are attractive in nature (e.g. an exit location). The DFF specifies the immediate behavior of the crowd in the vicinity of the individual being tracked. The BFF specifies influences exhibited by the barriers in the scene (e.g. walls, no-go areas). By combining cues from all three fields with the available appearance information, we track individual targets in high density crowds.

[1]  Jiří Matas,et al.  Computer Vision - ECCV 2004 , 2004, Lecture Notes in Computer Science.

[2]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  James J. Little,et al.  Robust Visual Tracking for Multiple Targets , 2006, ECCV.

[4]  Frank Dellaert,et al.  An MCMC-Based Particle Filter for Tracking Multiple Interacting Targets , 2004, ECCV.

[5]  Roberto Cipolla,et al.  Unsupervised Bayesian Detection of Independent Motion in Crowds , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[6]  Gregory D. Hager,et al.  Probabilistic data association methods in visual tracking of groups , 2004, CVPR 2004.

[7]  Chris Stauffer,et al.  Estimating Tracking Sources and Sinks , 2003, 2003 Conference on Computer Vision and Pattern Recognition Workshop.

[8]  Ris S. C. Lee,et al.  Exploring Trampling and Crushing in a Crowd , 2005 .

[9]  Andreas Schadschneider,et al.  Simulation of evacuation processes using a bionics-inspired cellular automaton model for pedestrian dynamics , 2002 .

[10]  A. Schadschneider,et al.  Simulation of pedestrian dynamics using a two dimensional cellular automaton , 2001 .

[11]  D. Rubinstein,et al.  Computation of Pressure Distribution Using PIV Velocity Data , 2002 .

[12]  Ramakant Nevatia,et al.  Bayesian human segmentation in crowded situations , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[13]  Mubarak Shah,et al.  A Lagrangian Particle Dynamics Approach for Crowd Flow Segmentation and Stability Analysis , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Ramakant Nevatia,et al.  Tracking multiple humans in crowded environment , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[15]  T. Kanade,et al.  Cell Population Tracking and Lineage Construction Using Multiple-Model Dynamics Filters and Spatiotemporal Optimization , 2007 .

[16]  Margrit Betke,et al.  Tracking Large Variable Numbers of Objects in Clutter , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.