Crowd Detection with a Multiview Sampler

We present a Bayesian approach for simultaneously estimating the number of people in a crowd and their spatial locations by sampling from a posterior distribution over crowd configurations. Although this framework can be naturally extended from single to multiview detection, we show that the naive extension leads to an inefficient sampler that is easily trapped in local modes. We therefore develop a set of novel proposals that leverage multiview geometry to propose global moves that jump more efficiently between modes of the posterior distribution. We also develop a statistical model of crowd configurations that can handle dependencies among people and while not requiring discretization of their spatial locations. We quantitatively evaluate our algorithm on a publicly available benchmark dataset with different crowd densities and environmental conditions, and show that our approach outperforms other state-of-the-art methods for detecting and counting people in crowds.

[1]  van Marie-Colette Lieshout,et al.  Markov Point Processes and Their Applications , 2000 .

[2]  Frank Dellaert,et al.  EM, MCMC, and Chain Flipping for Structure from Motion with Unknown Correspondence , 2004, Machine Learning.

[3]  Robert T. Collins,et al.  Evaluation of sampling-based pedestrian detection for crowd counting , 2009, 2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance.

[4]  Pascal Fua,et al.  Fixed point probability field for complex occlusion handling , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

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

[6]  Robert T. Collins,et al.  Marked point processes for crowd counting , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  James W. Davis,et al.  Kernel-Based 3D Tracking , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  J. Beveridge,et al.  Average of Synthetic Exact Filters , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Andrew J. Davison,et al.  Active Matching , 2008, ECCV.

[10]  Bernt Schiele,et al.  Pedestrian detection in crowded scenes , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[11]  Larry S. Davis,et al.  M2Tracker: A Multi-view Approach to Segmenting and Tracking People in a Cluttered Scene Using Region-Based Stereo , 2002, ECCV.

[12]  Josiane Zerubia,et al.  A Marked Point Process of Rectangles and Segments for Automatic Analysis of Digital Elevation Models , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Z. Zivkovic.  Improved adaptive Gaussian mixture model for background subtraction , 2004, ICPR 2004.

[14]  A. Voter,et al.  Smart Darting Monte Carlo , 2001 .

[15]  Mubarak Shah,et al.  Tracking Multiple Occluding People by Localizing on Multiple Scene Planes , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Leonidas J. Guibas,et al.  Counting people in crowds with a real-time network of simple image sensors , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[17]  Merrilee Hurn,et al.  Bayesian object identification , 1999 .

[18]  Ambrish Tyagi,et al.  Fusion of Multiple Camera Views for Kernel-Based 3D Tracking , 2007, 2007 IEEE Workshop on Motion and Video Computing (WMVC'07).

[19]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[20]  David A. McAllester,et al.  A discriminatively trained, multiscale, deformable part model , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Naoki Mukawa,et al.  Multiview occlusion analysis for tracking densely populated objects based on 2-D visual angles , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[22]  P. Green.  Reversible jump Markov chain Monte Carlo computation and Bayesian model determination , 1995 .

[23]  F. Fleuret,et al.  Multiple object tracking using flow linear programming , 2009, 2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance.

[24]  A. Ellis,et al.  PETS2009 and Winter-PETS 2009 results: A combined evaluation , 2009, 2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance.

[25]  Rong Zhang,et al.  Integrating bottom-up/top-down for object recognition by data driven Markov chain Monte Carlo , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[26]  Nuno Vasconcelos,et al.  Analysis of Crowded Scenes using Holistic Properties , 2009 .

[27]  Ting Yu,et al.  Unified Crowd Segmentation , 2008, ECCV.

[28]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[29]  Mads Nielsen,et al.  Computer Vision — ECCV 2002 , 2002, Lecture Notes in Computer Science.

[30]  Yannick Boursier,et al.  Sparsity-driven people localization algorithm: Evaluation in crowded scenes environments , 2009, 2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance.

[31]  Geoffrey E. Hinton,et al.  A Mode-Hopping MCMC sampler , 2003 .