The Community for Technology Leaders
RSS Icon
Issue No.02 - February (2008 vol.30)
pp: 267-282
Given two to four synchronized video streams taken at eye level and from different angles, we show that we can effectively combine a generative model with dynamic programming to accurately follow up to six individuals across thousands of frames in spite of significant occlusions and lighting changes. In addition, we also derive metrically accurate trajectories for each one of them.Our contribution is twofold. First, we demonstrate that our generative model can effectively handle occlusions in each time frame independently, even when the only data available comes from the output of a simple background subtraction algorithm and when the number of individuals is unknown a priori. Second, we show that multi-person tracking can be reliably achieved by processing individual trajectories separately over long sequences, provided that a reasonable heuristic is used to rank these individuals and avoid confusing them with one another.
Multi-people tracking, Multi-camera, Visual surveillance, Probabilistic occupancy map, Dynamic Programming, Hidden Markov Model
Fran?ois Fleuret, J?r? Berclaz, Richard Lengagne, Pascal Fua, "Multicamera People Tracking with a Probabilistic Occupancy Map", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.30, no. 2, pp. 267-282, February 2008, doi:10.1109/TPAMI.2007.1174
[1] J. Black, T.J. Ellis, and P. Rosin, “Multi-View Image Surveillance and Tracking,” Proc. IEEE Workshop Motion and Video Computing, 2002.
[2] D. Beymer, “Person Counting Using Stereo,” Proc. Workshop Human Motion, pp. 127-133, 2000.
[3] J. Berclaz, F. Fleuret, and P. Fua, “Robust People Tracking with Global Trajectory Optimization,” Proc. Conf. Computer Vision and Pattern Recognition, 2006.
[4] Q. Cai and J.K. Aggarwal, “Automatic Tracking of Human Motion in Indoor Scenes across Multiple Synchronized Video Streams,” Proc. Sixth IEEE Int'l Conf. Computer Vision, 1998.
[5] R.T. Collins, “Mean-Shift Blob Tracking through Scale Space,” Proc. Conf. Computer Vision and Pattern Recognition, p. 234, 2003.
[6] D. Comaniciu, V. Ramesh, and P. Meer, “Real-Time Tracking of Non-Rigid Objects Using Mean Shift,” Proc. Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 142-149, 2000.
[7] F. Fleuret, R. Lengagne, and P. Fua, “Fixed Point Probability Field for Complex Occlusion Handling,” Proc. 10th Int'l Conf. Computer Vision, Oct. 2005.
[8] D. Focken and R. Stiefelhagen, “Towards Vision-Based 3D People Tracking in a Smart Room,” Proc. Fourth IEEE Int'l Conf. Multimodal Interfaces, 2002.
[9] J. Giebel, D.M. Gavrila, and C. Schnorr, “A Bayesian Framework for Multi-Cue 3D Object Tracking,” Proc. Eighth European Conf. Computer Vision, 2004.
[10] I. Haritaoglu, D. Harwood, and L. Davis, “Who, When, Where, What: A Real-Time System for Detecting and Tracking People,” Proc. Third IEEE Int'l Conf. Automatic Face and Gesture Recognition, pp. 222-227, 1998.
[11] M. Han, W. Xu, H. Tao, and Y. Gong, “An Algorithm for Multiple Object Trajectory Tracking,” Proc. Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 864-871, June 2004.
[12] M. Isard and J. MacCormick, “Bramble: A Bayesian Multiple-Blob Tracker,” Proc. Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 34-41, July 2001.
[13] J. Kang, I. Cohen, and G. Medioni, “Tracking People in Crowded Scenes Across Multiple Cameras,” Proc. Sixth Asian Conf. Computer Vision, 2004.
[14] J. Krumm, S. Harris, B. Myers, B. Brummit, M. Hale, and S. Shafer, “Multi-Camera Multi-Person Tracking for Easy Living,” Proc. Third IEEE Workshop Visual Surveillance, 2000.
[15] S. Khan, O. Javed, and M. Shah, “Tracking in Uncalibrated Cameras with Overlapping Field of View,” Proc. Second IEEE Workshop Performance Evaluation of Tracking and Surveillance, 2001.
[16] S. Khan and M. Shah, “Tracking People in Presence of Occlusion,” Proc. Fourth Asian Conf. Computer Vision, 2000.
[17] V.I. Morariu and O.I. Camps, “Modeling Correspondences for Multi-Camera Tracking Using Nonlinear Manifold Learning and Target Dynamics,” Proc. Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 545-552, 2006.
[18] A. Mittal and L. Davis, “M2tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene,” Int'l J.Computer Vision, vol. 51, no. 3, pp. 189-203, 2003.
[19] I. Mikic, S. Santini, and R. Jain, “Video Processing and Integration from Multiple Cameras,” Proc. DARPA Image Understanding Workshop, 1998.
[20] T. Zhao and R. Nevatia, “Tracking Multiple Humans in Crowded Environment,” Proc. Conf. Computer Vision and Pattern Recognition, 2004.
[21] K. Otsuka and N. Mukawa, “Multi-View Occlusion Analysis for Tracking Densely Populated Objects Based on 2D Visual Angles,” Proc. Conf. Computer Vision and Pattern Recognition, 2004.
[22] N.M. Oliver, B. Rosario, and A.P. Pentland, “A Bayesian Computer Vision System for Modeling Human Interactions,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 831-843, Aug. 2000.
[23] K. Okuma, A. Taleghani, N. de Freitas, J.J. Little, and D.G. Lowe, “A Boosted Particle Filter: Multitarget Detection and Tracking,” Proc. Eighth European Conf. Computer Vision, May 2004.
[24] F. Porikli and A. Divakaran, “Multi-Camera Calibration, Object Tracking and Query Generation,” Proc. Int'l Conf. Multimedia and Expo, vol. 1, pp. 635-6569, 2003.
[25] K. Smith, D. Gatica-Perez, and J.-M. Odobez, “Using Particles to Track Varying Numbers of Interacting People,” Proc. IEEE Int'l Conf. Computer Vision and Pattern Recognition, 2005.
[26] D.B. Yang, H.H. Gonzáles-Baños, and L.J. Guibas, “Counting People in Crowds with a Real-Time Network of Simple Image Sensors,” Proc. Ninth Int'l Conf. Computer Vision, pp. 122-129, 2003.
[27] F. Ziliani and A. Cavallaro, “Image Analysis for Video Surveillance Based on Spatial Regularization of a Statistical Model-Based Change Detection,” Proc. 10th Int'l Conf. Image Analysis and Processing, 1999.
30 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool