People Tracking From Multiple Cameras
Outdoor surveillance is one of the most attractive application of video processing and analysis. Robust algorithms must be defined and tuned to cope with the non-idealities of outdoor scenes. For instance, in a public park, an automatic video surveillance system must discriminate between shadows, reflections, waving trees, people standing still or moving, and other objects. Visual knowledge coming from multiple cameras can disambiguate cluttered and occluded targets by providing a continuous consistent labeling of tracked objects among the different views.
We propose a new approach for coping with this problem in multi-camera systems with overlapped Fields of View (FoVs). The presence of overlapped zones allows the definition of a geometry-based approach to reconstruct correspondences between FoVs, using only homography and epipolar lines (hereinafter HECOL: Homography and Epipolar-based COnsistent Labeling) computed automatically with a training phase.
We develop a complete system that provides segmentation and tracking of people in each camera module. Segmentation is performed by means of the SAKBOT (Statistical and Knowledge Based Object Tracker) approach, suitably modified to cope with multimodal backgrounds, reflections and other artefacts, typical of outdoor scenes. The extracted objects are tracked using a statistical appearance model robust against occlusions and segmentation errors. The main novelty of this paper is the approach to consistent labeling. A specific Camera Transition Graph is adopted to efficiently select the possible correspondence hypotheses between labels. A Bayesian MAP optimization assigns consistent labels to objects detected by several points of views: the object axis is computed from the shape tracked in each camera module and homography and epipolar lines allow a correct axis warping in other image planes. Both forward and backward probability contributions from the two different warping directions make the approach robust against segmentation errors, and capable of disambiguating groups of people. The system has been tested in a real setup of a urban public park, within the Italian LAICA (Laboratory of Ambient Intelligence for a friendly city) project. The experiments show how the system can correctly track and label objects in a distributed system with real-time performance. Comparisons with simpler consistent labeling methods and extensive outdoor experiments with ground truth demonstrate the accuracy and robustness of the proposed approach.
|1||Calderara, Simone; Prati, Andrea; Cucchiara, Rita "Moving pixels in static cameras: detecting dangerous situations due to environment or people" Intelligent Multimedia Analysis for Security Applications, pp. 1 -28 , 2010 Chapter in Book|
|2||Calderara, Simone; Prati, Andrea; Cucchiara, Rita "HECOL: Homography and Epipolar-based Consistent Labeling for Outdoor Park Surveillance" COMPUTER VISION AND IMAGE UNDERSTANDING, vol. 111(1), pp. 21 -42 , 2008 | DOI: 10.1016/j.cviu.2007.07.006 Journal|
|3||Calderara, Simone; Cucchiara, Rita; Prati, Andrea "Bayesian-competitive Consistent Labeling for People Surveillance" IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 30, pp. 354 -360 , 2008 | DOI: 10.1109/TPAMI.2007.70814 Journal|
|4||Calderara, Simone; Cucchiara, Rita; Prati, Andrea "A Distributed Outdoor Video Surveillance System for Detection of Abnormal People Trajectories" 2007 First ACM/IEEE International Conference on Distributed Smart Cameras, Vienna, Austria, pp. 364 -371 , September 25-28 2007, 2007 | DOI: 10.1109/ICDSC.2007.4357545 Conference|
|5||S. CALDERARA; R. CUCCHIARA; A. PRATI "Group Detection at Camera Handoff for Collecting People Appearance in Multi-camera Systems" Proceedings of AVSS 2006, Sydney, Australia, pp. 36 -41 , 22-24 November 2006, 2006 Conference|
|6||Calderara, S.; Cucchiara, R.; Prati, A. "Multimedia Surveillance: Content-based Retrieval with Multicamera People Tracking" Proceedings of the 4th ACM international workshop on Video surveillance and sensor networks, Santa Barbara (CA), pp. 95 -100 , 27 October 2006, 2006 | DOI: 10.1145/1178782.1178797 Conference|
|7||S. CALDERARA; R. CUCCHIARA; A. PRATI "The LAICA project: Experiments on Multicamera People Tracking and Logging" Atti di CISI 2006, Ancona, Italy, pp. - -- , 27-29 September 2006, 2006 Conference|
|8||S. Calderara; R. Vezzani; A. Prati; R. Cucchiara "Entry Edge of Field of View for multi-camera tracking in distributed video surveillance" Proceedings of IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS2005), vol. 1, Como, Italy, pp. 93 -98 , 15-16 September 2005, 2005 Conference|
|9||S. Calderara; A. Prati; R. Vezzani; R. Cucchiara "Consistent labeling for multi-camera object tracking" Image Analysis and Processing ICIAP 2005, vol. LNCS 3617, Cagliari, Italy, pp. 1206 -1214 , Sept. 6-8, 2005 Conference|