An Efficient Sequential Approach to Tracking Multiple Objects through Crowds for Real-Time Intelligent CCTV Systems
Artikel i vetenskaplig tidskrift, 2008
Efficiency and robustness are the two most important issues for multi-object tracking algorithms in real-time intelligent video surveillance systems. We propose a novel
2 1/2 D approach to real time multi-object tracking in crowds, which is formulated as a MAP estimation problem and is approximated through an “assignment” step and a “location” step. Observing that the occluding object is usually less affected by the occluded objects, sequential solutions for the assignment and the location are derived. A novel dominant color histogram (DCH) is proposed as an efficient object model. The DCH can be regarded as a generalized color histogram, where dominant colors are selected based on a given distance measure. Comparing with conventional color histograms, DCH only requires a few color components (31 in average). Further, our theoretical analysis and evaluation on real data have shown that DCHs are robust to illumination changes. Using DCH, efficient implementations of sequential solutions for the assignment and the location steps are proposed. The "Assignment" step includes the estimation of depth order for the objects in a dispersing group, one-by-one assignment, and feature exclusion from the group representation. The "Location" step includes the depth order estimation for the objects in a new group, two-phase mean-shift location, and the exclusion of tracked objects from the new position in the group. Multi-object tracking results and evaluation from public datasets are presented. Experiments on image sequences captured from crowded public environments have shown good tracking results, where about 90% of objects have been successfully tracked with the correct identification numbers by the proposed method. Our results and evaluation have indicated that the method is efficient and robust for tracking multiple objects (large than or equal to 3) in complex occlusions for real world surveillance scenarios.