Abstract：In actual surveillance conditions, many uncertainties exist in pedestrian movement. These movements may disturb the current tracking algorithms and result in tracking lost. An adaptive pedestrian tracking algorithm is proposed. In this algorithm, the prior knowledge of pedestrian detection is embedded into the self-learning process of object model. Firstly, offline training is performed to get a set of sub-classifiers with strong discriminability and prior knowledge of the pedestrians. Then, online boosting algorithm is used for learning and updating the pedestrian's dynamic model from the offline trained sub classifier set. Experimental results show that the proposed method efficiently relieves the conflict between adaptation and drifting, and tracks pedestrian with various uncertain movement under the actual surveillance conditions.
[1] Hager G D, Belhumeu P N. Efficient Region Tracking with Parametric Models of Geometry and Illumination. IEEE Trans on Pattern Analysis and Machine Intelligence, 1998, 20(10): 1025-1039 [2] Comaniciu D, Ramesh V, Meer P. Kernel-Based Object Tracking. IEEE Trans on Pattern Analysis and Machine Intelligence, 2003, 25(5): 564-577 [3] Zhao Tao, Nevatia R. Tracking Multiple Humans in Complex Situations. IEEE Trans on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1208-1221 [4] Deutscher J, Blake A, Reid I. Articulated Body Motion Capture by Annealed Particle Filtering // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Hilton Head Island, USA, 2000, Ⅱ: 2126-2133 [5] Avidan S. Ensemble Tracking. IEEE Trans on Pattern Analysis and Machine Intelligence, 2007, 29(2): 261-271 [6] Grabner H, Bischof H. On-line Boosting and Vision // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA, 2006: Ⅰ: 260-267 [7] Javed O, Ali S, Shah M. On-line Detection and Classification of Moving Objects Using Progressively Improving Detectors // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005, Ⅰ: 696-701 [8] Wu Bo, Nevatia R. Improving Part Based Object Detection by Unsupervised, On-line Boosting // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Minneapolis, USA, 2007: 1-8 [9] Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, USA, 2005, Ⅰ: 886-893 [10] Wu Bo, Nevatia R. Detection of Multiple, Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors // Proc of the 10th IEEE International Conference on Computer Vision. Beijing, China, 2005, Ⅰ: 90-97 [11] Sabzmeydani P. Mori G. Detecting Pedestrians by Learning Shapelet Features // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Minneapolis, USA, 2007: 1-8 [12] Papageorgiou C , Poggio T. A Trainable System for Object Detection. International Journal of Computer Vision, 2000, 38(1): 15-33 [13] Schapire R, Freund Y, Bartlett P, et al. Boosting the Margin: A New Explanation for the Effectiveness of Voting Methods. The Annals of Statistics, 1998, 26(5): 1651-1686 [14] Oza N, Russell S. On-line Bagging and Boosting // Proc of the IEEE International Conference on Systems, Man and Cybernetics. Waikoloa, USA, 2005, Ⅲ: 2340-2345
2009, Vol. 22 
