A Pedestrian Tracking Algorithm Based on Mean Shift Using Color Histogram Equalization Method

This paper presents an improved pedestrian tracking algorithm with image sequences acquired by surveillance cameras. This pedestrian tracking algorithm is based on mean shift algorithm, and it uses color histogram equalization to improve the original algorithm. The improved algorithm performs much better than the original algorithm in some situations. We use the CAVIAR project/IST 2001 37540 dataset to evaluate the algorithm.

[1]  Dorin Comaniciu,et al.  Real-time tracking of non-rigid objects using mean shift , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[2]  Levente Kovács,et al.  Video Surveillance Framework for Crime Prevention and Event Indexing , 2008, ICT4Justice.

[3]  Dorin Comaniciu,et al.  Kernel-Based Object Tracking , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Sridha Sridharan,et al.  Automatic surveillance in transportation hubs: No longer just about catching the bad guy , 2015, Expert Syst. Appl..

[5]  Yizong Cheng,et al.  Mean Shift, Mode Seeking, and Clustering , 1995, IEEE Trans. Pattern Anal. Mach. Intell..