The accurate locating for the target is critical for robust visual tracking methods. This paper addresses the target position confirmation and relocation in mean shift tracking, and proposes a novel method to integrate a MOSSE based correlation filter into the mean shift tracker to obtain its ability of accurate locating. To confirm whether the estimated location of the target is accurate, four measures are evaluated. If the proposed conditions for relocating the target are satisfied, the estimated target position will be adjusted to be more accurate. When the target is occluded, a relocating approach is developed using the correlation filter to find the target after occlusion. The target model and the filter template are updated in each frame according to the evaluation results of the estimated target. Experimental results show the integration of the correlation filter can help the mean shift tracker locate and relocate the target well.

Date Published: 4 March 2015
PDF: 7 pages
Proc. SPIE 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 94432S (4 March 2015); doi: 10.1117/12.2179325

Published in SPIE Proceedings Vol. 9443:
Sixth International Conference on Graphic and Image Processing (ICGIP 2014)
Yulin Wang; Xudong Jiang; David Zhang, Editor(s)