Title: Region covariance tracking with hybrid search strategy

Authors: Ruhan He; Yongsheng Yu; Jia Chen; Min Li; Xun Yao

Addresses: Institute for Pattern Recognition and Artificial Intelligence, Huazhong University of Science and Technology, Wuhan 430074, China ' The Green Building Materials and Manufacturing Engineering Research Center of Ministry of Education, Wuhan University of Technology, Wuhan 430070, China ' Collaborative Innovation Center of Common Technology in Textile Industry Chain in Hubei Province, Wuhan Textile University, Wuhan 430073, China ' Collaborative Innovation Center of Common Technology in Textile Industry Chain in Hubei Province, Wuhan Textile University, Wuhan 430073, China ' Collaborative Innovation Center of Common Technology in Textile Industry Chain in Hubei Province, Wuhan Textile University, Wuhan 430073, China

Abstract: Covariance tracking has achieved impressive successes owing to its competent region covariance-based feature descriptor. However, the brute-force search strategy in covariance tracking is inefficient and it possibly leads to inconsecutive tracking trajectory and distraction. In this work, a hybrid search strategy for optimisation on covariance tracking is proposed. The hybrid strategy contains the integral region computation, the coarse-to-fine and circular search, and mean shift optimisation. The integral region is much faster than integral image and adaptive to the tracking target and tracking condition. The other three dramatically speed up the convergence of the search. The proposed approach yields much better efficiency, robustness of distraction, and stable trajectory by local search in normal steady state. Our approach shows excellent target representation ability, faster speed, and more robustness, which has been verified on some video sequences.

Keywords: covariance tracking; integral region; coarse-to-fine; CTF; circular search; mean shift optimisation; hybrid search strategy; tracking targets; tracking conditions; video sequences.

DOI: 10.1504/IJES.2015.066142

International Journal of Embedded Systems, 2015 Vol.7 No.1, pp.55 - 62

Received: 15 Apr 2014
Accepted: 22 Apr 2014

Published online: 03 Dec 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article