Region covariance tracking with hybrid search strategy

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.