PROJECT TITLE :
Conjugate gradient algorithm for efficient covariance tracking with Jensen-Bregman LogDet metric
Region covariance descriptor that fuses multiple features compactly has proven to be terribly effective for visual tracking. Whereas operating effectively, the exhaustive world search strategy of covariance tracking is still inefficient, and there is a lot of room for improvement. It could cause inconsecutive tracking trajectory and distraction. A suitable region similarity metric for covariance matching between the candidate object region and a given look template is of abundant importance. But, the computational burden of the metric, especially for giant matrices beneath Riemannian area, could hinder its application in gradient-primarily based algorithms. During this study, the authors propose an algorithm that, by minimising the metric perform, exploits an efficient conjugate gradient technique to iteratively search the simplest matched candidate, and determines the search step size by non-monotonic liner strategy. Then, an inferential reasoning in view of new efficient metric is derived for the gradient-primarily based algorithm. The authors take a look at the proposed tracking technique on check baseline dataset. Both quantitative and qualitative results demonstrate the effectiveness of the proposed algorithm compared with other state-of-the-art methods.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here