Context-based occlusion detection for robust visual tracking
Xiaoguang Niu, Yu Qiao · 2017
Occlusion is one of the most challenging factors in visual tracking. In this paper, we propose a novel context-based occlusion detection algorithm for robust visual tracking. The basic idea of our algorithm is that occlusion indicates that some background points in previous frame move into the target region in current frame. Our algorithm investigates background patches with background trackers. The occlusion is examined by the a occlusion detector. The template updating strategy is that if occlusion is detected, the target template stops updating. Comprehensive experiments in CVPR2013 Online Objecting Tracking Benchmark (OOTB) show that our tracker achieves comparable performance with other state-of-art trackers.