#203: A hybrid local and global multi-object tracking with semantic spatial and appearance modules


Abstract

Multi-object tracking is one of the most challenging problem among computer vision applications due to computational cost, partial or full occlusions, crowded scenes, and etc. It has many real-life applicable uses from surveillance to video analysis and video summarization. In this paper, we propose a hybrid tracking-by-detection system that combines local and global data association scheme to ensure efficiency and reduce complexity. In local data association, spatial and appearance modules are used to ensure first step assignment for the strongest object matching. Then tracklet linking is applied during global data association step after filtering out all unreliable and distractor hypotheses using spatial, temporal and appearance descriptors. Our framework can handle the appearance of new objects, temporal disappearance, object terminations, and object occlusions. Our experiments on MOT16 dataset consisting of challenging real-world videos show the integration between local and global data association is important and having promising performance.