Structure-aware multi-object discovery for weakly supervised tracking

Yuankai Qi, Hongxun Yao, Xiaoshuai Sun, Xin Sun, Yanhao Zhang, Qingming Huang

Abstract: Recent progress on tracking has focused on designing robust statistical model or proposing effective appearance features to improve precision. This paper addresses another problem, namely the discovery and tracking of generic multi-object which have the similar appearance and motion pattern based on limited human annotations. We present a model-free tracking method that can automatically discover and track multi-object sharing the same spatial and motion structure, and update the structure during the tracking without prior acknowledge. The candidate objects are first selected by a SVM classifier trained on histogram-of-gradient (HOG) features. Then a segment algorithm is exploited to decide the suitable sizes of tracking boxes. The structure constrains are updated in a real-time manner according to the motion measure among the specified object and corresponding candidates. Experimental results reveal significant convenience and remarkable performance of our approach for the task of structure preserving multi-object discovery and tracking.