Multiple object tracking by multi-feature combination based on min-cost network flow
Mengmeng Wang, Xiaofeng Li, Peixin Liu, Kai Meng Xu, Zhizhong Fu · 2016
Multiple object tracking has been modelled as minimum cost network flow (MCNF) optimization problem recently. It is one of the most popular tracking-by-detection algorithm. MCNF is particularly effective due to its simple model and optimal solutions. However, complex scenarios, such as noisy detections and multi-objective interactions, make it difficult to track multi-objects in consecutive frames of video sequence. To effectively handle such situations, we proposed a novel method. The idea is a combination of multiple features and min-cost network flows (MF-MCNF). Experimental results on public tracking datasets demonstrate that our approach achieves a greater improvement comparing with existing MNCF algorithms.