Multiobject Tracking by Submodular Optimization

• Published in: IEEE transactions on cybernetics Vol. 49; no. 6; pp. 1990 - 2001
• Main Authors: Shen, Jianbing, Liang, Zhiyuan, Liu, Jianhong, Sun, Hanqiu, Shao, Ling, Tao, Dacheng
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Detectors; Low-level tracklet; multiobject tracking (MOT); Multiple target tracking; Occlusion; Optical tracking; Optimization; Source code; submodular optimization; Target tracking; Task analysis; Tracking problem; tracklets selecting process; Trajectories; Trajectory; Visualization
• ISSN: 2168-2267; 2168-2275; 2168-2275
• DOI: 10.1109/TCYB.2018.2803217

In this paper, we propose a new multiobject visual tracking algorithm by submodular optimization. The proposed algorithm is composed of two main stages. At the first stage, a new selecting strategy of tracklets is proposed to cope with occlusion problem. We generate low-level tracklets using overlap criteria and min-cost flow, respectively, and then integrate them into a candidate tracklets set. In the second stage, we formulate the multiobject tracking problem as the submodular maximization problem subject to related constraints. The submodular function selects the correct tracklets from the candidate set of tracklets to form the object trajectory. Then, we design a connecting process which connects the corresponding trajectories to overcome the occlusion problem. Experimental results demonstrate the effectiveness of our tracking algorithm.<xref ref-type="fn" rid="fn1"> 1 1 Our source code is available at https://github.com/shenjianbing/submodulartrack .