Abstract | ||
---|---|---|
Tracking multiple objects is a challenging task when objects move in groups and occlude each other. Existing methods have investigated the problems of group division and group energy-minimization; however, lacking overall object-group topology modeling limits their ability in handling complex object and group dynamics. Inspired with the social affinity property of moving objects, we propose a Graphical Social Topology (GST) model, which estimates the group dynamics by jointly modeling the group structure and the states of objects using a topological representation. With such topology representation, moving objects are not only assigned to groups, but also dynamically connected with each other, which enables in-group individuals to be correctly associated and the cohesion of each group to be precisely modeled. Using well-designed topology learning modules and topology training, we infer the birth/death and merging/splitting of dynamic groups. With the GST model, the proposed multi-object tracker can naturally facilitate the occlusion problem by treating the occluded object and other in-group members as a whole while leveraging overall state transition. Experiments on both RGB and RGB-D datasets confirm that the proposed multi-object tracker improves the state-of-the-arts especially in crowded scenes. |
Year | Venue | Field |
---|---|---|
2017 | arXiv: Computer Vision and Pattern Recognition | Cohesion (chemistry),Topology,Computer vision,Group structure,Pattern recognition,Computer science,Video tracking,RGB color model,Artificial intelligence,Merge (version control),Machine learning |
DocType | Volume | Citations |
Journal | abs/1702.04040 | 0 |
PageRank | References | Authors |
0.34 | 24 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shan Gao | 1 | 5 | 5.17 |
Xiaogang Chen | 2 | 184 | 25.18 |
Qixiang Ye | 3 | 913 | 64.51 |
Junliang Xing | 4 | 1193 | 63.31 |
Arjan Kuijper | 5 | 1063 | 133.22 |
Xiangyang Ji | 6 | 533 | 73.14 |