Multi-Object Tracking Based on Formation Stability

被引：0

作者：

Xu, Liang ^{[1
]}

Li, Weihai ^{[1
]}

机构：

[1] Univ Sci & Technol China, Sch Informat Sci & Technol, Key Lab Electromagnet Space Informat, Chinese Acad Sci, 96 JinZhai Rd, Hefei 230026, Anhui, Peoples R China

来源：

NINTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2017) | 2017年 / 10420卷

关键词：

multi-object tracking; interaction; F-formation; tracklets association;

D O I：

10.1117/12.2281982

中图分类号：

TB8 [摄影技术];

学科分类号：

0804 ;

摘要：

Multi-object tracking in semi-crowded environment is a difficult task. Traditional methods relying only on visual cues, like appearance and simple motion prediction fails because of frequent occlusions. In this paper, a new method based on formation stability is proposed to learn the interaction information among pedestrians. whatever the relationship of a pedestrian with others is, it will remain unchanged for a while. That is, when a pedestrian is occluded, the relationship with others will stay the same after the reappearance of the pedestrian. So trajectory clips caused by occlusions can be associated together. Effectiveness of this method is validated by experiments.

引用

页数：5

共 9 条

[1] Ess A, 2008, PROC CVPR IEEE, P1857
[2] Kuo CH, 2011, PROC CVPR IEEE, P1217, DOI 10.1109/CVPR.2011.5995384
[3] Leal-Taixé L, 2011, 2011 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCV WORKSHOPS), DOI 10.1109/ICCVW.2011.6130233
[4] Continuous Energy Minimization for Multitarget Tracking
Milan, Anton
Roth, Stefan
Schindler, Konrad
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2014, 36 (01) : 58 - 72
[5] Multi-target tracking on confidence maps: An application to people tracking
Poiesi, Fabio
Mazzon, Riccardo
Cavallaro, Andrea
[J]. COMPUTER VISION AND IMAGE UNDERSTANDING, 2013, 117 (10) : 1257 - 1272
[6] F-Formation Detection: Individuating Free-Standing Conversational Groups in Images
Setti, Francesco
Russell, Chris
Bassetti, Chiara
Cristani, Marco
[J]. PLOS ONE, 2015, 10 (05):
[7] Yang B, 2012, PROC CVPR IEEE, P2034, DOI 10.1109/CVPR.2012.6247907
[8] Yang B, 2012, PROC CVPR IEEE, P1918, DOI 10.1109/CVPR.2012.6247892
[9] Yuan Li, 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), P2953, DOI 10.1109/CVPRW.2009.5206735

← 1 →