TY - GEN
T1 - Bayesian multi-object tracking using motion context from multiple objects
AU - Yoon, Ju Hong
AU - Yang, Ming Hsuan
AU - Lim, Jongwoo
AU - Yoon, Kuk Jin
N1 - Publisher Copyright:
© 2015 IEEE.
Copyright:
Copyright 2015 Elsevier B.V., All rights reserved.
PY - 2015/2/19
Y1 - 2015/2/19
N2 - Online multi-object tracking with a single moving camera is a challenging problem as the assumptions of 2D conventional motion models (e.g., first or second order models) in the image coordinate no longer hold because of global camera motion. In this paper, we consider motion context from multiple objects which describes the relative movement between objects and construct a Relative Motion Network (RMN) to factor out the effects of unexpected camera motion for robust tracking. The RMN consists of multiple relative motion models that describe spatial relations between objects, thereby facilitating robust prediction and data association for accurate tracking under arbitrary camera movements. The RMN can be incorporated into various multi-object tracking frameworks and we demonstrate its effectiveness with one tracking framework based on a Bayesian filter. Experiments on benchmark datasets show that online multi-object tracking performance can be better achieved by the proposed method.
AB - Online multi-object tracking with a single moving camera is a challenging problem as the assumptions of 2D conventional motion models (e.g., first or second order models) in the image coordinate no longer hold because of global camera motion. In this paper, we consider motion context from multiple objects which describes the relative movement between objects and construct a Relative Motion Network (RMN) to factor out the effects of unexpected camera motion for robust tracking. The RMN consists of multiple relative motion models that describe spatial relations between objects, thereby facilitating robust prediction and data association for accurate tracking under arbitrary camera movements. The RMN can be incorporated into various multi-object tracking frameworks and we demonstrate its effectiveness with one tracking framework based on a Bayesian filter. Experiments on benchmark datasets show that online multi-object tracking performance can be better achieved by the proposed method.
UR - http://www.scopus.com/inward/record.url?scp=84925424648&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84925424648&partnerID=8YFLogxK
U2 - 10.1109/WACV.2015.12
DO - 10.1109/WACV.2015.12
M3 - Conference contribution
AN - SCOPUS:84925424648
T3 - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015
SP - 33
EP - 40
BT - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015
Y2 - 5 January 2015 through 9 January 2015
ER -