TY - JOUR
T1 - Robust particle tracking via spatio-temporal context learning and multi-task joint local sparse representation
AU - Xue, Xizhe
AU - Li, Ying
N1 - Publisher Copyright:
© 2019, Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2019/8/15
Y1 - 2019/8/15
N2 - Particle filters have been proven very successful for non-linear and non-Gaussian estimation problems and extensively used in object tracking. However, high computational costs and particle decadency problem limit its practical application. In this paper, we present a robust particle tracking approach based on spatio-temporal context learning and multi-task joint local sparse representation. The proposed tracker samples particles according to the confidence map constructed by the spatio-temporal context information of the target. This sampling strategy can ameliorate problems of sample impoverishment and particle degeneracy, target state distribution to obtain robust tracking performance. In order to locate the target more accurately and be less sensitive to occlusion, the local sparse appearance model is adopted to capture the local and structural information of the target. Finally, the multi-task learning where the representations of particles are learned jointly is employed to further improve tracking performance and reduce overall computational complexity. Both qualitative and quantitative evaluations on challenging benchmark image sequences have demonstrated that the proposed tracking algorithm performs favorably against several state-of-the-art methods.
AB - Particle filters have been proven very successful for non-linear and non-Gaussian estimation problems and extensively used in object tracking. However, high computational costs and particle decadency problem limit its practical application. In this paper, we present a robust particle tracking approach based on spatio-temporal context learning and multi-task joint local sparse representation. The proposed tracker samples particles according to the confidence map constructed by the spatio-temporal context information of the target. This sampling strategy can ameliorate problems of sample impoverishment and particle degeneracy, target state distribution to obtain robust tracking performance. In order to locate the target more accurately and be less sensitive to occlusion, the local sparse appearance model is adopted to capture the local and structural information of the target. Finally, the multi-task learning where the representations of particles are learned jointly is employed to further improve tracking performance and reduce overall computational complexity. Both qualitative and quantitative evaluations on challenging benchmark image sequences have demonstrated that the proposed tracking algorithm performs favorably against several state-of-the-art methods.
KW - Local sparse representation
KW - Multi-task learning
KW - Spatio-temporal context
KW - Visual tracking
UR - http://www.scopus.com/inward/record.url?scp=85063090718&partnerID=8YFLogxK
U2 - 10.1007/s11042-019-7246-8
DO - 10.1007/s11042-019-7246-8
M3 - 文章
AN - SCOPUS:85063090718
SN - 1380-7501
VL - 78
SP - 21187
EP - 21204
JO - Multimedia Tools and Applications
JF - Multimedia Tools and Applications
IS - 15
ER -