Robust particle tracking via spatio-temporal context learning and multi-task joint local sparse representation

Xizhe Xue, Ying Li

科研成果: 期刊稿件文章同行评审

3 引用 (Scopus)

摘要

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.

源语言英语
页(从-至)21187-21204
页数18
期刊Multimedia Tools and Applications
78
15
DOI
出版状态已出版 - 15 8月 2019

指纹

探究 'Robust particle tracking via spatio-temporal context learning and multi-task joint local sparse representation' 的科研主题。它们共同构成独一无二的指纹。

引用此