Share Email Print

Optical Engineering • Open Access

Online visual tracking based on selective sparse appearance model and spatiotemporal analysis
Author(s): Ming Xue; Shibao Zheng; Hua Yang; Yi Zhou; Zhenghua Yu

Paper Abstract

To tackle robust visual tracking in complex environment, an online algorithm based on generative model is proposed. The target is represented with overlapped and selected local patches based on key point proportion ranking, and its location is estimated by spatiotemporal analysis. Temporally, a propagated affine warping dynamical model is newly introduced. Spatially, an observation model based on weighted sparse representation and geometric confidence inference is newly established. Both selection pattern and templates are periodically updated to adapt the target’s appearance variation. Experiments demonstrate that the proposed approach achieves more favorable performance compared with classical works on challenging image sequences.

Paper Details

Date Published: 23 January 2014
PDF: 16 pages
Opt. Eng. 53(1) 013103 doi: 10.1117/1.OE.53.1.013103
Published in: Optical Engineering Volume 53, Issue 1
Show Author Affiliations
Ming Xue, Shanghai Jiao Tong Univ. (China)
Shibao Zheng, Shanghai Jiao Tong Univ. (China)
Hua Yang, Shanghai Jiao Tong Univ. (China)
Yi Zhou, Dalian Maritime Univ. (China)
Zhenghua Yu, Bocom Smart Network Technologies Inc. (China)

© SPIE. Terms of Use
Back to Top