Online discriminative object tracking with local sparse representation

Qing Wang, Feng Chen, Wenli Xu, Ming Hsuan Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

135 Citations (Scopus)


We propose an online algorithm based on local sparse representation for robust object tracking. Local image patches of a target object are represented by their sparse codes with an over-complete dictionary constructed online, and a classifier is learned to discriminate the target from the background. To alleviate the visual drift problem often encountered in object tracking, a two-stage algorithm is proposed to exploit both the ground truth information of the first frame and observations obtained online. Different from recent discriminative tracking methods that use a pool of features or a set of boosted classifiers, the proposed algorithm learns sparse codes and a linear classifier directly from raw image patches. In contrast to recent sparse representation based tracking methods which encode holistic object appearance within a generative framework, the proposed algorithm employs a discrimination formulation which facilitates the tracking task in complex environments. Experiments on challenging sequences with evaluation of the state-of-the-art methods show effectiveness of the proposed algorithm.

Original languageEnglish
Title of host publication2012 IEEE Workshop on the Applications of Computer Vision, WACV 2012
Number of pages8
Publication statusPublished - 2012
Event2012 IEEE Workshop on the Applications of Computer Vision, WACV 2012 - Breckenridge, CO, United States
Duration: 2012 Jan 92012 Jan 11

Publication series

NameProceedings of IEEE Workshop on Applications of Computer Vision
ISSN (Print)2158-3978
ISSN (Electronic)2158-3986


Conference2012 IEEE Workshop on the Applications of Computer Vision, WACV 2012
Country/TerritoryUnited States
CityBreckenridge, CO

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Computer Science Applications


Dive into the research topics of 'Online discriminative object tracking with local sparse representation'. Together they form a unique fingerprint.

Cite this