18 August 2017 Object tracking by transitive learning using perspective transformation with asymptotic stability
Author Affiliations +
J. of Applied Remote Sensing, 11(4), 042602 (2017). doi:10.1117/1.JRS.11.042602
Abstract
Object tracking is a core subject in computer vision and has significant meaning in both theory and practice. We propose a tracking method in which a robust discriminative classifier is built based on both object and context information. In this method, we consider multiple frames of local invariant features on and around the object and construct the object template and context template. To overcome the limitation of the invariant representations, we also design a nonparametric learning algorithm using transitive matching perspective transformation. This learning algorithm can keep adding object appearance and can avoid improper updating when occlusions appear. We also analyze the asymptotic stability of our method and prove its drift-free capability in long-term tracking. Extensive experiments using challenging publicly available video sequences that cover most of the critical conditions in tracking demonstrate the enhanced strength and robustness of our method.
© 2017 Society of Photo-Optical Instrumentation Engineers (SPIE)
Chao Zheng, Zhenzhong Wei, "Object tracking by transitive learning using perspective transformation with asymptotic stability," Journal of Applied Remote Sensing 11(4), 042602 (18 August 2017). http://dx.doi.org/10.1117/1.JRS.11.042602 Submission: Received 9 February 2017; Accepted 18 July 2017
Submission: Received 9 February 2017; Accepted 18 July 2017
JOURNAL ARTICLE
20 PAGES


SHARE
KEYWORDS
Target detection

Detection and tracking algorithms

Optical tracking

Video

Databases

Statistical analysis

Image filtering

Back to Top