30 November 2012 On-line object tracking method based on co-training
Author Affiliations +
Proceedings Volume 8558, Optoelectronic Imaging and Multimedia Technology II; 855828 (2012); doi: 10.1117/12.999828
Event: Photonics Asia, 2012, Beijing, China
Abstract
The tracking method based on Co-Training framework considers the object tracking as a semi-supervised learning problem. This paper proposes a new on-line tracking method based on Co-Training framework. The method fuses two features to describe the object and do randomizing affine deformation with positive examples to increase the number of positive examples. Experimental results demonstrate, the on-line tracking method based on Co-training framework can work robustly in long-term tracking and the drift of tracking can be effectively avoided.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jianhong Lai, Zhenming Peng, Yong Yang, "On-line object tracking method based on co-training", Proc. SPIE 8558, Optoelectronic Imaging and Multimedia Technology II, 855828 (30 November 2012); doi: 10.1117/12.999828; https://doi.org/10.1117/12.999828
PROCEEDINGS
7 PAGES


SHARE
KEYWORDS
Video

Feature extraction

Detection and tracking algorithms

Error analysis

Video processing

Defense and security

Information security

Back to Top