Share Email Print
cover

Proceedings Paper

A visual tracking method based on improved online multiple instance learning
Author(s): Xianhui He; Yuxing Wei
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Visual tracking is an active research topic in the field of computer vision and has been well studied in the last decades. The method based on multiple instance learning (MIL) was recently introduced into the tracking task, which can solve the problem that template drift well. However, MIL method has relatively poor performance in running efficiency and accuracy, due to its strong classifiers updating strategy is complicated, and the speed of the classifiers update is not always same with the change of the targets’ appearance. In this paper, we present a novel online effective MIL (EMIL) tracker. A new update strategy for strong classifier was proposed to improve the running efficiency of MIL method. In addition, to improve the t racking accuracy and stability of the MIL method, a new dynamic mechanism for learning rate renewal of the classifier and variable search window were proposed. Experimental results show that our method performs good performance under the complex scenes, with strong stability and high efficiency.

Paper Details

Date Published: 27 September 2016
PDF: 8 pages
Proc. SPIE 9684, 8th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test, Measurement Technology, and Equipment, 968433 (27 September 2016); doi: 10.1117/12.2243218
Show Author Affiliations
Xianhui He, Institute of Optics and Electronics (China)
Univ. of Chinese Academy of Sciences (China)
Yuxing Wei, Institute of Optics and Electronics (China)


Published in SPIE Proceedings Vol. 9684:
8th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test, Measurement Technology, and Equipment
Yudong Zhang; Fan Wu; Ming Xu; Sandy To, Editor(s)

© SPIE. Terms of Use
Back to Top