Share Email Print

Proceedings Paper

A novel correlation filter tracking algorithm based on feature integration
Author(s): Qian Li; Zhezhou Yu; Zhao Chen
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper, we proposed a new object tracking method based on correlation filter, it performs good performance among various disturbances including illumination variation, background clutter, motion blur, scale variation and out-of-plane rotation, etc. Local Intensity Order Pattern(LIOP) feature and color names (CN) feature are integrated to the correlation filter framework. In the proposed method, it first predicts the center position, and then select seven different size of patches for scale selection to improve the accuracy of the algorithm. The experimental results on benchmark videos show that the proposed tracker achieves a higher accuracy compared with those classic trackers based on correlation filter and other popular ones.

Paper Details

Date Published: 9 August 2018
PDF: 9 pages
Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 108063V (9 August 2018); doi: 10.1117/12.2502945
Show Author Affiliations
Qian Li, Jilin Univ. (China)
Zhezhou Yu, Jilin Univ. (China)
Zhao Chen, Jilin Univ. (China)

Published in SPIE Proceedings Vol. 10806:
Tenth International Conference on Digital Image Processing (ICDIP 2018)
Xudong Jiang; Jenq-Neng Hwang, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?