Robust Object Tracking with Adaptive Fusion of Color and Edge Strength Local Mean Features Based on Particle Filter

Author

Li Chunxin ; Xiaotong, Wang ; Xiaogang, Xu

Author_Institution

Dept. of Navig., Dalian Naval Acad., Dalian, China

Volume

3

fYear

2009

fDate

15-17 May 2009

Firstpage

285

Lastpage

289

Abstract

Aiming at the problem of real time and robustness of visual object tracking in a clutter background, an adaptive fusion of color rectangle feature and edge strength local mean tracking algorithm based on particle filter is put forward. To improve the tracking speed and precision, integral image is used to quickly compute the color rectangle feature and edge strength local mean, besides fuzzy logic is applied to adaptively adjust each feature weight. The simulation results illustrate the algorithm is robust and effective.

Keywords

computer vision; edge detection; image colour analysis; image fusion; object detection; particle filtering (numerical methods); adaptive fusion; computer vision; edge strength local mean tracking algorithm; fuzzy logic; integral image; particle filter; rectangle feature mean tracking algorithm; visual object tracking; Colored noise; Cost function; Information technology; Iterative algorithms; Lighting; Navigation; Particle filters; Particle tracking; Robustness; State-space methods; Edge Strength Local Mean; adaptive fusion; color rectangle feature; particle filter; visual tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Technology and Applications, 2009. IFITA '09. International Forum on

Conference_Location

Chengdu

Print_ISBN

978-0-7695-3600-2

Type

conf

DOI

10.1109/IFITA.2009.157

Filename

5232116