Object Tracking with Occlusion Handling Using Mean Shift, Kalman Filter and Edge Histogram

被引：0

作者：

Iraei, Iman ^{[1
]}

Faez, Karim ^{[1
]}

机构：

[1] Amirkabir Univ Technol, Dept Elect Engn, Tehran Polytech, Tehran, Iran

来源：

2015 2ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION AND IMAGE ANALYSIS (IPRIA) | 2015年

关键词：

Kalman Filter; Occlusion Handling; Mean Shift; Object Tracking; Edge Histogram; MATLAB Simulation;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper propose an algorithm that uses Mean Shift and Kalman Filter for object tracking. Also this method uses Edge Histogram for occlusion handling. Firstly, we use Mean Shift algorithm to obtain center of desired object. But the robust of tracking is not very well, so we use Kalman Filter to improve the effect of tracking. Bhattacharyya coefficient and Edge Histogram are used for finding out both partial and full occlusions. With this approach we can track the object more accurately. The results prove that the robust of tracking is very well.

引用

页数：6

共 14 条

[1]

[Anonymous], 2012, WORLD ACAD SCI ENG T

[2] A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking [J].