A New Improved Camshift Algorithm and Its Experimental Analysis

DOI

10.2991/esac-15.2015.67How to use a DOI?

Keywords

Visual tracking, Camshift algorithm, Kalman filter, Color histogram, Occlusion judgment

Abstract

Camshift is an adaptive tracking algorithm based on color histogram with the advantages of translation, scale and rotation invariance, which is widely used in visual tracking. But in the moving scenes, due to the changing background, occlusion and environmental illumination, the tracking effectiveness and efficiency will be affected and even lead to loss of moving target. Combined with the idea of both bottom-up and top-down, this paper suggests an improved one by using pixel filtering, histogram improvement and occlusion judgment, as well as Kalman filter. The comparative analysis results on the traditional Camshift algorithm and combined with Kalman traditional Camshift algorithm demonstrate that the proposed algorithm enhances the accuracy and stability in complex condition in an effective way and improves the real-time performance as well.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Qiang Wang
AU  - Xiao Li
AU  - Chaobing Liu
AU  - Mengyao Wu
PY  - 2015/08
DA  - 2015/08
TI  - A New Improved Camshift Algorithm and Its Experimental Analysis
BT  - Proceedings of the 2015 International Conference on Electronic Science and Automation Control
PB  - Atlantis Press
SP  - 275
EP  - 280
SN  - 2352-538X
UR  - https://doi.org/10.2991/esac-15.2015.67
DO  - 10.2991/esac-15.2015.67
ID  - Wang2015/08
ER  -