Object Tracking Based on Multi-feature Mean-shift Algorithm

DOI

10.2991/citcs.2012.149How to use a DOI?

Keywords

object trackingn; Mean-shift; color-texture histogram;Kalman

Abstract

Object tracking is one of the key technologies in intelligent video surveillance and how to describe the moving target is a key issue. Traditional color histogram Mean-shift (MS) algorithm only considered object's color statistical information, and didn't contain object's space information, so when the object color was close to the background color, the traditional MS algorithm easily caused object tracking inaccurately or lost. To solve this problem, a novel object tracking algorithm which based on improved MS and Kalman was proposed in this paper. Firstly, using the joint color-texture histogram to represent a target and applying it to the MS framework, then the improved MS goes for a small range of search and target match according to the result of Kalman prediction. The experimental results show that our algorithm tracking the object accurately and effectively even though the object color was close to the background color or the target moves fast.

Copyright

© 2012, 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  - Jiafu Jiang
AU  - Hui Xiong
PY  - 2012/11
DA  - 2012/11
TI  - Object Tracking Based on Multi-feature Mean-shift Algorithm
BT  - Proceedings of the 2012 National Conference on Information Technology and Computer Science
PB  - Atlantis Press
SP  - 579
EP  - 582
SN  - 1951-6851
UR  - https://doi.org/10.2991/citcs.2012.149
DO  - 10.2991/citcs.2012.149
ID  - Jiang2012/11
ER  -