Moving target detection algorithm: Improved-Vibe

DOI

10.2991/ameii-15.2015.171How to use a DOI?

Keywords

Background Modeling; Motion Detection; Ghost Processing; Shadow Suppression

Abstract

Vibealgorithm initializes the background model very quickly by using the first frame.However, when the target has been in the first frame, the ghostwill be produced with the initialization.And the original Vibe algorithm has no special inhibition about it.In addition, the shadow of the moving target will be detected as a goal, which will influence the accuracy of detection.In order to solve these problems, this paper presents an improved algorithm to inhibit the ghost and shadows.If a pixelis judged as a foreground pixel for many times, it will be compared with the pixel which is the closest one of it, and judged whether they are belong to the same area. Besides, this paper uses a fusion method based on LBP operator and gray space to delete the shadow. Experimental results show that the Improved-Vibe algorithm can absorb the ghost quickly and reduce the influence of shadow compared with the original Vibe algorithm.

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  - Yuntao Dou
AU  - Zhenghua Liu
AU  - Le Chang
AU  - Jianping Huang
PY  - 2015/04
DA  - 2015/04
TI  - Moving target detection algorithm: Improved-Vibe
BT  - Proceedings of the International Conference on Advances in Mechanical Engineering and Industrial Informatics
PB  - Atlantis Press
SP  - 920
EP  - 925
SN  - 2352-5401
UR  - https://doi.org/10.2991/ameii-15.2015.171
DO  - 10.2991/ameii-15.2015.171
ID  - Dou2015/04
ER  -