Proceedings of the 2015 International Conference on Electrical, Computer Engineering and Electronics

Object detection algorithm based on the video stream for complex environment

Authors
Zhaoxia Fu
Corresponding Author
Zhaoxia Fu
Available Online June 2015.
DOI
10.2991/icecee-15.2015.11How to use a DOI?
Keywords
Object Detection; Gaussian Mixture Models; Background Modeling; Frame-difference
Abstract

Due to the complexity of the environment and the diversity of the goal itself in the visual system, the technology of object detection has brought great difficulties. The practical experience shows that the technology of object detection is far from mature in the general sense and there are still certain gaps away from practical application. In this paper, for solving these problems of complex background and lighting mutation of the fixed monitoring scenes, a moving object detection algorithm based on the video stream is proposed and can be applied to the complex of indoor and outdoor environments. The convergence rate is improved by improved Gaussian mixture model. Taken into account the interference of light mutation and combined with the advantage of frame-difference method, the system detection capability for fast moving target is improved. Morphological method is used for noise processing of motion region, while remedying the generated hole during object detection. Experimental results show that the algorithm can complete detecting under the light mutation quickly and accurately and has a strong robustness.

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)

Volume Title
Proceedings of the 2015 International Conference on Electrical, Computer Engineering and Electronics
Series
Advances in Computer Science Research
Publication Date
June 2015
ISBN
10.2991/icecee-15.2015.11
ISSN
2352-538X
DOI
10.2991/icecee-15.2015.11How to use a DOI?
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/).

Cite this article

TY  - CONF
AU  - Zhaoxia Fu
PY  - 2015/06
DA  - 2015/06
TI  - Object detection algorithm based on the video stream for complex environment
BT  - Proceedings of the 2015 International Conference on Electrical, Computer Engineering and Electronics
PB  - Atlantis Press
SP  - 47
EP  - 50
SN  - 2352-538X
UR  - https://doi.org/10.2991/icecee-15.2015.11
DO  - 10.2991/icecee-15.2015.11
ID  - Fu2015/06
ER  -