Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)

The Improved Genetic Algorithm Used to Optimize Gabor Filters for Vehicle Detection

Authors
Dajiang Jin1, Lan Long, Jiye Zhang
1Traction Power State Key Laboratory, Southwest Jiaotong University
Corresponding Author
Dajiang Jin
Available Online October 2007.
DOI
10.2991/iske.2007.4How to use a DOI?
Keywords
Vehicle detection, Gabor filter, Genetic algorithm, Support vector machine.
Abstract

Our focus in this paper is on using the improved Genetic Algorithm (IGA) to optimize Gabor filters for vehicle detection. The Gabor filters parameters are encoded in a chromosome and optimized using genetic operators. Considering the deficiency of the traditional crossover operator at global searching, the partheno-crossover operator, a new crossover operator, is proposed and used to improve GA. The objective is to build the specifically set of filters which are capable of responding stronger to vehicles than to nonvehicles. Compared with using general GA, the Gabor filter optimized by using the IGA allows better correct rate of vehicle detection.

Copyright
© 2007, 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 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
Series
Advances in Intelligent Systems Research
Publication Date
October 2007
ISBN
10.2991/iske.2007.4
ISSN
1951-6851
DOI
10.2991/iske.2007.4How to use a DOI?
Copyright
© 2007, 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  - Dajiang Jin
AU  - Lan Long
AU  - Jiye Zhang
PY  - 2007/10
DA  - 2007/10
TI  - The Improved Genetic Algorithm Used to Optimize Gabor Filters for Vehicle Detection
BT  - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
PB  - Atlantis Press
SP  - 14
EP  - 18
SN  - 1951-6851
UR  - https://doi.org/10.2991/iske.2007.4
DO  - 10.2991/iske.2007.4
ID  - Jin2007/10
ER  -