Dynamic flies: a new pattern recognition tool applied to stereo sequence processing

被引：20
|
作者：
Louchet, J
Guyon, M
Lesot, MJ
Boumaza, A
机构：
[1] Ecole Natl Super Tech Avancees, Lab Elect & Informat, F-75739 Paris 15, France
[2] INRIA Rocquencourt, F-78153 Le Chesnay, France
来源：
PATTERN RECOGNITION LETTERS | 2002年 / 23卷 / 1-3期
关键词：
artificial evolution; pattern recognition; computer vision; image processing; parameter space exploration;
D O I：
10.1016/S0167-8655(01)00129-5
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The "fly algorithm" is a fast artificial evolution-based technique devised for the exploration of parameter space in pattern recognition applications. In the application described, we evolve a population which constitutes a particle-based three-dimensional representation of the scene. Each individual represents a three-dimensional point in the scene and may be fitted with optional velocity parameters. Evolution is controlled by a fitness function which contains all pixel-level calculations, and uses classical evolutionary operators (sharing, mutation, crossover). The combined individual approach and low complexity fitness function allow fast processing. Test results and an application to mobile robotics are presented. (C) 2002 Elsevier Science B.V. All rights reserved.
引用
收藏
页码：335 / 345
页数：11
相关论文
共 45 条
12345