Pareto optimal sensing strategies for an active vision system

被引:3
作者
Dunn, E [1 ]
Olague, G [1 ]
Lutton, E [1 ]
Schoenauer, M [1 ]
机构
[1] CICESE Res Ctr, EvoVis Lab, Ensenada 22860, Baja California, Mexico
来源
CEC2004: PROCEEDINGS OF THE 2004 CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1 AND 2 | 2004年
关键词
D O I
10.1109/CEC.2004.1330892
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present a multi-objective methodology, based on evolutionary computation, for solving the sensor planning problem for an active vision system. The application of different representation schemes, that allow to consider either fixed or variable size camera networks in a single evolutionary process, is studied. Furthermore, a novel representation of the recombination and mutation operators is brought forth. The developed methodology is incorporated into a 3D simulation environment and experimental results shown. Results validate the flexibility and effectiveness of our approach and offer new research alternatives in the field of sensor planning.
引用
收藏
页码:457 / 463
页数:7
相关论文
共 19 条
[1]  
[Anonymous], 2000, LECT NOTES COMPUTER
[2]  
BAJCSY R, 1986, P IEEE WORKSH COMP V
[3]   Automatic sensor placement for model-based robot vision [J].
Chen, SY ;
Li, YF .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2004, 34 (01) :393-408
[4]  
DASGUPTA D, 1993, IKBS1193 U STRATHCL
[5]  
Deb K., 2001, Multi-Objective Optimization using Evolutionary Algorithms
[6]   Evolutionary computation for sensor planning: The task distribution plan [J].
Dunn, E ;
Olague, G .
EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING, 2003, 2003 (08) :748-756
[7]  
DUNN E, 2004, IN PRESS 6 EUR WORKS
[8]  
FRASER CS, 1996, CLOSE RANGE PHOTOGRA
[9]  
Knowles J, 2002, P C EV COMP
[10]  
Olague G, 2003, LECT NOTES COMPUT SC, V2611, P410