Evaluation of Color Constancy Vision Algorithm for Mobile Robots

被引：0

作者：

Takemura, Yasunori ^{[1
]}

Ishii, Kazuo ^{[1
]}

机构：

[1] Kyushu Inst Technol, Grad Sch Life Sci & Syst Engn, Fukuoka, Japan

来源：

NEURAL INFORMATION PROCESSING, PT 2, PROCEEDINGS | 2009年 / 5864卷

关键词：

color constancy; robot vision; Self-Organizing Map; Neural Gas; SELF-ORGANIZING MAPS; CONVERGENCE PROPERTIES;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

One of important subjects for mobile robots is the vision based decision making system, where the color constancy is big problem for robots which use color property to recognize environments. We have been working on color constancy vision algorithms using bio-inspired information processing as creatures can recognize color and shape of objects even if there exits a large change of light conditions in outdoor environments. In this paper, we evaluate the performances of color recognition using bio-inspired processing algorithms such as Self-Organizing Map (SOM), modular network SOM (mnSOM) and Neural Gas (NO). The experimental results in various light conditions are discussed.

引用

页码：409 / 419

页数：11

共 17 条

[1] AZEURA K, 2006, P RSJ 2006 OK
[2] BARRETO GA, 100687 IEICE, P149
[3] ERWIN E, BIOL CHERNETICS, V67, P47
[4] Furukawa T, 2005, LECT NOTES COMPUT SC, V3696, P391, DOI 10.1007/11550822_61
[5] HEIDEMANN SG, 2002, LNCS, V2415, P902
[6] ISHII K, 2004, P ICRA, P4466
[7] SELF-ORGANIZED FORMATION OF TOPOLOGICALLY CORRECT FEATURE MAPS
KOHONEN, T
[J]. BIOLOGICAL CYBERNETICS, 1982, 43 (01) : 59 - 69
[8] KOHONEN T, P I EL EL ENG, V78, P1460
[9] Lo Z., 1991, International Parallel Processing Symposium, 6th, Los Alamitos, p, P247
[10] ANALYSIS OF THE CONVERGENCE PROPERTIES OF TOPOLOGY PRESERVING NEURAL NETWORKS
LO, ZP
YU, YQ
BAVARIAN, B
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1993, 4 (02): : 207 - 220

← 1 2 →