조명 변화에 강인한 로봇 축구 시스템의 색상 분류기

Robust Color Classifier for Robot Soccer System under Illumination Variations

  • 이성훈 (메가로보틱스) ;
  • 박진현 (진주산업대 메카트로닉스공학과) ;
  • 전향식 (한국항공우주연구원) ;
  • 최영규 (부산대 전자전기정보컴퓨터공학부)
  • 발행 : 2004.01.01

초록

The color-based vision systems have been used to recognize our team robots, the opponent team robots and a ball in the robot soccer system. The color-based vision systems have the difficulty in that they are very sensitive to color variations brought by brightness changes. In this paper, a neural network trained with data obtained from various illumination conditions is used to classify colors in the modified YUV color space for the robot soccer vision system. For this, a new method to measure brightness is proposed by use of a color card. After the neural network is constructed, a look-up-table is generated to replace the neural network in order to reduce the computation time. Experimental results show that the proposed color classification method is robust under illumination variations.

키워드

참고문헌

  1. 김종환, 로봇 축구 시스템, 대영사, 2000.1
  2. James Brusey and Lin Padgham, 'Techniques for obtaining robust, real-time, colour-based vision for robotics,' RMIT-Computer Science Postgraduate Students Conference, 1999
  3. Chu-Sik In and Yong-Hee Choi, 'Implementation of the multi-target tracker for MIROSOT,' Proceedings of the l Ith KACC, pp. 828-831, 1997
  4. 김도윤, 박현근, 박현우, 정명진, 'Fast & robust color detection using look-up table,' 제 1차 로봇 축구 워크샵, pp. 155-172, 1998.
  5. 주병규, 조필형, 정슬, 'Development of soccer robot system for multi-agent system research,' 제 13차 한국 자동제어 학술회의, pp. 244-247, 1998
  6. Chin-Teng Lin and C.S. George Lee, Neural Fuzzy Systems, Prentice-Hall, 1996
  7. Alexandre Da Silva Simoes and Anna Helena Reali Costa, 'Using neural color classification in robotic soccer domain,' International Joint Conference IBERAMIA'2000 and SBIN2000, Workshop Proceedings, pp. 208-213, 200
  8. 이수호, 김경훈, 고국원, 김주곤, 조형석, 'The development of a microrobot system for robot soccer game,' 제 11차 한국 자동제어 학술회의, pp. 507-510, 1996
  9. James Bruce, Tucker Balch and Manuela Veloso, 'Fast and cheap color image segmentation for interactive robots,' Workshop of WIRE '2000, 2000
  10. Karl E. Nelson, Jeffrey W. Collins, Michael A. Soderstrand and Tien C. Hsia, 'Vision systems and software design for soccer playing mobile robots,' AutoSoft Journal Volume 6, pp. 19-32, 1997
  11. Newton Research Labs., Cognachrome Vision User's Guide, 1998