DOI QR코드

DOI QR Code

방해물 분석 및 배경 영상 갱신을 이용한 바둑 기보 기록

Recognition of Go Game Positions using Obstacle Analysis and Background Update

  • 김민성 (광운대학교 컴퓨터과학과) ;
  • 윤여경 (광운대학교 컴퓨터과학과) ;
  • 이광진 (광운대학교 컴퓨터과학과) ;
  • 이윤구 (광운대학교 컴퓨터과학과)
  • Kim, Min-Seong (Department of Computer Science, Kwangwoon University) ;
  • Yoon, Yeo-Kyung (Department of Computer Science, Kwangwoon University) ;
  • Rhee, Kwang-Jin (Department of Computer Science, Kwangwoon University) ;
  • Lee, Yun-Gu (Department of Computer Science, Kwangwoon University)
  • 투고 : 2017.09.04
  • 심사 : 2017.11.16
  • 발행 : 2017.11.30

초록

바둑 기보를 자동으로 기록하는 기존의 방법들은 대국 중 발생하는 방해물(손 혹은 물체)의 바둑판 가림 현상을 제대로 고려하지 않았다. 방해물에 의해 바둑판이 가려지는 경우 바둑돌의 착수 위치를 인식하지 못하거나, 바둑돌의 착수 순서가 실제와 다르게 저장되는 문제가 발생할 수 있다. 제안된 알고리즘은 방해물이 없는 온전한 바둑판 영상만을 배경 영상으로 내부에 저장하고 배경 영상과 현재 입력 영상을 비교하여 방해물을 인식한다. 그림자가 방해물로 오인식되는 현상을 제거하기 위해 단순한 차 영상이 아닌 미분영상을 기반으로 한 방해물 검출 방법이 제안되었다. 추가로 노이즈에 강인하게 방해물을 인식하기 위한 노이즈 제거 방법도 제안되었다. 방해물이 없는 때는 배경 영상을 지속적으로 갱신한다. 최종적으로 각 순간마다 저장된 배경 영상들을 비교하여 바둑돌의 착수 위치와 바둑돌의 종류를 인식한다. 실험 결과에 따르면 일반적인 조명환경에서 제안된 알고리즘은 95%이상의 인식률을 보여준다.

Conventional methods of automatically recording Go game positions do not properly consider obstacles (hand or object) on a Go board during the Go game. If the Go board is blocked by obstacles, the position of a Go stone may not be correctly recognized, or the sequences of moves may be stored differently from the actual one. In the proposed algorithm, only the complete Go board image without obstacles is stored as a background image and the obstacle is recognized by comparing the background image with the current input image. To eliminate the phenomenon that the shadow is mistaken as obstacles, this paper proposes the new obstacle detection method based on the gradient image instead of the simple differential image. When there is no obstacle on the Go board, the background image is updated. Finally, the successive background images are compared to recognize the position and type of the Go stone. Experimental results show that the proposed algorithm has more than 95% recognition rate in general illumination environment.

키워드

참고문헌

  1. Corsolini, Mario, and Andrea Carta. "A New Approach to an Old Problem: The Reconstruction of a Go Game through a Series of Photographs." arXiv preprint arXiv:1508.03269, 2015.
  2. D. Park and K, Jun, "CHT-based Automatic Go Recording System under Illumination Change and Stone Dislocation", Journal of KIISE : Software and Application, Vol.41, No.6, pp.448-455, June 2014.
  3. BALLARD, Dana H. "Generalizing the Hough transform to detect arbitrary shapes". Pattern Recognition, Vol.13, No.2, pp.183-194, 1991.
  4. D. Lee and Y. Lee, "Algorithm of recognizing Go stones for the automatic records of Go games", IEIE Summer Conference, Jeju, Korea, pp.809-812, 2016.
  5. DUDA, Richard O. and HART, Peter E, "Use of the Hough transformation to detect lines and curves in pictures", Communications of the ACM, Vol.15, No.1, pp.11-15. 1972. https://doi.org/10.1145/361237.361242
  6. K. Lee, and Y. Lee, "Prediction of Camera Intrinsic Parameter using Go Board Image", The Korean Institute of Broadcast and Media Engineers Summer Conference, Jeju, Korea, pp.237-240, 2017.6.
  7. K. Lee, and Y. Lee, "Prediction of Camera Intrinsic Parameter using Go Board Image", The Korean Institute of Broadcast and Media Engineers Summer Conference, Jeju, Korea, pp.237-240, 2017.6.
  8. D. Comaniciu, V. Ramesh and P. Meer, "Kernel-based object tracking," IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol.25, No.5, pp.564-577, 2003. https://doi.org/10.1109/TPAMI.2003.1195991
  9. C. Stauffer and W. E. L. Grimson, "Adaptive background mixture models for real-time tracking," Proceeding of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Fort Collins, Colorado, USA, pp. 246-252, 1999.
  10. Euncheol Choi, Suk-Ho Lee, Moon Gi Kang. "Object Tracking Algorithm Using Weighted Color Centroids Shifting". JOURNAL OF BROADCAST ENGINEERING, Vol.15, No.2, pp.236-247, 2010 https://doi.org/10.5909/JBE.2010.15.2.236
  11. Kim Cheol-Mun, Kwak Gae-Ho, Kim Whoi-Yul. "Moving Cast Shadow Detection based on Global Gaussian Modeling". The Korean Institute of Broadcast and Media Engineers Conference Proceedings, Seoul, Korea, pp.259-262. 2009.
  12. K A Divya, K I Roshna, Shelmy Mathai, "Shadow detection and removal by object-wise segmentation." Computational Intelligence and Computing Research, International Conference on IEEE, Madurai, India, pp. 1-4, 2015