대한전자공학회논문지SP (Journal of the Institute of Electronics Engineers of Korea SP)

대한전자공학회 (The Institute of Electronics and Information Engineers)
권호 표지

Plane-converging Belief Propagation을 이용한 고속 스테레오매칭

Fast Stereo matching based on Plane-converging Belief Propagation using GPU

  • 투고 : 2010.08.10
  • 심사 : 2010.10.19
  • 발행 : 2011.03.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

스테레오 매칭은 두 영상의 차이를 이용하여 거리를 추정하는 연구 분야로 성능 개선과 함께 처리속도 향상을 위한 연구가 계속되고 있다. 본 논문에서는 계층적 Belief Propagation(BP) 알고리즘을 개선하여 기존의 BP에서의 수렴구간을 메시지 맵으로 만들고 이를 이용하여 처리속도를 향상시키는 Plane-converging BP 알고리즘을 제안한다. 또한 GPU 아키텍쳐인 Nvidia의 CUDA를 이용하여 다수의 계산을 병렬화 하고 이를 동시에 처리하여 실시간 어플리케이션에 적합한 스테레오 매칭 기법을 개발하였다. Plane-converging BP 알고리즘은 기존의 계층적 BP 알고리즘과 유사한 에러율을 가지면서 약 2.7배의 속도 향상을 이루었다.

Stereo matching is the research area that regarding the estimation of the distance between objects and camera using different view points and it still needs lot of improvements in aspects of speed and accuracy. This paper presents a fast stereo matching algorithm based on plane-converging belief propagation that uses message passing convergence in hierarchical belief propagation. Also, stereo matching technique is developed using GPU and it is available for real-time applications. The error rate of proposed Plane-converging Belief Propagation algorithm is similar to the conventional Hierarchical Belief Propagation algorithm, while speed-up factor reaches 2.7 times.

키워드

참고문헌

  1. K. Konolige, M. Agrawal, R. C. Bolles, "Outdoor Mapping and Navigation using Stereo Vision," Springer, vol.39, pp. 179-190, 2008.
  2. K. Sabe, M. Fukuchi, J. S. Gutmann, T. Ohashi, K. Kawamoto, T. Yoshiqahara, "Obstacle avoidance and path planning for humanoid robots using stereo vision," Robotics and Automation, vol. 1, pp. 592-597, 2004.
  3. S. Bahadori, L. Iocchi, G. R. Leone, "Real time people localization and tracking through fixed stereo vision," Applied Intelligence, vol. 26, pp. 83-97, 2007. https://doi.org/10.1007/s10489-006-0013-3
  4. J. Collado, C. Hilario, M. Armingol, "Self -calibration of an on-board stereo-vision system for driver assistance systems," IEEE Intel.Veh.Symp., pp.156-162, 2006.
  5. J. P. Lewis, "Fast normalized cross-correlation," Vision Interface, pp.120-123, 1995.
  6. J. Banks, M. Bennamoun, "Reliability analysis of the rank transform for stereo matching," Systems, Man and Cybernetics, vol.31, pp. 870-880, 2001. https://doi.org/10.1109/3477.969491
  7. O. Veksler, "Stereo correspondence by dynamic programming on a tree," IEEE CVPR, vol.2, pp. 384-390, 2005.
  8. V. Kolmogorov and R. Zabih, "Computing Visual Correspondence with Occlusions using Graph Cuts," ICCV, vol.1, pp. 508-515, 2001.
  9. J. Sun, N. N. Zheng, H. Y. Shum, "Stereo Matching using Belief Propagation," PAMI, vol.25, no.7, 2003.
  10. P. F. Felzenszwalb and D. P. Huttenlocher, "Efficient Belief Propagation for Early Vision," CVPR, vol.1, pp. 261-268, 2004.
  11. A. Brunton, C. Shu, G. Roth, "Belief Propagation on the GPU for stereo vision," Computer and Robot Vision, p76, 2006.
  12. Q. Yang, L. Wang, R. Yang, S. Wang, M. Liao, and D. Nister, "Real-time global stereo matching using hierarchical belief propagationm," British Machine Vision Conf, pp. 989-998, 2006.
  13. NVIDIA CUDA, programming Guide, v2.3, 2009, http://www.nvidia.com/object/cuda_home.html
  14. Middlebury Stereo Vision Research Page, http://vision.middlebury.edu/stereo
  15. D. Scharstein and R. Szeliski, "A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms," IJCV, vol. 47, pp. 7-42, 2002. https://doi.org/10.1023/A:1014573219977