The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

A Simple Stereo Matching Algorithm using PBIL and its Alternative

PBIL을 이용한 소형 스테레오 정합 및 대안 알고리즘

  • 한규필 (금오공과대학교 컴퓨터공학부)
  • Published : 2005.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

A simple stereo matching algorithm using population-based incremental learning(PBIL) is proposed in this paper to decrease the general problem of genetic algorithms, such as memory consumption and inefficiency of search. PBIL is a variation of genetic algorithms using stochastic search and competitive teaming based on a probability vector. The structure of PBIL is simpler than that of other genetic algorithm families, such as serial and parallel ones, due to the use of a probability vector. The PBIL strategy is simplified and adapted for stereo matching circumstances. Thus, gene pool, chromosome crossover, and gene mutation we removed, while the evolution rule, that fitter chromosomes should have higher survival probabilities, is preserved. As a result, memory space is decreased, matching rules are simplified and computation cost is reduced. In addition, a scheme controlling the distance of neighbors for disparity smoothness is inserted to obtain a wide-area consistency of disparities, like a result of coarse-to-fine matchers. Because of this scheme, the proposed algorithm can produce a stable disparity map with a small fixed-size window. Finally, an alterative version of the proposed algorithm without using probability vector is also presented for simpler set-ups.

본 논문에서는 유전자 알고리즘의 일반적인 문제점인 과도한 저장공간의 소모와 탐색의 비효율성을 줄이기 위해 PBIL을 이용한 단순한 스테레오 정합 기법을 제안한다. PBIL은 확률벡터에 기반해서 통계적 탐색과 경쟁학습을 이용하는 변종 유전자 알고리즘이며 확률벡터의 사용으로 인해 직렬 및 병렬 유전자 알고리즘군에 비해 단순한 구조를 가진다. 본 논문에서는 이 PBIL을 스테레오 정합 환경에 맞게 변형 및 단순화시켜 정합 알고리즘을 개발한다. 높은 적응성을 갖는 염색체는 생존 확률 또한 높다는 진화 법칙을 보존하면서 유전자 풀, 염색체 교차 및 유전자 돌연변이를 제거할 수 있으며 그 결과 저장공간을 줄이고 정합 규칙을 간소화하여 계산 비용을 감소시킬 수 있다. 추가적으로 다해상도 정합 기법처럼 넓은 영역의 변이 일관성을 획득하기 위해 변이 연속성에 대한 이웃들의 거리를 제어하는 방식을 추가하여 고정된 작은 정합창을 사용하면서 안정된 결과를 얻을 수 있게 한다. 마지막으로 단순한 시스템에 적용될 수 있게 하기 위해서 확률벡터를 사용하지 않는 제안한 알고리즘의 소형 대안 기법을 제시한다.

Keywords

References

  1. M. Pollefeys, L. Van Goal, M. Vergauwen, F. Verbiest, K. Camelis, J. Tops, R. Koch, 'Visual Modeling with a Hand-held Camera,' International Journal of Computer Vision, vol.59, No.3, pp.207-232, 2004 https://doi.org/10.1023/B:VISI.0000025798.50602.3a
  2. M. Billinghurst and H. Kato, 'Collaborative Augmented Reality,' Communications of the ACM, vol.45, No.7, pp.64-70, 2002 https://doi.org/10.1145/514236.514265
  3. S. Panis, M. Ziegler, and J. P. Cosmas, 'The Use of Stereo and Motion in a Generic Object-based Coder,' Signal Processing: Image Communication, vol.9, pp.221-238, 1997 https://doi.org/10.1016/S0923-5965(96)00020-3
  4. J. R. Ohm, K. Griineberg, E. Hendriks, M. E. Izquierdo, D. Kalivas, M. Karl, D. Papadimatos, and A. Redert, 'A Realtime Hardware System for Stereoscopic Videoconferencing with Viewpoint Adaptation,' Signal Processing: Image Communication, vol.14, pp.147-171, 1998 https://doi.org/10.1016/S0923-5965(98)00034-4
  5. Robert M. Haralick and Linda G. Shapiro, Computer and Robot Vision, Volume 2, New York : Addison-Wesley Publishing Co., 1993, pp.289-378
  6. A. C. Kak, Handbook of Industrial Robotics, New York : John Wiley, 1985, pp.272-319
  7. Kyu-Phil Han, Tae-Min Bae, and Yeong-Ho Ha, 'Hybrid Stereo Matching with a New Relaxation Scheme of Preserving Disparity Discontinuity,' Pattern Recognition, Vol.33, No.5, pp.767-785, 2000 https://doi.org/10.1016/S0031-3203(99)00095-3
  8. W. Eric L. Grimson, 'Computational Experiments with a Feature Based Stereo Algorithm,' IEEE Trans. Patt. Anal. Machine Intell., Vol.7, No.1, pp.17-34, 1985 https://doi.org/10.1109/TPAMI.1985.4767615
  9. D. De Vleeschauwer, 'An Intensity-based, Coarse-to-fine Approach to Reliably Measure Binocular Disparity,' CVGIP: Image Understanding, Vol.57, No.2, pp.204-218, 1993 https://doi.org/10.1006/ciun.1993.1013
  10. Gerard Medioni and Ramakant Nevatia, 'Segment-based Stereo Matching,' Computer Vision, Graphics, and Image Processing, Vol.31, pp.2-18, 1985 https://doi.org/10.1016/S0734-189X(85)80073-6
  11. John R. Jordan and Alan C. Bovik, 'Using Chromatic Information in Edge-based Stereo Correspondence,' CVGIP: Image Understanding, Vol.54, No.1, pp.98-118, 1991 https://doi.org/10.1016/1049-9660(91)90077-3
  12. John (Juyang) Weng, 'Image Matching Using the Windowed Fourier Phase,' International Journal of Computer Vision, Vol.11, No.3, pp.211-236, 1993 https://doi.org/10.1007/BF01469343
  13. Yong-Suk Kim, Jun-Jae Lee, and Yeong-Ho Ha, 'Stereo Matching Algorithm Based on Modified Wavelet Decomposition Process,' Pattern Recognition, Vol.30, pp.929-952, 1997 https://doi.org/10.1016/S0031-3203(96)00125-2
  14. Kyu-Phil Han, Kun-Woen Song, Eui-Yoon Chung, Seok-Je Cho, and Yeong-Ho Ha, 'Stereo Matching Using Genetic Algorithm with Adaptive Chromosomes,' Pattern Recognition, Vol.34, No.9, pp.1729-1740, 2001 https://doi.org/10.1016/S0031-3203(00)00114-X
  15. Shumeet Baluja, 'Population-based Incremental Learning: A Method for Integrating Genetic Search Based Function Optimization and Competitive Learning,' Technical reports CMU-CS-94-163, Carnegie Mellon Univ., Jun., 1994
  16. P. H. Winston, Artificial Intelligence-3rd edition, New York: Addison-Wesley Publishing Co., 1993, pp.505-528
  17. David B. Fogel, 'Evolutionary Computation: Comments on the History and Current State,' IEEE Transactions on Evolutionary Computation, Vol.1, No.1, pp.3-17, 1997 https://doi.org/10.1109/4235.585888
  18. D. V. Papadimitriou and T. J. Dennis, 'Epipolar Line Estimation and Rectification for Stereo Image Pairs,' IEEE Transactions on Image Processing, Vol.5, No.4, pp.672-676, 1996 https://doi.org/10.1109/83.491345
  19. D. Marr and T. Poggio, A Computational Theory of Human Stereo Vision, Proc. Royal Soc. London, Vol.B204, pp.301-328, 1979 https://doi.org/10.1098/rspb.1979.0029