3D Model Extraction Method Using Compact Genetic Algorithm from Real Scene Stereoscopic Image

소형 유전자 알고리즘을 이용한 스테레오 영상으로부터의 3차원 모델 추출기법

  • 한규필 (금오공과대학교 컴퓨터공학부) ;
  • 엄태억 (구미기능대학 전자과)
  • Published : 2001.09.01

Abstract

Currently, 2D real-time image coding techniques had great developments and many related products were commercially developed. However, these techniques lack the capability of handling 3D actuality, occurred by the advent of virtual reality, because they handle only the temporal transmission for 2D image. Besides, many 3D virtual reality researches have been studied in computer graphics. Since the graphical researches were limited to the application of artificial models, the 3D actuality for real scene images could not be managed also. Therefore, a new 3D model extraction method based on stereo vision, that can deal with real scene virtual reality, is proposed in this paper. The proposed method adapted a compact genetic algorithm using population-based incremental learning (PBIL) to matching environments, in order to reduce memory consumption and computational time of conventional genetic algorithms. Since the PBIL used a probability vector and competitive learning, the matching algorithm became simple and the computation load was considerably reduced. Moreover, the matching quality was superior than conventional methods. Even if the characteristics of images are changed, stable outputs were obtained without the modification of the matching algorithm.

최근 2차원 실시간 영상통신기술들이 급속한 발전을 거듭하여 여러 제품에 상용화되고 있는 추세이다. 그러나 이 기술들은 2차원 영상의 시각적 전송이므로 가상현실의 도래로 인해 수반된 3차원 현실감을 다루기에는 불충분하다고 할 수 있다. 이밖에 컴퓨터 그래픽 분야의 3차원 가상현실 연구가 합성 영상에 국한되어 연구되어졌기 때문에 실 영상에 대한 가상현실의 구현이 어려운 실정이다 그러므로 본 논문에서는 스테레오 시각을 이용하여 실 영상 가상현실 구현에 적용될 수 있는 유전자 알고리즘 기반의 새로운 3차원 객체 추출기법을 제시한다. 제안한 방법은 저장공간의 낭비와 알고리즘의 복잡성을 줄이기 위해서 확률벡터와 반복학습에 기반한 개체군기반 증가 학습이라는 소형 유전자 알고리즘을 정합 환경에 맞게 변형시켰다. 그 결과 정합 성능이 기존의 스테레오 정합 기법보다 우수하며, 간단하고 빠른 정합 알고리즘을 제시할 수 있었다. 또한, 영상의 특성에 무관하게 알고리즘의 변경 없이 안정된 결과를 얻을 수 있다는 장점이 있었다.

Keywords

References

  1. K. Sugihara, 'Three principle in stereo vision,' Robotics, vol. 1, no. 4, pp. 391-400, 1986
  2. R. M. Haralick and L. G. Shapiro, Computer And Robot Vision, Addison-Wesley Publishing Co., 1993
  3. W. Eric L. Grimson, 'Computational Experiments with a Feature Based Stereo Algorithm,' IEEE Trans. Patt. Anal. Machine Intell. vol. 7, no. 1, 17-34, 1985
  4. D. De Vleeschauwer, 'An Intensity-based, Coarse-to-fine Approach to Reliably Measure Binocular Disparity,' CVGIP: Image Understanding vol. 57, no. 2, 204-218, 1993 https://doi.org/10.1006/ciun.1993.1013
  5. Kyu-Phil Han, Tae-Min Bae, Yeong-Ho Ha, 'ybrid Stereo Matching with a New Relaxation Scheme of Preserving Disparity Discontinuity,' Pattern Recognition, vol. 33, no. 5, pp. 767-785, May 2000
  6. John (Juyang) Weng, 'Image Matching Using the Windowed Fourier Phase,' Intern. J. Comp. Vision vol. 11, no. 3, 211-236, 1993 https://doi.org/10.1007/BF01469343
  7. Yong-Suk Kim, Jun-Jae Lee, and Yeong-Ho Ha, 'Stereo Matching Algorithm Based on Modified Wavelet Decomposition Process,' Pattern Recognition vol. 30, 929-952, 1997 https://doi.org/10.1016/S0031-3203(96)00125-2
  8. Kyu-Phil Han, Yong-Suk Kim, and Yeong-Ho Ha, 'Stereo Matching Using Genetic Algorithm and Region Information,' FCV'98-4th Japan-Korea Joint Workshop on Computer Vision, pp. 85-89, 1998
  9. S. Baluja, 'Population based incremental learning,' Tech. reports, Carnegie Mellon Univ., 1994
  10. T. Back, U. Hammel, and H.-P. Schwefel, 'Evolutionary Computation: Comments on the History and Current State,' IEEE Trans. on Evolutionary Computation, vol. 1, no. 1, pp. 3-17, 1997 https://doi.org/10.1109/4235.585888
  11. P. H. Winston, Artificial Intelligence-3rd edition, Addison-Wesley Publishing Co., New York, pp. 505-528, 1993
  12. S. Baluja, 'Population-based Incremental Learning,' Tech. report, Carnegie Mellon Univ., 1994
  13. Kyu-Phil Han, Yong-Suk Kim, Young-Sik Park, and Yeong-Ho Ha, 'Relaxation Algorithm to Solve Correspondence Problems,' Proceedings of the 3rd Korea - Japan Joint Workshop on Computer Vision [Frontiers of Computer Vision], pp. 104-109, 1997