Unsupervised Segmentation of Objects using Genetic Algorithms

유전자 알고리즘 기반의 비지도 객체 분할 방법

  • 김은이 (건국대학교 인터넷미디어공학부) ;
  • 박세현 (대구대학교 정보통신공학부)
  • Published : 2004.07.01

Abstract

The current paper proposes a genetic algorithm (GA)-based segmentation method that can automatically extract and track moving objects. The proposed method mainly consists of spatial and temporal segmentation; the spatial segmentation divides each frame into regions with accurate boundaries, and the temporal segmentation divides each frame into background and foreground areas. The spatial segmentation is performed using chromosomes that evolve distributed genetic algorithms (DGAs). However, unlike standard DGAs, the chromosomes are initiated from the segmentation result of the previous frame, then only unstable chromosomes corresponding to actual moving object parts are evolved by mating operators. For the temporal segmentation, adaptive thresholding is performed based on the intensity difference between two consecutive frames. The spatial and temporal segmentation results are then combined for object extraction, and tracking is performed using the natural correspondence established by the proposed spatial segmentation method. The main advantages of the proposed method are twofold: First, proposed video segmentation method does not require any a priori information second, the proposed GA-based segmentation method enhances the search efficiency and incorporates a tracking algorithm within its own architecture. These advantages were confirmed by experiments where the proposed method was success fully applied to well-known and natural video sequences.

본 논문은 동영상내의 객체를 자동으로 추출하고 추적할 수 있는 유전자 알고리즘 기반의 분할 방법을 제안한다. 제안된 방법은 시간 분할과 공간 분할로 이루어진다. 공간 분할은 각 프레임을 정확한 경계를 가진 영역으로 나누고 시간 분할은 각 프레임을 전경 영역과 배경 영역으로 나눈다. 공간 분할은 분산 유전자 알고리즘을 이용하여 수행된다. 그러나, 일반적인 유전자 알고리즘과는 달리, 염색체는 이전 프레임의 분할 결과로부터 초기화되고, 동적인 객체 부분에 대응하는 불안정 염색체만이 진화연산자에 의해 진화된다. 시간 분할은 두 개의 연속적인 프레임의 밝기 차이에 기반을 둔 적응적 임계치 방법에 의해 수행한다. 얻어진 공간과 시간 분할 결과의 결합을 통해서 객체를 추출하고, 이 객체들은 natural correspondence에 의해 전체 동영상을 통해 정확히 추적된다. 제안된 방법은 다음의 두 가지 장점을 가진다. 1) 제안된 비디오 분할 방법은 사전 정보를 필요로 하지 않는 자동 동영상 분할 방법이다. 2) 제안된 공간 분할방법은 기존의 유전자 알고리즘보다 해공간의 효율적인 탐색을 제공할 수 있을 뿐만 아니라, 정확한 객체 추적 메커니즘을 포함하고 있는 새로운 진화 알고리즘이다. 이러한 장점들은 제안된 방법이 잘 알려진 동영상과 실제 동영상에 성공적으로 적용됨을 통해 검증된다.

Keywords

References

  1. N. R. Pal and S. K. Pal, A review on image segmentation techniques, Pattern Recognition, vol. 26, no. 9, pp. 1277-1294, 1993 https://doi.org/10.1016/0031-3203(93)90135-J
  2. P. Salembier and F. Marques, Region-based representation of image and video: segmentation tools for multimedia services, IEEE Trans. Circuits Syst. Video Technol., vol. 9, no. 8, pp. 1147-1169, Dec. 1999 https://doi.org/10.1109/76.809153
  3. M. Kim, J. G. Choi, K. Kim, H. Lee, m. H. lee, C. Ahn, and Y. Ho, A VOP generation tool: automatic segmentation of moving objects in image sequences based on spatio-temporal information, IEEE Trans. Circuits Syst, Video Technol., vol. 9, no. 8, pp. 1216-1226, Dec. 1999 https://doi.org/10.1109/76.809157
  4. P. Salembier et al., Segmentation-based video coding system allowing the manipulation of objects, IEEE Trans. Circuits Syst, Video Technol., vol. 7, no. 1, pp. 60-74, Feb. 1997 https://doi.org/10.1109/76.554418
  5. C. Toklu, A. M. Telalp, and A. T. Erdem, Semi -automatic video object segmentation in the presence of occlusion, IEEE Trans. Circuits Syst. Video Technol., vol.10, no. 4, pp. 624-629, June 2000 https://doi.org/10.1109/76.845008
  6. Al Bovik, Handbook of Image & Video Processing, Academic Press, Canada, 2000
  7. H. S. Kim, E. Y. Kim, and H. J. Kim, Motion estimation and segmentation using genetic algorithm, in Proc. ISCA Int. Conf. Computer Applications in Industry and Engineering, 2000, pp. 106-109
  8. H. T. Nguyen, M. Worring, and A. Dev, Detecting of moving objects in video using a robust motion similarity measure, IEEE Trans. Image Processing, vol. 9, no. 1, pp. 137-141, Jan. 2000 https://doi.org/10.1109/83.817605
  9. E. Y. Kim, S. W. Hwang, S. H. Park, and H. J. Kim, Spatiotemporal segmentation using genetic algorithms, Pattern Recognition, Vol.23, No.7, pp. 2063-2066, Feb, 2001 https://doi.org/10.1016/S0031-3203(00)00129-1
  10. G. K. Wu and T. R. Reed, Image sequence processing using spatiotemporal segmentation, IEEE Trans. Circuits Syst, Video Technol., vol. 9, no. 5, pp. 798-807, 1999 https://doi.org/10.1109/76.780367
  11. S. Z. Li, Markov random field modeling in computer vision, Springer-Verlag, Tokyo, 1995
  12. D. W. Murray and B. F. Buxton, Experiments in the machine interpretation of visual motion, MIT Press, Cambridge, Mass., 1990
  13. F. Lunthon and D. Dragomirescu, A cellular analog network for MRF-based video motion detection, IEEE Trans. Circuits Syst. Video Technol., vol. 46, no. 2, pp. 281-293, 1999 https://doi.org/10.1109/81.747202
  14. E. Y. Kim, S. H. Park, and H. J. Kim, A genetic algorithm based segmentation of Markov random field images, IEEE Signal Processing Letters, vol. 7, no. 11, pp. 301-303, Nov. 2000 https://doi.org/10.1109/97.873564
  15. P. Andrey and P. Tarroux, Unsupervised segmentation of Markov random field modeled textured images using selectionist relaxation, IEEE Trans. Pattern Anal. Machine Intel., vol. 20, no. 3, March 2000 https://doi.org/10.1109/34.667883
  16. S. K. Pal and P. P. Wang, Genetic Algorithms for Pattern Recognition, CRC press, Florida, 1996
  17. S. H. Park, J. K Lee, H. J. Kim, Evolutionary Segmentation of Road Traffic Scenes, Proceedings of IEEE ICEC'97, pp 397-400, 1997 https://doi.org/10.1109/ICEC.1997.592342
  18. N. habili, A. Moini, and N. Burgess, Automatic thresholding for change detection in digital video, in Proc. SPIE, 2000, vol.4067, pp. 133-142 https://doi.org/10.1117/12.386578
  19. S. G. Nadabar and A. K. Jain, Parameter estimation in MRF line process models, in Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.528-523, 1992 https://doi.org/10.1109/CVPR.1992.223140