Adaptive Background Subtraction Based on Genetic Evolution of the Global Threshold Vector

전역 임계치 벡터의 유전적 진화에 기반한 적응형 배경차분화

  • 임양미 (서울산업대학교 매체공학과)
  • Published : 2009.10.30

Abstract

There has been a lot of interest in an effective method for background subtraction in an effort to separate foreground objects from a predefined background image. Promising results on background subtraction using statistical methods have recently been reported are robust enough to operate in dynamic environments, but generally require very large computational resources and still have difficulty in obtaining clear segmentation of objects. We use a simple running-average method to model a gradually changing background, instead of using a complicated statistical technique. We employ a single global threshold vector, optimized by a genetic algorithm, instead of pixel-by-pixel thresholds. A new fitness function is defined and trained to evaluate segmentation result. The system has been implemented on a PC with a webcam, and experimental results on real images show that the new method outperforms an existing method based on a mixture of Gaussian.

주어진 배경 이미지로부터 전경 객체를 분리하는 것을 목표로 하는 배경 차분화 기법에 관한 많은 연구가 있어 왔다. 최근에 발표된 몇 가지 통계 기반 배경 차분화 기법들은 동적인 환경에서 동작할 수 있을 정도로 안정된 성능을 보이는 것으로 보고되고 있다. 그러나 이들 기법은 일반적으로 매우 많은 계산 자원을 요구하며, 객체의 명확한 윤곽을 획득하는데 있어서는 아직 어려움이 있다. 본 논문에서는 점진적으로 변화하는 배경을 모델링하기 위해 복잡한 통계 기법을 적용하는 대신 간단한 이동-평균 기법을 사용한다. 또한 픽셀별로 할당되는 다중의 임계치 대신 유전자 학습에 의해 최적화되는 하나의 전역적 임계치를 사용한다. 유전자 학습을 위해 새로운 적합도 함수를 정의하여 학습하고 이를 이용하여 이미지의 분할 결과들을 평가한다. 본 논문의 시스템은 웹 카메라가 장착된 개인용 컴퓨터에서 구현하였으며, 실사 이미지들에 대한 실험 결과에 의하면 기존의 가우시안 믹스쳐 방식보다 우수한 성능을 보이는 것으로 나타났다.

Keywords

References

  1. R.J. Qian and M.I. Sezan, "Video background replacement without a blue screen," International Conference on Image Processing (ICIP 99), Vol. 4, pp. 143-146, 1999.
  2. D. Hong and W. Woo, "A background subtraction for a vision-based user interface," Fourth Pacific Rim Conference on Multimedia (IEEE PCM), Vol. 1 pp. 263-267, 2003.
  3. M. Piccardi, "Background subtraction techniques: a review," IEEE SMC International Conference on Systems, Man, and Cybernetics, Vol. 4, pp. 3099-3104, 2004.
  4. L. Li, W. Huang, I.Y. Gu and Q. Tian, "Statistical modeling of complex backgrounds for foreground object detection," IEEE Trans. on Image Processing, Vol. 13, Issue 11, pp. 1459-1472, 2004. https://doi.org/10.1109/TIP.2004.836169
  5. A.E. lgammal, D. Harwood and L. Davis, "Non-parametric model for background subtraction," 6th European Conference on Computer Vision, Part II, pp. 751-767, 2000.
  6. A Mittal and N. Paragiosm, "Motion-based background subtraction using adaptive kernel density estimation," IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPH '04), Vol. 2, pp. 302-309, 2004.
  7. K. Kim, T. Chalidabhongse, D. Harwood and L. Davis, "Heal-time foreground-background segmentation using codebook model," Real Time Imaging, Vol. 11, Issue 3, pp. 172-185, 2005. https://doi.org/10.1016/j.rti.2004.12.004
  8. M. Harville, "A framework for high-level feedback to adaptive, per-pixel, mixture-of-Gaussian background models," 7th European Conference on Computer Vision, Vol. 3, pp. 543-60, 2002.
  9. L. Greengard and J. Strain, "The fast Gauss transform," SIAM Journal on Scientific Computing, Vol. 2, Issue 1, pp. 79-94, 1991.
  10. L. Baoxin and M.I. Sezan, "Adaptive video background replacement," Proc. IEEE International Conference on Multimedia and Expo, pp. 269-272, 2001.
  11. Y.S. Raja, J. Mckenna and S. Gong, "Segmentation and tracking using colour mixture models," Asian Conference on Computer Vision, Vol. 1, pp, 607-614, 1998.
  12. 권혁종, 배상근, 김병국, “스테레오 CCD 카메라를 이용한 이동체의 실시간 3차원 위치추적” 한국GIS학회지, 13권, 2호, pp.129-138, 2005.
  13. B. Bhanu, L. Sungkee and J. Ming, "Adaptive image segmentation using a genetic algorithm," IEEE Trans. on Systems, Man and Cybernetics, Vol. 25, No. 12, pp. 1543-1567, 1995. https://doi.org/10.1109/21.478442
  14. L. Garcia-Perez, M.C. Garcia-Alegre, J. Marchant and T. Hague, "Dynamic threshold selection for image segmentation of natural structures based upon a performance criterion," 3rd European Conference on Precision Agriculture (3ECPA), pp. 193-198, 2001.
  15. P.K. Sahoo, A.A. Farag and Y.P. Yeap, "Threshold selection based on histogram modeling," IEEE International Conference on Man and Cybernetics, Vol. 1, pp. 351-356, 1992.
  16. 이창수, 지정규, “멀티미디어 서비스를 위한 동영상 이미지의 특징정보 분석 시스템에 관한 연구,” 한국데이타베이스학회, 9권, 3호, pp. 1-12, 2002. (RGB)
  17. D.E. Goldberg, "Applications of genetic-based machine learning," Chap. 7 in Genetic Algorithms In Search, Optimization & Machine Learning, Addison Wesley Publishing, pp. 261-307, 1989.
  18. B. Bhanu, "Automatic target recognition: state of the art survey," IEEE. Trans. on Aerospace and Electronic Systems, Vol. AES-22, pp. 364-379, 1986. https://doi.org/10.1109/TAES.1986.310772
  19. K. Ma and H. Wang, "Region-based non-parametric optical flow segmentation with pre-clustering and post-clustering," IEEE International Conference on Multimedia and Expo (ICME), Vol. 2, pp. 201-204, 2002.
  20. 강동중, 하종은, “Visual C++을 이용한 디지털 영상처리,” 사이텍미디어, pp. 257-259, 2003.
  21. J. E. Baker, "Adaptive selection methods for genetic algorithm," First International Conference on Genetic Algorithms and Applications, Their Applicat., pp. 101-111, 1985.
  22. K. Toyama, J. Krumm, B. Brumitt and B. Meyers, "Wallflower: principles and practice of background maintenance," 7th International Conference on Computer Vision, pp. 255-261, 1999.