The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

On-line Background Extraction in Video Image Using Vector Median

벡터 미디언을 이용한 비디오 영상의 온라인 배경 추출

  • 김준철 (서남대학교 전지전자공학과) ;
  • 박은종 (전북대학교 영상공학과) ;
  • 이준환 (전북대학교 전자정보공학부)
  • Published : 2006.10.30
Download PDF
⟨ Previous Next ⟩

Abstract

Background extraction is an important technique to find the moving objects in video surveillance system. This paper proposes a new on-line background extraction method for color video using vector order statistics. In the proposed method, using the fact that background occurs more frequently than objects, the vector median of color pixels in consecutive frames Is treated as background at the position. Also, the objects of current frame are consisted of the set of pixels whose distance from background pixel is larger than threshold. In the paper, the proposed method is compared with the on-line multiple background extraction based on Gaussian mixture model(GMM) in order to evaluate the performance. As the result, its performance is similar or superior to the method based on GMM.

배경추출은 비디오 감시 시스템에서 움직이는 물체를 찾는데 중요한 기술이다. 본 논문에서는 벡터 정렬을 이용한 새로운 온라인 컬러 배경 추출 방법을 제안한다. 제안된 방법에서 배경은 물체보다 발생빈도가 높다는 사실을 이용하여, 연속된 프레임의 컬러화소 값들의 벡터 미디언을 그 화소에서의 배경이라 간주한다. 본 알고리즘에서 현재 프레임의 물체는 얻어진 배경과의 거리가 문턱치보다 큰 화소들의 집합으로 구성된다. 알고리즘의 성능을 평가하기 위하여 온라인 가우시안 혼합 모델(Gaussian Mixture Model)을 이용한 다중 배경추출 방법과 비교하였으며, 비교결과 유사 또는 우월한 실험 결과를 확인하였다.

Keywords

References

  1. I. Haritaoglu, D. Harwood and L. S. Davis, 'W4:Real-Time Surveillance of people and Their Activities,' IEEE Tranns. PAMI, Vol.22, No.8, pp.809-830, 2000 https://doi.org/10.1109/34.868683
  2. 조태훈, 최영규 '다중 배경 분포를 이용한 움직임 검출', 정보처리학회논문지 제8권-B권 제4호, pp.381. 2000
  3. N. Frieman and S. Russell, 'Image segmentation In video sequences: A probabilistic approach,' Proc. 13th Cant. Uncertainty in Artificial Intelligence, Aug., 1997
  4. D. Wang, 'A Novel Probability Model for Background Maintenance and Subtraction,' 15th Conf. Vision Interface May, 2002
  5. S. S. Cheung and C. Kamath, 'Robust techniques for background subtraction in urban traffic video,' Proc. of SPIE Visuual Communications and Image Processing, 2004 https://doi.org/10.1117/12.526886
  6. Z. Hou and C. Han, 'A Background Reconstruction Algorithm based on Pixel Intensity Classification in Remote Video Surveillance,' Proc. of 7th Conf. Information Fusion, June, 2004
  7. B.P.L. LO and S.A. Velastin, 'Automatic Congestion Detection System for Underground Platforms,' Proc. Symp. Intelligence Multimedia, Video, and Speech Processing, pp.158-161, 2000 https://doi.org/10.1109/ISIMP.2001.925356
  8. B. Gloyer, H.K. Aghajan, K. Y. Siu and T. Kailath, 'Video-Based Freeway Monitoring System Using Recursive Vehicle Tracking,' Proc. SPIE Symp. Electronic Imaging: Imag and Video Processing, 1995 https://doi.org/10.1117/12.205477
  9. R. Cucchiara, C. Grana, M. Piccardi and A. Prati, 'Detecting Moving Objects, Ghosts, and Shadows in Video Streams,' IEEE Trans. PAMI, Vol.25, No.10, October, 2003 https://doi.org/10.1109/TPAMI.2003.1233909
  10. C. Stauffer and W. E. L. Grimson, 'Adaptive Background Mixture Models for Real-Time Tracking,' Proc. Computer Vision and Pattern Recognition 99, Colorado https://doi.org/10.1109/CVPR.1999.784637
  11. P.KaewTraKulPong and R. Bowden. 'An Improved Adaptive Background Mixture Model for Realtime Tracking with Shadow Detection,' 12nd. European Workshop on Advanced Video Based. Surveillance Systems, AVBS01, September, 2001
  12. D. S. Lee, 'Effective Gaussian Mixture Learning for Video background Subtraction,' lEEE Tran. on PAMI, Vol.27, pp.827-832, 2005 https://doi.org/10.1109/TPAMI.2005.102
  13. J. Astola, P. Haaristo and Y. Neuvo, 'Vector Median Filters,' Proceeding of IEEE, Vol.78, No.4, pp.678-689, 1990 https://doi.org/10.1109/5.54807
  14. 엄경배, 한서원, 이준환, '혼합된 컬러 잡음하에서 컬러 영상 향상을 위한 조건적인 퍼지 클러스터 필터' 정보처리학회논문지 제6권 제12호, pp.3718-3726, 1999.