Browse > Article
http://dx.doi.org/10.3745/KIPSTB.2010.17B.6.405

Non-parametric Background Generation based on MRF Framework  

Cho, Sang-Hyun (가톨릭대학교 컴퓨터공학과)
Kang, Hang-Bong (가톨릭대학교 디지털 미디어학부)
Publication Information
The KIPS Transactions:PartB / v.17B, no.6, 2010 , pp. 405-412 More about this Journal
Abstract
Previous background generation techniques showed bad performance in complex environments since they used only temporal contexts. To overcome this problem, in this paper, we propose a new background generation method which incorporates spatial as well as temporal contexts of the image. This enabled us to obtain 'clean' background image with no moving objects. In our proposed method, first we divided the sampled frame into m*n blocks in the video sequence and classified each block as either static or non-static. For blocks which are classified as non-static, we used MRF framework to model them in temporal and spatial contexts. MRF framework provides a convenient and consistent way of modeling context-dependent entities such as image pixels and correlated features. Experimental results show that our proposed method is more efficient than the traditional one.
Keywords
Background Generation; Background Model; Surveillance System; MRF Framework; Object Tracking;
Citations & Related Records
연도 인용수 순위
  • Reference
1 C. R. Wren, A. Azarbayejani, T. Darrell, A. P. Pentland, “Pfinder: Real-time tracking of the human body”, IEEE Transactions on Pattern Analysis and Machine Intelligence 19 (7) (1998) 780-785.   DOI   ScienceOn
2 C. Stauffer, W. Grimson, “Adaptive background mixture models for real-time tracking”, in: IEEE Conference on Computer Vision and Pattern Recognition, Fort Collins, USA, 1999, pp.246-252.
3 S. Rowe, A. Blake, “Statistical background modelling for tracking with a virtual camera”, in: British Machine Vision Conference, Birmingham, UK, 1995, pp.423-432.
4 C. Stauffer, W. E. L. Grimson, “Learning patterns of activity using real-time tracking”, IEEE Transactions on Pattern Analysis and Machine Intelligence 22 (8) (2000) 747-757.   DOI   ScienceOn
5 K. Toyama, J. Krumm, B. Brumitt, and B. Meyers, “Wallflower: Principles and Practice of Background Maintenance,” IEEE Proc. Int'l Conf. Computer Vision, 1999.
6 I. Haritaoglu, D. Harwoodand, L. S. Davis, “W4: real-time surveillance of people and their activities”, IEEE Transactions on Pattern Analysis and Machine Intelligence 22 (8) (2000) 809-830.   DOI   ScienceOn
7 A. Elgammal, D. Harwood, L. Davis, “Non-parametric model for background subtraction”, in: European Conference on Computer Vision, Dublin, Ireland, 2000, pp.751-767.
8 Yazhou Liu, Hongxun Yao, Wen Gao, Xilin Chen, Debin Zhao, “Nonparametric Background Generation”, ICPR 2006.
9 Sidibe D. D., Strauss O., Puech W, “Automatic Background Generation from a Sequence of Images Based on Robust Mode Estimation”, Proc. SPIE 7250 SPIE-IS&T Electronic Imaging, Digital Photography V, 2009.
10 Y. Zhou, Y. Gong, and H. Tao, “Background segmentation using spatial-temporal multi-resolution MRF,” in Proc. Workshop on Motion and Video Computing., 2005, pp. 8-13.   DOI
11 K. Nummiaro, E. Koller-Meier, and L. V. Gool, ‘An adaptive color-based particle filter,’ Image and Vision Computing 21(1), pp.99-110, 2003.   DOI   ScienceOn