An Optimization Algorithm of Foreground Objects Extraction

Abstract:

In this paper, we propose a novel algorithm for coarse-to-fine foreground objects extraction. There are two general approaches for foreground objects extraction: background subtraction and image matting. Our new approach can not only improve detection accuracy compared with general background subtraction approaches, but also reduce computation burden compared with general image matting approaches. Firstly, we present a novel method called Motion-mask Gaussian Mixture Models (Motion-mask GMMs) to extract coarse foreground regions. This new approach can classify foreground and background pixels more accurately, especially when there are long-time stopping objects in the scene. Secondly, with the coarse foreground regions, we propose a novel approach to make foreground object extraction more accurate based on effective fusion of image registration and image matting. This new method overcomes the template drift problem during template updating and also reduces the expensive computational cost of image matting. Our proposed approach is tested with kinds of video sequences in indoor and outdoor environments. Experimental results demonstrate the accuracy and efficiency of our proposed approach for foreground object extraction.

• Periodical: Advanced Materials Research (Volumes 403-408)
• Pages: 169-176
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.403-408.169
• Online since: November 2011
• Authors: Xia Yi Zhang, Zhi Peng Li, Fu Qiang Liu, Zhen Jia, Jian Wei Zhao
• Keywords: Gaussian Misture Model, Image Matting, Image Registration, Object Extraction

References

[1] S. Baker and I. Matthews. Lucas-kanade 20 years on: A unifying framework, International Journal of Computer Vision, 56(3): 221–255, (2004).

DOI: 10.1023/b:visi.0000011205.11775.fd

[2] R. Bayardo Jr and J. Pehoushek. Counting Models using Connected Components, In Proceedings of AAAI 2000, Austin, pages 157–162, (2000).

[3] N. Friedman and S. Russell. Image Segmentation in Video Sequences: A Probabilistic Approach, Proceedings of the Thirteenth Annual Conference on Uncertainty in Artificial Intelligence, pages 175–181, (1997).

[4] J. Huang and C. Chen. Moving cast shadow detection using physics-based features, Computer Vision and Pattern Recognition, pages 2310–2317, (2009).

DOI: 10.1109/cvpr.2009.5206629

[5] D. Lee. Effective gaussian mixture learning for video background subtraction, IEEE Transactions on PAMI, 27(5): 827–832, (2005).

DOI: 10.1109/tpami.2005.102

[6] A. Levin, D. Lischinski, and Y. Weiss. A closed-form solution to natural image matting, IEEE Transactions on PAMI, 30(2): 228–242, (2008).

DOI: 10.1109/tpami.2007.1177

[7] B. Lucas and T. Kanade. An iterative image registration technique with an application to stereo vision, International joint conference on artificial intelligence, volume 3, page 3. Citeseer, (1981).

[8] I. Matthews, T. Ishikawa, and S. Baker. The template update problem, , IEEE Transactions on PAMI, 26(6): 810–815, (2004).

[9] C. Stauffer and W. Grimson. Adaptive background mixture models for real-time tracking, Computer Vision and Pattern Recognition, volume 2, pages 246–252, (1999).

DOI: 10.1109/cvpr.1999.784637

[10] Y. Tsai and J. Lien. Efficient Object Segmentation Using Digital Matting for MPEG Video Sequences, Computer Vision–ACCV 2006, pages 591–601.

DOI: 10.1007/11612704_59

[11] N. Vlassis and A. Likas. A greedy EM algorithm for Gaussian mixture learning, Neural Processing Letters, 15(1): 77–87, (2002).

[12] J. Wang and M. Cohen. Image and video matting: A survey, Foundations and Trends R in Computer Graphics and Vision, 3(2): 97–175, (2007).

DOI: 10.1561/0600000019

[13] B. Zitova and J. Flusser. Image registration methods: a survey, Image and vision computing, 21(11): 977–1000, (2003).

DOI: 10.1016/s0262-8856(03)00137-9

[14] Xiayi Zhang, Fuqiang Liu, and Zhipeng Li. A Novel Foreground Object Detection Method Based on Motion-Mask Gaussian Mixture Model , MediaCOM 2010, Au. 7-8, HongKong.