Human Body Segmentation Based on Shape Model and Level Set

Abstract:

Human body segmentation is important for object tracking and recognition. When there are multiple human bodies, because of inter-occlusion, human body precise segmentation is difficult. A segmentation method based on prior shape model and level set is proposed. Human coarse shape models are constructed with position, scale and posture. For each human body, its corresponding human shape model is obtained by model matching by which position is obtained roughly after model matching, and object precise contour is obtained through curve evolution by multiphase level set with initial contour obtained from shape model. The proposed method could segment human object precisely.

• Periodical: Applied Mechanics and Materials (Volumes 433-435)
• Pages: 261-266
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.433-435.261
• Online since: October 2013
• Authors: Ying Na Deng, Xue Mei Hou
• Keywords: Bayesian Model, Human Shape Model, Level Set, Segmentaiton

References

[1] R. Yang, Q. Zheng, Multi-moving people detection from binocular sequences. in: Proceedings of International Conference on Acoustic, Speech and Signal Processing. Hong Kong, Vol. 2p. 297(2003).

DOI: 10.1109/icassp.2003.1199101

[2] J.G. Brostow, R. Cipolla. Unsupervised Bayesian Detection of Independent Motion in Crowds, in: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New Yourk: IEEE Computer Society, Vol. 1, p.594 (2006).

DOI: 10.1109/cvpr.2006.320

[3] A.M. Elgammal L.S. Davis. Probabilistic framework for segmenting people under Occlusion. in: Proceedings of 8th IEEE Conference on Computer Vision, Vancouver, Vol 2, p.145 (2001).

DOI: 10.1109/iccv.2001.937617

[4] D. Ramanan and D.A. Forsyth. Finding and tracking people from the bottom up. in: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Madison, Vol. 2, p.467 (2003).

DOI: 10.1109/cvpr.2003.1211504

[5] Z. Lin, S.D. Larry,D. Doermann, et. al. An interactive approach to pose-assisted and appearance-based segmentation of humans. In: ICCV Workshop on Interactive Computer Vision, Rio de Janeiro, Brazil, (2007).

DOI: 10.1109/iccv.2007.4409123

[6] Wu Bo and Ram Nevatia. in: International Journal of Computer Vision. Vol. 27(2)( 2007), p.247.

[7] B. Sapp, A. Toshev, and B. Taskar. Cascaded models for articulated pose estimation. in: ECCV (2), Heraklion, p.406 ( 2010).

DOI: 10.1007/978-3-642-15552-9_30

[8] H. Lu, G. Fang, X. Shao, X. Li, in: IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS—PART B: CYBERNETICS, Vol. 42(3), p.889(2012).

[9] Zhao Tao, Ram Nevatia. Bayesian human segmentation in crowded situations. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Madison, Vol. 2, p.459(2003).

DOI: 10.1109/cvpr.2003.1211503

[10] L. Zhe,L. S. Davis,D. Doermann, and D. Dementhon. Hierarchical part-template matching for human detection and segmentation. In: Proceedings of 11th International Conference on Computer Vision, Rio de Janeiro, (2007).

DOI: 10.1109/iccv.2007.4408975

[11] A-R. Mansouri, A. Mitiche, C. Vazquez, Multiregion competition, in: Computer Vision and Image Understanding, Vol. 101, p.137(2006).

DOI: 10.1016/j.cviu.2005.07.008