Human Motion Analysis Based On Silhouette and Centroid Displacement

Abstract:

Human motion analysis in an intelligence surveillance system is a hot research topic in computer vision field.In this paper we proposed a motion recognition method based on silhouette information and centroid displacement for static environment.We used background subtraction method added background update and did binarization processing on foreground image by using adaptive threshold segmentation technique,then extracted moving target from the videos.Last we used silhouette information and centroid displacement as human motion features for behaviour analysis.Experiments show that the method has high accuracy rate at daily behaviour recognition.

• Periodical: Applied Mechanics and Materials (Volumes 333-335)
• Pages: 1139-1144
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.333-335.1139
• Online since: July 2013
• Authors: Qing Ye, Jun Feng Dong, Yong Mei Zhang
• Keywords: Behaviour Analysis, Centroid Displacement, Moving Target, Silhouette Information

References

[1] Davis J, Bobick A. The representation and recognition of action using temporal templates. MIT Media Lab, Perceptual Computing Group: Technical Report 402, (1997).

[2] Bobick A，Davis J. Real-time recognition of activity using temporal templates[C]. Proc IEEE Workshop on Applications of Computer Vision. IEEE Computer Press, 1996: 39-42.

DOI: 10.1109/acv.1996.571995

[3] Polana R. Nelson R. Low level recognition of human motion[C]. Proc IEEE Workshop on Motion of Non-rigid and Articulated Objects. Austin: IEEE Computer Press, 1994: 77-82.

DOI: 10.1109/mnrao.1994.346251

[4] Ayers D, Shah M. Monitoring human behavior in an office environment. the Interpretation of Visual Motion. MIT Press, 1998: 65-72.

[5] Rota N, Thonnat M. Activity recognition from video sequences using declarative models[C]. 14th European Conference on Artificial Intelligence. Berlin: IOS Press Germany, 2000: 673-680.

[6] WANG Liang, HU We-i ming, TAN Tie-niu. A survey of visual a-nalysis of human motion [J]. Journal of Computers, 2002, 25(3): 225-237.

[7] AvklanS. Ensemble Tracking. IEEE Computer Soeiety Conference on Computer vision and Pattem Reeognition. 2005(2): 494-50.

[8] J. K. Aggarwal and M. S. Ryoo. Human Activity Analysis: A Review. The University of Texas at Austin, Electronics and Telecommunications Research Institute. (2012).

[9] Rodrigo Benenson, Markus Mathias, Radu Timofte and Luc Van Gool. Pedestrian detection at 100 frames per second. CVPR, (2012).

DOI: 10.1109/cvpr.2012.6248017

[10] Guillaume-Alexandre Bilodeau, Pier-Luc St-Onge, and Romain Garnier. Silhouette-based features for visible-infrared registration. LITIV Lab, Department of computer engineering and software engineering, CVPR, (2012).

DOI: 10.1109/cvprw.2011.5981676

[11] Deva Ramanan and D. A. Forsyth and Andrew Zisserman Strike a Pose: Tracking People by Finding Stylized Poses CVPR, (2005).

DOI: 10.1109/cvpr.2005.335