Real-Time Human Action Recognition System Using Depth Map Sequences

Abstract:

This work presents a real-time human action recognition system that uses depth map sequence as input. The system contains the segmentation of human, the action modeling based on 3D shape context and the action graph algorithm. We effectively solve the problem of segmenting human from complex and cluttered scenes by combing a novel quadtree split-and-merge method and the codebook background modeling algorithm. We aims at recognizing actions that are used in games and interactions, especially complex actions that contain foot motion and body heave. By expanding the shape context descriptor into 3D space, we obtain translation and scale invariant features and get rid of normalization error, which is a common problem of real-life applications. Experiments in various scenarios demonstrate the high speed and excellent performance of our procedure.

• Periodical: Advanced Materials Research (Volumes 760-762)
• Pages: 1647-1651
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.760-762.1647
• Online since: September 2013
• Authors: Yan Li Li, Gui Jin Wang, Xing Gang Lin, Guang Cheng, Li He
• Keywords: Action Recognition, Depth Image, Segmentation, Shape Context, Split-and-Merge

References

[1] R. Poppe, A survey on vision-based human action recognition, Image and vision computing, vol. 28, no. 6, p.976–990, (2010).

DOI: 10.1016/j.imavis.2009.11.014

[2] W. Li, Z. Zhang, and Z. Liu, Action recognition based on a bag of 3d points, in Computer Vision and Pattern Recognition Workshops(CVPRW), 2010 IEEE Computer Society Conference on. IEEE, 2010, p.9–14.

DOI: 10.1109/cvprw.2010.5543273

[3] J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp, M. Finocchio, R. Moore, A. Kipman, and A. Blake, Real-time human pose recognition in parts from single depth images, in CVPR, vol. 2, 2011, p.3.

DOI: 10.1109/cvpr.2011.5995316

[4] W. Li, Z. Zhang, and Z. Liu, Expandable data-driven graphical modeling of human actions based on salient postures, Circuits and Systems for Video Technology, IEEE Transactions on, vol. 18, no. 11, p.1499–1510, (2008).

DOI: 10.1109/tcsvt.2008.2005597

[5] Y. Ma, S. Worrall, and A. Kondoz, Automatic video object segmentation using depth information and an active contour model, in Multimedia Signal Processing, 2008 IEEE 10th Workshop on. IEEE, 2008, p.910–914.

DOI: 10.1109/mmsp.2008.4665204

[6] S. Lim, A. Mittal, L. Davis, and N. Paragios, Fast illumination-invariant background subtraction using two views: Error analysis, sensor placement and applications, in Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, vol. 1. IEEE, 2005, p.1071.

DOI: 10.1109/cvpr.2005.155