A Matching Method Based on Partial Body Silhouette

In order to reduce the searching space of shape context matching method and improve the speed of silhouette matching, a matching method based on partial body silhouette is proposed. In this method body silhouette is divided into segmentations according to the principle of human body composition, and then match the representative silhouettes under the restrictions of limbs silhouette characteristic. The similarity of the whole silhouette is evaluated by means of the statistical analysis of the similarity of every part. Experimental results show that the method can effectively improve the speed of the body silhouette matching.

[1]  Donald D. Hoffman,et al.  Parsing silhouettes: The short-cut rule , 1999, Perception & psychophysics.

[2]  Jitendra Malik,et al.  Recovering 3D human body configurations using shape contexts , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Guangxi Zhu,et al.  Contour based object detection using part bundles. , 2010, Computer vision and image understanding : CVIU.

[4]  Andrea Bottino,et al.  A Silhouette Based Technique for the Reconstruction of Human Movement , 2001, Comput. Vis. Image Underst..

[5]  Honghai Liu,et al.  Advances in View-Invariant Human Motion Analysis: A Review , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[6]  Donald D. Hoffman,et al.  Salience of visual parts , 1997, Cognition.

[7]  Jitendra Malik,et al.  Efficient shape matching using shape contexts , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Mubarak Shah,et al.  Shape matching and modeling using skeletal context , 2008, Pattern Recognit..

[9]  Kiyoshi Hoshino,et al.  Quick and accurate estimation of human 3D hand posture , 2010, Intell. Serv. Robotics.