Posture recognition with a 3D human model

This paper proposes an approach to recognise human postures in video sequences, which combines a 2D approach with a 3D human model The 2D approach consists in projections of moving pixels on the reference axis. The 3D model is a realistic articulated human model which is used to obtain reference postures to compare with test postures. We are interested in a set of specific postures which are representative of typical applications in video interpretation. We give results for recognition of general (e.g., standing) and detailed (e.g., standing with one arm up) postures. First results show the effectiveness of our approach for recognition of human posture.

[1]  Ramakant Nevatia,et al.  Tracking multiple humans in complex situations , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  François Brémond,et al.  Design and Assessment of an Intelligent Activity Monitoring Platform , 2005, EURASIP J. Adv. Signal Process..

[3]  David C. Hogg,et al.  An Adaptive Eigenshape Model , 1995, BMVC.

[4]  Rita Cucchiara,et al.  A machine learning approach for human posture detection in domotics applications , 2003, 12th International Conference on Image Analysis and Processing, 2003.Proceedings..

[5]  Dariu Gavrila,et al.  The Visual Analysis of Human Movement: A Survey , 1999, Comput. Vis. Image Underst..

[6]  Monique Thonnat,et al.  Human Posture Recognition in Video Sequence , 2003 .

[7]  Themis Panayiotopoulos,et al.  SimHuman: A Platform for Real-Time Virtual Agents with Planning Capabilities , 2001, IVA.

[8]  Olivier D. Faugeras,et al.  3D articulated models and multi-view tracking with silhouettes , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[9]  Larry S. Davis,et al.  Ghost: a human body part labeling system using silhouettes , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).