Multi-view Gait Recognition Based on Motion Regression Using Multilayer Perceptron

It has been shown that gait is an efficient biometric feature for identifying a person at a distance. However, it is a challenging problem to obtain reliable gait feature when viewing angle changes because the body appearance can be different under the various viewing angles. In this paper, the problem above is formulated as a regression problem where a novel View Transformation Model (VTM) is constructed by adopting Multilayer Perceptron (MLP) as regression tool. It smoothly estimates gait feature under an unknown viewing angle based on motion information in a well selected Region of Interest (ROI) under other existing viewing angles. Thus, this proposal can normalize gait features under various viewing angles into a common viewing angle before gait similarity measurement is carried out. Encouraging experimental results have been obtained based on widely adopted benchmark database.

[1]  David G. Stork,et al.  Pattern Classification , 1973 .

[2]  Rama Chellappa,et al.  Towards a view invariant gait recognition algorithm , 2003, Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, 2003..

[3]  Trevor Darrell,et al.  Integrated face and gait recognition from multiple views , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[4]  Ramakant Nevatia,et al.  Camera calibration from video of a walking human , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[6]  Yasushi Makihara,et al.  Gait Recognition Using a View Transformation Model in the Frequency Domain , 2006, ECCV.

[7]  Qiang Wu,et al.  Multiple views gait recognition using View Transformation Model based on optimized Gait Energy Image , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.