Gait analysis and recognition using angular transforms

An angular representation is proposed for gait analysis and recognition applications. Each human silhouette in a gait sequence is transformed into a low dimensional feature vector consisting of average pixel distances from the center of the silhouette. The proposed approach is very suitable for the processing of imperfectly segmented silhouettes since it is robust to segmentation errors. The sequence of feature vectors corresponding to a gait sequence is used for identification based on a minimum-distance criterion between test and reference sequences. By using the new transform on the gait challenge database, concrete improvements in recognition performance are seen in comparison to other methods of similar or higher complexity.

[1]  Rama Chellappa,et al.  A hidden Markov model based framework for recognition of humans from gait sequences , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[2]  Adam Prügel-Bennett,et al.  Automatic gait recognition using area-based metrics , 2003 .

[3]  Hyeonjoon Moon,et al.  The FERET evaluation methodology for face-recognition algorithms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  Kinh Tieu,et al.  Learning pedestrian models for silhouette refinement , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[5]  Yanxi Liu,et al.  Gait Sequence Analysis Using Frieze Patterns , 2002, ECCV.

[6]  Tieniu Tan,et al.  Silhouette Analysis-Based Gait Recognition for Human Identification , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Sudeep Sarkar,et al.  The gait identification challenge problem: data sets and baseline algorithm , 2002, Object recognition supported by user interaction for service robots.