What image information is important in silhouette-based gait recognition?

Gait recognition has recently gained significant attention, especially in vision-based automated human identification at a distance in visual surveillance and monitoring applications. Silhouette-based gait recognition is one of the most popular methods for recognising moving shapes. This paper aims to investigate the important features in silhouette-based gait recognition from point of view of statistical analysis. It is shown that the average silhouette includes a static component of gait (head and body) as the most important image part, while dynamic component of gait (swings of legs and arms) is ignored as the least important information. At the same time ignoring dynamic part of gait can result in loss in recognition rate in some cases, and the importance of better motion estimation is underlined.

[1]  Tieniu Tan,et al.  A new attempt to gait-based human identification , 2002, Object recognition supported by user interaction for service robots.

[2]  Rama Chellappa,et al.  A framework for activity-specific human identification , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  S. Stevenage,et al.  Visual analysis of gait as a cue to identity , 1999 .

[4]  W. Eric L. Grimson,et al.  Gait analysis for recognition and classification , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[5]  Jason M. Nash,et al.  Automatic gait recognition , 1999 .

[6]  W. Krzanowski.  Selection of Variables to Preserve Multivariate Data Structure, Using Principal Components , 1987 .

[7]  Mark S. Nixon,et al.  Automatic extraction and description of human gait models for recognition purposes , 2003, Comput. Vis. Image Underst..

[8]  Alice J. O'Toole,et al.  Face distinctiveness in recognition across viewpoint: an analysis of the statistical structure of face spaces , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[9]  Richard A. Johnson,et al.  Applied Multivariate Statistical Analysis , 1983 .

[10]  Robert T. Collins,et al.  Silhouette-based human identification from body shape and gait , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[11]  Mark S. Nixon,et al.  On a Large Sequence-Based Human Gait Database , 2004 .

[12]  G. J. G. Upton,et al.  Applied Multivariate Data Analysis, Volume 1: Regression and Experimental Design , 1994, The Mathematical Gazette.

[13]  Mark S. Nixon,et al.  Recognising humans by gait via parametric canonical space , 1999, Artif. Intell. Eng..

[14]  Murray Mp,et al.  Gait as a total pattern of movement. , 1967 .

[15]  Sudeep Sarkar,et al.  Baseline results for the challenge problem of HumanID using gait analysis , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[16]  Mark S. Nixon,et al.  Gait Extraction and Description by Evidence-Gathering , 1999 .

[17]  Tieniu Tan,et al.  Automatic gait recognition based on statistical shape analysis , 2003, IEEE Trans. Image Process..

[18]  I. Jolliffe.  Principal Component Analysis , 2002 .

[19]  J E Cutting,et al.  A biomechanical invariant for gait perception. , 1978, Journal of experimental psychology. Human perception and performance.