Recognising Movement and Gait by Masking Functions

We present a new area-based measure that can not only analyse motion (such as to highlight human movement) but also for biometric purposes to recognise people by the way they walk. The technique operates by measuring the rate of change of area in a way controlled by masking functions. We show how this approach can be used to determine human behaviour, as opposed to animal movement, and give illustrative results of its potential to recognise people by their gait.

[1]  G. Johansson Visual perception of biological motion and a model for its analysis , 1973 .

[2]  J. Little,et al.  Describing motion for recognition , 1995, Proceedings of International Symposium on Computer Vision - ISCV.

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

[4]  M. Nixon,et al.  Automatic Gait Recognition via Model-Based Evidence Gathering , 1999 .

[5]  M. P. Murray Gait as a total pattern of movement. , 1967, American journal of physical medicine.

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

[7]  A. B. Drought,et al.  WALKING PATTERNS OF NORMAL MEN. , 1964, The Journal of bone and joint surgery. American volume.

[8]  Hiroshi Murase,et al.  Moving object recognition in eigenspace representation: gait analysis and lip reading , 1996, Pattern Recognit. Lett..

[9]  M. Nixon,et al.  Human gait recognition in canonical space using temporal templates , 1999 .