PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Gait Sequence Synthesis and Reconstruction
Muayed Al-Huseiny, Sasan Mahmoodi and Mark Nixon
In: British Machine Vision Conference, 7-11 Sept. 2009, London, UK.


We describe a new technique to synthesize the boundary of a walking subject, with ability to predict movement in missing frames. The fact that real world images are mostly complex, noisy and occluded makes the implementation of a segmentation algorithms a serious challenge due to the difficulty in segmentation of those images. Some of these difficulties can be tackled via the introduction of prior knowledge, due to its capacity to compensate for missing or misleading image information. Accordingly a robust gait prior shape should enable improved segment ation of walking subjects.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Machine Vision
ID Code:5600
Deposited By:Sasan Mahmoodi
Deposited On:08 March 2010