We describe a new method for Automatic Gait Recognition based around the use of Fourier descriptors that model the periodic deformation of human gait. Fourier descriptors have been...
Abstract— This paper describes a novel algorithm for autonomous and incremental learning of motion pattern primitives by observation of human motion. Human motion patterns are ed...
The topic of this paper is the integration of Expectation Maximization (EM) background modeling and template matching using color histograms as templates to improve person trackin...
Paul J. Withagen, Klamer Schutte, Frans C. A. Groe...
This paper describes a fast technique for modifying motion sequences for complex articulated mechanisms in a way that preserves physical properties of the motion. This technique i...
This paper studies two types of spatial relationships that can be learned from training examples for object recognition. The first one employs deformable relationships between obj...