Title :
A Non-Parametric HMM Learning Method for Shape Dynamics with Application to Human Motion Recognition
Author :
Jin, Ning ; Mokhtarian, Farzin
Author_Institution :
Centre for Vision, Speech, & Signal Process., Surrey Univ., Guildford
Abstract :
The shape dynamics, i.e., the spatial-temporal shape deformation of an object during its movement, provides much important information about the identity of the object, and even motions performed by the object. In this paper, we proposed a system recognizing object motions based on their shape dynamics. In the proposed system, we use Kenall´s definition of shape to represent the object contour extracted from each frame, and construct a tangent space with the full Procrustes mean shape as the pole to approximate a linear space for the dataset, in which the Euclidean distance metric can be used to approximate the full Procrustes distance between shapes. The spatial-temporal shape deformation in motions is captured by hidden Markov models. Since in the traditional HMM framework the hidden states are typically coupled with the training data, which will bring many un-desired problems to the learning procedure, we introduce a non-parametric HMM approach that uses continuous output HMMs with arbitrary states (decoupled from training data) to learn the shape dynamics directly from large amounts of training data where a non-parametric kernel density estimation algorithm is applied to learn the observation probability distribution in order to compensate for the uncertainty introduced by those arbitrary hidden states. This optimizes the HMM training procedure. We then use the proposed system for view-dependent human motion recognition
Keywords :
hidden Markov models; image recognition; motion estimation; object detection; Euclidean distance metric; Kenall definition of shape; Procrustes mean shape; human motion recognition; nonparametric HMM learning method; nonparametric kernel density estimation algorithm; object contour extraction; observation probability distribution; shape dynamics; spatial-temporal shape deformation; Data mining; Euclidean distance; Hidden Markov models; Humans; Kernel; Learning systems; Linear approximation; Shape; State estimation; Training data;
Conference_Titel :
Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
0-7695-2521-0
DOI :
10.1109/ICPR.2006.130