Title :
A probabilistic framework for rigid and non-rigid appearance based tracking and recognition
Author :
De La Torre, Fernando ; Yacoob, Yaser ; Davis, Larry
Author_Institution :
Dept. of Commun. & Signal Theory, Univ. Ramon LLull., Barcelona, Spain
Abstract :
This paper describes an unified probabilistic framework for appearance-based tracking of rigid and non-rigid objects. A spatio-temporal dependent shape-texture eigenspace and mixture of diagonal Gaussians are learned in a hidden Markov model (HMM)-like structure to better constrain the model and for recognition purposes. Particle filtering is used to track the object while switching between different shape/texture models. This framework allows recognition and temporal segmentation of activities. Additionally an automatic stochastic initialization is proposed, the number of states in the HMM are selected based on the Akaike information criterion and comparison with deterministic tracking for 2D models is discussed. Preliminary results of eye tracking, lip tracking and temporal segmentation of mouth events are presented
Keywords :
Gaussian distribution; computer vision; eigenvalues and eigenfunctions; face recognition; filtering theory; hidden Markov models; image segmentation; image texture; object recognition; probability; tracking; user interfaces; Akaike information criterion; HMM; appearance-based recognition; appearance-based tracking; automatic stochastic initialization; diagonal Gaussian mixture; eye tracking; hidden Markov model; lip tracking; mouth events; non-rigid objects; object tracking; particle filtering; probabilistic framework; rigid objects; shape-texture eigenspace; spatio-temporal eigenspace; temporal segmentation; Active appearance model; Active contours; Computer vision; Electrical capacitance tomography; Eyes; Face detection; Mouth; Principal component analysis; Teeth; Tracking;
Conference_Titel :
Automatic Face and Gesture Recognition, 2000. Proceedings. Fourth IEEE International Conference on
Conference_Location :
Grenoble
Print_ISBN :
0-7695-0580-5
DOI :
10.1109/AFGR.2000.840679