Title :
Dynamic Shape and Appearance Models
Author :
Doretto, Gianfranco ; Soatto, Stefano
Author_Institution :
Visualization & Comput. Vision Lab, GE Global Res. Center, Niskmjuna, NY
Abstract :
We propose a model of the joint variation of shape and appearance of portions of an image sequence. The model is conditionally linear, and can be thought of as an extension of active appearance models to exploit the temporal correlation of adjacent image frames. Inference of the model parameters can be performed efficiently using established numerical optimization techniques borrowed from finite-element analysis and system identification techniques
Keywords :
computational geometry; finite element analysis; image sequences; solid modelling; active appearance models; dynamic textures; finite-element analysis; image motion; image sequence; linear dynamical systems; model parameters; numerical optimization techniques; system identification techniques; temporal correlation; video analysis; Active appearance model; Active shape model; Gaussian processes; Geometry; Image segmentation; Image sequences; Layout; Lighting; Solid modeling; Statistics; Active appearance models; dynamic textures.; image motion; linear dynamical systems; video analysis; Algorithms; Artificial Intelligence; Computer Simulation; Image Enhancement; Image Interpretation, Computer-Assisted; Information Storage and Retrieval; Models, Statistical; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2006.243