Title :
Nonlinear motion estimation using the supercoupling approach
Author :
Bober, M. ; Petrou, M. ; Kittler, J.
Author_Institution :
Sch. of Electron. Eng., Inf. Technol. & Math., Surrey Univ., Guildford, UK
fDate :
5/1/1998 12:00:00 AM
Abstract :
This paper presents the application of a very efficient multiresolution transformation, which is related to the renormalization group approach of physics, to the problem of motion segmentation. The approach proposed is much faster and yields much better results than the full resolution approach. The problem is formulated as one of global optimization where a cost function is constructed to combine the information obtained by various processors as well as the constraints we impose to the problem. The cost function is optimized using the supercoupling multiresolution approach
Keywords :
Markov processes; image segmentation; image sequences; motion estimation; optimisation; renormalisation; Markov random fields; cost function; global optimization; image sequences; motion segmentation; multiresolution transformation; nonlinear motion estimation; renormalization group; stochastic relaxation; supercoupling; Acceleration; Computer vision; Cost function; Image motion analysis; Markov random fields; Motion analysis; Motion estimation; Motion segmentation; Probability distribution; Stochastic processes;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on