Date: 08 Jun 2005

Segmentation and estimation of the optical flow

* Final gross prices may vary according to local VAT.

Get Access

Abstract

We propose an algorithm for simultaneous estimation and segmentation of the optical flow. The moving scene is decomposed in different regions with respect to their motion, by means of a pattern recognition scheme. The feature vectors are drawn from the image sequence and they are used to train a Radial Basis Functions (RBF) neural network. The learning algorithm for the RBF network minimizes a cost function derived from the probability estimation theory. The proposed algorithm was applied in real image sequences.