Segmentation and estimation of the optical flow
- First Online:
- Cite this paper as:
- Borş A.G., Pitas I. (1995) Segmentation and estimation of the optical flow. In: Hlaváč V., Šára R. (eds) Computer Analysis of Images and Patterns. CAIP 1995. Lecture Notes in Computer Science, vol 970. Springer, Berlin, Heidelberg
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.
Unable to display preview. Download preview PDF.