Optical flow estimation and moving object segmentation based on median radial basis function network
- 1 May 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 7 (5), 693-702
- https://doi.org/10.1109/83.668026
Abstract
Various approaches have been proposed for simultaneous optical flow estimation and segmentation in image sequences. In this study, the moving scene is decomposed into different regions with respect to their motion, by means of a pattern recognition scheme. The inputs of the proposed scheme are the feature vectors representing still image and motion information. Each class corresponds to a moving object. The classifier employed is the median radial basis function (MRBF) neural network. An error criterion function derived from the probability estimation theory and expressed as a function of the moving scene model is used as the cost function. Each basis function is activated by a certain image region. Marginal median and median of the absolute deviations from the median (MAD) estimators are employed for estimating the basis function parameters. The image regions associated with the basis functions are merged by the output units in order to identify moving objects.Keywords
This publication has 30 references indexed in Scilit:
- Object-oriented video coding employing dense motion fieldsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- An algorithm for simultaneous motion estimation and scene segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Order statistics learning vector quantizerIEEE Transactions on Image Processing, 1996
- Gibbs random fields, cooccurrences, and texture modelingIeee Transactions On Pattern Analysis and Machine Intelligence, 1994
- Multimodal estimation of discontinuous optical flow using Markov random fieldsIeee Transactions On Pattern Analysis and Machine Intelligence, 1993
- Motion-field segmentation using an adaptive MAP criterionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- An adaptive clustering algorithm for image segmentationIEEE Transactions on Signal Processing, 1992
- Motion estimation for coding of moving video at 8 kbit/s with Gibbs-modeled vectorfield smoothingPublished by SPIE-Intl Soc Optical Eng ,1990
- Nonlinear Digital FiltersPublished by Springer Science and Business Media LLC ,1990
- Probabilistic Solution of Ill-Posed Problems in Computational VisionJournal of the American Statistical Association, 1987