An approach to active vision based on information theory and statistical mechanics is presented. Density of entropy production measured along a spatio-chromatic diffusion of a colour image is used to build a conspicuity map of the image. The map is successively given as input to a dynamic neural network in order to drive a focus-of-attention scanpath.
An information-theoretic approach to active vision
01.01.2001
645403 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
An Information-Theoretic Approach to Active Vision
British Library Conference Proceedings | 2001
|Particle filter based information-theoretic active sensing
Tema Archiv | 2010
|Information-Theoretic Active Polygons for Unsupervised Texture Segmentation
British Library Online Contents | 2004
|An information-theoretic approach to analyzing CLEAN
IEEE | 2014
|