Objective The classical approach to artificial intelligence in vision, has faced many fundamental problems. Progress was made in very specific and strictly-controlled application domains only. On the other hand, during recent years a tremendous amount of new biological evidence has been brought about by visual neuroscience which could be used for developing artificial vision systems. This project proposes a new 3D object recognition system that will reconcile state-of-the-art computer vision techniques with neurobiological and psychophysical evidence of visual perception. Active vision, i.e. including intentional observer motion in the visual process, will be implemented based on locally-autonomous and self-organising brain-style neural networks. The aim of this project is to realise a working system which can recognize many (i.e. more than 100) types of natural or everyday 3D-objects, in a way which is invariant to changes in the presentation of the objects or to the presence of structural noise in the input. Fields of science natural sciencesbiological sciencesneurobiologynatural sciencescomputer and information sciencesartificial intelligencecomputer visionnatural sciencescomputer and information sciencesartificial intelligencecomputational intelligence Programme(s) FP4-TMR - Specific research and technological development programme in the field of the training and mobility of researchers, 1994-1998 Topic(s) 0302 - Post-doctoral research training grants TM28 - Signals, Speech & Image Process., Comp.Graphics & Human Comp.Int. Call for proposal Data not available Funding Scheme RGI - Research grants (individual fellowships) Coordinator ROYAL INSTITUTE OF TECHNOLOGY Address Lindstedtsvaegen 3 100 44 Stockholm Sweden See on map EU contribution € 0,00 Participants (1) Sort alphabetically Sort by EU Contribution Expand all Collapse all Not available Belgium EU contribution € 0,00 Address See on map
