KomForm
Research Project KomForm
Subject
Component-based form descriptions from perceptual grouping for the application to viewer-centered 3D object recognition
Abstract
As active computer vision systems are motivated by the visual systems of intelligent beings, they are designed to autonomously explore their environments, to deduce task dependent information and to develop intelligent behaviour in case of unexpected events. Starting from object recognition methods implemented in an existing active vision system, this project will continue the development of a biologically motivated object representation scheme. Its elements view-based recognition, temporal associations, and structural descriptions turned out to be incomplete as long as single views cannot be adequately represented and recognized. It remained an unsolved problem that the matching of feature maps - despite of complex features and flexible matching approaches - does not allow sufficiently reliable comparisons between input images and stored views.
Therefore, we intend to merge recent findings about shape perception and perceptual grouping methods to derive the foundations of a shape description framework. In contrast to known approaches, we will simultaneously perform the decomposition and grouping of shapes in order to bridge gaps between image features and to handle occlusions by a multi-layered representation scheme.
Status
Completed
Partners
None
Financing
Deutsche Forschungsgemeinschaft