Representations for Cognitive Vision: a Review of Appearance-Based, Spatio-Temporal, and Graph-Based Approaches
- Autores: Axel Pinz, Horst Bischof, Walter Kropatsch, Gerald Schweighofer, Yll Haxhimusa, Andreas Opelt, Adrian Ion
- Localización: ELCVIA. Electronic letters on computer vision and image analysis, ISSN-e 1577-5097, Vol. 7, Nº. Extra 2, 2008 (Ejemplar dedicado a: Special Issue on Computational Modelling of Objects Represented in Images), págs. 35-61
- Idioma: inglés
- Enlaces
-
Resumen
The emerging discipline of cognitive vision requires a proper representation of visual information includingspatial and temporal relationships, scenes, events, semantics and context. This review article summarizesexisting representational schemes in computer vision which might be useful for cognitive vision,and discusses promising future research directions. The various approaches are categorized according toappearance-based, spatio-temporal, and graph-based representations for cognitive vision. While the representationof objects has been covered extensively in computer vision research, both from a reconstructionas well as from a recognition point of view, cognitive vision will also require new ideas how to representscenes. We introduce new concepts for scene representations and discuss how these might be efficiently implemented in future cognitive vision systems.
