Semantic Reasoning for Scene Interpretation
In this paper, we propose a hierarchical architecture for representing scenes, covering 2D and 3D aspects of visual scenes as well as the semantic relations between the different aspects. We argue that labeled graphs are a suitable representational framework for this representation and demonstrate its potential by two applications. As a first application, we localize lane structures by the semantic descriptors and their relations in a Bayesian framework. As the second application, which is in the context of vision based grasping, we show how the semantic relations can be associated to actions that allow for grasping without using any object knowledge.
Keywordscognitive vision semantic reasoning bayesian classification
Unable to display preview. Download preview PDF.
- 1.Aarno, D., Sommerfeld, J., Kragic, D., Pugeault, N., Kalkan, S., Wörgötter, F., Kraft, D., Krüger, N.: Early reactive grasping with second order 3D feature relations. In: Lee, S., Suh, I.H., Kim, M.S. (eds.) Recent Progress in Robotics; ViableRobotic Service to Human, ICAR 2007. LNCIS. Springer, Heidelberg (2007)Google Scholar
- 2.Echtler, F., Huber, M., Pustka, D., Keitler, P., Klinker, G.: Splitting the scene graph – using spatial relationship graphs instead of scene graphs in augmented reality. In: GRAPP 2008: Int. Conference on Computer Graphics Theory and Applications (2008)Google Scholar
- 4.Mucke, E.P.: Shapes and implementations in three-dimensional geometry. Technical report, University of Illinois at Urbana-Champaign, Champaign, IL, USA (1993)Google Scholar
- 5.Korting, T.S., Fonseca, L.M.G., Dutra, L.V., da Silva, F.C.: Image re-segmentation – a new approach applied to urban imagery. In: VISAPP 2008: Int. Conference on Computer Vision Theory and Applications (2008)Google Scholar
- 8.Kovesi, P.: Image features from phase congruency. Videre: Journal of Computer Vision Research 1(3), 1–26 (1999)Google Scholar
- 10.Sabatini, S.P., Gastaldi, G., Solari, F., Diaz, J., Ros, E., Pauwels, K., Hulle, K.M.M.V., Pugeault, N., Krüger, N.: Compact and accurate early vision processing in the harmonic space. In: International Conference on Computer Vision Theory and Applications (VISAPP) (2007)Google Scholar
- 12.Krüger, N., Lappe, M., Wörgötter, F.: Biologically motivated multi-modal processing of visual primitives. Interdisciplinary Journal of Artificial Intelligence & the Simulation of Behaviour, AISB Journal 1(5), 417–427 (2004)Google Scholar
- 13.Pugeault, N.: Early Cognitive Vision: Feedback Mechanisms for the Disambiguation of Early Visual Representation. Ph.D thesis, Informatics Institute, University of Göttingen (2008)Google Scholar
- 14.Kalkan, S., Pugeault, N., Krüger, N.: Perceptual operations and relations between 2d or 3d visual entities. Technical Report 2007-3, Technical report of the Robotics Group, Maersk Institute, University of Southern Denmark (2007)Google Scholar
- 16.Kalkan, S., Yan, S., Krüger, V., Wörgötter, F., Krüger, N.: A signal-symbol loop mechanism for enhanced edge extraction. In: VISAPP 2008: Int. Conference on Computer Vision Theory and Applications (2008)Google Scholar
- 18.Popović, M.: An early grasping reflex in a cognitive robot vision system. Master’s thesis, University of Southern Denmark (2008)Google Scholar