Semantic Reasoning for Scene Interpretation

Jensen L. B. W., Baseski E., Kalkan S., Pugeault N., Woergoetter F., Krueger N.

4th International Cognitive Vision Workshop (ICVW 2008), Santorini, Greece, 12 - 15 May 2008, vol.5329, pp.121-123 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 5329
  • Doi Number: 10.1007/978-3-540-92781-5_10
  • City: Santorini
  • Country: Greece
  • Page Numbers: pp.121-123
  • Keywords: cognitive vision, semantic reasoning, bayesian classification
  • Middle East Technical University Affiliated: No


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.