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.

[1]  Hans-Hellmut Nagel,et al.  On the Estimation of Optical Flow: Relations between Different Approaches and Some New Results , 1987, Artif. Intell..

[2]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[3]  E. Mucke.  Shapes and implementations in three-dimensional geometry , 1993 .

[4]  Peter Kovesi,et al.  Image Features from Phase Congruency , 1995 .

[5]  Les A. Piegl,et al.  The NURBS Book , 1995, Monographs in Visual Communication.

[6]  Les A. Piegl,et al.  The NURBS book (2nd ed.) , 1997 .

[7]  Alain Trémeau,et al.  Regions adjacency graph applied to color image segmentation , 2000, IEEE Trans. Image Process..

[8]  Michael Felsberg,et al.  The monogenic signal , 2001, IEEE Trans. Signal Process..

[9]  Edwin R. Hancock,et al.  Graph-Based Methods for Vision: A Yorkist Manifesto , 2002, SSPR/SPR.

[10]  Markus Lappe,et al.  Biologically Motivated Multi-modal Processing of Visual Primitives , 2003 .

[11]  W..  Relative Neighborhood Graphs and Their Relatives , 2004 .

[12]  Fabio Solari,et al.  Compact (and accurate) early vision processing in the harmonic space , 2007, VISAPP.

[13]  Sinan Kalkan,et al.  Perceptual Operations and Relations between 2D or 3D Visual Entities , 2007 .

[14]  Danica Kragic,et al.  Early reactive grasping with second order 3D feature relations , 2007 .

[15]  Gudrun Klinker,et al.  Splitting the Scene Graph - Using Spatial Relationship Graphs Instead of Scene Graphs in Augmented Reality , 2008, GRAPP.

[16]  Nicolas Pugeault,et al.  Early cognitive vision: feedback mechanisms for the disambiguation of early visual representation , 2008 .

[17]  Yan Shi,et al.  A Signal-Symbol Loop Mechanism for Enhanced Edge Extraction , 2008, VISAPP.

[18]  Luciano Vieira Dutra,et al.  Image Re-Segmentation - a New Approach Applied to Urban Imagery , 2008, VISAPP.