During the last decade of the twentieth century, computer vision made considerable progress towards the consolidation of its fundaments, in particular regarding the treatment of geometry for the evaluation of stereo image pairs and of multi-view image recordings. Scientists thus began to look at basic computer vision solutions - irrespective of the well-perceived need to perfection these further - as components which should be explored in a larger context.

This volume is a post-event proceedings volume and contains selected papers based on the presentations given, and the lively discussions that ensued, during a seminar held in Dagstuhl Castle, Germany, in October 2003. Co-sponsored by ECVision, the cognitive vision network of excellence, it was organized to further strengthen cooperation between research groups from different countries, and scientists active in related areas were invited from around the world.

The 18 thoroughly revised papers presented are organized in topical sections on foundations of cognitive vision systems, recognition and categorization, learning and adaptation, representation and inference, control and systems integration, and conclusions.

Includes supplementary material: sn.pub/extras

Klappentext

This volume is a post-event proceedings volume and contains selected papers based on the presentations given, and the lively discussions that ensued, during a seminar held in Dagstuhl Castle, Germany, in October 2003. Co-sponsored by ECVision, the cognitive vision network of excellence, it was organized to further strengthen cooperation between research groups from different countries working in the field of cognitive vision systems.

Inhalt
Introductory Remarks.- Introductory Remarks.- I Foundations of Cognitive Vision Systems.- The Space of Cognitive Vision.- Cognitive Vision Needs Attention to Link Sensing with Recognition.- Organization of Architectures for Cognitive Vision Systems.- Cognitive Vision Systems: From Ideas to Specifications.- II Recognition and Categorization.- A System for Object Class Detection.- Greedy Kernel Principal Component Analysis.- Many-to-Many Feature Matching in Object Recognition.- Integrating Video Information over Time. Example: Face Recognition from Video.- Interleaving Object Categorization and Segmentation.- III Learning and Adaptation.- Learning an Analysis Strategy for Knowledge-Based Exploration of Scenes.- IV Representation and Inference.- Things That See: Context-Aware Multi-modal Interaction.- Hierarchies Relating Topology and Geometry.- Cognitive Vision: Integrating Symbolic Qualitative Representations with Computer Vision.- On Scene Interpretation with Description Logics.- V Control and Systems Integration.- A Framework for Cognitive Vision Systems or Identifying Obstacles to Integration.- Visual Capabilities in an Interactive Autonomous Robot.- VI Conclusions.- On Sampling the Spectrum of Approaches Toward Cognitive Vision Systems.