26. – 31. Oktober 2003, Dagstuhl-Seminar 03441

Cognitive Vision Systems


Henrik Iskov Christensen (Georgia Institute of Technology – Atlanta, US)
Hans-Hellmut Nagel (KIT – Karlsruher Institut für Technologie, DE)

Auskunft zu diesem Dagstuhl-Seminar erteilt

Dagstuhl Service Team


Dagstuhl's Impact: Dokumente verfügbar


Early attempts to integrate AI and Computer Vision failed due to lack of robust vision techniques for the derivation of symbolic descriptions of the `meaning' of images, and the lack of AI techniques to handle information with associated uncertainty. Over the last decade, significant progress has been achieved in Computational Vision, AI, and computer platforms.

Regarding Computational Vision, the basis in terms of generating a representation of the system environment through use of robust methods is not yet particularly strong. At the same time, the AI community has established new paradigms for handling uncertain information and scalable models. In parallel to these developments, the progress in the design and production of highly integrated circuits and computer programming systems has resulted in a system performance that facilitates real-time generation and processing of information even from video input streams.

The seminar discussed models for Cognitive Vision Systems (CVS) in terms of system layout and components. In addition, both Computer Vision and AI techniques as components of systems were presented. This seminar also involved discussions on the conceptual basis for Cognitive Vision and the feasibility of constructing computational systems that have `cognitive' functionality.

The presentations at the meeting will be summarised in a book to be published by Springer-Verlag together with reports from the round-table discussions. The outcome is expected to be a key component of a roadmap towards definition of a long-term research strategy for cognitive vision systems.

Dagstuhl-Seminar Series


  • Computer vision
  • Cognitive vision
  • Embedded computer vision systems
  • Machine learning and vision
  • Conceptual representations
  • Spatiotemporal logic and computer vision
  • Autonomous vision-guided robots


In der Reihe Dagstuhl Reports werden alle Dagstuhl-Seminare und Dagstuhl-Perspektiven-Workshops dokumentiert. Die Organisatoren stellen zusammen mit dem Collector des Seminars einen Bericht zusammen, der die Beiträge der Autoren zusammenfasst und um eine Zusammenfassung ergänzt.


Download Übersichtsflyer (PDF).

Dagstuhl's Impact

Bitte informieren Sie uns, wenn eine Veröffentlichung ausgehend von Ihrem Seminar entsteht. Derartige Veröffentlichungen werden von uns in der Rubrik Dagstuhl's Impact separat aufgelistet  und im Erdgeschoss der Bibliothek präsentiert.


Es besteht weiterhin die Möglichkeit, eine umfassende Kollektion begutachteter Arbeiten in der Reihe Dagstuhl Follow-Ups zu publizieren.