Objective
The objective of this Working Group on vision was to forge a solid scientific community concerned with the problems of machine and natural vision. This community is intended to serve as a spawning ground for future European projects. The Group accomplished its objective by the organisation of meetings, workshops, conferences and scientific exchanges, as well as the publication of books.
This project was a collection of 36 institutions organised into 6 consortia. It organised meetings, workshops, and a scientific conference on topics related to computer vision. Scientific workshops were organised on computer and machine vision in topic areas proposed by member consortia. These workshops provided a forum for the presentation of research in progress, and an opportunity for the scientific community to discuss current problems and results.
The issues involved in vision based robotics systems have been addressed. It was concluded that complete autonomy, although desirable, was not practical within current restrictions. The methodology of design was discussed and it was found that common to all methodologies was intuition based upon experience in the field.
A system was developed which was capable of inspecting a 300 mm by 280 mm circuit board containing 360 components in 50 seconds and 200 components in 39 seconds, averaging 7 components per second. The system proved far more reliable than manual inspection procedures.
A skeleton system for actively maintaining an interpretation of a scene has been developed. It uses rule based recognition procedures triggered by constantly active demons, thus permitting event detection and identification.
When contextual or semantic information was available, or some interpretation of the scene was required, it was found that a combination of knowledge based and computational systems was necessary. The combined system was able to exploit artificial intelligence tools and control techniques for error recovery.
Model based tracking was used to develop a system for vehicle monitoring and proved adequate under various conditions of lighting or weather. The system relies on a prior knowledge of the objects it will encounter.
APPROACH AND METHODS
The Group organised scientific workshops on computer vision in topic areas proposed by its member consortia. These workshops provided a forum for the presentation of research in progress, and an opportunity for the scientific community to discuss current problems and results. The Group was also involved in the continuing organisation of the "European Conference on Computer Vision". The Group actively encourages the participation of representatives from other ESPRIT projects at its scientific workshops.PROGRESS AND RESULTS
The First European Conference on Computer Vision was held in Antibes in April 1990. Workshops organised so far have included:
-Control of Perception in Active Vision, Antibes, April 1990
-Real-Time Architectures for Computer Vision, Antibes, April 1990
-Learning in Vision, Antibes, April 1990
-Advanced Matching in Vision and Artificial Intelligence, Mnchen, June 1990
-From Pixels to Features II, Bonas, August 1990
-ESPRIT Vision Workshop Week, Iraklion, September 1990
-Neural Networks in Vision, Grenoble, January 1991
-Vision in Context, Kilarney, Ireland, August 1991
-BARNAIMAGE, Barcelona, September 1991
-ECCV BRA Workshops, ECCV-2, Genoa, May 1992
POTENTIAL
Fields of science
- natural sciencescomputer and information sciencesartificial intelligencecomputer vision
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringrobotics
- natural sciencescomputer and information sciencesartificial intelligencecomputational intelligence
Topic(s)
Data not availableCall for proposal
Data not availableFunding Scheme
Data not availableCoordinator
38031 Grenoble
France