Hide menu

Gösta H. Granlund

Research Interests

The research of the Computer Vision Laboratory is on methods which will allow systems to `see', i.e. interpret image information Such systems are increasingly used in robotics, industrial automation, visual communication, medical image processing and analysis, quality inspection, surveillance, etc.

The processing is either intended to generate an enhanced version of an image or from an entire data set such as a tomographic data volume. Or it is intended to generate autonomous physical actions, such as for a robot.

The direction of research at CVL has been on methods for development of the complex models required for a cognitive system to understand a complex world. It is a firm belief that systems have to be organized in a hierarchical or pyramid manner, where lower level operation outputs feed into higher level operations. Similarly, higher level information will be used for control of lower level operations in the form of context. Learning has to be used to overcome the immense complexity in specification of a multiplicity of partly overlapping models in dependence upon context. This generates particular demands upon the information representation, to allow information to be communicated and usable at levels different from where it was generated.

Percept-response pyramid

It is argued that information must be acquired actively by the system itself, through response driven association with percept transformations. After an active training, however, the system can exhibit a reactive behavior to passively observed percepts. From this derives our view that the development of powerful Cognitive Vision structures inevitably has to go the path over Active Vision, Learning and Robotics, even if the systems will be used for interpretation of static imagery.

Action-description sequence

For a brief description of our present research work (in Swedish) please look at Seende och Tolkning and Populärvetenskaplig Forskningsguide.


The CVL image database.


International Cooperation Research Projects

  • The International Consortium for Medical Imaging Technology, ICMIT
  • An exciting new development is The Foundation for Intelligent Physical Agents FIPA


Various Information


Adresses


   Office:			Home:
   Linköping University		Valhallagatan 16
   Computer Vision Laboratory	SE-582 43 Linköping
   SE-581 83 Linköping		SWEDEN
   SWEDEN			
   Phone: +46 13 281303		
   Fax:   +46 13 138526		


   Email: gosta@isy.liu.se



Page responsible: Gösta H. Granlund
Last updated: 2012-06-16