Workshop: From features to actions - Unifying perspectives in computational and robot vision

Objectives Paper submission Program Registration Organizers and contact

Date: April, 10 (Tuesday)
Time: 8.30 - 18.00
Place: Sala Chiostro

The field of computer vision has developed significantly over the past few years and its importance for robotics is also growing. Due to many practical applications in a diverse variety of sub-disciplines, such as surveillance, robot control, and virtual environments, vision algorithms have a significant application impact. The robotics and computer vision communities have, however, remained largely separate. Dialog between the two communities would then contribute greatly to the progress in both disciplines. In many cases, methods available in the computer vision community are not in general use in the robotics community. On the other hand, the system level perspective is often neglected in the computer vision community, because the research is focused on individual problems and algorithms. There is consequently a need to bring the communities of robot and computer vision to a joint appreciation of the value of systems, where there is a need to consider all aspects from perception to action generation. This workshop is intended to highlight the problems and new approaches to the above issues by bringing together computer vision and robotics researchers.


Invited speakers:
Prof. Jiri Matas (Czech Technical University, Czech Republic)
Prof. David Hogg (University of Leeds, UK)
Prof. James Little (University of British Columbia, Canada)
Prof. Norbert Kruger (Sydansk University, Danmark)

Detailed program with the list of speakers and abstracts.


There are many characteristics in common in computer vision research and vision research in robotics. For example, the Structure-and-Motion problem in vision has its analog of SLAM (Simultaneous Localization and Mapping) in robotics, visual SLAM being one of the current hot topics. Tracking is another area seeing increased interest in both communities, in its many variations, such as 2-D and 3-D tracking, single and multi-object tracking, rigid and deformable object tracking. Other topics of interest for both communities are object and action recognition.

Despite having these common interests, however, "pure" computer vision has seen significant theoretical and methodological advances during the last decade which many of the robotics researchers are not fully aware of. On the other hand, the manipulation and control capabilities of robots as well as the range of application areas have developed greatly. In robotics, vision can not be considered an isolated component, but it is instead a part of a system resulting in an action. Thus, in robotics the vision research must include consideration of the control of the system, in other words, the entire perception-action loop. This requires that a holistic system approach is useful and could provide significant advances in this application domain.

We believe that although there have been good examples of robust vision systems, there is a gap between the research conducted in computer vision and robotics communities. This workshop aims to bring together researchers in computer vision and robotics to encourage dialog, demonstrate novel approaches and highlight current challenges in computational and robot vision.

The topics covered in the workshop may include, but are not limited to, recent advances and challenges in:

  • visual SLAM and Structure-and-Motion
  • cognitive vision systems and vision for humanoid robots
  • visual tracking
  • action learning and recognition
  • object recognition
  • active control of imaging process
  • benchmarking issues
Paper submission



Is available through ICRA 2007 web

Organizers and contact
Danica Kragic Ville Kyrki
Centre for Autonomous Systems
Royal Institute of Technology
Lappeenranta University of Technology
Department of Information Technology

Danica Kragic
10044 Stocholm, Sweden
Phone: +468 7906729, Fax: +468 7230302

For any further information, please contact the organizers at (dani at kth dot se)