The CogVis Project

The CogVis project (Cognitive Vision) was a European Union funded collaborative project which ran from 2001 to 2004 (Contract IST-2000-29375) to study the design of Cognitive Vision Systems. In this context a "cognitive vision system" is defined as a system that uses visual information to achieve:

Recognition and categorisation of objects, structures and events
Learning and adaptation
Memory and representation of knowledge
Control and attention

The Leeds branch of the consortium was involved in the analysis of temporal events and the incorporation of Qualitative Spatial Reasoning (QSR) into practical machine vision systems, in collaboration with the KRR research group. This resulted in research including the following four topics:

Protocol learning	Combining continuous and symbolic models to learn games from observation
Temporal Continuity	Enforcing global spatio-temporal consistency to enhance reliability of moving object tracking and classification
Traffic interaction	Modelling traffic interaction using learnt qualitative spatio-temporal relations and variable length Markov models
Car/blob tracking	A generic object tracker, demonstrated tracking vehicles

CogVis consortium

The consortium homepage may be found here. Institutions making up the consortium are:

Royal Institute of Technology (KTH), Stockholm, Sweden
Hamburg University (CSL), Hamburg, Germany
Max-Planck Institute for Biological Cybernetics (MPIK), Tuebingen, Germany
University of Leeds, Leeds, UK
Sistemistica e Telematica (DIST), Genova, Italy
Swiss Federal Institute of Technology (ETH), Zurich, Switzerland
University of Ljubljana, Ljubljana, Slovenia

Leeds contributors

Professor David Hogg
Professor Anthony Cohn
Dr Brandon Bennett
Dr Derek Magee
Dr Aphrodite Galata
Dr Vincent Devin
Dr Paulo Santos
Dr Chris Needham

Software

Various pieces of software developed under this project are available for download.

Deliverables

3.4

FINAL Deliverables

Review Meetings Talks Slides

Leeds, June 2003.

Leeds Publications

Needham, Chris J; Santos, Paulo E; Magee, Derek R; Devin, Vincent; Hogg, David C; Cohn, Anthony G. Protocols from perceptual observations. Artificial Intelligence, vol. 167, pp. 103-136. 2005.(PDF)

Magee, D R; Needham, C J; Santos, P E; Rao, S. Inducing the focus of attention by observing patterns in space in: IJCAI Workshop on Modelling Others from Observations (MOO 2005), pp. 47-52. 2005. (PDF)

Bennett, B; Magee, D; Cohn, A G; Hogg, D C. Using spatio-temporal continuity constraints to enhance visual tracking of moving objects in: Lopez de Mantaras, R & Saitta, L (editors) ECAI 2004 Proceedings of the 16th European Conference on Artificial Intelligence, pp. 922-926 IOS Press. 2004. (PDF)

Magee, D. Tracking multiple vehicles using foreground, background and motion models. Image and Vision Computing, vol. 22, pp. 143-155. 2004.

Magee, D R; Needham, C J; Santos, P; Cohn, A G; Hogg, D C. Autonomous learning for a cognitive agent using continuous models and inductive logic programming from audio-visual input in: Proceedings AAAI-04 Workshop on Anchoring Symbols to Sensor Data, pp. 17-24. 2004. (PDF)

Santos, P; Magee, D; Cohn, A G. Looking for logic in vision in: Proceedings Eleventh Workshop on Automated Reasoning, pp. 61-62. 2004.

Santos, Paulo; Magee, Derek; Cohn, Anthony; Hogg, David. Combining multiple answers for learning mathematical structures from visual observation in: Lopez de Mantaras, R & Saitta, L (editors) ECAI 2004 Proceedings of the 16th European Conference on Artificial Intelligence, pp. 544-548 IOS Press. 2004. (PDF)

Cohn, A G; Magee, D; Galata, A; Hogg, David; Hazarika, S. Towards an architecture for cognitive vision using qualitative spatio-temporal representations and abduction in: Freksa, C, Brauer, W, Habel, C & Wender, K F (editors) Spatial Cognition III, Routes and Navigation, Human Memory and Learning, Spatial Representation and Spatial Learning, pp. 232-248 Springer-Verlag. 2003. (PDF)

Magee, D. A sequential scheduling approach to combining multiple object classifiers using cross-entropy in: Windeatt, T & Roli, F (editors) Multiple Classifier Systems, pp. 135-145 Springer-Verlag. 2003. (PDF)

Magee, D; Liebe, B. Online face tracking using a feature driven level-set in: Harvey, R, & Bangham, A (editors) Proceedings of the 14th British Machine Vision Conference , pp. 419-428 BMVA. 2003.

Magee, D. Tracking multiple vehicles using foreground, background and motion models in: Proceedings ECCV Workshop on Statistical Methods in Video Processing, pp. 7-12. 2002. Available as a Research Report.

Magee, D. A qualitative, multi-scale grammar for image description and analysis in: British Machine Vision Conference 2002, pp. 293-302. 2002.

Galata, Aphrodite; Cohn, Anthony G; Magee, Derek; Hogg, David. Learning temporal and qualitative spatial components of an interaction model in: Proceedings ECCV Workshop on Vision and Modelling of Dynamic Scenes (VAMODS). 2002.

Galata, Aphrodite; Cohn, Anthony G; Magee, Derek; Hogg, David. Modeling interaction using learnt qualitative spatio-temporal relations and variable length Markov models in: van Harmelen, F (editors) Proceedings of the 15th European Conference on Artificial Intelligence (ECAI'02), pp. 741-745. 2002. (PDF)

[Vision Group Webpage] [The School of Computing] [The University of Leeds]