July 13 – 18 , 2008, Dagstuhl Seminar 08291

Statistical and Geometrical Approaches to Visual Motion Analysis. 14th Workshop “Theoretic Foundations of Computer Vision”


Daniel Cremers (Universität Bonn, DE)
Bodo Rosenhahn (Leibniz Universität Hannover, DE)
Alan L. Yuille (UCLA, US)

For support, please contact

Dagstuhl Service Team


Dagstuhl Seminar Proceedings DROPS
List of Participants
Dagstuhl's Impact: Documents available

Press Room

Seminar Program


Motion analysis is central to both human and machine vision. It involves the interpretation of image data over time. It is crucial for a range of motion tasks such as obstacle detection, depth estimation, video analysis, scene interpretation, video compression and other applications. Motion analysis is difficult because it requires modeling the complicated relationships between the observed image data and the motion of objects and motion patterns (e.g. falling rain) in the visual scene.

This workshop was focused on critical aspects of motion analysis, including motion segmentation and the modeling of motion patterns. The aim was to gather researchers who are experts in the different motion tasks and in the different techniques used. These techniques include variational approaches, level set methods, probabilistic models, graph cut approaches, factorization techniques, and neural networks. All these techniques can be subsumed within statistical and geometrical frameworks.

We also involved experts in the study of human and primate vision. Primate visual systems are extremely sophisticated at processing motion so there is much to be learnt from studying them. In particular, we wanted to relate the computational models of primate visual systems to those developed for machine vision. Here, several researchers from the cognitive sciences and biologically inspired vision rounded off the overall high quality of presentations and discussions.

Another important component of the workshop was to develop datasets of image sequences with the associated motion ground truth. These datasets can be used as benchmarks to compare the performance of motion analysis models. They can also be used as data to train statistical models of motion analysis. Datasets with ground truth are being increasingly used in other aspects of machine vision but, at present, there are only very limited motion datasets (e.g. the Yosemite sequence). Here we would like to point out the empeda test sequences, available at or several discussions about the current optic flow benchmark at middlebury

We made the seminar interactive with plenty of time for discussion. The participants were also encouraged to exchange different modeling techniques and research experiences. We have also identified outstanding unsolved problems in motion analysis and discussed them during highly active group meetings. The participants of this seminar enjoyed the atmosphere and the services at Dagstuhl very much. The quality of this center is unique. It was also a pleasure for the organizers to be involved in a radio interview of the extit{Computer Club Zwei}.

There will be an edited book (within Springer's series on Lecture Notes of Computer Science, LNCS) following the seminar, and all seminar participants have been invited to contribute with chapters. The deadline for those submissions is in November 2008 (allowing to incorporate results or ideas stimulated by the seminar), and submissions will be reviewed (as normal). Expected publication date is 2009.

Dagstuhl Seminar Series


  • Computer Graphics / Computer Vision


  • Motion Analysis
  • Statistical Methods
  • Computational Geometry


In the series Dagstuhl Reports each Dagstuhl Seminar and Dagstuhl Perspectives Workshop is documented. The seminar organizers, in cooperation with the collector, prepare a report that includes contributions from the participants' talks together with a summary of the seminar.


Download overview leaflet (PDF).

Dagstuhl's Impact

Please inform us when a publication was published as a result from your seminar. These publications are listed in the category Dagstuhl's Impact and are presented on a special shelf on the ground floor of the library.


Furthermore, a comprehensive peer-reviewed collection of research papers can be published in the series Dagstuhl Follow-Ups.