Statistical and Geometrical Approaches to Visual Motion Analysis

This workshop is focused on critical aspects of motion analysis, including motion segmentation and the modeling of motion patterns. The aim is 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 will also involve 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 want to relate the computational models of primate visual systems to those developed for machine vision.

Another important component of the workshop is to develop datasets of image sequences with the associated motion groundtruth. 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 groundtruth 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).

We intend to make the seminar very interactive with plenty of time for discussion. The participants will be encouraged to exchange different modeling techniques and research experiences. We will also intend to identify the outstanding unsolved problems in motion analysis and determine strategies for solving them.

This seminar is intended to focus on these aspects, and to support establishments of future research collaborations. There will be an edited book following the seminar, and all seminar participants will be invited to contribute with chapters. The deadline for those chapters will be in September 2008 (allowing to incorporate results or ideas stimulated by the seminar), and submissions will be reviewed (as normal).

13th (2006): Human Motion - Understanding, Modeling, Capture and Animation: proceedings published in 2008 by Springer. (ed. B. Rosenhahn, R. Klette and D. Metaxas)
12th (2004): Imaging Beyond the Pinhole Camera: proceedings published in 2006 by Kluwer, (ed. K. Daniilidis and R. Klette).
11th (2002): Geometry, Morphology, and Computational Imaging: proceedings published in 2003, LNCS 2616, Springer (ed. T. Asano, R. Klette, Ch. Ronse).
10th (2000): LNCS 2032, published in 2001 (ed. by R. Klette, Th. Huang and G. Gimel'farb).
9th (1998): Evaluation and Validation of Computer Vision Algorithms: proccedings published in 2000 (ed. by R. Klette, S. Stiehl, M. Viergever and K. Vincken), Kluwer, Amsterdam.
8th (1996): Advances in Computer Vision (ed. by F. Solina, W. Kropatsch, R. Klette and R. Bajcsy), Advances in Computing Science, Springer Wien New York, 1997 (ISSN 1433-0113).
7th (1994): Theoretical Foundations of Computer Vision (ed. by W. Kropatsch, R. Klette and F. Solina), Computing Supplement 11, Springer Wien New York, 1996 (ISSN 0344-8029).
6th (1992): Theoretical Foundations of Computer Vision (ed. by R. Klette and W. Kropatsch), Mathematical Research, Akademie Verlag Berlin, 1992 (ISSN 0138-3019).
5th (1990): Theoretische Grundlagen der Digitalen Bildverarbeitung, Mägdesprung/Harz
(no proceedings published).
4th (1988): Theoretische Grundlagen der Digitalen Bildverarbeitung (ed. by R. Klette and W.-D. Klix), Heft 104/88, Technische Universität Dresden, Sektion Mathematik, 1988.
3rd (1986): Digitale Bildverarbeitung (Theoretische Grundlagen) (ed. by R. Klette and W.-D. Klix), Heft 93/86, Technische Universität Dresden, Sektion Mathematik, 1986.
2nd (1984): Methoden und Algorithmen der Digitalen Bildverarbeitung (ed. by R. Klette and W.-D. Klix), Heft 77/84, Technische Universität Dresden, Sektion Mathematik, 1984.
1st (1982): Digitale Bildverarbeitung (ed. by R. Klette and W.-D. Klix), Heft 60/82, Technische Universität Dresden, Sektion Mathematik, 1982.