Machine Learning for Vision-based Motion Analysis

 

A Book Edited by

Dr. Liang Wang, The University of Melbourne, Australia

Dr. Guoying Zhao, University of Oulu, Finland 

Dr. Li Cheng, TTI-Chicago, USA

Prof. Matti Pietikäine, University of Oulu, Finland

　

                

 

Introduction
　

Vision-based motion analysis aims to detect, track and identify objects, and more generally, to understand their behaviors, from video sequences. With the ubiquitous presence of video data and the increasing importance in a wide range of real-world applications such as visual surveillance, human-machine interfaces and sport event interpretation, it is becoming increasingly demanding to automatically analyze and understand object motions from large amount of video footage.

        Not surprisingly, this exciting research area has received growing interest in recent years. Although there has been much progress in the past decades, many challenging problems remain unsolved, e.g., robust object detection and tracking, unconstrained object activity recognition, etc. Recently, statistical machine learning algorithms, such as manifold learning, probabilistic graphical models and kernel machines, have been successfully applied in this area for object tracking, activity modeling and recognition. It is fully believed that novel statistical learning technologies have strong potential to further contribute to the development of robust yet flexible vision systems. The process of improving the performance of vision systems has also brought new challenges to the field of machine learning, e.g., learning from partial or limited annotations, online and incremental learning, and learning with very large datasets. Solving the problems involved in object motion analysis will naturally lead to the development of new machine learning algorithms. In return, new machine learning algorithms are able to address more realistic problems in object motion analysis and understanding.

 

 

Objective of the Book

This edited book will highlight the development of robust and effective vision-based motion understanding systems from a machine learning perspective. Major contributions of this book are as follows:  (1) It will provide new researchers with a comprehensive review of the recent development in this field, and present a variety of study cases where the state-of-the-art learning algorithms are devised to address specific tasks in human motion understanding; (2) It will give the readers a clear picture of the most active research forefronts and discussions of challenges and future directions, which different levels of researchers might find to be useful for guiding their future research. (3) It will draw great strength from the research communities of human motion understanding and machine learning and demonstrates the benefits from the interaction and collaboration of both fields.

 

Target Audience

The targeted audiences are mainly researchers, engineers as well as graduate students in the areas of computer vision and machine learning. The book is also intend to be accessible to a broader audience including practicing professionals working with specific vision applications such as surveillance, sport event analysis, healthcare, video conferencing, and motion video indexing and retrieval.

 

　

This book aims to solicit those research contributions that address vision-based object motion by using machine learning approaches.

　

Recommended topics include, but are not limited to, the following:

 1) Machine Learning Theories

′         Supervised/unsupervised/semi-supervised learning

′         Generative and discriminative approaches

′         Probabilistic graphical models and exponential families

′         Large-margin methods with structured output

′         Manifold learning

′         Kernel machines

′         Online and incremental learning

2) Vision-based Motion Analysis and Understanding

3) Machine Learning in Motion Analysis and Understanding

 

Submission Procedure

Researchers and practitioners are invited to submit on or before July 31, 2009, a 2-3 page chapter proposal clearly explaining the mission and concerns of the proposed chapter, together with a tentative title and chapter organization. Proposals will be accepted based on pertinence criteria and topic balancing needs. Authors of accepted proposals will be notified by August 15, 2009 about the status of their proposals and sent chapter guidelines. Full chapters are expected to be submitted no later than Dec. 15, 2009. All submitted chapters will be reviewed on a double-blind review basis. The book is scheduled to be published in the advanced in PR series by Springer, http://springer.com.

 

Author Information

The springer format (templates) can be found at:

http://www.springer.com/authors/manuscript+guidelines?SGWID=0-40162-12-357799-0.
　

　

Important Dates

Inquiries and submissions can be forwarded electronically (Word document) or by mail to:

 

Dr. Liang Wang

Department of Computer Science & Software Engineering

The University of Melbourne, Parkville, Vic 3010, Melbourne, Australia

Tel.: +61 3 8344 1364 • Fax: +61 3 9348 1184

Email: lwwang@csse.unimelb.edu.au

 

Dr. Guoying Zhao
Department of Electrical and Information Engineering
P.O.Box 4500 FI-90014 University of Oulu, Finland
Phone: +358 8 553 7564 •  Fax: +358 8 553 2612
Email: gyzhao@ee.oulu.fi

　

Dr. Li Cheng

TTI-Chicago, USA

Tel: +1 773 834 6840

 Email: chengli@ieee.org

　

Prof. Matti Pietikäinen

University of Oulu, Finland

Tel: +358 8 553 2782

 Email: mkp@ee.oulu.fi