US:
Kluwer Academic Publishers
101 Philip Drive, Norwell, MA 02061, USA

Europe:
Kluwer Academic Publishers
P.O. Box 322, 3300 AH Dordrecth, The Netherlands

Motion-based recognition deals with the recognition of an object and or its motion based on motion in a sequence of images. In this approach, a sequence containing a large number of frames is used to extract motion information. The advantage is that a longer sequence leads to recognition of higher level motions, like walking or running, which consist of a complex and coordinated series of events Unlike much previous research in motion, this approach does not require explicit reconstruction of shape from the images prior to recognition.

This book provides the state of art in in this rapidly growing area. It consists of a collection of invited chapters by leading researchers in the world covering various aspects of motion-based recognition including: lipreading, gesture recognition, facial expression recognition, cyclic motion detection, and activity recognition.

1. Visual Recognition of Activities, Gestures, Facial Expressions and Speech: An Introduction and a Perspective, Mubarak Shah and Ramesh Jain, UCF and UCSD.

   PART I

   Human Activity Recognition

2. Estimating Image Motion using Temporal Multi-scale Optical Flow and acceleration, Yaser Yacoob and Larry Davis, Maryland.
3. Learning Deformable models for tracking the human body, Adam Baumberg and David Hogg, Leeds.
4. Cyclic Motion Analysis Using Periodic Trace, Steven M Seitz and Charles R. Dyer, University of Wisconsin.
5. Temporal Texture and Activity Recognition, Ramprasad Polana and Randal Nelson, University of Rochester.
6. Action Recognition Using Temporal Templates, Aaron Bobick and Jim Davis, MIT.
7. Human Activity Recognition, N. Goddard, Pittsburgh Supercomputing Center.
8. Recognition of Human Movements Based on Explicit Motion Models, K. Rohr, Germany.

   PART II

   Gesture Recognition And Facial Expression Recognition

9. State-based recognition of gesture, Aaron Bobick and Andy Wilson, MIT.
10. Real-Time American Sign Language From Video Using Hidden Markov Models, Thad Starner and Alex Pentland, MIT.
11. Recognizing Human Motion using Parameterized Models of Optical Flow, M. J. Black, Y. Yacoob, and S. X. Ju, Maryland, Xerox PARC.
12. Facial Expression Recognition Using Image Motion, Irfan Essa and Alex Pentland, MIT.

    PART III

    Lipreading

13. Learning Visual Models for Lipreading, Christopher Bregler and Stephen M. Omohundro, Berkeley, and NEC.
14. Continuous Automatic Speech Recognition by Lipreading, Alan J. Goldschen, MITRE, Eric D. Petajan, ATT, and Oscar N. Garcia Wright State University.
15. Visually Recognizing Speech Using Eigen Sequences, Li Nan, Shawn Dettmer and Mubarak Shah, UCF.