Motion-Based RecognitionMubarak Shah, Ramesh Jain Motion-based recognition deals with the recognition of an object and/or its motion, based on motion in a series 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-the-art in this rapidly developing discipline. 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, gait analysis, cyclic motion detection, and activity recognition. Audience: This volume will be of interest to researchers and post- graduate students whose work involves computer vision, robotics and image processing. |
Contents
VISUAL RECOGNITION OF ACTIVITIES GESTURES FACIAL EXPRESSIONS AND SPEECH AN INTRODUCTION AND A PERSPECTIVE | 1 |
Human Activity Recognition | 15 |
ESTIMATING IMAGE MOTION USING TEMPORAL MULTISCALE MODELS OF FLOW AND ACCELERATION | 17 |
LEARNING DEFORMABLE MODELS FOR TRACKING THE HUMAN BODY | 39 |
CYCLIC MOTION ANALYSIS USING THE PERIOD TRACE | 61 |
TEMPORAL TEXTURE AND ACTIVITY RECOGNITION | 87 |
ACTION RECOGNITION USING TEMPORAL TEMPLATES | 125 |
HUMAN ACTIVITY RECOGNITION | 147 |
STATEBASED RECOGNITION OF GESTURE | 201 |
REALTIME AMERICAN SIGN LANGUAGE RECOGNITION FROM VIDEO USING HIDDEN MARKOV MODELS | 227 |
RECOGNIZING HUMAN MOTION USING PARAMETERIZED MODELS OF OPTICAL FLOW | 245 |
FACIAL EXPRESSION RECOGNITION USING IMAGE MOTION | 271 |
Lipreading | 299 |
LEARNING VISUAL MODELS FOR LIPREADING | 301 |
CONTINUOUS AUTOMATIC SPEECH RECOGNITION BY LIPREADING | 321 |
VISUALLY RECOGNIZING SPEECH USING EIGENSEQUENCES | 345 |
HUMAN MOVEMENT ANALYSIS BASED ON EXPLICIT MOTION MODELS | 171 |
Gesture Recognition and Facial Expression Recognition | 199 |
Other editions - View all
Common terms and phrases
acoustic action active shape models activity algorithm analysis approach articulated automatic speech recognition camera centroid clustering components Computer Vision configuration space constraints contour corresponding covariance covariance matrix cycle cyclic motion database defined deformation described detection dynamic eigensequences eigenvectors estimate example facial expressions facial motion feature vector Figure function gesture recognition Goldschen Hidden Markov Models human motion IEEE image frame image motion image sequence input interpolation iteration Kalman filter letter linear lipreading magnitude match matrix measure method model-based motion estimation motion model motion-based recognition movement moving objects muscle optical flow oral-cavity P-value parameterized parameters patch Pattern Recognition Pentland performed period trace pixels principal curve Proc prototype curve recognize region represent representation robust rotation samples scale scenario scene segmentation Shah shape spatial spatio-temporal technique templates temporal tion tracking trajectory triseme HMMs values velocity vertical viseme visual features walking
Popular passages
Page 320 - Visual Learning and Recognition of 3D Objects from Appearance," International Journal of Computer Vision, vol.