DocumentCode :
1461779
Title :
A state-based approach to the representation and recognition of gesture
Author :
Bobick, Aaron F. ; Wilson, Andrew D.
Author_Institution :
Media Lab., MIT, Cambridge, MA, USA
Volume :
19
Issue :
12
fYear :
1997
fDate :
12/1/1997 12:00:00 AM
Firstpage :
1325
Lastpage :
1337
Abstract :
A state-based technique for the representation and recognition of gesture is presented. We define a gesture to be a sequence of states in a measurement or configuration space. For a given gesture, these states are used to capture both the repeatability and variability evidenced in a training set of example trajectories. Using techniques for computing a prototype trajectory of an ensemble of trajectories, we develop methods for defining configuration states along the prototype and for recognizing gestures from an unsegmented, continuous stream of sensor data. The approach is illustrated by application to a range of gesture-related sensory data: the two-dimensional movements of a mouse input device, the movement of the hand measured by a magnetic spatial position and orientation sensor, and, lastly, the changing eigenvector projection coefficients computed from an image sequence
Keywords :
dynamic programming; fuzzy set theory; image sequences; motion estimation; configuration states; eigenvector projection coefficients; gesture recognition; gesture representation; hand movement; image sequence; magnetic spatial position and orientation sensor; mouse input device; repeatability; state-based approach; two-dimensional movements; variability; Computer Society; Image sensors; Magnetic devices; Magnetic domains; Magnetic sensors; Mice; Motion measurement; Position measurement; Prototypes; Streaming media;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/34.643892
Filename :
643892
Link To Document :
بازگشت