DocumentCode
2861607
Title
View-based interpretation of real-time optical flow for gesture recognition
Author
Cutler, Ross ; Turk, Mattew
Author_Institution
Maryland Univ., College Park, MD, USA
fYear
1998
fDate
14-16 Apr 1998
Firstpage
416
Lastpage
421
Abstract
The authors have developed a real-time, view-based gesture recognition system. Optical flow is estimated and segmented into motion blobs. Gestures are recognized using a rule-based technique based on characteristics of the motion blobs such as relative motion and size. Parameters of the gesture (e.g., frequency) are then estimated using context specific techniques. The system has been applied to create an interactive environment for children
Keywords
image recognition; image segmentation; image sequences; knowledge based systems; real-time systems; children; context specific techniques; interactive environment; motion blobs; optical flow estimation; optical flow segmentation; real-time view-based gesture recognition system; relative motion; relative size; rule-based technique; view-based real-time optical flow interpretation; Arm; Cameras; Educational institutions; Frequency estimation; Hidden Markov models; Image motion analysis; Motion estimation; Music; Real time systems; Virtual reality;
fLanguage
English
Publisher
ieee
Conference_Titel
Automatic Face and Gesture Recognition, 1998. Proceedings. Third IEEE International Conference on
Conference_Location
Nara
Print_ISBN
0-8186-8344-9
Type
conf
DOI
10.1109/AFGR.1998.670984
Filename
670984
Link To Document