Title :
Invariant features for 3-D gesture recognition
Author :
Campbell, Lee W. ; Becker, David A. ; Azarbayejani, Ali ; Bobick, Aaron E. ; Pentland, Alex
Author_Institution :
Media Lab., MIT, Cambridge, MA, USA
Abstract :
Ten different feature vectors are tested in a gesture recognition task which utilizes 3D data gathered in real-time from stereo video cameras, and HMMs for learning and recognition of gestures. Results indicate velocity features are superior to positional features, and partial rotational invariance is sufficient for good performance
Keywords :
computer vision; feature extraction; image recognition; 3D data; HMMs; feature vectors; gesture recognition; learning; partial rotational invariance; recognition; stereo video cameras; velocity features; Arm; Birds; Brushes; Cameras; Clouds; Hidden Markov models; Horses; Knee; Tail; Testing;
Conference_Titel :
Automatic Face and Gesture Recognition, 1996., Proceedings of the Second International Conference on
Conference_Location :
Killington, VT
Print_ISBN :
0-8186-7713-9
DOI :
10.1109/AFGR.1996.557258
