Recognizing human action in time-sequential images using hiddenMarkov model
Yamato, J.; Ohya, J.; Ishii, K.
Computer Vision and Pattern Recognition, 1992. Proceedings CVPR apos;92., 1992 IEEE Computer Society Conference on
Volume , Issue , 15-18 Jun 1992 Page(s):379 - 385
Digital Object Identifier 10.1109/CVPR.1992.223161
Summary:A human action recognition method based on a hidden Markov model
(HMM) is proposed. It is a feature-based bottom-up approach that is
characterized by its learning capability and time-scale invariability.
To apply HMMs, one set of time-sequential images is transformed into an
image feature vector sequence, and the sequence is converted into a
symbol sequence by vector quantization. In learning human action
categories, the parameters of the HMMs, one per category, are optimized
so as to best describe the training sequences from the category. To
recognize an observed sequence, the HMM which best matches the sequence
is chosen. Experimental results for real time-sequential images of
sports scenes show recognition rates higher than 90%. The recognition
rate is improved by increasing the number of people used to generate the
training data, indicating the possibility of establishing a
person-independent action recognizer
View citation and abstract |
Cart
