Human action recognition by fuzzy hidden Markov model

Abstract

Hidden Markov model (HMM) has been widely applied in human action recognition. In this paper an extension of HMM called fuzzy hidden Markov model (fuzzy HMM) is used for action recognition. It tries to increase the classification performance and decrease the information loss due to feature vector quantisation. Using fuzzy concepts with HMM leads to better recognition of similar actions such as walking, jogging and running. Two feature extraction methods including skeleton and space-time approaches are used for action representation. Actions could be represented efficiently using skeleton features where scene background is plain. Space-time features are extracted directly from video, and therefore avoid possible failures of other pre-processing methods. We propose space-time-based features by considering temporal relation between them. Experimental results show the effectiveness of fuzzy HMM in human action recognition. Moreover, it is shown that fuzzy HMM leads to significant improvement in recognition of similar actions. The accuracy rates of fuzzy HMM in comparison to HMM are incremented 3.33% and 5.59% in Weizmann and KTH datasets respectively.