5 Conclusions
In this paper, a novel the HDBN-based action recognition method is proposed. Our contribution can be described as:
(1) We propose a novel graph-based action recognition model. The model combines the hierarchical action semantic dictionary and Bayesian graph model inference together, and uses recursion-based method to recognize action video data.
(2) Based on some theories, such as Bayesian rules, graph model, the probability-based recursion calculation structure is presented to obtain the higher accuracy of action recognition. Experimental results show that the proposed model has better performance than some existing algorithms.
