In this paper, we propose a novel approach for human action recognition based on motion capture (MOCAP) information using a Fuzzy convolutional neural network. The MOCAP tracking information of human joints is used to compute the temporal variation of displacement between joints during the execution of an action. Fuzzy membership functions designed to emphasize the discriminative pose associated with each action are considered for feature extraction.
The temporal variation of membership values associated with these fuzzy membership functions is considered as the feature representation for action recognition. A convolutional neural network (CNN) capable of recognizing localpatterns in input data is trained to recognize human actions from the local patterns in the feature representation. Experimental evaluation on Berkeley MHAD dataset demonstrates the effectiveness of the proposed approach.