Skeleton based action recognition with convolutional neural network

Temporal dynamics of postures over time is crucial for sequence-based action recognition. Human actions can be represented by the corresponding motions of articulated skeleton. Most of the existing approaches for skeleton based action recognition model the spatial-temporal evolution of actions based on hand-crafted features. As a kind of hierarchically adaptive filter banks, Convolutional Neural Network (CNN) performs well in representation learning. In this paper, we propose an end-to-end hierarchical architecture for skeleton based action recognition with CNN. Firstly, we represent a skeleton sequence as a matrix by concatenating the joint coordinates in each instant and arranging those vector representations in a chronological order. Then the matrix is quantified into an image and normalized to handle the variable-length problem. The final image is fed into a CNN model for feature extraction and recognition. For the specific structure of such images, the simple max-pooling plays an important role on spatial feature selection as well as temporal frequency adjustment, which can obtain more discriminative joint information for different actions and meanwhile address the variable-frequency problem. Experimental results demonstrate that our method achieves the state-of-art performance with high computational efficiency, especially surpassing the existing result by more than 15 percentage on the challenging ChaLearn gesture recognition dataset.