Human Action Recognition From Digital Videos Based on Deep Learning

With the development of closed-circuit television, video-based human motion recognition has made great progress. A large number of surveillance video footages have been archived. In this paper, we implement deep learning methods to resolve human action recognition problem. We propose a new method that combines Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) together, which is able to produce a better result after expansive and extensive experiments. The experimental results of this paper show that it is feasible to implement human action recognition through deep learning algorithms, the outcome is excellent. The CNN+LSTM method proposed in this paper can better recognize human actions, which is more efficient than general deep learning methods. In addition, in this paper, we compare the differences in the recognition results using deep learning methods.