Simulation and Experiment of Human action Recognition Based on Convolutional Neural Network

Ge Zhang
Cyberspace Administration Center,Henan University of Economics and Law,Zhengzhou 450000, Henan, China

Abstract:

Human motion recognition, as one of the key technologies in the field of computer vision, plays a vital role in the development and progress of modern society. How to improve the accuracy of machine recognition of human movements without being affected by complex environment and target individual differences, and make it quickly and accurately understand the movement information expressed by human beings is the focus of researchers in various fields. The Kinect device released by Microsoft can collect three different types of data, among which the depth data and bone data only depend on the spatial position of the target, with color independence, and the motion recognition is less interfered by external factors, which provides great convenience for the research of human motion recognition technology. This paper analyzes the current research algorithms and achievements of human motion recognition, and realizes human motion recognition based on the depth information of Kinect.