Gesture Recognition Method Based On Deep Learning

摘要

With the rapid development of science and technology, human-computer interaction is born more frequently around us. Human motion analysis and recognition based on attitude sensor is a new field, which overcomes many shortcomings and limitations of motion recognition based on video and is more practical. In this paper, we proposes a new method based on time gesture recognition. By analyzing the kinematics of gestures, the features of gestures are extracted and classified using Recurrent Neural Networks and their variant networks. The methods achieved an accuracy of over 98% in 16 experimenters. The results show that the algorithm can quickly and accurately identify gestures.