Human body behavior recognition method based on convolutional neural network and recurrent neural network

Abstract

The invention discloses a human body behavior recognition method based on a convolutional neural network and a recurrent neural network, and the method comprises the steps: tracking a human body behavior through a sensor, and collecting a three-dimensional coordinate vector group and an RGB video of a human body joint in a time period; training the three-dimensional coordinates of the human jointby using a recurrent neural network RNN to obtain a time feature vector; and training the RGB video by using a convolutional neural network (CNN) to obtain a space-time feature vector, finally combining the time feature vector and the space-time feature vector and normalizing, feeding the normalized space-time feature vector and the normalized space-time feature vector to a classifier of the linear SVM, finding a parameter C of the linear support vector machine (SVM) by using the verification data set, and finally obtaining a comprehensive identification model. According to the method, the problem of overfitting of action classification of the model in the model training process can be solved, and meanwhile, the human body behavior recognition efficiency and accuracy can be effectively improved.

Description

technical field [0001] The invention relates to a human behavior recognition method based on a convolutional neural network and a recurrent neural network, and belongs to the interdisciplinary technical fields of behavior recognition, deep learning, and machine learning. Background technique [0002] Behavior recognition and classification in video is an important research topic in the field of computer vision. Its wide application in video tracking, motion analysis, virtual reality and artificial intelligence interaction has become a research hotspot in the field of computer vision. [0003] Because the same action scene will be different under different lighting, viewing angle and background conditions, and the same target and action in different action scenes will have obvious differences in characteristics and postures, even in a constant action scene. Among them, human body movements also have a large degree of freedom, and each same movement has great differences in di...

AI Technical Summary

Problems solved by technology

[0006] In general TV and video images, it is often 3D video, but the technology used for behavior recognition in 3D video is not mature at present. Most human behavior recognition systems rely on manual marking and processing of data, and then put the data into the model. identify in

There is a strong dependence on data, and its system operation efficiency is low, which is not suitable for the needs of industrialization and commercialization

Images