A daily human behavior identification method based on a depth convolution neural network

Abstract

The invention discloses a daily human behavior identification method based on a depth convolution neural network, which is characterized in that the method comprises the following steps: S1, establishing a depth convolution neural network model; 2, acquiring and preprocessing the human body image; 3, extracting human body image features through a depth convolution neural network model; S4, outputting a human body behavior sequence through the human body image features; 5, classifying the human behavior sequence to obtain a classification result. The invention extracts the features of the humanbody image through the depth convolution neural network, and then cooperates with the classifier to classify the features, so as to quickly and accurately recognize and classify the daily human bodybehavior.

Description

technical field [0001] The present invention relates to the field of deep learning, and more specifically, relates to a daily human behavior recognition method based on a deep convolutional neural network. Background technique [0002] At present, as an important branch of computer vision, human behavior recognition technology can be widely used in intelligent video surveillance, robot vision, human-computer interaction, game control, etc., with broad application market prospects. At present, methods based on overall features, methods based on models, and methods based on deep learning are commonly used, and studies have shown that people can recognize the behavior of the human body through some points that describe the movement of the main joints of the human body. And experiments have shown that a large number of human behaviors can be fully identified from the joints. Human Behavior Recognition Technology [0003] Since the success of the convolutional neural network bu...

AI Technical Summary

Problems solved by technology

At present, there is no mature solution to apply deep convolutional neural network to human behavior recognition technology, which cannot further improve the accuracy of human behavior recognition.

Images