Human Behavior Recognition Method Based on Quaternion Space-Time Convolutional Neural Network

Abstract

The invention belongs to the field of computer vision, and in particular relates to a human behavior recognition method based on quaternion spatiotemporal convolutional nerves. The specific implementation steps of the present invention are as follows: (1) inputting the action video set to be recognized; (2) image preprocessing to extract images of key regions of human motion; (3) constructing a quaternion spatiotemporal convolutional neural network; (4) adopting The BP algorithm trains the network and outputs the training results; (5) Input the video test set and output the test results. The present invention uses the codebook model to extract the image of the human body movement area, and can detect the movement of the human body under the condition of complex background. The quaternion spatiotemporal convolutional neural network of the present invention directly takes the color image as the input, solves the problem of missing image features in the process of converting the color image into a grayscale image or dividing the channel by the traditional convolutional neural network, and improves the network feature extraction. performance, making the recognition of human behavior more accurate.

Description

technical field [0001] The invention belongs to the field of computer vision, and further relates to a human behavior recognition method based on a quaternion space-time convolutional neural network in target recognition. The invention can be used in applications such as human-computer interaction and intelligent monitoring. Background technique [0002] Human behavior recognition is an important research direction of computer vision, pattern recognition, image processing and artificial intelligence. It has great application value and theoretical significance in the fields of human-computer interaction, intelligent monitoring and medical treatment. It mainly analyzes and processes moving image sequences containing people, extracts features, and classifies motions to realize the recognition and understanding of individual human actions, interactions between people and between people and the external environment. [0003] Compared with object classification based on still imag...

AI Technical Summary

Problems solved by technology

However, the current convolutional neural network model only processes grayscale image sequences or RGB three-channels separately, without considering the correlation and integrity of the three channels, which destroys the color characteristics of the real environment and affects the recognition method in the actual environment. robustness

Images