Human body behavior recognition method based on self-feedback gene expression programming

Abstract

The invention discloses a human body behavior recognition method based on self-feedback gene expression programming. According to the method, for a deep human body behavior image, three-dimensional time series data of a plurality of joints of the human body are extracted from the image as samples; modeling is carried out on the samples by using self-feedback gene expression programming constructed by adding a TIS insertion string operation into gene expression programming after intersection and variation, thereby obtaining a human body motion model, wherein the TIS insertion string operation indicates the operation of inserting a function string into a joint motion sequence head; and then gradient information is extracted as a model feature. The model characteristics of the human body motion model of the training sample are input to a neural network and training is carried out to obtain a neural network model as a human body behavior classifier; and model characteristic of a human body movement model corresponding to a tested sample are inputted into the obtained human body behavior classifier to obtain a human body behavior recognition result. The method has advantages of high human body behavior identification accuracy and fast identification speed.

Description

technical field [0001] The invention relates to the field of human behavior recognition, in particular to a human behavior recognition method based on self-feedback gene expression programming. Background technique [0002] In recent years, human behavior recognition research is one of the most popular frontier research topics in computer science in the world. It has important theoretical research value, and the research topics are rich in content, involving image processing and analysis, machine vision, human physiology, and human kinematics. , pattern recognition and artificial intelligence and other multidisciplinary domain knowledge. The research on human behavior recognition not only broadens the research direction between disciplines, but also drives the development of related disciplines. It is also a key technology that urgently needs to be solved in smart cities and public safety. It is widely used in human-computer intelligent interaction, intelligent visual monito...

AI Technical Summary

Problems solved by technology

At present, most of the research on human body recognition has only stopped at static recognition. The complexity and variability of human body movement make the accuracy and efficiency of recognition unable to meet the practical requirements of related industries.

[0003] At present, the recognition of human behavior in the prior art mainly uses joint-point wearing sensors or multi-cameras for multi-view monitoring. Joint-point wearing sensors refer to placing sensors on a certain part of the human body. The types of behaviors are limited, and the recognition accuracy is not high, the recognition speed is slow, the recognition behavior is single, and the scalability is poor; the use of multiple cameras for multi-view surveillance refers to installing cameras at various viewing angles, and judging the human body through the pictures captured by the cameras of each viewing angle. This method has defects such as high cost, low data accuracy, inconvenient use, and great influence by environmental factors.

Images