Illegal behavior identification method based on convolution and graph convolution

Abstract

The invention discloses an illegal behavior recognition method based on convolution and graph convolution, and the method comprises the following steps: S1, collecting behavior object images, and building an image database; s2, extracting the posture of each behavior object from the image database by adopting a human body posture extraction scheme HighHRNet; s3, partial optimization is carried out on the HighHRNet; s4, constructing an undirected graph based on the key point pose information identified by the HighHRNet, and performing preprocessing enhancement on the undirected graph; and S5, determining the abnormal type of the violation. According to the invention, the key point detection module is improved, so that the key point information can be extracted more quickly while the precision is maintained; the diversity of data is improved by applying various undirected graph data enhancement modes, so that the training model has stronger generalization ability; a video sequence is converted into an undirected graph sequence to construct a 3D feature graph space, and feature information is extracted based on a 3D feature graph, so that the accuracy of an illegal behavior recognition algorithm is improved.

Description

technical field [0001] The invention relates to the field of behavior analysis, in particular to a method for identifying violations based on convolution and graph convolution. Background technique [0002] At present, video violation detection based on AI algorithm is still an emerging field in my country. With more and more enterprises and scholars paying attention to and investing in this field, the field of video violation detection is rapidly developing and maturing, and the scope of application is also increasing. Wider and wider. [0003] Generally, there are two methods for reviewing video materials: one is to review each video frame by frame through reviewers. A video file may require multiple reviewers, which requires a lot of labor costs, and because it is manually reviewed, it is inevitable There are situations where examiners are fatigued and make mistakes, omissions and mistrials, the accuracy rate is not high, and it is easily affected by the environment; ther...

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to provide a method of illegal behavior identification based on convolution and graph convolution, aiming to solve the technical problem that most of the behavior recognition algorithms in the prior art can only identify a single person, and the data collection cost of multi-person identification is relatively high

Images