Abnormal behavior intelligent detection method and system based on similarity graph neural network

Abstract

The invention provides an abnormal behavior intelligent detection method and system based on a similarity graph neural network, and relates to the technical field of behavior detection, and the method comprises the following steps: an information obtaining step: shooting the abnormal behavior of a person in a monitoring video to obtain a training video sequence; a network training step: extracting human skeleton points in the training video sequence to obtain a skeleton point sequence, constructing a graph network structure, learning the skeleton point sequence by using a similarity graph neural network, and training the network; an anomaly detection step: recognizing human body skeleton points in the training video sequence, constructing a graph network structure, performing feature extraction on the skeleton point sequence by using a similarity graph neural network, and performing abnormal behavior recognition; and an intelligent recording step: automatically intercepting abnormal video clips, marking abnormal behavior types, and storing the abnormal behavior types in a database. According to the invention, the credibility of abnormal behavior recognition can be greatly improved, the recognition process is greatly simplified, the recognition time is shortened, and the real-time recognition effect is achieved.

Description

technical field [0001] The invention relates to the technical field of behavior detection, in particular to an intelligent detection method and system for abnormal behavior based on a similarity graph neural network. Background technique [0002] Since the concept of deep learning algorithm was proposed in 2006, artificial intelligence technology has made breakthroughs, gradually integrated with various scenarios, and applied to more and more fields. The application of artificial intelligence to procuratorial work has also become an inevitable trend in the development of procuratorial technology. [0003] At present, the video surveillance system generally only records and transmits the video, but still focuses on the manual monitoring and analysis of the video by the surveillance personnel. When a sudden abnormal event occurs, the monitoring personnel cannot respond in a timely manner, and even missed detection and reporting may occur. Manual detection methods can no long...

AI Technical Summary

Problems solved by technology

This method relies on optical flow to extract motion information. However, the calculation of optical flow is not only time-consuming but also requires high hardware memory, which cannot achieve the effect of real-time early warning.

However, starting from the monitoring environment of the supervision place, the real-time detection system for the abnormal behavior of the personnel in the supervision place has not yet been proposed.

Images