Deep convolutional neural network-based abnormal crowd behavior visual detection and analysis early warning system

Abstract

The invention discloses a deep convolutional neural network-based abnormal crowd behavior visual detection and analysis early warning system. The system comprises a camera mounted at a monitoring target facility, a security prevention cloud server and an abnormal crowd behavior visual detection and analysis early warning system. In the system, various human body objects in the target facility areextracted through a deep convolutional neural network technology; then motion states of human bodies are calculated, identified and judged by using an optical flow method; different states of the human body objects are subjected to clustering and crowd modeling; further crowd objects are subjected to density calculation and danger index calculation; and finally according to different combinationsof crowd density, motion vector values and duration quantitative index data, various abnormal crowd behaviors are identified and judged, and according to the states of the abnormal crowd behaviors, corresponding crowd gathering management control policies are enabled. The deep convolutional neural network-based abnormal crowd behavior visual detection and analysis early warning system provided bythe invention is unlimited in scale, relatively high in precision and relatively good in robustness, and is based on a deep convolutional neural network.

Description

technical field [0001] The invention relates to the application of artificial intelligence, convolutional neural network and computer vision in crowd density detection and belongs to the field of public security. Background technique [0002] With the rapid growth of the population and the constant conflicts of social interests, crowd incidents are becoming more and more common. In some first-tier cities, the population density is very high, and the probability of mass incidents in these places is very high. Especially in areas such as bustling streets, large shopping malls, stadiums and large factories, major crowd accidents often occur, causing casualties and property losses. Therefore, the gathering of a large number of people will increase the probability of accidents. [0003] In large and medium-sized cities in my country, video surveillance systems play a very important role in security work. At present, video surveillance systems have spread all over various publi...

AI Technical Summary

Problems solved by technology

[0021] Aiming at the limitations of scale, low precision and poor robustness existing in the existing crowd gathering visual detection, the present invention proposes a depth-based Crowd Abnormal Behavior Visual Detection and Analysis Early Warning System Based on Convolutional Neural Network

Images