Construction site personnel abnormal behavior real-time detection method based on neural network

Abstract

A construction site personnel abnormal behavior real-time detection method based on a neural network comprises the following steps: 1) deploying a camera at a construction site for collecting personnel image information; acquiring a video information stream of a construction site camera, and intercepting a single-frame picture; 2) changing the size of the input image according to the preset size requirement of the input image; 3) processing the image processed in the step 2) by adopting an encoder-decoder architecture neural network to generate feature mapping graphs under different scales; 4)based on the feature mapping graphs under different scales, obtaining position areas of targets of different sizes; 5) filtering false alarm detection; 6) deducing whether an abnormal behavior occursor not according to the existence state of the interested target; and 7) outputting an abnormal behavior real-time detection result. The Internet of Things, machine learning and blockchain technologies are adopted to achieve the effect of improving the intelligent and transparent degree of construction site management, and the problem of high construction site management difficulty is solved.

Description

technical field [0001] This technical solution is the application technology of computer technology in the security monitoring scene, specifically a real-time detection method for abnormal behavior of personnel, specifically the application of this method in the construction site scene, this real-time detection method adopts the encoder-decoder architecture neural network . Background technique [0002] Traditional construction site management faces problems such as complex construction site environment, difficult management of employees, frequent accidents and difficult investigation and evidence collection, and difficult project safety management. [0003] With the popularization of mobile phone use, the use of mobile phones by construction site workers will increase the possibility of safety accidents. It is difficult to rely on personnel supervision to play a real-time supervision role. If post-event surveillance video is used for inspection, it will also require a lot ...

AI Technical Summary

Problems solved by technology

[0002] Traditional construction site management faces problems such as complex construction site environment, difficult management of employees, frequent accidents, difficult investigation and evidence collection, and difficult project safety management.

[0003] With the popularization of mobile phone use, the use of mobile phones by construction site workers will increase the possibility of safety accidents

It is difficult to rely on personnel supervision to play a real-time supervision role. If post-event surveillance video is used for inspection, it will also require a lot of manpower and time costs, and the effect of preventing safety accidents is far inferior to instant discovery and immediate processing.

Images