Construction method of neural network for personnel abnormal behavior detection

Abstract

The invention provides a construction method of a neural network for personnel abnormal behavior detection, the neural network is an encoder-decoder architecture neural network, the input of the neural network is an acquired image, and the construction method of the neural network comprises the following steps: step 1, based on a multi-branch convolution module, generating feature mapping graphs under different scales; step 2, constructing a convolutional neural network as an encoder decoder architecture, extracting semantic and detail information by an encoder, recovering the size of the feature map by a decoder, and obtaining a final segmentation result; and step 3, fusing the features on different branches to obtain an accurate target segmentation result. The neural network can be used for real-time detection application of personnel abnormal behaviors in a construction site scene.

Description

technical field [0001] The technical solution is an application method of computer technology in a security monitoring scene, specifically a method for constructing a neural network suitable for abnormal behavior detection of personnel, and the neural network is an encoder-decoder architecture neural network. The neural network can be used for real-time detection of abnormal behavior of personnel in construction site scenes. 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...

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