Unlock instant, AI-driven research and patent intelligence for your innovation.

Helmet wearing detection method and system based on deep learning

A technology of deep learning and detection methods, applied in neural learning methods, image analysis, image enhancement, etc., can solve problems such as low accuracy, achieve high accuracy, facilitate site management, and reduce the amount of calculation

Inactive Publication Date: 2021-01-05
HUAZHONG UNIV OF SCI & TECH
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above defects or improvement needs of the prior art, the present invention provides a safety helmet wearing detection method and system based on deep learning, the purpose of which is to solve the technical problem of low accuracy of the prior art

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Helmet wearing detection method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] A safety helmet wearing detection method based on deep learning, such as figure 1 shown, including the following steps:

[0032] S1. On the server side, perform moving object detection on all camera videos on the scene, and extract each moving target in the camera video to obtain a moving target image;

[0033] In this embodiment, the video data of the cameras at the entrance and exit of the construction site are obtained, and after being transmitted to the server, on the server side, all camera videos on the site are detected for moving objects. Specifically, the following steps are included:

[0034] S11. Obtain the foreground target map of the current frame in the camera video by using the background difference method;

[0035] S12. Perform edge detection on the current frame, the previous frame and the next frame of the current frame respectively; perform a difference operation on the edge detection images of the current frame and the previous frame to obtain a dif...

Embodiment 2

[0045] A hard hat wearing detection system based on deep learning, deployed on a server, including: a moving target image extraction module and a hard hat wearing detection module;

[0046] The moving target image extraction module is used to detect moving objects on all camera videos on the scene, extract each moving target in the camera video, obtain the moving target image, and input it into the helmet wearing situation detection module;

[0047] The helmet wearing condition detection module is used to input the moving object image into the pre-trained helmet detection model to detect the wearing condition of the helmet;

[0048] Among them, the hard hat detection model is a deep learning model; the data set used to train the hard hat detection model includes images marked with whether workers wear hard hats.

[0049] The relevant technical solutions are the same as those in Embodiment 1, and will not be repeated here.

Embodiment 3

[0051] A computer-readable storage medium, the computer-readable storage medium includes a stored computer program, wherein, when the computer program is run by a processor, the device where the storage medium is located is controlled to execute a method provided by the first aspect of the present invention. A deep learning based helmet wearing detection method. The relevant technical solutions are the same as those in Embodiment 1, and will not be repeated here.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a safety helmet wearing detection method and system based on deep learning, and belongs to the field of security and protection monitoring. The method comprises the following steps: S1, carrying out moving object detection on all camera videos at a server end, and extracting all moving objects in the camera videos to obtain a moving object image; and S2, inputting the moving target image into a pre-trained safety helmet detection model, and detecting the wearing condition of the safety helmet, wherein the safety helmet detection model is a deep learning model, and a data set used for training the safety helmet detection model comprises an image marked with whether a worker wears a safety helmet. According to the invention, human body information of field workers andvideo data of a large number of cameras are fully utilized, invalid information in camera videos is filtered by extracting moving targets in the camera videos, then moving target images are detectedbased on a deep learning model, the wearing condition of the safety helmet is obtained, the accuracy is high, and the speed is high.

Description

technical field [0001] The invention belongs to the field of security monitoring, and more specifically relates to a safety helmet wearing detection method and system based on deep learning. Background technique [0002] In the process of building construction, there are many potential safety hazards, which makes the incidence of accidents high. In the course of practice, we found that before construction work, checking the behavioral ability of construction workers and wearing safety equipment can effectively reduce the probability of accidents. Therefore, in daily construction operations, it is particularly important to supervise whether workers wear safety helmets and other safety facilities. However, most of the construction sites currently use manual monitoring, which relies heavily on experienced managers on site. They need to observe and inspect in real time, which is time-consuming and laborious. There is a low level of automation and a large workload. In the case ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T7/246G06N3/04G06N3/08G06T7/13G06T7/194
CPCG06T7/246G06T7/13G06T7/194G06N3/08G06T2207/10016G06T2207/20228G06N3/045
Inventor 袁烨许典董云龙
Owner HUAZHONG UNIV OF SCI & TECH