Construction site image safety helmet detection method based on deep learning

A technology of deep learning and detection methods, applied in the fields of instruments, character and pattern recognition, computer parts, etc., to achieve the effect of large application potential, improved accuracy, good accuracy and real-time performance

Inactive Publication Date: 2019-09-20
WENZHOU UNIVERSITY
View PDF4 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the need to count and monitor the situation that workers wear helmets on construction sites, in order to solve the problem of the accuracy of helmet detection on construction sites, the present invention provides a method for detecting helmets on construction sites based on deep learning. The identification method is simple and convenient for engineering applications Integration can greatly improve the accuracy of the detection results of helmet wearing

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
  • Construction site image safety helmet detection method based on deep learning
  • Construction site image safety helmet detection method based on deep learning
  • Construction site image safety helmet detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0040] The present invention adopts such as image 3 The original image of the construction site video shown is used as the input image, and there are workers on the construction site in the image. First, the original picture is input to the target detection network, and the target detection network will detect pedestrians in the original picture. The result is as follows Figure 4 As shown, the target detection network frames pedestrians using anchor boxes. After obtaining the pedestrian's anchor frame, select the upper 1 / 3 area of ​​the pedestrian's anchor frame area as the head area to be detected, such as Figure 5 shown. The obtained head area is used as the input data of the helmet wearing detection network, and is input into the trained deep learning classification network of wearing a helmet to predict whether to wear a helmet or not. The network will output whether wearing a helmet or not wearing a helmet. The predicted value of the helmet. When the predicted value...

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 construction site image safety helmet detection method based on deep learning. The method comprises the following steps: firstly, detecting a constructor target area through a deep learning target detection method; obtaining a target image area of the person; intercepting an image of the upper 1 / 3 part of the area; and training the safety helmet classification network of the image of the last 1 / 3 part by using a transfer learning method in deep learning, judging whether the image part contains the information of the safety helmet, if the image part is classified as the safety helmet, the person in the image wearing the safety helmet, and otherwise, the person in the image not wearing the safety helmet. The method disclosed by the invention can meet the accuracy requirement of safety helmet detection and has a relatively high use value.

Description

technical field [0001] The invention relates to a method for detecting whether a helmet is worn on a construction site, in particular to a method for detecting a helmet on a construction site image based on deep learning. Background technique [0002] The work of construction site workers is often accompanied by potential safety hazards. Safety helmets, as a kind of personal head protection, can effectively prevent and reduce injuries to the head of operators when they encounter falling objects or fall themselves during production operations. It is a necessary safety measure for workers to wear safety helmets, which can protect the personal safety of construction workers to a certain extent. Therefore, it is of great significance to wear safety helmets for construction workers on the construction site. Monitor the construction workers entering and leaving the construction site, and send an alarm in time when workers without helmets are found, which can realize the rational a...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
CPCG06V20/41
Inventor 叶修梓张三元洪振杰陈如龙
Owner WENZHOU UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap