Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Construction site safety helmet wearing detection system and method

The technology of a detection system and detection method is applied in the direction of closed-circuit television system, parts of TV system, parts of color TV, etc., which can solve problems such as easy misidentification, poor recognition effect, and many helmet data requirements, and achieve Reduce network costs and requirements, improve functional scalability, and improve communication efficiency

Inactive Publication Date: 2018-07-24
安徽金禾软件股份有限公司
View PDF7 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Aiming at the problems existing in the prior art of easy misidentification, too many helmet data requirements, and poor recognition effect, the present invention provides a safety helmet wearing detection system and detection method on the construction site, which can accurately determine whether the safety helmet is Exist, requiring less original data and accurate identification

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 safety helmet wearing detection system and method
  • Construction site safety helmet wearing detection system and method
  • Construction site safety helmet wearing detection system and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] This solution automatically detects whether the construction site personnel wear helmets through the computer system, and triggers an alarm and records relevant information for violations without helmets.

[0058] Such as figure 1 As shown, this scheme is equipped with a safety helmet wearing detection system on the construction site, including a video device and a detection system. The video device is a camera, and several cameras can be set up according to needs, and are installed at the entrance and at the worker's work place on the construction site. The detection system is the background system, the detection system includes a video stream access module arranged sequentially, which can adapt the video stream to be accessed, and has better functional scalability and wider adaptability to video equipment; the image acquisition module is in front of the front end Set the machine to detect the outline and position of the moving object, and locate and mark the video fra...

Embodiment 2

[0060] Such as figure 2 , 3 , Shown in 4, based on the system of above-mentioned embodiment 1, safety helmet wearing detection method, the steps are as follows:

[0061] A. Collect video surveillance images, and manually mark the image content and format required for detection and recognition. Manual marking must indicate that there is a head area wearing a helmet in the video picture, etc., and mark the color and type of safety helmet according to the requirements, and establish Detection and recognition model; here, the video stream can be obtained by accessing a camera or a stored video file. Here, artificially labeled pictures are used to train a deep learning SSD detection and recognition model. The detection tasks of the SSD detection and recognition model include proposal layer, regression task, and classification In the regression task, a proposal corresponds to four outputs. The classification task needs to classify each proposal. The proposal layer includes N propo...

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 present invention discloses a construction site safety helmet wearing detection system and method, belonging to the field of video identification detection. Aiming at problems that mis-identification is easily generated, there are many data requirements of a safety helmet and the identification result is not good in the prior art, the present invention provides a construction site safety helmet wearing detection system and method, a video device and a detection system. The method comprises the steps of: A, collecting video monitoring images, and establishing a detection and identificationmodel; B, collecting real-time monitoring images of a construction site to perform detection of moving objects, and uploading images of the moving objects to an identification system if the images ofthe moving objects are detected; C, receiving the images sent in the step B by the identification system to perform detection and identification and determine the state of a helmet; D, transmitting aresult to a message queue; and E, displaying a detection and identification result. The construction site safety helmet wearing detection system and method can accurately determine whether there is asafety helmet or not, required original data is few and identification is accurate.

Description

technical field [0001] The invention relates to the field of video recognition and detection, and more specifically, to a safety helmet wearing detection system and detection method on a construction site. Background technique [0002] Safety helmet is a kind of protective equipment to prevent impact objects from hurting the head. Personnel entering the construction site must wear a safety helmet to protect the head and prevent accidental falling objects. However, there are often situations where personnel entering the construction site do not wear safety helmets correctly. In order to better avoid this situation, it is very important to monitor the construction site in real time and detect whether the safety helmets are worn in accordance with the regulations. By installing a camera at the entrance, the video captured by the camera is processed in real time, so as to judge whether the worker is wearing a helmet and give an alarm in time, which can effectively reduce the lab...

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): G06K9/00G06K9/62H04N5/14H04N7/18
CPCH04N5/144H04N7/181G06V20/47G06V20/52G06F18/214
Inventor 王山东殷志炜华志魁丁磊战博奇樊志远
Owner 安徽金禾软件股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com