Early warning method and device for high-fall accident of construction worker

A technology for construction workers and accidents, which is applied in the field of early warning methods and devices for high-falling accidents of construction workers, can solve problems such as poor results, false detection and missed detection, and achieve the effect of preventing construction accidents at heights

Pending Publication Date: 2020-05-12
SHANDONG UNIV
View PDF5 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The inventors found that the poor effect of human body pose estimation technology in practical applications is mainly due to the complex environment of the workplace, and the human body pose estimation mod

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
  • Early warning method and device for high-fall accident of construction worker
  • Early warning method and device for high-fall accident of construction worker
  • Early warning method and device for high-fall accident of construction worker

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] figure 1 A flow chart of an early warning method for high fall accidents of construction workers in this embodiment is given.

[0045] The specific implementation process of the construction worker high fall accident early warning method of this embodiment will be described in detail below with reference to the accompanying drawings.

[0046] Such as figure 1 As shown, the early warning method for high fall accidents of construction workers in this embodiment includes:

[0047] Step S101: Establish a data set, and use a transfer learning method to train the target detection network and the behavior detection network respectively;

[0048] In specific implementation, the process of establishing a data set is:

[0049] Acquire pictures of construction workers at high places on construction sites, and calibrate the helmets, safety belts and workers in the pictures to form a data set;

[0050] Amplify the data set through data augmentation operations to improve the generalization abil...

Embodiment 2

[0084] This embodiment provides an early warning device for high fall accidents of construction workers, which includes:

[0085] (1) A network training module, which is used to build a data set and uses a transfer learning method to train the target detection network and the behavior detection network respectively.

[0086] In specific implementation, the process of establishing a data set is:

[0087] Obtain pictures of construction workers at high places on construction sites, and calibrate the helmets, safety belts and workers in the pictures to form a data set;

[0088] Amplify the data set through data augmentation operations to improve the generalization ability of the target detection network and behavior detection network.

[0089] Among them, the data augmentation operation includes: using a flip matrix to flip the picture from left to right and from top to bottom, performing affine transformation of different scales on the picture, and performing Gaussian blur on the picture....

Embodiment 3

[0122] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the figure 1 The steps in the early warning method for construction workers' high fall accidents are shown.

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 provides an early warning method and device for a high falling accident of a construction worker. The early warning method for the high fall accident of the construction worker comprisesthe following steps: establishing a data set, and respectively training a target detection network and a behavior detection network by adopting a transfer learning method; acquiring a monitoring video of a preset area, inputting the monitoring video into the trained target detection network, calibrating an operator, a safety helmet and a safety belt, and judging whether to output equipment abnormality alarm information or not according to the existence and wearing positions of the safety helmet and the safety belt; inputting a worker target color image detected by the target detection networkinto the trained behavior detection network; extracting a skeleton key point sequence of a worker, connecting joints, evaluating the correlation between skeleton key points, estimating the posture ofthe worker according to a preset worker action category and the unsafe posture of the corresponding worker, and giving an alarm when detecting that the behavior of the worker is abnormal.

Description

Technical field [0001] The invention belongs to the field of early warning of high fall accidents for construction workers, and in particular relates to an early warning method and device for high fall accidents of construction workers. Background technique [0002] The statements in this section merely provide background information related to the present invention, and do not necessarily constitute prior art. [0003] High-altitude operations are common in various projects in the construction industry. The workload is large, the working environment is complex and changeable, and multiple types of work are often required. However, accidents occur due to poor safety awareness and fluke mentality among personnel working at heights. According to the statistical analysis of construction safety accidents in China from 2009 to 2018, the number of deaths caused by high fall accidents accounted for the highest proportion of construction production accidents. High fall accidents have been ...

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): G06K9/00G06K9/62G06N3/04G06N3/08G06Q10/04G06Q10/06G06Q50/08G06Q50/26
CPCG06Q10/04G06Q10/0635G06Q50/08G06Q50/265G06N3/08G06V40/20G06V40/10G06N3/045G06F18/241
Inventor 马晓静饶颖露张恒张源民阎震贾磊马思乐陈纪旸栾义忠姜向远
Owner SHANDONG UNIV
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