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

Electric power operation personnel safety dressing detection method based on YOLOv3 target detection

A technology for electric power operation and target detection, which is applied in the field of safety clothing detection for electric power workers and video surveillance systems for electric power work sites. The effect of high rate and overcoming poor promotion

Inactive Publication Date: 2019-04-16
ELECTRIC POWER RES INST OF STATE GRID ZHEJIANG ELECTRIC POWER COMAPNY +1
View PDF3 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This model not only has the complexity of artificially designed features, but also has poor robustness and generalization.

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
  • Electric power operation personnel safety dressing detection method based on YOLOv3 target detection
  • Electric power operation personnel safety dressing detection method based on YOLOv3 target detection
  • Electric power operation personnel safety dressing detection method based on YOLOv3 target detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The preferred embodiments will be described in detail below in conjunction with the accompanying drawings. It should be emphasized that the following description is only exemplary and not intended to limit the scope of the invention and its application.

[0039] like figure 1 As shown, the method for detecting safe attire of electric workers based on YOLOv3 target detection provided by the present invention, the specific implementation steps are as follows.

[0040] Step 1: Collect clothing pictures of electric workers and make a training sample set. like figure 2 As shown in Fig. 1, the production of a training sample set of electrical workers' attire for training the network model is implemented in the following steps:

[0041] Step 11: Collect different clothing pictures of different people. There are the following two approaches. First, capture and save pictures containing workers frame by frame from the historical surveillance videos of different power work si...

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 an electric power operation personnel safety dressing detection method based on YOLOv3 target detection. According to the technical scheme, the method comprises: firstly, dressing pictures of electric power operators are collected, and a training sample set is made; secondly, constructing a YOLOv3 network model, and training the network model by adopting the training sampleset to obtain a trained YOLOv3 network model; Thirdly, taking the power operation on-site monitoring video as input data of the trained YOLOv3 network model, and detecting the safe dressing conditionof the power operation personnel in the video. Compared with a traditional method of manually designing characteristics, the method has the advantages that the characteristics are automatically extracted to realize detection, the applicability and the generalization performance are high, the safety helmet wearing and work clothes dressing conditions of electric power operation personnel in a video can be detected at the same time, and the method can be applied to a video monitoring system of an electric power operation site.

Description

technical field [0001] The invention belongs to the field of intelligent video monitoring, and relates to a method for detecting safe attire of electric workers based on YOLOv3 target detection, which can be applied to a video monitoring system at an electric power work site. Background technique [0002] There are many work sites in daily power production, and the relevant power safety work regulations have made strict regulations on the safety requirements that relevant personnel should abide by when entering the work site, among which there are clear requirements for wearing safety helmets and work clothes correctly. Safe attire is very important to ensure the personal safety of operators. Therefore, video surveillance of operators entering the job site can effectively ensure and supervise the safe attire of relevant operators and reduce the potential safety hazards of operators. [0003] In order to reduce the workload of manual viewing of video surveillance, automatic d...

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): G06K9/00G06K9/62
CPCG06V40/10G06V20/52G06F18/24G06F18/214
Inventor 王刘旺韩嘉佳颜拥姚影吕磅孙昌华
Owner ELECTRIC POWER RES INST OF STATE GRID ZHEJIANG ELECTRIC POWER COMAPNY
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