DSSD algorithm-based safety helmet wearing inspection method, device and system

An inspection method and safety helmet technology, applied in the field of image recognition, can solve the problems of easy omission, low safety helmet accuracy, low manual inspection efficiency, etc., and achieve the effect of high technology application value and avoiding human input.

Pending Publication Date: 2021-06-25
NANJING NARI GROUP CORP +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the complex environment of electric power construction, manual inspection is inefficient and prone to omissions, the accuracy of helmet detection is low

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
  • DSSD algorithm-based safety helmet wearing inspection method, device and system
  • DSSD algorithm-based safety helmet wearing inspection method, device and system
  • DSSD algorithm-based safety helmet wearing inspection method, device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] This embodiment introduces a safety helmet wearing inspection method, refer to Figure 4 , methods include:

[0050] Acquire images collected from the construction environment;

[0051] Preprocess the acquired image;

[0052] Input the pre-processed image into the pre-trained helmet wearing inspection model;

[0053] According to the output of the safety helmet wearing inspection model, obtain the safety helmet wearing result information of the personnel in the image;

[0054] The pre-trained safety helmet wearing inspection model adopts the DSSD algorithm model, and the training samples include public data sets and custom sample sets, and the self-definition sample set includes image samples of labeled personnel wearing safety helmets and personnel not wearing safety helmets image sample.

[0055] The specific implementation of the method in this embodiment involves the following contents.

[0056] 1. Construction of helmet wearing inspection model

[0057] Progr...

Embodiment 2

[0072] This embodiment introduces a safety helmet wearing inspection device, including:

[0073] an image acquisition module configured to acquire images collected from the construction environment;

[0074] An image preprocessing module configured to preprocess the acquired image;

[0075] The image recognition module is configured to input the pre-processed image into the pre-trained helmet wearing inspection model, and check whether the person in the image is wearing a helmet;

[0076] And, the inspection result output module is configured to obtain the helmet wearing inspection result information of the person in the image according to the output of the helmet wearing inspection model;

[0077] Wherein the pre-trained hard hat wearing inspection model adopts the DSSD algorithm model, and its training samples include public data sets and custom sample sets, and the custom sample sets include image samples of marked personnel wearing hard hats and personnel not wearing An ...

Embodiment 3

[0085] refer to Figure 4 , this embodiment introduces a safety helmet wearing inspection system, including image acquisition equipment and safety helmet wearing inspection equipment installed at multiple points on the construction site;

[0086] The image acquisition device collects the image of the construction personnel at the corresponding position of the installation point, and transmits it to the safety helmet wearing inspection device;

[0087] The safety helmet wearing inspection device uses the acquired image of the construction personnel as the image to be inspected, executes the safety helmet wearing inspection method described in the first aspect, and outputs the safety helmet wearing inspection result information.

[0088] The output inspection result information can be image information, alarm information, etc., which is convenient for monitoring personnel to monitor and improve construction safety.

[0089] Those skilled in the art should understand that the em...

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 DSSD algorithm-based safety helmet wearing inspection method, device and system. The method comprises the following steps: acquiring an image acquired from a construction environment; preprocessing the obtained image; inputting the image obtained by preprocessing into a pre-trained safety helmet wearing inspection model; according to the output of the safety helmet wearing inspection model, obtaining safety helmet wearing result information of the personnel in the image. The pre-trained safety helmet wearing inspection model adopts a DSSD algorithm model, training samples comprise a public data set and a self-defined sample set, and the self-defined sample set comprises marked image samples of personnel wearing safety helmets and image samples of personnel not wearing safety helmets. According to the invention, the safety helmet wearing condition of the personnel in the power construction environment can be checked according to the collected image, the safety check efficiency is improved, and the result is reliable.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a safety helmet wearing inspection method, device and system based on a DSSD algorithm. Background technique [0002] At the electric power construction site, safety helmets play an important role in the safety protection of construction personnel and are an essential item for head protection. However, due to temporary negligence or lack of safety awareness of construction workers, there is often a phenomenon of not wearing safety helmets at the construction site, resulting in certain potential safety hazards. Therefore, the management personnel are required to check the wearing conditions of the safety helmets of the personnel in the construction. However, due to the complex environment of electric power construction, manual inspection is inefficient and prone to omissions, the accuracy of helmet detection is low. With the rapid development of artificial intelligence...

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): G06K9/00G06K9/62G06N3/04
CPCG06V40/103G06V20/41G06N3/045G06F18/214
Inventor 贾向博余晓明钟平原来钰黎华灿蒋亦凡李辉郝后堂
Owner NANJING NARI GROUP CORP
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