Unlock instant, AI-driven research and patent intelligence for your innovation.

Industrial manufacturing site helmet wearing recognition system and method based on deep learning

An industrial manufacturing and deep learning technology, applied in the field of image recognition, can solve the problems of poor recognition effect and low efficiency of helmet wearing recognition, achieve accurate recognition range, improve versatility and stability, and solve the effect of low accuracy

Inactive Publication Date: 2020-12-29
CHENGDU AIRCRAFT INDUSTRY GROUP
View PDF9 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In order to solve the above technical problems, the present invention proposes a safety helmet wearing recognition system and method based on deep learning, which can effectively solve the problems of low safety helmet wearing recognition efficiency and poor recognition effect, and can be applied to complex industrial manufacturing scenes

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
  • Industrial manufacturing site helmet wearing recognition system and method based on deep learning
  • Industrial manufacturing site helmet wearing recognition system and method based on deep learning
  • Industrial manufacturing site helmet wearing recognition system and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] As the basic implementation of the present invention, the present invention includes a safety helmet wearing recognition system based on deep learning in an industrial manufacturing site, including a data collection module, an image processing and labeling module, a model training module and a real-time detection and early warning module. The data acquisition module is used to collect raw video data; the image processing labeling module is used to extract picture data from the video data and mark the head region as the original training set; the model training module is used to build a convolutional neural network based The human head area recognition model of the human body, and establishes the automatic identification algorithm of the helmet according to the color and shape characteristics of the helmet; the real-time detection and early warning module is used to detect the real-time video according to the built model and algorithm, when it is recognized that the person...

Embodiment 2

[0046] As a preferred embodiment of the present invention, the present invention includes a safety helmet wearing recognition system based on deep learning at industrial manufacturing sites, including a data acquisition module, an image processing and labeling module, a model training module and a real-time detection and early warning module. The method of using the system specifically includes the following steps:

[0047] Step S 1 : Video data acquisition, the data acquisition module records live video through a high-definition camera and uploads it to the management system server.

[0048] Step S 2 : The training data set is prepared, and the image processing and labeling module performs frame processing on the video data to obtain image information, labels the information of the human head area in the image, and takes it as the region of interest, and obtains the labeled image sample.

[0049] Step S 3 : Model training, the model training module obtains a human head det...

Embodiment 3

[0054] As the best implementation mode of the present invention, the present invention includes a deep learning-based safety helmet wearing recognition system at the industrial manufacturing site, referring to the attached Figure 4 , including data acquisition module, image processing and labeling module, model training module and real-time detection and early warning module. Refer to the attached figure 1 , the specific method of using the recognition system includes the following steps:

[0055] Step S 1 : Video data acquisition, the data acquisition module records live video in real time through a high-definition camera and uploads and stores it to the management system server.

[0056] Step S 2 : Prepare the training dataset. The image to be recognized is the image of the staff in the complex scene of the industrial manufacturing site. Therefore, the image frame operation can be performed from the on-site video data stored in the management system server, and the imag...

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 relates to the technical field of image recognition, and especially relates to an industrial manufacturing site helmet wearing recognition system and method based on deep learning. The system comprises a data collection module, an image processing and marking module, a model training module and a real-time detection and early warning module. The method based on the system comprises the following steps: acquiring real-time video data of a construction site, performing stream extraction on the real-time video data, acquiring single-frame image data to be identified, inputting the single-frame image data to be identified into a pre-constructed human head detection model, performing safety helmet identification on the identified human head information based on color and shape characteristics, and when it is recognized that the person does not wear the safety helmet, sending alarm information, and reserving field data. Through the system and the method, the problems of low safety helmet wearing identification efficiency and poor identification effect can be effectively solved, and the system and the method can be suitable for complex industrial manufacturing sites.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to a system and method for identifying helmet wearing in industrial manufacturing sites based on deep learning. Background technique [0002] With the popularity of security surveillance cameras, identification requirements in various scenarios have emerged, especially for the identification of personnel safety. In construction sites, factories and other specific areas, there are often falling objects on site. From a safety point of view, all workers entering the site must wear safety helmets, and security personnel are required to inspect such areas or conduct 24-hour monitoring of such areas through security surveillance cameras. Real-time monitoring, but due to the wide range of points, omissions are inevitable, and the results are unsatisfactory. [0003] Most of the existing monitoring methods are based on human body recognition plus helmet recognition to jud...

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): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/10G06V20/52G06V10/48G06V10/44G06N3/045G06F18/241
Inventor 黎小华刘倍铭王飞扬方亿刘崛雄
Owner CHENGDU AIRCRAFT INDUSTRY GROUP