Automatic identification method and alarm system for wearing state of work clothes and hats based on video

A technology of wearing state and automatic identification, applied in the field of image processing, can solve problems such as difficult on-site management, and achieve the effect of eliminating hidden safety hazards, reducing false alarm rate and convenient application.

Active Publication Date: 2019-01-01
武汉昊广智联科技有限公司
View PDF6 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the large spatial breadth of the construction site, the intersecting operation time of various professional types, and the timely ha

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
  • Automatic identification method and alarm system for wearing state of work clothes and hats based on video
  • Automatic identification method and alarm system for wearing state of work clothes and hats based on video
  • Automatic identification method and alarm system for wearing state of work clothes and hats based on video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment example

[0105] An implementation case of the present invention is as follows:

[0106]Hikvision network camera is used, model: DS-2CD3T26DWD-I3. The video image acquisition frame rate is 25. In order to improve the processing speed, during the detection process, the video frame is scaled to the standard size of 320*240.

[0107] 1. Moving target detection. 1) In the three-frame difference method for detecting moving objects, when calculating the difference between two frames of images, the N(x,y) neighborhood is selected as 3x3, and the constant value C is the macro FLT_EPSILON of the c++11 standard library. The color distance between two pixels in the Lab color space adopts the CIEDE2000 distance algorithm standard. In obtaining the template image through binarization threshold processing on the difference image, set k1=10 and k2=20. The values ​​of k1 and k2 are empirical values, which have a certain relationship with the camera itself, and the specific values ​​can be adjusted ...

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 belongs to the technical field of image processing and discloses a method and an alarm system for automatically identifying the wearing state of a work clothes work cap based on a video.Based on a video stream time sequence image, a moving object in the video image is extracted by combining a time domain difference and background subtraction. Classification of human objects and other objects is accomplished according to the detected feature of the target block and the time period feature of the outline of the block. Segmentation of the head and torso of the detected human target; In Lab color space, whether the human target head wears safety helmet or not and whether the torso part wears working clothes are analyzed intelligently. If security protection abnormality is found,the security alarm message shall be reported to the manager in real time, and at the same time, the security alarm message shall be filmed and archived. The invention does not need to increase the installation and maintenance cost of the equipment. Adopting artificial intelligence technology, it is easy to use and low cost to realize the all-weather monitoring of workers' and employees' service caps on the construction site, which has a great application prospect.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a video-based automatic identification method and an alarm system for the wearing state of work clothes and hats. Background technique [0002] At present, our country is still in the stage of large-scale construction, and hundreds of thousands of construction sites are under construction every year. At the same time, it is also in the stage of transition from extensive to intensive. Construction companies are in urgent need of efficient on-site management methods to reduce costs and improve efficiency, and safety management can be said to be the top priority of construction site management. On-site safety management involves many aspects. At present, pre-employment education and manual supervision during the work process are still the main focus. The various disciplines and work surfaces of construction projects are interlaced in time and space, and they ar...

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): G06K9/00G06K9/32G06T7/246G06T7/12G06T7/136G06T5/30G06T5/00
CPCG06T5/009G06T5/30G06T7/12G06T7/136G06T7/246G06T2207/10016G06T2207/30196G06V40/10G06V10/255
Inventor 罗小安
Owner 武汉昊广智联科技有限公司
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