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

Safety helmet wearing detection and tracking method based on improved YOLOv3

A safety helmet and detection frame technology, applied in the field of image recognition, can solve the problems of inability to contact the previous and subsequent frames, unable to identify the same target, etc., to achieve the effect of meeting real-time requirements

Pending Publication Date: 2020-02-28
NANJING INST OF TECH
View PDF5 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Nowadays, YOLOv3 has been used in the field of helmet wearing detection, but it is only a frame detection process based on video streams, and cannot link the previous and subsequent frames, so that it cannot identify the same target that reappears after being briefly occluded

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
  • Safety helmet wearing detection and tracking method based on improved YOLOv3
  • Safety helmet wearing detection and tracking method based on improved YOLOv3
  • Safety helmet wearing detection and tracking method based on improved YOLOv3

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0039] Such as figure 1 As shown, a kind of helmet wearing detection and tracking method based on improved YOLOv3 disclosed in the present invention comprises the following steps:

[0040] 1. Data preparation and training set.

[0041] The sample data is composed of the construction site surveillance video and the self-made video of the network hard disk video recorder. The video resolution of the construction site is 960×544, and the self-made video resolution is 1280×720. Such as figure 2 As shown, the sample data is converted into pictures at 27 frames per second, and a video picture is intercepted every 10 frames as a picture data set, and then the preliminary classification of person pictures and background pictures is carried out through HOG+SVM binary classification, and then there are The image of the person is rotated clockwise by ...

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 safety helmet wearing detection and tracking method based on improved YOLOv3, and relates to the technical field of image recognition. The method comprises the following steps: (1) preparing data and making a training set; (2) constructing an improved YOLOv3-MobileNetV2 target detection model; (3) performing video stream real-time recognition through the safety helmet wearing detection model; (4) predicting the position of the prediction frame of the next frame by using the state of the detection frame of the current frame without the safety helmet, matching the intersection ratio of the detection frame and the prediction frame to realize the association of the front frame and the rear frame, and finally tracking and counting the constructors without the safety helmet; and (5) taking the central point of the detection frame without wearing the safety helmet as a target tracking track point, and completing the drawing of the tracking track. According to the invention, safety helmet wearing detection and tracking counting of people who do not wear safety helmets are realized, and the detection speed and accuracy of an original YOLOv3 target detection model are greatly improved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to an image recognition method for detecting and tracking the wearing of a safety helmet. Background technique [0002] As an effective head protection tool, hard hats have been widely used in various construction sites. However, due to negligent construction site safety management and weak safety protection awareness of construction workers, some casualties caused by not wearing hard hats are also frequent. occur. Therefore, it is of great significance for the safety protection management and intelligent information management of the construction site to realize the identification of helmet wearing on the construction site and the real-time detection and tracking of those who do not wear the helmet. [0003] MobileNet is a new generation of mobile convolutional neural network (Convolutional NeuralNetwork, CNN) model proposed by Google. This model has a simple structure ...

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
CPCG06V20/41G06V20/52G06F18/23G06F18/2411G06F18/214
Inventor 张嘉超秦嘉曹雪虹龙静焦良葆
Owner NANJING INST OF TECH
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