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

Industrial part detection method based on YOLO v3 neural network

A neural network and detection method technology, applied in the field of parts detection in intelligent assembly, can solve the problems of low detection efficiency and high false detection rate, and achieve the effects of reducing manpower, ensuring parts detection, and facilitating updating and improvement

Inactive Publication Date: 2020-07-17
TIANJIN UNIVERSITY OF TECHNOLOGY
View PDF6 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art, and propose an industrial parts detection method based on YOLO v3 neural network, which can solve the problems of low detection efficiency and high false detection rate in the dynamic real-time environment existing in the industrial parts detection method question

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 part detection method based on YOLO v3 neural network
  • Industrial part detection method based on YOLO v3 neural network
  • Industrial part detection method based on YOLO v3 neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Embodiments of the present invention are described in further detail below in conjunction with the accompanying drawings:

[0044] An industrial parts detection method based on YOLO v3 neural network, such as figure 1 shown, including the following steps:

[0045] Step 1. Collect video samples of industrial parts;

[0046] The industrial parts in step 1 are 9 kinds of 3D printing industrial parts, and their shapes include: triangular prism, quadrangular prism, cylinder, flower-shaped column, hexagonal prism, circle, flower-shaped, triangle and cube.

[0047] In this embodiment, high-precision cameras are used to collect video samples of industrial parts, and according to needs, the collected objects can also be expanded to video samples of specific objects of various shapes in industrial parts.

[0048] Step 2. Obtain the single-frame image of the video sample of the industrial parts collected in step 1 to form a basic data set, perform data enhancement on the image o...

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 an industrial part detection method based on a YOLO v3 neural network. The method comprises the following steps: step 1, collecting an industrial part video sample; step 2, acquiring a single-frame image of the video sample of the industrial part acquired in the step 1, forming a basic data set, performing data enhancement on the images of the basic data set to form an industrial part data set, labeling the position and category information of the industrial parts in the industrial part data set, and dividing the labeled industrial part data set into a sample trainingset, a verification set and a test set; step 3, generating a trained convolutional neural network detection model of the industrial part; and step 4, inputting the test set into an improved industrialpart convolutional neural network detection model to obtain a detection result. According to the invention, operations such as detection and classification of industrial parts can be quickly and efficiently identified in a dynamic environment.

Description

technical field [0001] The invention belongs to the technical field of parts detection in intelligent assembly, and relates to a detection method of industrial parts, in particular to a detection method of industrial parts based on a YOLO v3 neural network. Background technique [0002] At present, with the continuous development of my country's manufacturing industry, intelligent assembly systems are gradually being applied. The detection and recognition of industrial parts is an important part of the intelligent assembly system, involving computer vision, deep learning, image recognition and other research fields. At present, traditional assembly systems rely on manpower for repetitive labor, which is prone to errors due to the characteristics of human fatigue and limited resolution of human eyes. Intelligent systems have not been widely used, and the application of specific target detection for research on industrial parts Level methods are less. Therefore, in order to ...

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): G06T7/00G06K9/00G06K9/62G06N3/04
CPCG06T7/0004G06V20/40G06V10/25G06N3/045G06F18/23213G06F18/214
Inventor 张静刘凤连郭纪志汪日伟李文龙李雷辉孟赵明肖峻熙俎晨洋
Owner TIANJIN UNIVERSITY OF TECHNOLOGY
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