Check patentability & draft patents in minutes with Patsnap Eureka AI!

An automatic sorting method for pipe fittings based on deep learning

An automatic sorting and deep learning technology, applied in the field of machine vision, to achieve the effect of saving use, improving recognition accuracy, and reducing wrong and wrong grasping

Active Publication Date: 2022-05-13
ZHONGBEI UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Traditional industrial robots can generally only recognize pipe fittings of the same type and size. If you want to sort pipe fittings of multiple types and sizes, you need multiple robots

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
  • An automatic sorting method for pipe fittings based on deep learning
  • An automatic sorting method for pipe fittings based on deep learning
  • An automatic sorting method for pipe fittings based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] A method for automatic sorting of pipe fittings based on deep learning, comprising the following steps:

[0044] Step 1, take images of pipe fittings such as tees, outer wires, inner wires, and elbows, and use the labelme tool to label the collected pipe fitting images with categories and mask contours to obtain the pipe fitting images of the json type labeling results;

[0045] Step 2, perform data enhancement on the pipe image with the labeling results: rotation, flip, blur, Gaussian filtering, bilateral filtering and adding white noise, to obtain a data set; where the data before the enhancement is selected as a training set, as a test set. Gaussian filtering, bilateral filtering, etc. are existing technologies, and will not be described in detail here.

[0046]Step 3, design the network structure, read the data set in step 2 into the network for training, use 3000 tubes as the training set, 1000 tubes as the test set, batch size is 3, and the learning rate is 0....

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 machine vision, and in particular relates to an automatic sorting method for pipe fittings based on deep learning. The current manual sorting is costly, inefficient, complicated and tasteless, and the recognition degree is low using traditional methods. The invention improves the recognition rate and mask judgment of the algorithm by improving the MaskR-CNN algorithm, and improves the recognition rate while ensuring the speed. Put the photos taken by the camera into the network to get the classification result and mask. Determine the type and size of the pipe fittings and record the information. Through Zhang Zhengyou's calibration and eye-in-hand calibration, the grabbing point of the pipe fittings is located. The mechanical arm grabs and stacks the pipe fittings. The pipe fitting automatic sorting method of the present invention not only has high efficiency, but also has higher robustness for pipe fitting recognition and grasping in different environments; it can be widely used in factory sorting, object classification and grasping.

Description

technical field [0001] The invention belongs to the technical field of machine vision, and in particular relates to an automatic sorting method for pipe fittings based on deep learning. Background technique [0002] Studying the vision technology of robots can not only improve the robot's ability to perceive the external environment, but also greatly reduce the burden on the staff, freeing them from the complicated and boring working environment. At present, the labor demand in our country is still very high. Robots can be applied to these fields to reduce production costs, improve work efficiency, and improve the market competitiveness of enterprises. Therefore, many industries regard industrial robots as the core workers of enterprises to improve enterprises. production efficiency. [0003] In the field of pipe fitting recognition of industrial robots, deep learning can be used instead of traditional learning methods to make the robot's recognition effect better and impro...

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 Patents(China)
IPC IPC(8): G06V20/00G06V10/26G06V10/44G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08G06T3/00G06T7/00G06T7/73G06T7/80B07C5/36
CPCG06N3/04G06N3/08G06T7/80G06T7/73G06T7/0004B07C5/362G06T2207/10004G06T2207/30164B07C2501/0063G06V20/10G06V10/267G06V10/44G06F18/24G06T3/02
Inventor 韩慧妍吴伟州韩燮乔道迹
Owner ZHONGBEI UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com