Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Mechanical part semantic segmentation method based on independent coding network

A technology of encoding network and mechanical parts, applied in the field of semantic segmentation of mechanical parts, can solve the problems of accurate attenuation, severe dynamic changes, low accuracy of semantic segmentation, etc., and achieve the effect of improving the average cross-merge ratio

Active Publication Date: 2020-05-08
KUNMING UNIV OF SCI & TECH
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] However, existing methods, usually based on specific procedures dealing with structured manufacturing conditions, may inevitably lead to precise attenuation as well as the influence of severe dynamic changes of the unconstrained surrounding environment, leading to low semantic segmentation accuracy.

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
  • Mechanical part semantic segmentation method based on independent coding network
  • Mechanical part semantic segmentation method based on independent coding network
  • Mechanical part semantic segmentation method based on independent coding network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The method for semantic segmentation of mechanical parts based on an individual encoding network provided by the present invention uses an individual encoding model to individually encode a single or multiple mechanical parts to be segmented to achieve semantic segmentation.

[0039] Among the separate encoding models employed here are:

[0040] convolutional layer conv ( l , o , h , p ), used to extract features of mechanical parts to be divided, l Represents the kernel of the convolutional layer, o Indicates the number of outputs of the convolutional layer, h Indicates the expansion factor of the convolutional layer, p Represents the padding of the convolutional layer;

[0041] pooling layer ( l , s , p ), which is used to partition and sample the features extracted by the convolutional layer to form a small matrix containing the features of the mechanical parts to be segmented, l and s Indicates the stride of the pooling layer, p Indicates the padding 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 discloses a mechanical part semantic segmentation method based on an independent coding network. According to the segmentation method, an independent coding model is used for independently coding one or more to-be-segmented mechanical parts to achieve semantic segmentation. Single or multiple to-be-segmented mechanical parts are independently coded by utilizing the independent codingmodel, so that semantic segmentation of the mechanical parts is realized, and the semantic segmentation precision and the average cross-parallel ratio on union set measurement are improved. The output quantity of the last convolution layer of each layer in the four spatial pyramid pooling (ASPP) branches is 2, so as to obtain binary prediction of each mechanical part.

Description

technical field [0001] The invention relates to a method for semantic segmentation of mechanical parts based on a separate encoding network. Background technique [0002] Semantic segmentation of objects in natural scenes is a fundamental problem in the field of computer vision research. In addition, semantic segmentation also plays an important role in the high-tech fields of autonomous robot navigation, self-driving vehicles, security monitoring, and industrial automation. [0003] In the field of actual industrial inspection, the semantic segmentation of mechanical parts is a huge challenge. First, mechanical parts captured by cameras usually have large dynamic changes in appearance and scale, which are caused by changes in lighting and viewing distance at the manufacturing site. Variations in appearance and scale of mechanical parts will inevitably inhibit image segmentation performance in terms of accuracy. Second, a typical production line often needs to handle mult...

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): G06K9/34G06N3/04G06N3/08
CPCG06N3/08G06V10/267G06N3/045
Inventor 何自芬张印辉
Owner KUNMING UNIV OF SCI & TECH
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
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