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

Image segmentation method, apparatus, and computer-readable storage medium

An image segmentation and image technology, applied in image analysis, computer components, calculations, etc., can solve the problems of inaccurate coverage of pixels, inability to obtain accurate posture, inaccurate positioning, etc., to achieve accurate posture, high efficiency and accuracy Accurate effect of classification and positioning

Active Publication Date: 2019-01-04
SHENZHEN DORABOT ROBOTICS CO LTD
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the existing image segmentation algorithms usually only calculate a roughly rectangular border, which cannot accurately cover all the pixels of the object, contains a large amount of background information, and causes inaccurate positioning and cannot obtain accurate poses.

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
  • Image segmentation method, apparatus, and computer-readable storage medium
  • Image segmentation method, apparatus, and computer-readable storage medium
  • Image segmentation method, apparatus, and computer-readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] This embodiment provides an image segmentation method for object segmentation in a logistics system.

[0043] Please see figure 1 , the image segmentation method includes:

[0044] Step S101, obtaining an original image.

[0045] Step S102, inputting the original image into a pre-trained neural network for calculation, calculating and segmenting each object in the first image, and obtaining a set of pixel points corresponding to each object.

[0046] In this embodiment, the original image is obtained first. In this embodiment, the original image is a two-dimensional RGB image.

[0047] After the original image is obtained, the original image is input into a pre-trained neural network for calculation, and each object in the first image is calculated and classified to obtain a set of pixel points corresponding to each object. Among them, the original image is used as the input of the neural network. The pre-trained neural network can calculate and obtain the output v...

Embodiment 2

[0051] This embodiment provides an image segmentation method. This embodiment further describes step S102 on the basis of the above embodiments, please refer to figure 2 ,details as follows:

[0052] please check figure 2 , the step S102, inputting the original image into a pre-trained neural network for calculation, calculating and classifying each object in the first image, and obtaining a set of pixel points corresponding to each object includes:

[0053] Step S201, using a neural network dimensionality reduction algorithm on the original image to obtain a dimensionality reduction image of the original image;

[0054] Step S202, classify each pixel of the dimensionality reduction image according to the dimensionality reduction image and a preset classification model;

[0055] In step S203, the dimensionality reduction image is passed through a neural network dimensionality enhancement algorithm to obtain a classification image with the same size as the original image. ...

Embodiment 3

[0065] This embodiment proposes an image segmentation method. This embodiment is based on the foregoing embodiments, and additional steps are added. details as follows:

[0066] The image segmentation method also includes:

[0067] Step S301, obtaining multiple training images;

[0068] Step S302, according to the input instruction, obtain the annotation of the object whose integrity reaches 70% in the training image;

[0069] Step S303, train the neural network according to the training images and corresponding labels.

[0070] In this embodiment, multiple training images are obtained. Among them, the training images can be tens of thousands, and the more accurate the classification model can be trained through the more training images. Specifically, the plurality of training models include objects in various shapes, angles, distances and / or rays. Therefore, the training result can be more robust.

[0071] Then, manually mark, that is, mark the pixels of the object to b...

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 an image segmentation method, an apparatus and a computer-readable storage medium. The original image is inputted to a pre-trained neural network for calculation, and each object in the first image is classified to obtain a pixel point set corresponding to each object. The invention has the effects of accurately dividing each pixel of an object to achieve accurate positioning and accurate attitude judgment.

Description

technical field [0001] The invention relates to the field of robot sorting, in particular to an image segmentation method, device and computer-readable storage medium. Background technique [0002] At present, with the development of logistics automation, robot sorting is becoming more and more popular. More and more goods need to be sorted quickly. In actual operation, many goods are stacked together and need to be distinguished. [0003] However, the existing image segmentation algorithm usually only calculates a roughly rectangular frame, which cannot accurately cover all the pixels of the object, contains a large amount of background information, and causes inaccurate positioning and cannot obtain an accurate pose. Contents of the invention [0004] The main purpose of the present invention is to provide an image segmentation method, device and computer-readable storage medium, aiming at accurately segmenting each pixel of an object so as to achieve accurate position...

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): G06T7/10G06K9/62
CPCG06T7/10G06T2207/20081G06T2207/20084G06F18/213G06F18/24
Inventor 吕仕杰
Owner SHENZHEN DORABOT ROBOTICS CO LTD
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