An image segmentation method based on deep learning

An image segmentation and deep learning technology, applied in the field of computer vision, can solve the problems of deep network learning difficulties, low segmentation effect, and less image data, and achieve the effects of accelerating convergence, increasing generalization ability, and reducing the amount of parameters

Active Publication Date: 2019-05-10
BEIJING UNIV OF TECH
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the field of geological salt layer images, it is difficult to achieve better results when using these networks to do segmentation tasks. The main reason is that geological images are affected by the depth of the stratum, and the results of geological imaging at different depths are inconsistent. Secondly, there is less image data. , which brings difficulties to deep network learning, which leads to low segmentation effect

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 image segmentation method based on deep learning
  • An image segmentation method based on deep learning
  • An image segmentation method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be described in further detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0035] The used hardware equipment of the present invention has 1 PC machine, 1 1080 graphics cards;

[0036] Such as figure 1 As shown, the present invention provides a method for segmenting images of geological salt layers based on deep learning, which specifically includes the following steps:

[0037] Step 1. Obtain the geological salt layer image data set in the relevant field, and perform the first cleaning on these data (for example, delete dirty data).

[0038] Step 2, use image enhancement technology to enhance the original data, so as to increase the number of samples and enrich the content of the data set.

[0039] Step 2.1, shape enhancement, mark the original image and its mask, scale its length and width according to a certain ratio, and then intercept the size required by the semantic segmentation ne...

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 based on deep learning, and the method comprises the steps: carrying out the expansion of a data set through employing an image data enhancement and extraction technology; and carrying out five-fold processing in consideration of underground depth information during image acquisition. And finally, an improved classification network is adopted asan encoder, an improved FPN network structure is adopted as a decoder, and TGS open-source data is used for model training.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to some image processing, image semantic segmentation methods, deep learning image segmentation methods and the like. Background technique [0002] With the development of artificial intelligence technology, the application of computer vision is more common. In the application of computer vision, image segmentation is an indispensable link. Image semantic segmentation can be said to be the cornerstone technology of image understanding, and it is of great significance in medical image research, geological image research, automatic driving system, modern industry and other fields. For example, areas where a large amount of oil and natural gas accumulate on the earth tend to form huge salt deposits below the surface, and these salt deposits exist in the form of high-temperature liquids underground. Prior to mining, rigorous geological exploration is carried out 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): G06K9/34G06K9/62
Inventor 刘博刘银星
Owner BEIJING UNIV OF 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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap