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

Refinement segmentation method of ice layer in ice sheet radar image based on fcn-aspp network

A radar image and refinement technology, which is applied in the fields of computer vision and pattern recognition, can solve the problems of insufficient segmentation and refinement, and achieve the effects of improving classification and judgment efficiency, reducing consumption, and achieving refinement and robustness

Active Publication Date: 2020-10-16
BEIJING UNIV OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the FCN segmentation network also has the disadvantage of insufficient segmentation refinement. Based on the FCN segmentation network, the method in this paper improves it, strengthens the fine segmentation ability of the network, and makes it more in line with the requirements of ice radar image segmentation.

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
  • Refinement segmentation method of ice layer in ice sheet radar image based on fcn-aspp network
  • Refinement segmentation method of ice layer in ice sheet radar image based on fcn-aspp network
  • Refinement segmentation method of ice layer in ice sheet radar image based on fcn-aspp network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] A detailed description is given below in conjunction with the drawings:

[0034] The technical block diagram of the present invention is as figure 1 Shown. The specific implementation steps are as follows:

[0035] 1. Pretreatment

[0036] The first step is to perform logarithmic conversion on the collected radar amplitude image, and calculate the radar amplitude a by formula (1) i Corresponding pixel value b i

[0037] b i =20×log10(a i ) (1)

[0038] The second step is to normalize the image by formula (2) to normalize the image to 255 pixel level.

[0039]

[0040] Where b i Is the pixel value after logarithmic conversion, c i Is the pixel value after normalization, max is the maximum pixel value before normalization, and min is the minimum pixel value before normalization.

[0041] The third step is to perform Lee filter processing on the original image to eliminate the coherent speckle noise of the radar image and save the obtained image as a training image. Coherent speckl...

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 ice cover radar image ice layer fine segmentation method based on an FCN-ASPP network, and relates to the field of computer vision and mode recognition. According to the invention, the radar amplitude image is used as a training sample of a network, corresponding data amplification is carried out for the problem of less ice layer image data, and the wide applicability ofthe method is expanded. Lee filtering is carried out on the ice cover image. In order to save edge information as much as possible, a threshold judgment process is added to a filtering process. FCN-is constructed, and FCN-is constructed; according to the ASPP ice layer segmentation deep network, the ASPP layer is improved, so that the extraction capability of the network on small-scale characteristics is enhanced. The preliminary classification result is further processed through CRF, and the segmentation result is further refined on the basis of achieving end-to-end pixel level segmentation.In addition, the network greatly realizes the autonomous learning process.

Description

Technical field [0001] The invention belongs to the field of computer vision and pattern recognition, and relates to a method for segmentation of ice cover radar images based on deep learning. Background technique [0002] In recent years, global warming has seriously threatened our living environment. In recent decades, the melting of Antarctica's ice sheets has accelerated, causing sea levels to rise and have a considerable impact on ocean currents. It may even cause serious geological disasters. Therefore, collecting data on the thickness and distribution of polar ice sheets and how they change over time can effectively understand and predict the effects of glacier melting. The radar sensor is one of the instruments that can penetrate the ice layer and provide terrain information under the ice on a large area. Because air, ice, and rocks have different dielectric constants, the backscattering of radar waves is different when passing through objects in different media, so th...

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): G06T7/11G06K9/00
Inventor 蔡轶珩马杰胡绍斌李媛媛
Owner BEIJING UNIV OF TECH
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