Full-polarization synthetic aperture radar image super-resolution reconstruction method

A technology of synthetic aperture radar and super-resolution reconstruction, which is used in image analysis, image enhancement, graphic image conversion, etc.

Active Publication Date: 2021-02-26
WUHAN UNIV
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the technical problems existing in the existing super-resolution reconstruction algorithm, the present invention provides a super-resolution reconstruction method

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
  • Full-polarization synthetic aperture radar image super-resolution reconstruction method
  • Full-polarization synthetic aperture radar image super-resolution reconstruction method
  • Full-polarization synthetic aperture radar image super-resolution reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0065] Step 1: Establish the observation model of the full-polarization SAR image. In the embodiment, the high-resolution full-polarization SAR image is represented as x, and the degraded low-resolution full-polarization SAR image is represented as y. Then the observation model of full polarization SAR image can be expressed as:

[0066] y=f ds (x) (1)

[0067] where f ds (.) represents the downsampling function.

[0068] Step 2: Image preprocessing.

[0069] Step 2.1: Perform radiation correction, terrain correction, multi-view processing and other preprocessing on the image to obtain the corrected image. According to the observation model established in step 1, the high-resolution image is down-sampled to obtain a low-resolution image. The high-resolution and low-resolution full-polarization SAR image pairs containing...

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 provides a full-polarization aperture radar image super-resolution reconstruction method based on a multi-scale attention mechanism, constructs a residual convolutional neural network with embedded feature layer up-sampling, spatial attention, channel attention, multi-scale attention, adaptive loss function and other modules, and combines supervised and zero-projection training mechanisms. A training convergence network is obtained. Through the trained network, super-resolution reconstruction is carried out on the to-be-processed low-resolution synthetic aperture radar image to obtain a high-resolution full-polarization synthetic aperture radar image, and spatial information of the image is effectively reconstructed while polarization information of the image is maintained.

Description

technical field [0001] The invention is designed in the fields of remote sensing image processing and computer vision, and specifically designs a super-resolution reconstruction method for full-polarization synthetic aperture radar images based on a multi-scale attention mechanism. Background technique [0002] Full-polarization synthetic aperture radar can obtain multiple scattering information of ground objects in a single scene through different polarization methods, so it plays an important role in ship identification, post-earthquake assessment, land use classification and other applications. However, limited by various factors such as the signal bandwidth of the SAR system and the size of the antenna, the spatial resolution of the image will inevitably be reduced while obtaining multi-polarization information. Therefore, using super-resolution reconstruction technology to reconstruct the spatial resolution is an important way to improve the spatial information of full-...

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): G06T3/40G06T5/50
CPCG06T3/4053G06T5/50G06T2207/10044G06T2207/20081G06T2207/20084
Inventor 沈焕锋林镠鹏李杰袁强强
Owner WUHAN UNIV
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