SAR image despeckling method based on wavelet transform and interval dense network

A dense network and wavelet transform technology, applied in the field of image processing, can solve problems such as easy generation of artifacts and blurred edge information.

Active Publication Date: 2021-09-10
XIAN UNIV OF TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a SAR image speckle removal method based on wavelet transform and interval dense

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
  • SAR image despeckling method based on wavelet transform and interval dense network
  • SAR image despeckling method based on wavelet transform and interval dense network
  • SAR image despeckling method based on wavelet transform and interval dense network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0039] SAR image speckle method of the present invention and the closely spaced wavelet transform-based network, such as a flowchart figure 1 As shown, specifically, follow the steps below:

[0040] Step 1, to obtain an image to be trained;

[0041] 1 is the specific steps:

[0042] Step 1.1, use common classification of remote sensing data sets UC Merced Land-Use image as the training sample set, the data set includes buildings, parks, roads, forests, ports and other 21 categories of color scene graph, each category has 100 total 2100, all of the image size 256 × 256;

[0043] Step 1.2, step 1.1 2100 gradation color image processing, to obtain a gray scale image 2100 as the network training label, referred to as R.

[0044] Step 2, according to the image to be trained in step 1, a simulated SAR image data set;

[0045] Step 2 The specific operatio...

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 SAR image despeckling method based on wavelet transform and an interval dense network. The SAR image despeckling method comprises the following steps: 1, acquiring an image to be trained; 2, making a simulation SAR image data set according to the to-be-trained image in the step 1; 3, carrying out logarithmic transformation on the to-be-trained image in the step 1 and the simulation SAR image data set obtained in the step 2, and then carrying out primary wavelet transformation to obtain four components; 4, inputting the corresponding components in the step 3 into the interval dense network for training to obtain four components with speckle noise removed; and 5, carrying out wavelet inverse transformation on the four components after speckle noise removal obtained in the step 4, and then carrying out indexing to obtain a despeckled SAR image. According to the invention, the problems of blurred edge information and easy generation of artifacts after image despeckling in the prior art are solved.

Description

Technical field [0001] The present invention belongs to the technical field of image processing method, particularly relates to a SAR image speckle method based wavelet transform and the network of closely spaced. Background technique [0002] Synthetic Aperture Radar (SAR) is mounted on an aircraft or spacecraft and other platforms, you can create active earth observation system and the goal of two-dimensional images of the landscape. It visualization feature target echo signals by SAR imaging algorithm, SAR image to obtain a target range and azimuth direction. Synthetic aperture radar can overcome the limitations of optical imaging and infrared imaging, regardless of the day or night, regardless of weather conditions and other simple sunny or rainy, foggy and other complex weather conditions can work on the ground object imaging, provides a reliable and irreplaceable spatial data source. Therefore synthetic aperture radar and imaging is widely used in many fields of national de...

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): G06T5/00
CPCG06T5/003G06T2207/10044G06T2207/20064G06T2207/20081G06T2207/10024
Inventor 刘晶李倩楠向朋霞
Owner XIAN 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