SAR image denoising method based on multi-scale cavity residual attention network

An attention, multi-scale technology, applied in the field of remote sensing image processing, to achieve the effect of good removal, maintaining detailed information, and fast calculation speed

Pending Publication Date: 2019-08-13
NORTHWESTERN POLYTECHNICAL UNIV
View PDF15 Cites 47 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem of SAR image quality degradation caused by coherent speckle noise caused by the coherence of scattering phenomena in the SAR imaging process, a high-pe

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 denoising method based on multi-scale cavity residual attention network
  • SAR image denoising method based on multi-scale cavity residual attention network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0021] The present invention extracts multi-scale features from images through multi-scale convolution groups, uses dilated convolutions to increase the receptive field of convolution kernels, extracts more contextual information from images, and uses skip connections to transfer shallow feature information to deep convolutions. Layers are stacked to maintain image details, an attention mechanism is added to focus on extracting noise-related features, and residual learning is combined to learn the complex mapping relationship between the original coherent speckle noise image and coherent speckle noise. details as follows:

[0022] Step 1: Generate training sample pairs. Since it is difficult to obtain clean SAR images without coherent speckle noise, it is necessary to use simulated SAR images as training data. The present invention selects 410 images in the UCM...

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 relates to an SAR image denoising method based on a multi-scale hole residual attention network. The method comprises the following steps of by extracting features of different scales ofthe image through a multi-scale convolution group, broadening a convolution kernel receptive field by utilizing cavity convolution; exuecting more context information of the image; and transmitting the feature information of the shallow layer to a deep convolutional layer by using jump connection to keep image details, adding an attention mechanism to intensively extract noise-related features, and automatically learning the SAR image speckle noise distribution form in combination with a residual error learning strategy to achieve the purpose of removing speckle noise. Experimental results show that compared with a traditional SAR image noise removal method, the method has the advantages that the speckle noise removal effect is good, the number of artificial traces is small, detail information of the image is kept, and the calculation speed is higher through the GPU.

Description

technical field [0001] The invention relates to a SAR image multiplicative coherent speckle noise removal method based on a multi-scale hole residual attention network, which belongs to the field of remote sensing image processing. Background technique [0002] Synthetic aperture radar (SAR) is a coherent imaging sensor that can acquire large amounts of high-quality surface data. Due to its ability to operate at night and in harsh weather conditions such as thin clouds and smog, SAR has gradually become an important source of remote sensing data in fields such as geographic mapping, resource investigation, and military reconnaissance. However, SAR images are often affected by multiplicative noise caused by the coherence of scattering phenomena, that is, coherent speckle noise. The existence of coherent speckle noise seriously affects the quality of SAR images, and greatly reduces the efficiency of SAR image interpretation tasks such as object detection and instance segmenta...

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): G06T5/00G06N3/04
CPCG06T5/002G06T2207/10044G06T2207/20081G06T2207/20084G06N3/048
Inventor 李映李静玉
Owner NORTHWESTERN POLYTECHNICAL 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