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

A method of remote sensing image deblurring based on dark channel

A remote sensing image and deblurring technology, applied in the field of image processing, can solve the problems of non-blind processing transition deblurring method PSF kernel value estimation is inaccurate, does not consider the characteristics of remote sensing imaging, etc., to solve the problem of PSF kernel value estimation inaccurate, high High level of visual comprehension and high degree of automatic processing

Active Publication Date: 2019-02-01
BEIJING RES INST OF SPATIAL MECHANICAL & ELECTRICAL TECH
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The technical problem solved by the present invention is: in the current prior art, in the process of repairing large-scale fuzzy remote sensing images combined with imaging parameter conditions, non-blind processing transitions that are prone to occur, and the PSF kernel value estimation of the deblurring method is not accurate and relies too much on Conditions do not consider the characteristics of remote sensing imaging, and propose a remote sensing image deblurring method based on dark channels

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
  • A method of remote sensing image deblurring based on dark channel
  • A method of remote sensing image deblurring based on dark channel
  • A method of remote sensing image deblurring based on dark channel

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] A remote sensing image deblurring method based on dark channel, such as figure 1 As shown, the specific steps are as follows:

[0047] (1) Select a fuzzy image I with a certain surface object from the satellite image data of the in-orbit image fuzzy phenomenon blur As the image to be processed, the fuzzy image I with certain features is selected blur The weather in the selected area must be sunny, and the atmospheric transmittance should not be lower than 0.6;

[0048] (2) Set the upper limit k of the fuzzy kernel of the remote sensing satellite image max is a fixed value, and at the same time for the blurred image I blur Carry out image block, to fuzzy image I blur The specific method for image segmentation is as follows:

[0049] For blurred images I blur Perform image block processing from bottom to top, from top to bottom, from left to right, and from right to left, where the size of the block processing is set to d h × d v ,Such as figure 2 As shown, the ...

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

A remote sensing image deblurring method based on dark channel is disclosed, For large-scale fuzzy remote sensing images, combined imaging parameter condition, the shortcomings of the prior dark channel methods in remote sensing images are corrected, It overcomes the difficulties of blur kernel estimation and result smoothing, and does not depend on the specific image features. At the same time, the deblurring results keep the geometric structure information in the image, improve the visual understanding level, give attention to the production requirements of remote sensing images, and processlarge-scale remote sensing images stably and reliably.

Description

technical field [0001] The invention relates to a dark channel-based remote sensing image deblurring method, which belongs to the field of image processing. Background technique [0002] Due to atmospheric effects, platform jitter and / or the mismatch between integration time and satellite flight speed, the images acquired by remote sensing cameras are blurred to varying degrees, especially when the imaging system reaches the end of periodic calibration. obvious. Blurring effects can degrade the image quality, greatly affecting the user's visual interpretation ability and expert interpretation results. The image results after deblurring can support the restoration of observation information in the case of poor weather or bad viewing angles, and can be used in special imaging occasions such as major disaster observations. Therefore, how to remove image blur has become the focus of research in the past few decades. [0003] For a long time, researchers have attributed the pr...

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): G06T5/00G06T7/10G06T3/40
CPCG06T3/4038G06T7/10G06T2207/20021G06T2207/10032G06T5/73
Inventor 曹世翔谭伟邢坤何红艳
Owner BEIJING RES INST OF SPATIAL MECHANICAL & ELECTRICAL 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