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

A relative radiation correction method based on pseudo-invariant feature point classification and layering

A technology of relative radiation correction and radiation correction, which is applied in image analysis, image data processing, instruments, etc., can solve the problem of low correction accuracy and achieve the effect of small mean difference, small root mean square error, and reduced mean difference

Pending Publication Date: 2019-04-23
HARBIN INST OF TECH +1
View PDF10 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem of low correction accuracy of the existing relative radiation correction method for remote sensing images, and to propose a relative radiation correction method based on classification and layering of pseudo-invariant feature points

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 relative radiation correction method based on pseudo-invariant feature point classification and layering
  • A relative radiation correction method based on pseudo-invariant feature point classification and layering
  • A relative radiation correction method based on pseudo-invariant feature point classification and layering

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0022] A relative radiation correction method based on classification and layering of pseudo-invariant feature points. The relative radiation correction method includes the following steps:

[0023] Step 1: Obtain sub-images of ground features based on remote sensing image classification;

[0024] Step 2: Based on the nonlinear regression analysis of the spectrum, determine the initial relative radiation correction model and initial PIFs of the ground object sub-images; where PIFs refer to pseudo-invariant pixels;

[0025] Step 3: Based on the gradient-based fine nonlinear regression analysis, determine the refined nonlinear relative radiation correction model and refined PIFs of the ground object sub-images;

[0026] Step 4: Use refined PIFs and refined nonlinear relative radiation correction model to perform relative radiation correction on the sub-image of the ground object to be corrected;

[0027] Step 5: Synthesize the corrected image into a complete image, and evaluate its accura...

specific Embodiment approach 2

[0028] The difference from the first embodiment is that the relative radiation correction method of this embodiment is based on the classification and stratification of pseudo-invariant feature points. In the first step, the specific process of obtaining sub-images of ground objects based on remote sensing image classification is :

[0029] Step 1: Reference image production and analysis, select the original remote sensing image with clear cloud content less than or equal to 2%, use the calibration information of the original data to calibrate the image, and then use the atmospheric condition data acquired at the same time to correct The remote sensing image is subjected to atmospheric correction to obtain the reference image required for relative radiometric correction; among them, the original remote sensing image with clear cloud content less than or equal to 2% is in the multiple original remote sensing images with clear cloud content information provided by the image data sel...

specific Embodiment approach 3

[0039] The difference from the second embodiment is that the relative radiation correction method of this embodiment is based on the classification and stratification of pseudo-invariant feature points. In the second step, the non-linear regression analysis of the spectrum is used to determine the The specific process of the initial relative radiation correction model and initial PIFs is:

[0040] (1) The process of determining the initial relative radiation correction model of the ground object sub-image based on the nonlinear regression analysis of the spectrum is as follows:

[0041] Based on the theoretically non-linear relationship between the invariant pixel radiation relationship between the reference image and the corresponding ground object sub-image of the image to be corrected, a second-order polynomial is used to describe the radiation relationship of the corresponding pixels of the two sub-images, as shown in the following equation:

[0042]

[0043] Where x ij Represen...

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 a relative radiation correction method based on pseudo-invariant feature point classification and layering, and belongs to the field of remote sensing image radiation correction. An existing radiation correction method is low in correction precision of relative radiation on remote sensing images including coastlines, islands and the like occupying dominant ground object areas. The method comprises the steps of 1, obtaining ground object sub-images based on remote sensing image classification; 2, determining an initial relative radiation correction model and an initial PIFs of the ground object sub-image based on nonlinear regression analysis of the spectrum; 3, based on gradient-based fine nonlinear regression analysis, determining a fine nonlinear relative radiation correction model and a fine PIFs of the ground object sub-image; 4, performing relative radiation correction on the to-be-corrected surface feature sub-image by using the refined PIFs and the refined nonlinear relative radiation correction model; and 5, synthesizing the corrected image into a complete image. The method is applied to the field of remote sensing image radiation correction.

Description

Technical field [0001] The invention relates to a method for relative radiation correction of remote sensing images, in particular to a method for relative radiation correction combining remote sensing satellite imaging characteristics and target area characteristics. Background technique [0002] The acquisition of remote sensing images is affected by the sensor itself, illumination, atmosphere, terrain and other factors, resulting in great differences in the spectral characteristics of the same objects on different images. Therefore, before using multi-source or multi-temporal remote sensing images for change detection or feature information extraction, it is necessary to carry out radiation correction processing on the images to control and reduce the “falseness” of the landscape caused by differences in lighting conditions, atmospheric effects, and sensor responses. Change", to retain the true information of surface changes. Therefore, radiometric correction of remote sensin...

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): G06T5/00G06T5/50
CPCG06T5/50G06T2207/10032G06T5/00
Inventor 陈浩刘江张梅燕
Owner HARBIN INST 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