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

Automatic registration method for high-spatial-resolution remote-sensing images based on SIFI feature points

A high spatial resolution, remote sensing image technology, applied in the field of automatic registration of high spatial resolution remote sensing images, to achieve the effect of wide application value

Inactive Publication Date: 2015-07-22
FUJIAN NORMAL UNIV
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, so far there is no solution or method that can simultaneously possess the above five characteristics, and most of the methods are specific to specific applications.

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
  • Automatic registration method for high-spatial-resolution remote-sensing images based on SIFI feature points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0020] In step 101, two remote sensing images image1 and image2 to be registered are input as multi-spectral images of Quick bird.

[0021] In step 102, in order to ensure that the edge information is preserved while removing the noise, the anisotropic heat diffusion equation is used to construct the nonlinear scale space of the remote sensing image, and the iterative equation is as follows:

[0022] I t+1 = I t +λ(cN x,y ▽ N (I t )+cS x,y ▽ S (I t )+cE x,y ▽ E (I t )+cW x,y ▽ W (I t ))

[0023] Among them, I is the image, ▽ N (I t ),▽ S (I t ),▽ E (I t ) and ▽ W (I t ) are the partial derivatives in four directions, cN x,y 、cS x,y 、cE x,y and cW x,y are the thermal conductivity coefficients in the four directions, and λ is the smooth control coefficient, which takes a value of 50. In order to retain the edge informa...

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 automatic registration method for high-spatial-resolution remote-sensing images based on SIFI feature points. The automatic registration method includes the steps of 1, preprocessing; 2, extracting the SIFI feature points; 3, refining the SIFI feature points; 4, building a KD tree; 5, searching nearest-neighbor node and next nearest neighbor node; 6, extracting feature matching pairs; 7, calculating matrix for affine transformation; and 8, performing affine transformation. According to the invariant feature of the SIFI feature points, the problem of high registration error of high-spatial-resolution remote-sensing images is solved, precise and automatic registration can be achieved, and accordingly the automatic registration method has high application value in the remote-sensing image variation detection.

Description

technical field [0001] The invention relates to the field of remote sensing image processing, in particular to an automatic registration method for high spatial resolution remote sensing images based on SIFT feature points. Background technique [0002] A good remote sensing image registration method or scheme should have the following characteristics: A. Strong robustness; that is, the algorithm is not affected by the content and quality of the input image. B. Wide adaptability; adaptability includes two aspects: one is the type of input image, which can be images of different time phases, or images of different sensors, or even the registration between images and maps; on the other hand Is the type of geometric transformation model, which can be similar transformation, affine transformation or polynomial transformation, or even more complex transformation forms. C. High degree of automation; the algorithm does not require operator participation as much as possible, includ...

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): G06T3/00
Inventor 施文灶
Owner FUJIAN NORMAL UNIV
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