A multi-time multispectral image feature level information fusion method based on iteration implicit regularization

A multi-spectral image and fusion method technology, applied in the field of multi-temporal multi-spectral image feature-level information fusion based on iterative implicit regularization, can solve problems such as poor fusion results, improve the effect, solve the problem of image feature set fusion, and overcome the accuracy. low effect

Inactive Publication Date: 2019-06-28
XIDIAN UNIV
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for some high-resolution images, the results obtained by this method are still seriously affected by noise, resulting in poor fusion results.

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 multi-time multispectral image feature level information fusion method based on iteration implicit regularization
  • A multi-time multispectral image feature level information fusion method based on iteration implicit regularization
  • A multi-time multispectral image feature level information fusion method based on iteration implicit regularization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] refer to figure 1 , the implementation steps of the present invention are as follows:

[0026] Step 1, input multi-temporal image X 1 and x 2 : Input two images before and after fusion acquired at different times in the same area, marked as X 1 and x 2 .

[0027] Step 2, perform superpixel extraction operation on two original multispectral images: use SLIC method to perform superpixel extraction operation on the original image;

[0028] 2a) Randomly initialize the seed point, that is, the cluster center: according to the set number of superpixels, evenly distribute the seed point in the two original multispectral images. The usual method is to randomly select a certain number of pixels in the image as the initial seed point.

[0029] 2b) Calculate the gradient values ​​of all pixels in the n×n neighborhood (generally n=3) of each seed, and use the seed point to move to the minimum gradient point in the neighborhood to replace the pixel value of the seed point as a...

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 multi-time multispectral image feature level information fusion method based on iterative implicit regularization. The method comprises the following steps: (1) inputting twomulti-time multispectral images; (2) realizing super pixel extraction; (3) performing unsupervised clustering on the superpixels to generate grouping information; (4) realizing feature extraction; (5) performing operation on the extracted features to generate a pseudo tag; (6) forming a training sample set according to the sample data, the pseudo label data and the group information; (7) selecting and initializing a classifier; (8) judging whether a termination condition is met or not, if yes, executing (10), and if not, executing (9); (9) training a classifier by using a method based on iteration implicit regularization, and returning to the step (8) after the classifier training is finished; and (10) classifying all the features by using a classifier to obtain a final fusion result image. According to the method, the change information of the two hyperspectral images can be distinguished through fusion, and different change types can be distinguished.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a multi-temporal multi-spectral image feature fusion method, in particular to a multi-temporal multi-spectral image feature-level information fusion method based on iterative implicit regularization, which can obtain a better fusion result image for eliminating The mutually exclusive and redundant information among them reduces the fuzzy uncertain information, and finally obtains useful and reliable image information in this scene, and can further obtain the changes in multi-temporal multispectral images in the same area by fusing the resulting images Part of it can be applied to disaster assessment before and after flood disasters, medical diagnosis, glacier change detection, earthquake disaster assessment, land resource detection, urban planning, environmental detection, video surveillance, etc. Background technique [0002] Multi-temporal and multi-spectral image featur...

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): G06K9/62G06T5/50
Inventor 马晶晶段莹莹李豪张明阳武越张育泽陈澜涛焦李成
Owner XIDIAN 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