Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Multispectral image change detection method for analyzing kernel fusion based on kernel intermodal factor

A multi-spectral image and spectral image technology, applied in the field of image change detection, can solve the problems of not considering the correlation of various characteristics, so as to improve the accuracy and achieve the effect of feature fusion

Active Publication Date: 2017-06-16
XIDIAN UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when this method deals with multispectral images, it does not consider the correlation between various characteristics, and cannot fully mine and fuse various image features, so its detection accuracy needs to be further improved.

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
  • Multispectral image change detection method for analyzing kernel fusion based on kernel intermodal factor
  • Multispectral image change detection method for analyzing kernel fusion based on kernel intermodal factor
  • Multispectral image change detection method for analyzing kernel fusion based on kernel intermodal factor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] refer to figure 1 , the specific implementation process of the present invention is as follows:

[0030] Step 1. Transform the preprocessed spectral image to HIS space.

[0031] Given the original preprocessed three-channel spectral image of the same size at two moments, denoted as {R t ,G t ,B t},t=t 0 ,t 1 , where R t ,G t ,B t respectively represent the three-channel spectral image in the original RGB space;

[0032] Use the RGB-HIS transformation to transform the three-channel spectral image into the HIS space, and obtain the two-time spectral image of the HIS channel {H t ,I t ,S t}, where H t is the hue component of the spectral image at time t, S t is the saturation component of the spectral image at time t, I t is the intensity component of the spectral image at time t.

[0033] Among them, R in the RGB space represents the red component of the spectral image, G represents the green component of the spectral image, and B represents the blue compon...

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 multispectral image change detection method for analyzing kernel fusion based on a kernel intermodal factor, and mainly solves the problems that the existing difference kernel function cannot fully mine and use the correlation between multiple features of the image and then the detection accuracy is low. The implementation process comprises the steps that 1) a two-time three-channel spectral image is transformed to an HIS space so as to obtain tone, saturation and intensity information of the two-time image; 2) the color features and the intensity texture features of the two-time image are extracted according to the result of the step 1); 3) a color difference kernel function matrix and an intensity texture difference kernel function matrix are obtained by using the extracted features; 4) weighting fusion is performed on the two matrixes obtained in the step 3) so as to form a composite kernel function matrix and adaptively select the optimal weighting coefficient; and step 5) the composite kernel function matrix is inputted to a support vector machine SVM to be detected so as to obtain the change detection result. The method is high in detection accuracy, stable in result and low in computing burden and can be used for multispectral image change detection.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image change detection method, which can be used for monitoring and evaluating ground object state changes on multi-spectral images. Background technique [0002] Multispectral images are digital images of Earth observation in multiple bands acquired by remote sensing satellites. Multispectral image change detection determines the characteristics and process of ground object changes by analyzing multiple multispectral images observed at different times in the same area. Multispectral images have rich spectral information and can well reflect the characteristics of ground objects. Multispectral image change detection has a prominent role in military and civilian fields. [0003] The most commonly used multispectral image change detection method is the change vector analysis method CVA, which defines the multi-channel original two-time image as a vector, a...

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): G06K9/00G06K9/34G06K9/62
CPCG06V20/13G06V10/267G06F18/2411
Inventor 李明谭啸峰张鹏贾璐吴艳
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
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