Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for improving remote sensing image classification by using main color data fusion

A data fusion and remote sensing image technology, applied in the field of remote sensing images, can solve the problem of insensitivity to color features, and achieve the effect of improving classification accuracy, performance and classification accuracy.

Inactive Publication Date: 2020-04-17
青海省地理信息中心
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] When the convolutional neural network processes remote sensing image classification, it can quickly and comprehensively extract position and shape-related features; however, it is very insensitive to color features

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
  • Method for improving remote sensing image classification by using main color data fusion
  • Method for improving remote sensing image classification by using main color data fusion
  • Method for improving remote sensing image classification by using main color data fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The present invention will be further described below in combination with embodiments.

[0028] In an embodiment of the present invention, the method for improving remote sensing image classification by using main color data fusion includes the following steps:

[0029] S1: When fusing the main color and position and shape related features, use the differential evolution algorithm to find the optimal feature proportion;

[0030] S2: Set the color feature weight as α, and use the following formula to calculate the fitness value of individual α:

[0031] fit(α)=ZVAL-ERR Top10 (1)

[0032]

[0033]

[0034] S3: Use the adaptive data fusion algorithm based on differential evolution to update each individual αi, and put the generated new samples into the original sample library.

[0035] Preferably, in the formula in S2: n refers to the number of epochs, VALi refers to the average classification result of one cross-validation, ZVAL refers to the average classificat...

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 provides a method for improving remote sensing image classification by using main color data fusion. The method for improving remote sensing image classification through main color datafusion comprises the following steps that S1, when main color and position and shape related features are fused, using a differential evolution algorithm for searching for the optimal feature proportion; S2, setting a color feature weight as alpha, and calculating an adaptive value of an individual alpha by utilizing a formula; and S3, updating each individual alpha i by using an adaptive data fusion algorithm based on differential evolution, and putting a generated new sample into an original sample library. The method for improving remote sensing image classification through main color datafusion has the advantages that design is reasonable, classification precision can be improved, and therefore the performance of a discriminator for discriminating real images and generating images isimproved.

Description

technical field [0001] The invention relates to the technical field of remote sensing images, in particular to a method for improving classification of remote sensing images by using main color data fusion. Background technique [0002] Remote sensing images are films (or photos) that only record the size of electromagnetic waves of various ground objects. In remote sensing, they mainly refer to aerial photos and satellite photos. Remote sensing images processed by computers must be digital images, and analog images obtained by photography must be digital images. Use an image scanner to perform analog / digital (A / D) conversion; the digital data obtained by scanning must be transferred to a general carrier such as CCT that can be read by a general digital computer, and computer image processing must be carried out in the image processing system The image processing system is composed of hardware (computer, display, digitizer, tape drive, etc.) and software (with functions of d...

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): G06K9/62
CPCG06F18/23213G06F18/241G06F18/253
Inventor 李伟祝茂良许长军杨鸿海李红英
Owner 青海省地理信息中心
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com