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

Fuzzy interval automatic determination method for object segmentation weight parameters of remote sensing image

A weight parameter, remote sensing image technology, applied in image analysis, image data processing, image enhancement and other directions, can solve cumbersome efficiency, low and other problems, and achieve the effect of accurate and automatic determination

Pending Publication Date: 2021-09-07
GUILIN UNIVERSITY OF TECHNOLOGY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for automatically determining the fuzzy interval of the weight parameter for the object-oriented segmentation method of remote sensing images. The two weight parameters of spectral heterogeneity and compactness need repeated experiments to select pairings, which are cumbersome and inefficient. Simplify the pairing and combination process of the two, and improve the work efficiency of image segmentation

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
  • Fuzzy interval automatic determination method for object segmentation weight parameters of remote sensing image
  • Fuzzy interval automatic determination method for object segmentation weight parameters of remote sensing image
  • Fuzzy interval automatic determination method for object segmentation weight parameters of remote sensing image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0088] The invention is a method for automatically determining fuzzy intervals of object-oriented segmentation weight parameters of remote sensing images, and the specific embodiments are as follows:

[0089] Step 1: Segment the remote sensing image for the first time.

[0090] Use the Mean Shift algorithm for figure 2 A QuickBird panchromatic image is segmented for the first time, wherein the MeanShift algorithm parameters are set to hs=30, hr=3, M=50, and the segmentation results are as follows image 3 shown.

[0091] Step 2, the calculation formula of the segmentation scale.

[0092] The segmentation scale f is given by the spectral heterogeneity Δh color and shape heterogeneity Δh shape Composition, its calculation formula is:

[0093] f=w color Δh color +w shape Δh shape ,w color ∈[0,1],w shape ∈[0,1],w color +w shape = 1

[0094] in,

[0095]

[0096] Δh shape =w compt Δh compt +w smooth Δh smooth

[0097] Shape heterogeneity Δh shape Medium sm...

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 fuzzy interval automatic determination method for object segmentation weight parameters of a remote sensing image, and the method comprises the steps: carrying out initial segmentation of a remote sensing image, and dividing the remote sensing image into a plurality of to-be-merged regions; combining segmentation scale calculation formulas composed of spectral heterogeneity and shape heterogeneity into a calculation formula composed of spectral heterogeneity, smoothness and compactness, and setting constraint conditions corresponding to segmentation weight parameters; establishing a normalized matrix of spectrum heterogeneity, smoothness and compactness; establishing a corresponding Vague set matrix; establishing a Vague set fuzzy entropy matrix; and based on the minimum Vague set fuzzy entropy, establishing a linear programming model and segmentation weight parameter lower and upper bound constraints, and automatically determining a segmentation weight parameter value in the solving process of the linear programming model. The pairing combination process of the segmentation weight parameters is simplified, the determination efficiency of the segmentation weight parameters is improved, and the working efficiency of remote sensing image segmentation is improved.

Description

technical field [0001] The invention relates to the technical field of object-oriented segmentation of remote sensing images, in particular to a method for automatically determining fuzzy intervals of weight parameters of object-oriented segmentation of remote sensing images. Background technique [0002] Remote sensing image segmentation is a process or a technology that extracts useful data from remote sensing images and converts them into information. It is the only way and the primary work to achieve subsequent image analysis, classification and processing. To the subsequent area description, feature extraction, target recognition, remote sensing classification and other accuracy. Object-oriented segmentation is the basis of object-oriented classification methods for remote sensing images, and the quality of segmentation directly affects the accuracy of image classification. In the object-oriented segmentation method, in order to obtain the optimal segmentation effect, ...

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): G06T7/11
CPCG06T7/11G06T2207/10032
Inventor 韦波王熙宇
Owner GUILIN UNIVERSITY OF TECHNOLOGY
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