Non-supervision and Fourier kernel function based remote sensing image pixel purity identification method

A technology of remote sensing images and identification methods, applied in image analysis, image data processing, instruments, etc., can solve problems such as low accuracy and inconvenient application

Inactive Publication Date: 2014-04-16
CHANGCHUN INST OF TECH +1
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, in the existing technology, the recognition of the purity of remote sensing image pixels is mainly a qualitative method, which has the disadvantage of low precision, and it is inconvenient to carry out subsequent applications based on the purity of remote sensing image pixels

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
  • Non-supervision and Fourier kernel function based remote sensing image pixel purity identification method
  • Non-supervision and Fourier kernel function based remote sensing image pixel purity identification method
  • Non-supervision and Fourier kernel function based remote sensing image pixel purity identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] The present invention is described in detail below in conjunction with accompanying drawing:

[0072] Such as figure 1 As shown, the present invention provides a remote sensing image pixel purity recognition method based on unsupervised and Fourier kernel function, comprising the following steps:

[0073] S1, read the original remote sensing image; wherein, the original remote sensing image is composed of M*N pixels in M ​​rows and N columns, and the pixel set is S={S 1 , S 2 ,...,S M×N};

[0074] S2. Segment the original remote sensing image to obtain P relatively independent objects with a size greater than or equal to 1 pixel, expressed as: V={V 1 , V 2 ,...,V P};

[0075] In this step, the image segmentation of the original remote sensing image can be performed based on the maximum a posteriori probability criterion by using the Markov random field image module.

[0076] What needs to be emphasized is that in the subsequent steps, the present invention takes...

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 non-supervision and Fourier kernel function based remote sensing image pixel purity identification method. The non-supervision and Fourier kernel function based remote sensing image pixel purity identification method comprises performing segmentation on the original remote sensing image to obtain P objects; performing clustering operation on the P objects to obtain n block masses; setting any block mass ti to comprise d objects and executing following operation which comprises calculating the Fourier kernel function hull convexity which is corresponding to the block mass ti, calculating the distance from the specified object Vf to every object in the b objects to obtain the object T which has the smallest distance from the specified object Vf, wherein the distance from the specified object Vf to the object T is M1, calculating the distance M2 from the specified object Vf to the center of the hull convexity, calculating the distance M3 from the object T to the center of the hull convexity, and calculating the mapping distance value M2 / (M3+M1) which serves as the integral purity value of the specified object Vf. The non-supervision and Fourier kernel function based remote sensing image pixel purity identification method serves as a quantitative method and accordingly the pixel purity of a remote sensing image can be identified accurately.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image analysis and processing, and in particular relates to a remote sensing image pixel purity recognition method based on unsupervised and Fourier kernel functions. Background technique [0002] Remote sensing images are the records and reflections of sensor detection elements reflecting or emitting electromagnetic radiation energy on target objects. Remote sensing images with high spatial resolution can describe objects more finely and provide rich detailed information. [0003] Pixel is the basic unit of remote sensing image, mainly including two types: mixed pixel and pure pixel. Among them, the mixed pixel refers to the pixel that contains multiple types of ground objects. The main reasons are: the complexity of the distribution of ground objects, the influence of various environments in the process of electromagnetic radiation transmission, and the physical characteristics of the det...

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): G06T7/00
Inventor 潘欣张素莉门玉琢孙浩鹏刘国松赵健李天宇龚宇辉
Owner CHANGCHUN INST OF TECH
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