Check patentability & draft patents in minutes with Patsnap Eureka AI!

High spectrum remote sensing image combined weighting random sorting method

A hyperspectral image and hyperspectral remote sensing technology, which is applied in the field of joint weighted random classification of hyperspectral remote sensing images, can solve problems such as not being able to meet the requirements of image classification accuracy, improve computer processing speed, reliably classify remote sensing images, and improve overall classification accuracy Effect

Inactive Publication Date: 2004-02-04
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, when processing, it is not enough to use only one classification algorithm, and it cannot meet the classification accuracy requirements for images.
In addition, since the size of hyperspectral images is generally on the order of hundreds of megabytes, processing speed is also a problem to be solved when applying these existing methods for image classification decision-making

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
  • High spectrum remote sensing image combined weighting random sorting method
  • High spectrum remote sensing image combined weighting random sorting method
  • High spectrum remote sensing image combined weighting random sorting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] In order to better understand the technical solutions of the present invention, the implementation manners of the present invention will be further described below in conjunction with the accompanying drawings.

[0020] figure 1 A kind of overall block diagram that is used for hyperspectral remote sensing image classification processing that the present invention proposes, the input of data file is figure 2 (a) The OMIS hyperspectral remote sensing image, whose band is 117, has a file size of 662 pixels×686 pixels, and a spatial resolution of 20m. The image contains various features such as land (farmland), buildings, green space and water body. The specific implementation details of each part are as follows:

[0021] 1. Extraction of data characteristics, obtaining characteristic data of hyperspectral and panchromatic images Using the ENVI_DISPLAY_BANDS function of the ENVI / IDL development platform, the file size, number of bands and spatial resolution can be displa...

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

In the present invention, the partitioning image is roughly classified by modified adaptive minimum distance method with utilizing development language provided by image processing and developing platform ENVI / IDC to give out a certain right coefficient as per file size of high spectrum image and speed of computer processing. Then, the fine classification is finalized by error norm and supporting norm function with utilizing cluster repeating iteration, according to another weighed coefficient. Finally, montage is carried out to obtain complete piece classified image of high spectrum-remote sensing image according to the classified result of partitioning image.

Description

Technical field: [0001] The invention relates to a method for joint weighted random classification of hyperspectral remote sensing images, which performs high-precision and fast classification on preprocessed hyperspectral remote sensing images. It is a core technology for classification and decision-making of remote sensing images. It can be widely used in processing systems, digital city spatial information systems and other fields. Background technique: [0002] Distinguishing multiple targets contained in one or more remote sensing images in the same area is called classification of remote sensing images, or fusion of classification decisions. Try to identify the type of ground features as accurately as possible. This technology plays a very important role in regional planning and surface ecosystem research. For example, for a specified ground object, the information characteristics of its remote sensing image are not static, not only with the change of seasons and met...

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): G06F7/24
Inventor 周前祥敬忠良
Owner SHANGHAI JIAO TONG UNIV
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