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

Regression parameter transformation based method for extracting thematic information of remote sensing images

A technology of remote sensing images and thematic information, applied in the field of remote sensing, can solve problems such as legacy and adverse effects of classification, and achieve the effects of small information loss, reduced adverse effects, and convenient operation.

Inactive Publication Date: 2012-02-29
ZHEJIANG FORESTRY UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But these data compression methods also have disadvantages
If the orthogonal transformation method has a linear assumption, when the data does not meet the linear assumption, the selected principal component may contain unnecessary information, which will have an adverse effect on the classification, and the unselected principal component may also contain important information.

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
  • Regression parameter transformation based method for extracting thematic information of remote sensing images
  • Regression parameter transformation based method for extracting thematic information of remote sensing images
  • Regression parameter transformation based method for extracting thematic information of remote sensing images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention will be described in further detail below in conjunction with the embodiments and accompanying drawings.

[0037]The embodiment uses a water body extraction example from a TM image. From the consideration of water body information extraction, it is only necessary to divide the ground objects into two types: water body and non-water body. The difficulty in extracting water bodies is that water bodies and shadows are easily confused. In order to better illustrate the ability of the method of the present invention to distinguish water bodies and shadows, this embodiment divides land types into water bodies, shadows (including terrain shadows and cloud shadows) and others. There are 3 categories in total. The shadow itself is not a feature, but a special image caused by terrain or clouds blocking the electromagnetic radiation of the sun. The data are three full-view TM images received in 2007: 118 / 39, 118 / 40, and 119 / 39, covering northern Zhejiang an...

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 relates to a regression parameter transformation based method for extracting the thematic information of remote sensing images, mainly comprising the following steps of: selecting and classifying wavebands; sequencing according to the luminance value of a target land class; establishing a linear regression equation by respectively using a sequence number and the luminance value as an independent variable and a dependent variable; linearly stretching a slope a and an intercept b and rounding to the integers of 0-255; establishing a two-dimensional histogram and smoothing; transforming the density value of a single-class histogram into a probability value; making a two-dimensional code lookup table according to the single-class probability histogram; expanding the lookup tableto the whole space by using a mathematical morphology method; calculating the a and the b of each pixel of the images and looking up the land class code of the pixel in the lookup table after stretching and rounding the a and the b, thereby realizing the information extraction. The method has the advantage of transforming high-dimensional data into two-dimensional planes, thereby achieving the purposes of compacting data, being convenient for visual analysis, eliminating the bad influences of redundant data and improving the precision of the information extraction.

Description

【Technical field】 [0001] The invention belongs to the technical field of remote sensing, in particular to a method for extracting thematic information of remote sensing image dimensionality reduction and compression based on regression parameter transformation. 【Background technique】 [0002] Thematic information extraction from remote sensing images is the core issue in the application of remote sensing technology. The so-called thematic information refers to a certain type of land cover, such as water bodies, agricultural land, roads and other specialized information. At present, the commonly used methods can be divided into the following two categories: one is the visual interpretation method, which means that the interpreter extracts information from printed paper remote sensing images or extracts information on a computer screen based on various experiences. The advantage of this method is that it is simple and easy to implement, but the disadvantage is that the extrac...

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 Patents(China)
IPC IPC(8): G06K9/46G06T9/00G01S17/89
Inventor 王鑫葛宏立杜华强
Owner ZHEJIANG FORESTRY UNIVERSITY
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