Mixed pixel decomposition and end member extraction method

A hybrid pixel decomposition and endmember technology, which is applied in the fields of instruments, character and pattern recognition, computer parts, etc. Effect

Inactive Publication Date: 2012-02-08
张灵芝
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With the application of new sensors, the improvement of spectral resolution, and the application of spatial structure information, there are more effective solutions to the phenomenon of "different objects with the same spectrum", but there is still no good solution for "same object with different spectra".

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0006] 1 From the perspective of imaging mechanism, study the physical model of pixel decomposition. From the physical mechanism of mixed pixel imaging, the mixed pixel decomposition model can be divided into three types: linear model, nonlinear model and geometric optics model [Pan Jianping, 2005]. The linear model considers that the reflectance of a single pixel in each spectral band is expressed as a linear combination of its component characteristic reflectance and their respective contents.

[0007] 2. In the actual formation of remote sensing images, photons that cause spectral reflectance do not only reflect once on the surface of the earth, but reflect and scatter multiple times. This is the physical difference between linear and nonlinear models. The linear model assumes that the photons arriving at the sensor interact with the surface once; the nonlinear model assumes that the photons are transmitted and scattered through multiple objects, resulting in nonlinear mix...

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 mixed pixel decomposition and end member extraction method. Remote sensing refers to the modern application technology which obtains surface information through sensors on various platforms run in the upper air or an outer space, and obtains the shape, the location, the spatial distribution, the category, the nature and the like of a surface object through an information processing method. The remote sensing is originated from 1960s, and integrates aerospace, computer, sensor, information processing and other technologies. An obtained remote sensing image contains rich spectral and spatial information, and is widely applied to a plurality of aspects, such as environment monitoring, surveying and mapping, geological rock and mineral identification, agriculture, forestry, archaeology, tourism, military affairs and the like.

Description

【Technical field】 [0001] The invention relates to a method for decomposing mixed pixels and extracting endmembers thereof. In particular, the ground resolution and spectrum resolution of acquired remote sensing data are fundamentally improved, but the classification accuracy is not improved as it should be. Although this is due to factors such as processing objects, classification strategies, and comparison methods, it also shows that with the continuous use of new sensors, the development of remote sensing information processing technology lags behind the development of sensors. Therefore, it is particularly urgent to carry out the research and development of remote sensing information processing technology. . 【Background technique】 [0002] "Same object with different spectrum" and "different object with same spectrum" are one of the important reasons that affect the processing accuracy in remote sensing information processing. "Same object with different spectrum" means...

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
Inventor 张灵芝
Owner 张灵芝
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