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

Method for selecting hyperspectral remote sensing image bands based on partial least squares

A partial least squares, hyperspectral remote sensing technology, applied in the field of remote sensing image processing, can solve the problem of time-consuming calculation, achieve fast calculation speed, and avoid the effect of feature subset search

Inactive Publication Date: 2011-12-21
FUDAN UNIV
View PDF3 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This kind of method has clear physical meaning and is easy to implement, but the calculation is relatively time-consuming

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
  • Method for selecting hyperspectral remote sensing image bands based on partial least squares
  • Method for selecting hyperspectral remote sensing image bands based on partial least squares
  • Method for selecting hyperspectral remote sensing image bands based on partial least squares

Examples

Experimental program
Comparison scheme
Effect test

experiment example 1

[0041] Experimental example 1. AVIRIS hyperspectral remote sensing data

[0042] category Corresponding features Number of Classified Samples C1 Corn-notill 1256 C2 Corn-min 726 C3 Grass / Pasture 431 C4 Grass / Tress 626 C5 Hay-windowed 443 C6 Soybeans-notil 828 C7 Soybeans-min 2284 C8 Soybeans-clean 503 C9 Woods 1198

[0043] The experiment uses the hyperspectral images collected by the Airborne Visible / Infrared Imaging Spectrometer (AVIRIS) in 1992 at the Pine test site in Indiana, USA (provided by https: / / engineering.purdue.edu / ~biehl / MultiSpec / free download of this data). The image block size is 145 × 145 pixels, with a total of 220 spectral bands. The wavelength range is from 0.4 to 2.5 μm, the spectral resolution is 10nm, and the spatial resolution is 17m. This data has been widely used in classification research of remote sensing images.

[0044] Bands 1-4, 103-113 and 148-166 were remov...

experiment example 2

[0049] Experimental example 2. HYDICE hyperspectral remote sensing data

[0050] The experiment uses Washington DC hyperspectral images collected by the (Hyperspectral Digital Imagery Collection Experiment, HYDICE) sensor. The image block size is 1280 × 307 pixels, with a total of 210 spectral bands. The ground resolution of this data is as high as 2.8 m, with few mixed pixels, and the differences of various ground objects are obvious.

[0051] Remove the noise and water absorption bands 103-106, 138-148, 207-210, leaving 191 spectral bands. Take the 53rd, 32nd, and 20th bands as R, G, and B components to synthesize pseudo-color images, such as figure 2 shown.

[0052] According to the ground object information in the literature [12], the seven types of ground objects, namely Water, Grass, Shadow, Street, Path, Trees, and Roof, are selected for classification, and the rest of the area is used as a blank area and is not used for classification. The number of selected samp...

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 belongs to the technical field of hyperspectral remote sensing image processing and in particular provides a method for selecting hyperspectral remote sensing image bands based on partial least squares. The method has the following beneficial effects: based on the characteristic that components extracted by partial least squares maintain hyperspectral image variation information andhas high degree of correlation with classified information, the energy of the product of the spectrum matrix and the membership matrix is regarded as the standard of band selection and the recursive residual of the selected band is obtained through iteration to select the next group of bands to realize the process of band selection; the following defects of the traditional methods for selecting multispectral image bands can be effectively overcome: the computation complexity is high and relevant bands need to be removed; the hyperspectral remote sensing image classification experiment result shows that the hyperspectral remote sensing image has good classification effect after the method is used for selecting the bands; and the method has important application value for efficiently utilizing the information resources of the hyperspectral images.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and in particular relates to a hyperspectral remote sensing image band selection method based on a partial least square method. Background technique [0002] Hyperspectral remote sensing acquires information simultaneously on dozens to hundreds of very narrow and continuous spectral segments in the ultraviolet, visible, near-infrared, and mid-infrared regions of the electromagnetic spectrum, resulting in a complete and continuous spectral curve for each pixel [1] . The development of hyperspectral remote sensing technology provides people with detailed and accurate ground object spectral information, but a large number of highly correlated band information also brings difficulties to the further processing of hyperspectral images. High-dimensional data will not only cause redundancy and increase computational complexity, but also due to the Hughes phenomenon [2] (That is...

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): G06K9/62G06T7/00
Inventor 葛亮王斌张立明
Owner FUDAN UNIV
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