Hyperspectral remote sensing image band selection method based on time sequence important point analysis

A hyperspectral remote sensing and time series technology, applied in the field of hyperspectral remote sensing image band selection, can solve problems such as high computational complexity and complex computational process

Inactive Publication Date: 2010-10-13
HOHAI UNIV
View PDF4 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method effectively removes redundancy and greatly improves the classification accuracy. It is feasible and effective, but the calculation process is complicated.
[0004] To sum up, the existing hyperspectral remote sensing image band selection methods all have the problem of high computational complexity, and put forward extremely high requirements for the software and hardware configuration of the image processing system.

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
  • Hyperspectral remote sensing image band selection method based on time sequence important point analysis
  • Hyperspectral remote sensing image band selection method based on time sequence important point analysis
  • Hyperspectral remote sensing image band selection method based on time sequence important point analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The technical scheme of the present invention is described in detail below in conjunction with accompanying drawing:

[0051] Here, the public test image data of the Washington DC Mall area acquired by the HYDICE spectrometer is still used as an example to specifically illustrate the specific implementation of the present invention. The wavelength range of the image data is from 0.40 μm to 2.40 μm, and contains 210 continuous bands in total. After removing invalid bands, there are 191 effective bands left. The image contains seven categories such as grass, roofs and roads, and 137 known ground truth categories have been manually marked. In order to ensure that the training and test data sets do not overlap, the marked areas with odd numbers are taken as training samples. , the labeled regions with even numbers are used as test samples.

[0052] Use the method of the present invention to carry out band selection to this image, as attached figure 1 As shown, follow the ...

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 discloses a hyperspectral remote sensing image band selection method based on time sequence important point analysis, which realizes the selection of characteristic bands by clustering the data sample of a hyperspectral remote sensing image into K categories by a K-means clustering method based on DBI (Data Base Index), using wavelet analysis to carry out noise-removal processing and then extracting important points according to the time sequence analysis. Compared with the prior art, the method has the advantages of low computation complexity and convenient and rapid realization process and provides a brand-new idea for reducing dimensions of high-dimension data.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method for selecting bands of hyperspectral remote sensing images. Background technique [0002] With the rapid development of science and technology and the rapid progress of aerospace technology and remote sensing science, the available hyperspectral remote sensing data is growing at an alarming rate. How to process and utilize such rich spectral information, and hope to improve learning efficiency and speed, It is a hot topic of research. One of the most important prerequisites for processing hyperspectral remote sensing data is to reduce the number of bands. Common dimensionality reduction methods are divided into feature extraction and feature selection. At this time, feature selection is band selection. Usually feature extraction will change the original physical meaning of spectral bands, which is not conducive to ground object inversion. Therefore, many researchers are ...

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): G06K9/62G06T7/00G06K9/40
Inventor 李士进杨金花余宇峰万定生冯钧朱跃龙
Owner HOHAI UNIV
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