Band selection method for hyperspectral images based on low-rank representation

A technology of hyperspectral image and low rank representation, applied in the field of image processing, it can solve the problems of not fully considering feature correlation, unable to select feature subsets, and missing important features, so as to reduce processing complexity and improve anti-interference. ability, the effect of improving classification accuracy

Active Publication Date: 2018-04-17
XIDIAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it still results in the loss of important features
[0011] The above methods only consider the overall structure of the features, but do not fully consider the correlation between the features, so the optimal feature subset cannot be selected, resulting in low classification accuracy.

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
  • Band selection method for hyperspectral images based on low-rank representation
  • Band selection method for hyperspectral images based on low-rank representation
  • Band selection method for hyperspectral images based on low-rank representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] refer to figure 1 , the invention mainly includes three parts: low-rank representation of hyperspectral data, band selection of hyperspectral data and classification of selected bands. The following are the implementation steps of these three parts:

[0033] 1. Low-rank representation of hyperspectral data

[0034] Step 1: Convert the hyperspectral data into a two-dimensional matrix Y.

[0035] Input raw hyperspectral data D∈R M×N×L , since the hyperspectral data is a three-dimensional matrix, in order to facilitate subsequent processing, it is necessary to convert the hyperspectral data into a two-dimensional matrix Y∈RQ×L , where M×N represents the number of pixels, L represents the number of bands, Q=M×N, the hyperspectral image contains c-type pixels, each pixel of the image is a sample, and R represents the real number field.

[0036] Step 2: Normalize the two-dimensional matrix Y to obtain the hyperspectral matrix X∈R Q×L .

[0037] pair transformed two-dimen...

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 image band selection method based on low-rank representation, which mainly solves the problems of high hyperspectral data processing complexity and low hyperspectral image classification accuracy. The processing process is: (1) acquire hyperspectral data and normalize the data; (2) perform low-rank representation on the processed hyperspectral data; (3) use the enhanced Lagrangian multiplier method ALM Solve the low-rank representation coefficient; (4) cluster the bands according to the low-rank representation coefficient; (5) select a representative band from each cluster as the final selected band; (6) classify the selected bands . The present invention not only removes redundant information between bands, but also selects bands containing large amounts of information, which are more conducive to classification, improve the classification accuracy of hyperspectral images, and reduce the complexity of data processing. Dimensionality reduction for hyperspectral data.

Description

technical field [0001] The invention belongs to the technical field of image processing and relates to the selection of hyperspectral image bands, which can be applied to dimensionality reduction of hyperspectral data and reduce the computational complexity of data processing. Background technique [0002] Hyperspectral remote sensing technology is an important remote sensing technology developed in the 1920s. The hyperspectral imager can obtain almost continuous surface object spectrum images under the condition of multi-band and narrow spacing, which makes the hyperspectral image have higher spatial resolution and spectral resolution than the traditional remote sensing image, and is used in agriculture, Geology, coastal and inland water environment, atmospheric research, global environmental research and other fields have been widely used. However, hundreds or even thousands of bands also bring problems such as large data volume, "dimension disaster", information redundan...

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): G06K9/62
CPCG06F18/211G06F18/2411
Inventor 张向荣焦李成韩超冯婕侯彪白静马文萍马晶晶
Owner XIDIAN 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