Hyperspectral image waveband selection method based on biclustering and neighborhood analysis

A hyperspectral image and neighborhood analysis technology, applied in the field of image processing, can solve problems such as algorithm defects, and achieve the effect of improving accuracy and clustering accuracy

Active Publication Date: 2016-10-05
XI'AN INST OF OPTICS & FINE MECHANICS - CHINESE ACAD OF SCI
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the results of this type of algorithm depend too much on the clustering process. In the case of poor clustering results, this algorithm has obvious defects.

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 image waveband selection method based on biclustering and neighborhood analysis
  • Hyperspectral image waveband selection method based on biclustering and neighborhood analysis
  • Hyperspectral image waveband selection method based on biclustering and neighborhood analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Such as figure 1 As shown, taking the Indian tree data set as an example, the steps of the present invention are as follows:

[0033] Step 1, after inputting an Indian tree image, extract PHA features (sub-features) and original band features (main features) from the original image at the same time. The PHA feature is a new type of dual spectral angle between adjacent pixels constructed by performing neighborhood analysis on hyperspectral pixels in the present invention. This feature includes two kinds of spectral angles. Angle A, and the second is an angle E between adjacent bands.

[0034] Specifically, the feature value of one band of one pixel is taken as a unit, and the bispectral angle is the neighborhood information of the unit. The following is an explanation of the two spectral angles: On the one hand, a two-dimensional vector is formed by the values ​​of each band on two pixels, and two adjacent bands k and k-1 are taken, and the corresponding two vectors ar...

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 provides a hyperspectral image waveband selection method based on biclustering and a neighborhood analysis. The method comprises the following steps of extracting a dual-spectral angle characteristic and a hyperspectral-image original wave band; clustering the characteristic; clustering the acquired characteristics respectively and then constructing connection between two clustering results; according to the acquired wave band clustering results, selecting one representative from each cluster, and simultaneously considering a specificity of each representative and expressivity of each representative in the corresponding cluster so as to deciding a cluster representative, which means that the final wave band is selected; and using the acquired wave band to carry out hyperspectral image classification. In the invention, a bicharacteristic idea is provided, and a limitation that a wave band gray value is only used as a spectral characteristic in a traditional cluster algorithm is overcome so that wave band selection precision is increased.

Description

technical field [0001] The invention belongs to the technical field of image processing, and is mainly aimed at band selection in hyperspectral images. In practical applications, the selected important bands can be used to classify, segment, and detect abnormalities in hyperspectral images to obtain better results. Background technique [0002] Band selection in hyperspectral images is an effective feature extraction technique. Usually, we need to compress high-dimensional hyperspectral images into low-dimensional ones, so as to improve the processing efficiency of hyperspectral images. However, the high similarity between bands and the diversity of the most specific bands corresponding to different hyperspectral pixels make the selection of representative bands difficult. In addition, it is often not efficient and practical to distinguish bands only by using the original spectral features of hyperspectral images. Therefore, introducing appropriate hyperspectral features t...

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): G06T7/00G06K9/62
Inventor 袁媛王琦林健哲
Owner XI'AN INST OF OPTICS & FINE MECHANICS - CHINESE ACAD OF SCI
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