A semi-supervised hyperspectral image dimensionality reduction method based on improved k-means clustering

A K-means and hyperspectral technology, which is applied in the field of hyperspectral remote sensing image processing, can solve the problems of not distinguishing the difference in importance, achieve fast dimensionality reduction, high classification accuracy, and reduce the amount of calculation

Inactive Publication Date: 2016-02-10
HOHAI UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Using the simple average method when selecting the cluster center, there is no difference in the importance of different bands with different information content

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
  • A semi-supervised hyperspectral image dimensionality reduction method based on improved k-means clustering
  • A semi-supervised hyperspectral image dimensionality reduction method based on improved k-means clustering
  • A semi-supervised hyperspectral image dimensionality reduction method based on improved k-means clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Example 1: Experimental data The images of the Indian Pines area acquired by the AVIRIS sensor in June 1992 in the northwestern part of Indiana. The data covers 220 spectral bands from 0.4 to 2.4um spectral interval, with a spectral resolution of 10nm and a spatial resolution of 20m. After preprocessing the dataset to remove water absorption and low SNR bands, 202 bands remained. The size of the data is 145×145, and it contains 16 different object types, each object has a different number of sample data; in the experiment, the average value of all samples of each object is used as the typical spectral feature of the object.

[0057] Such as Figure 4 As shown, the specific implementation steps are:

[0058] (1) Carry out data preprocessing on the original hyperspectral remote sensing image data, remove noise bands, and then determine the number of bands k to be selected, typical spectral data and training sample data.

[0059] (2) Choose B 1 and B 2 As the initial ...

Embodiment 2

[0074] Example 2: The hyperspectral image Cuprite data of band 224 in the Nevada region acquired by the AVIRIS sensor on June 19, 1997, the size of the sub-image is 350×350 pixels, and the spatial resolution of the data is 20m. After removing the water absorption and low SNR bands, 189 bands were retained. The image contains five minerals: Alunite, Buddingtonite, Calcite, Kaolinite and Muscovite. According to field investigation, the image actually contains more than 20 kinds of minerals.

[0075] In order to verify the proposed k-value estimation algorithm, this experiment is designed. According to the existing literature, the VD of the data, that is, the number of end members, is about 22. Therefore, theoretically speaking, when using K-means clustering on this data, its k value should also be around 22. Algorithm RICD, R 2 、SR 2 and the experimental results of pseudoF as Figure 6(a) to Figure 6(d) shown.

[0076] According to the theory of evaluating the number of k...

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 semi-supervised hyperspectral image dimension reduction method based on improved K-means clustering. The semi-supervised hyperspectral image dimension reduction method comprises the following steps: 1), selecting a hyperspectral image needing dimension reduction and a typical ground object spectrum thereof; 2), using a similarity non-supervised method to select wave bands for the image, and determining the wave band that replaces the K-means initial clustering center; 3), inputting the typical ground object spectrum of the image to the K-means, calculating the distance between the wave bands, and distributing each wave band to the nearest clustering center thereof; 4), using each re-calculated clustering centre to replace the originally specified initial clustering centre; 5), calculating the distance between each current wave band and the current clustering centre, and distributing the wave band to the nearest clustering center thereof; 6), constantly repeating steps 4) and 5) until the clustering centers of all the wave bands do not change any more, and dimension reduction characteristic data is acquired; and 7), calculating the ratio of a between-class distance to an intra-class distance at the moment. The semi-supervised hyperspectral image dimension reduction method provided by the invention has such characteristics as low complexity, high adaptability and the like.

Description

technical field [0001] The invention belongs to the technical field of hyperspectral remote sensing image processing, and in particular relates to a semi-supervised hyperspectral image dimensionality reduction method based on improved K-means clustering. Background technique [0002] Hyperspectral Remote Sensing (Hyperspectral Remote Sensing) refers to the technology of using many narrow electromagnetic wave bands to obtain data about objects. It is one of the major technological breakthroughs in earth observation in the last 20 years of the 20th century. Frontier technology of remote sensing. Compared with conventional multispectral remote sensing, hyperspectral data has the characteristics of large data volume, many narrow bands, strong correlation between bands, more information redundancy, and map integration. However, it is precisely its massive data and high-dimensional features that bring great difficulties to the transmission and storage of hyperspectral data, and a...

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): G06T7/00
Inventor 苏红军李茜楠
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