Hyperspectral remote sensing image segmentation method based on K-means clustering

A k-means clustering and hyperspectral remote sensing technology, applied in the fields of instruments, character and pattern recognition, computer parts, etc., can solve the problems of inaccurate segmentation of hyperspectral remote sensing images and insufficient use of a large amount of information in hyperspectral remote sensing images. , to achieve accurate segmentation results

Inactive Publication Date: 2019-08-16
HARBIN ENG UNIV
View PDF10 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to solve the problem that the current clustering segmentation method does not make full use of the large amount of information contained in hyperspectral remote sensing images, resulting in inaccurate segmentation of hyperspectral remote sensing images, and proposes a method based on K-means clustering hyperspectral remote sensing image segmentation method

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 segmentation method based on K-means clustering
  • Hyperspectral remote sensing image segmentation method based on K-means clustering
  • Hyperspectral remote sensing image segmentation method based on K-means clustering

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0023] Specific implementation mode one: as figure 2 Shown: a kind of hyperspectral remote sensing image segmentation method based on K-means clustering described in the present embodiment, this method comprises the following steps:

[0024] Step 1, using principal component analysis (Principal Component Analysis, PCA) to reduce the dimensionality of the hyperspectral remote sensing image to obtain a three-dimensional RGB pseudo-color image, the dimension of the hyperspectral remote sensing image is d;

[0025] Use the K-means method (K value needs to be specified in advance) to cluster and segment the obtained 3D RGB pseudo-color image, and obtain K cluster centers of the cluster segmentation results; use the obtained K cluster centers as hyperspectral remote sensing images The initial cluster centers of each dimension of ;

[0026] Step 2, using the initial clustering center to cluster each pixel in each dimension in the hyperspectral remote sensing image, and obtain the c...

specific Embodiment approach 2

[0034] Specific implementation mode two: the difference between this implementation mode and specific implementation mode one is: the specific process of said step two is:

[0035] Use the initial clustering center to cluster each pixel in each dimension in the hyperspectral remote sensing image, that is, assign each pixel in each dimension to the nearest clustering center according to the Euclidean distance , to obtain the clustering result.

[0036] For the i'th pixel in the hyperspectral remote sensing image, assign the spectral value of the i'th pixel to the initial clustering center closest to the i'th pixel. Similarly, for the hyperspectral remote sensing image For each pixel in , perform the same operation until all clustering is completed.

specific Embodiment approach 3

[0037] Specific implementation mode three: the difference between this implementation mode and specific implementation mode two is: the specific process of the step three is:

[0038] The d-dimensional label vector X of the i-th pixel in the hyperspectral remote sensing image i The expression is:

[0039] x i ={c 1 ,c 2 ,...,c d},i=1,2,...,m×n

[0040] Among them: m×n represents the total number of pixels in the hyperspectral remote sensing image, c 1 Represents the category label of the i-th pixel in the hyperspectral remote sensing image in the first dimension, c 2 Represents the category label of the i-th pixel in the hyperspectral remote sensing image in the second dimension, c d Represents the category label of the i-th pixel in the hyperspectral remote sensing image in the d-th dimension, c j The value of is [1,K], and c j The value of is a positive integer, j=1,2,...,d;

[0041] Scan each pixel in turn, and read in the category label data of each pixel;

[00...

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 segmentation method based on K-means clustering, and belongs to the technical field of clustering segmentation of hyperspectral remote sensing images. According to the invention, the problem of inaccurate segmentation of the hyperspectral remote sensing image by the existing clustering segmentation method is solved. According to the invention, collaborative clustering is carried out on d dimensions of the hyperspectral remote sensing image; when K-means iteration is performed on a hyperspectral remote sensing image each time, clustering results of d dimensions are cooperated; and after each K-means iteration is finished, a probability value of the pixel point belonging to each category is calculated by utilizing d clustering results of each pixel point, then a new clustering center is calculated by utilizing the obtained probability value, and a next iteration process of each dimension is started according to the same clustering center until a final clustering result is obtained. Compared with an existing method, the method has the advantage that the segmentation result is more accurate. The method can be applied to the technical field of clustering segmentation of hyperspectral remote sensing images.

Description

technical field [0001] The invention belongs to the technical field of clustering and segmentation of hyperspectral remote sensing images, and in particular relates to a hyperspectral remote sensing image segmentation method. Background technique [0002] Image segmentation is to divide the image into several regions corresponding to objects, which is convenient for locating the position and range of the target of interest in the image, and belongs to the intermediate step from image processing to image analysis. Image clustering and segmentation technology regards the image segmentation problem as an application of clustering technology, and marks different regions of the image by clustering the image. [0003] Specifically, the image clustering and segmentation technology is to represent the pixels in the image space as points in the corresponding feature space, and then gather all the points in the feature space into clusters according to certain rules to achieve the purp...

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): G06K9/34G06K9/62
CPCG06V10/26G06F18/23213
Inventor 刘咏梅姚爱红门朝光
Owner HARBIN ENG 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