Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Hyperspectral image semi-supervised classification method based on space-spectral information

A hyperspectral image and classification method technology, applied in the field of pattern recognition, image processing, and semi-supervised classification using hyperspectral image spectral information and spatial information, which can solve the problem of ignoring spatial dimension information and spectral information to improve classification accuracy. And other issues

Inactive Publication Date: 2016-10-26
NORTHWEST UNIV(CN)
View PDF4 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Traditional classification methods usually only use the information on the spectral dimension of data, but ignore the information contained in the spatial dimension, and the effect of a single spectral information on the classification accuracy is limited.

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 semi-supervised classification method based on space-spectral information
  • Hyperspectral image semi-supervised classification method based on space-spectral information
  • Hyperspectral image semi-supervised classification method based on space-spectral information

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0104] The experimental data was taken in 1992 by AVIRIS at the Indian Pines experimental base in northwest Indiana, USA. The data contains images of 145×145 size in 224 bands with a spatial resolution of 20 m and a wavelength range of 0.4-2.5 μm (water absorption bands 104-108, 150-163, and 220 were removed before the experiment, and 200 bands were actually used). It contains farmland, forest, and a variety of other native vegetation.

[0105] In this embodiment, the specific parameters set by the method are:

[0106] Randomly select 25% of the total samples as the test sample set T, 75% as the training sample set, select N=9 categories for classification, use numbers 1 to 9 to represent different categories, and select s= for each category from the training sample set 15 samples, a total of n=135 labeled samples constitute the initial training sample set D l ={(x l1 ,y l1 ),…,(x l135 ,y l135 )}, the remaining samples are the unlabeled sample set U; set the maximum freq...

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 semi-supervised classification method based on space-spectral information. The hyperspectral image semi-supervised classification method combines spectral information and spatial information in a hyperspectral image to act on a support vector machine classifier, adopts a self-training semi-supervised classification framework, utilizes an active learning method as a sample selecting strategy of semi-supervised classification, decomposes initial classification results obtained through semi-supervised classification according to classes so as to obtain various classes of binary images as input images of an edge preserving filter, regards a first principal component content as a reference image of the filter, utilizes the edge preserving filter to perform local smoothing, eliminates noise, and classifies image elements according to a class with maximum probability, thus the classification process is completed. The hyperspectral image semi-supervised classification method combines the spectral information and the spatial information to improve the classifiability of classes, utilizes the self-training semi-supervised classification framework to solve the classification problem of hyperspectral image small samples, can effectively eliminate spot-like errors in the initial classification results, and increases classification precision.

Description

technical field [0001] The invention belongs to the field of information technology, relates to pattern recognition and image processing technology, and in particular relates to a semi-supervised classification method using spectral information and spatial information of hyperspectral images in combination. Background technique [0002] The classification of hyperspectral image (spectral image with spectral resolution in the range of 10l) is an important content of hyperspectral remote sensing data information processing, and it is also an important way for people to obtain useful information from remote sensing images. Hyperspectral image classification is based on the spatial and spectral characteristics of image pixels, and determines and labels the category attributes of different types of ground objects represented by each pixel or a relatively homogeneous group of pixels. [0003] In recent years, with the continuous development of aerospace technology and remote sensi...

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): G06K9/62
CPCG06F18/2411G06F18/214
Inventor 彭进业赵二龙刘胜杰王珺章勇勤李展祝轩周剑虹艾娜
Owner NORTHWEST UNIV(CN)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products