Multi-kernel support vector machine classification method for remote sensing images

A technology of support vector machine and classification method, which is applied in the field of support vector machine classification to achieve the effects of improving classification accuracy and reliability, improving accuracy, and improving classification accuracy

Inactive Publication Date: 2011-02-16
CHINA UNIV OF MINING & TECH
View PDF0 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But only considering the classification of spectral information

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
  • Multi-kernel support vector machine classification method for remote sensing images
  • Multi-kernel support vector machine classification method for remote sensing images
  • Multi-kernel support vector machine classification method for remote sensing images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0015] Example 1: Using OMIS in Changping District, Beijing Hyperspectral image, with a size of 512 rows, 512 columns, and 64 bands. In the comparison of classification methods of multi-core support vector machines, spectral information and wavelet texture are combined first, then the first 4 components of PCA transform and wavelet texture are used for classification, and finally one-dimensional wavelet texture and two-dimensional wavelet texture are combined for classification. The classification results and Kappa coefficients are shown in Table 1.

[0016] Specific implementation steps:

[0017] (1) Preprocess the original multispectral or hyperspectral remote sensing image data, remove noise bands, and then determine the classification system and select training samples.

[0018] (2) Perform principal component transformation on the data set obtained in step (1), select the first four components as spectral features to participate in classification, and use Represents ...

Embodiment 2

[0031] Embodiment 2: The experimental data is the data of the University of Pavia in Italy acquired by the ROSIS sensor in 2003. Experimental data 1 is the same as experimental data 2. First, single-core SVM classification is performed, and then multi-core SVM classification is performed. The classification accuracy is shown in Table 3 and Table 4.

[0032] Table 3 Single-core SVM classification accuracy

[0033] .

[0034] Table 4 Multi-core SVM classification accuracy

[0035]

[0036] It can be seen that the result of test 2 is the same as that of test 1, and the multi-core support vector machine method using the first four components of principal component transformation and one-dimensional wavelet texture features can obtain the highest precision, which fully demonstrates the reliability and effectiveness of the present invention.

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 multi-kernel support vector machine classification method for remote sensing images, and belongs to a support vector machine classification method for the remote sensing images. The method comprises the following steps of: performing principal component transform on original data; taking first four principal components to represent spectral information, performing wavelet texture feature extraction on the first principal component, and combining the spectral feature and spacial feature by adopting two independent radial basis functions; and finally performing classification by utilizing a multi-kernel support vector machine method. The wavelet texture feature and the spectral feature are combined thorough a plurality of basis functions, so the spectral feature extracted by principal component analysis is fully utilized, the wavelet texture feature is fused, the support vector machine is optimized, and the limitation that the traditional method separately adopts the spectral feature for classification is overcome; therefore, the classification accuracy is effectively improved. The method has the main advantage of improving the classification accuracy by combining the spectral information and the spacial information through the plurality of basis functions.

Description

technical field [0001] The invention relates to a support vector machine classification method for remote sensing images, in particular to a multi-core support vector machine classification method for remote sensing images. Background technique [0002] The support vector machine algorithm (support vector machine, SVM) has better performance than the traditional classification method in hyperspectral data classification, and the remote sensing image classifier designed based on the support vector machine algorithm has achieved good results in practical applications. However, in the classification process, the classifier only uses spectral data to learn and often cannot achieve good classification results. The usual process of using the support vector machine classification algorithm for remote sensing image classification is: through training samples of known categories in remote sensing images to support The vector machine classifier is trained to establish a classification...

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): G06K9/66
Inventor 杜培军谭琨
Owner CHINA UNIV OF MINING & TECH
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