Remote sensing hyperspectral image classification method based on local binary pattern and KNN classifier

A local binary mode, hyperspectral image technology, applied in the field of remote sensing hyperspectral images, can solve difficult remote sensing hyperspectral image classification and other problems

Active Publication Date: 2020-11-03
ANHUI UNIVERSITY
View PDF6 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] The purpose of the present invention is to solve the defect that it is difficult to classify remote sensing hyperspectral images in the prior art, and provide a remote sensing hyperspectral image classification method based on local binary mode and KNN classifier to solve the above problems

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
  • Remote sensing hyperspectral image classification method based on local binary pattern and KNN classifier
  • Remote sensing hyperspectral image classification method based on local binary pattern and KNN classifier
  • Remote sensing hyperspectral image classification method based on local binary pattern and KNN classifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0174] In order to verify the impact of different parameter settings on the classification accuracy in the method proposed by the present invention, the number p of the principal components, the neighborhood radius r of the LBP algorithm, the number of neighboring sampling points s, the size w of the divided local area, the classification The neighbor number k of the device is verified on these five parameters. In order to improve the accuracy and reliability of the experiment, each experiment was repeated 10 times, each time 10% of the training samples were randomly selected from each type of ground object samples, and the rest were used as test samples, and the classification accuracy of the 10 experiments was averaged. to the final result.

[0175] Table 4 Comparison table of variance contribution rate and cumulative contribution rate of each principal component in different data sets

[0176]

[0177] Figure 5 It is the OA dot-line diagram of the classification metho...

Embodiment 2

[0181] In order to further verify the effectiveness of the method proposed in the present invention, three data sets of Pavia University, Indian Pines, and Salinas will be used for verification, and the classification method LBP-MFKNN described in the present invention will be compared with some existing hyperspectral classifications The methods KNN, RBF-SVM and KSOMP are compared, and the number of training samples used by each classification method is exactly the same.

[0182] Table 6 Comparison results of the classification accuracy of the classification method LBP-MFKNN described in the present invention and the existing method on the Pavia University dataset.

[0183]

[0184] right figure 2 The shown Pavia University hyperspectral image is classified, and 10% samples are randomly selected as a training set from each type of ground object, and the remaining samples are used as a test set. In the classification method proposed by the present invention on this data set...

Embodiment 3

[0192] In order to verify the impact of the classification method of the present invention on the hyperspectral classification accuracy under different sample ratios, five different training sample ratios of 1%, 2%, 5%, 10%, 15%, and 20% were set up for verification , the classification method LBP-MFKNN described in the present invention is to Pavia University, Indian Pines, Salinas data set OA, AA, Kappa experiment result under different sample proportions respectively as follows Figure 11 (a,b,c), Figure 11 (d, e, f), Figure 11 (g, h, i). From Figure 11 It can be seen that with the continuous increase of the training sample size, the classification accuracy of different classification methods is also continuously improved, and gradually tends to be stable. Under various training sample sizes, the classification method that combines more features has higher OA, AA, and Kappa coefficients than the classification method that only uses a single feature in most cases. Whe...

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 relates to a remote sensing hyperspectral image classification method based on a local binary pattern and a KNN classifier. Compared with the prior art, the defect that remote sensing hyperspectral image classification is difficult to carry out is overcome. The method comprises the following steps: acquiring training data; extracting a spectral feature vector; extracting a spatial feature vector; extracting a color feature vector; stacking a plurality of feature vectors; constructing and training a KNN classifier; acquiring a remote sensing hyperspectral image to be classified; preprocessing the remote sensing hyperspectral images to be classified; and obtaining a remote sensing hyperspectral image classification result. According to the method, spectrum, space and color features are combined, the similarity of similar pixels is enhanced; meanwhile, the dissimilarity of different pixels is increased, and compared with a partially proposed classification method, the overall classification precision, the average classification precision and the Kappa coefficient are improved to different extents.

Description

technical field [0001] The invention relates to the technical field of remote sensing hyperspectral images, in particular to a remote sensing hyperspectral image classification method based on a local binary model and a KNN classifier. Background technique [0002] Hyperspectral image classification has been a very active area of ​​research in recent years, and it plays an important role in many remote sensing applications, such as environmental mapping, crop analysis, plant and mineral exploration, and biological and chemical detection. effect. Therefore, making full use of the spatial and spectral information of hyperspectral data and continuously improving the classification accuracy has become the goal that researchers are constantly pursuing. [0003] Hyperspectral images can obtain hundreds of the same narrow-band spectral channels, and can provide richer spectral information to support fine identification of various land covers. To obtain valuable spectral features,...

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): G06K9/62G06K9/46
CPCG06V10/40G06V10/467G06F18/2135G06F18/24147G06F18/253
Inventor 赵晋陵胡磊黄林生梁栋徐超黄文江翁士状张东彦郑玲
Owner ANHUI UNIVERSITY
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