A Classification Method and System for Hyperspectral Remote Sensing Images
A hyperspectral remote sensing and classification method technology, which is applied in the directions of instruments, computing, character and pattern recognition, etc., can solve the problem of low classification accuracy, achieve the effect of reducing time and space complexity and improving classification accuracy
Active Publication Date: 2019-12-27
SHENZHEN UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In view of this, the object of the present invention is to provide a classification method and system for hyperspectral remote sensing images, aiming to solve the problem of low classification accuracy in the prior art
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0040] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
[0041] The specific embodiment of the present invention provides a kind of classification method of hyperspectral remote sensing image, and described method mainly comprises the following steps:
[0042] S11. Generate a plurality of three-dimensional Gabor filters parallel to the spectral direction;
[0043] S12. Convolving the hyperspectral remote sensing image with the generated three-dimensional Gabor filters to obtain a three-dimensional Gabor phase feature; then performing quadrant encoding on the three-dimensional Gabor phase feature of each pixel; and
[0044] S13. Using the coded features ...
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
Login to View More Abstract
The invention provides a method for classifying hyperspectral remote sensing images, comprising: generating a plurality of three-dimensional Gabor filters parallel to the spectral direction; performing convolution operation on hyperspectral remote sensing images and the generated plurality of three-dimensional Gabor filters , to obtain the three-dimensional Gabor phase feature, and perform quadrant encoding on the three-dimensional Gabor phase feature of each pixel; and use the encoded feature to classify the hyperspectral remote sensing image through the regularized Hamming distance. The invention also provides a classification system for hyperspectral remote sensing images. The technical solution provided by the present invention is based on three-dimensional Gabor phase feature encoding, and selects the feature subset with the most discriminative ability from a large number of three-dimensional Gabor phase features, which not only improves the classification accuracy, but also reduces the time and space complexity of the algorithm.
Description
technical field [0001] The invention relates to the field of image processing, in particular to a classification method and system for hyperspectral remote sensing images. Background technique [0002] Currently, the large discrepancy between the hyperspectral dimensions of hyperspectral data and limited training samples is an important challenge for hyperspectral remote sensing image classification problems. Due to the interference of noise and the ubiquity of the phenomenon of "same spectrum and different objects" (that is, the spectral characteristics of different ground objects have high similarity), the traditional classification method based on the difference of spectral characteristics between ground objects is difficult to obtain satisfactory accuracy. At the same time, feature extraction and band selection techniques are used to reduce the spectral dimension of hyperspectral data, alleviating the "Hughes phenomenon" (that is, given a fixed number of training samples...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/46G06K9/62
CPCG06V10/449G06F18/24147G06F18/22G06V10/40
Inventor 贾森沈琳琳
Owner SHENZHEN UNIV