High-spectral remote-sensing image classification method based on semi-supervision sparse discriminant embedding

A technology of sparse identification embedding and hyperspectral remote sensing, which is applied in character and pattern recognition, instruments, computing, etc., and can solve the problem of not effectively using identification information

Inactive Publication Date: 2014-02-19
CHONGQING UNIV
View PDF0 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the SPP algorithm does not need to mark the training samples, it does n

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
  • High-spectral remote-sensing image classification method based on semi-supervision sparse discriminant embedding
  • High-spectral remote-sensing image classification method based on semi-supervision sparse discriminant embedding
  • High-spectral remote-sensing image classification method based on semi-supervision sparse discriminant embedding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0136] The Washington DC Mall hyperspectral remote sensing image dataset used in this experiment is a local area of ​​the National Mall in Washington DC. The dataset has 191 bands with a band spacing of 10nm and a spatial resolution of 3m. The known object categories include "building", "forest", "(stone path) path", "road", "lawn", "lake" and "shadow". In the experiment, four classification experiments were carried out for each classification method involved in the comparison. The four classification experiments randomly selected 2, 4, 6, and 8 data points from each type of ground object as classified points, and obtained from the remaining training samples. Randomly select 60 unlabeled data as unlabeled samples to form a training sample set, and all the remaining data points are used as test samples. The four classification experiments are recorded as 2-lab, 4-lab, 6-lab, 8-lab, respectively. lab, for each classification method involved in the comparison, the final classifi...

Embodiment 2

[0141] The Indian Pine hyperspectral remote sensing image dataset used in the experiment covers an agricultural area in the northwest of Indiana, USA. The data point space size of this dataset is 145×145, and there are 220 bands and 17 known object categories. Considering the influence of noise, this experiment selects 200 bands and selects 6 categories from the ground object categories with more data points for experiments. The fifth categories of the 6 categories are "Hay_windrowed", "Soybeans_min", "Woods", "Corn_notill", "Grass_pasture", "Grass_trees". In the experiment, four kinds of classification experiments were carried out for each classification method participating in the comparison. The four classification experiments randomly selected 2, 4, 6, and 8 data points with category labels from each type of ground object, and selected data points from the remaining training samples. Randomly select 60 unlabeled data as unlabeled samples to form a training sample set, and...

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 provides a high-spectral remote-sensing image classification method based on semi-supervision sparse discriminant embedding. The method simplifies the dimension of high-spectral remote-sensing images in a semi-supervision sparse discriminant embedding algorithm, and combines advantages of neighborhood manifold structure and sparsity, wherein the sparse reconstruction relations among samples are reserved, the natural discrimination capability with sparse expression requires no manual selection of neighborhood property values, so that the difficulty in neighborhood parameter selection is reduced to certain extent; and a few of marked training samples and partial unmarked training samples are used to discover intrinsic attributes and low-dimension manifold structure contained in high-dimension data, so that the precision of natural object classification in the high-spectral remote-sensing images can be improved. At the same time, the method of the invention discriminately treat marked data and unmarked data, and the capability of gathering data points of the same natural-object classification is enhanced to the largest degree, thereby further improving the precision of natural object classification in the high-spectral remote-sensing images.

Description

technical field [0001] The invention relates to the technical field of hyperspectral data processing methods and applications, in particular to a hyperspectral remote sensing image classification method based on semi-supervised sparse discriminant embedding. Background technique [0002] Hyperspectral remote sensing technology has developed rapidly since the 1980s. Its images record the continuous spectrum of ground objects, contain richer information, and have the ability to identify more types of ground objects and classify objects with higher accuracy. However, since hyperspectral data consists of a large number of bands to form a high-dimensional feature space, the complexity of most algorithms increases exponentially with the number of dimensions, and its processing requires a greater amount of calculation, and its bands are highly correlated and redundant. , at the same time, there are problems such as high dimensionality, easy to obtain ideal results due to Hughes phe...

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
IPC IPC(8): G06K9/62G06K9/66
Inventor 黄鸿曲焕鹏
Owner CHONGQING 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