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

Spatial-spectral integrated hyperspectral remote sensing image classification method

A technology of hyperspectral remote sensing and classification methods, which is applied in the directions of instruments, character and pattern recognition, computer components, etc., and can solve problems such as ignoring spatial dimension information

Inactive Publication Date: 2013-12-25
HANGZHOU DIANZI UNIV
View PDF3 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional hyperspectral classification methods often only focus on the characteristics of the spectral dimension of the data, while ignoring the information of the spatial dimension

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
  • Spatial-spectral integrated hyperspectral remote sensing image classification method
  • Spatial-spectral integrated hyperspectral remote sensing image classification method
  • Spatial-spectral integrated hyperspectral remote sensing image classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] 1) Data overview

[0059] The experimental data is provided by the Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, and consists of two bands: visible near-infrared and short-wave infrared. The visible and near-infrared region has a total of 80 bands, and the spatial size is 226×500 pixels. The grayscale image of the 55th band is as follows figure 1 shown.

[0060] Through the grayscale image, it can be observed that in the two-channel hyperspectral images, the remote sensing data features include a van, two semi-trailers and multiple targets ( different material and covered with different paint). In the experiment, the target is the target area. In order to facilitate post-processing, the 5 targets on the semi-trailer are marked as target 1 to target 5 from left to right, and the rectangular targets on the crop field are marked as target 6 to target 10 from left to right.

[0061] This test also provides indoor spectr...

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 spatial-spectral integrated hyperspectral remote sensing image classification method. A conventional hyperspectral image classification technology mainly focuses on how to use the classification information of spectral spaces better, but ignores the information of image spatial domains. According to the invention, in the process of carrying out self spectral feature classification by using data, spectral classification results are supplemented by using effective spatial domain information combining a region growing method with a binary morphology method. According to the invention, an SVM (support vector machine) based classification method is adopted for carrying out spectral domain classification on data firstly; then, effective spatial domain information is introduced by using the region growing method and the binary morphology method so as to correct spectral classification results. According to the invention, information contained in hyperspectral data is used more fully, and the precision of hyperspectral image classification is improved.

Description

technical field [0001] The invention belongs to the field of information technology, relates to pattern recognition and image processing technology, in particular to a space-spectrum integrated hyperspectral remote sensing image classification method. Background technique [0002] With the development of earth observation technology, spectral remote sensing technology has become an important means for people to obtain surface information. As a new type of remote sensing, hyperspectral remote sensing plays an extremely important role in both military and civilian fields. Hyperspectral image classification is an important direction of hyperspectral information processing, and high-precision classification algorithms are an important prerequisite for various applications. [0003] Hyperspectral images have brought great challenges to traditional image classification techniques due to their high resolution, multi-band numbers, and large data volume. The traditional classificat...

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): G06K9/62
Inventor 郭宝峰高晓健陈春种彭冬亮左燕谷雨
Owner HANGZHOU DIANZI UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com