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

Method for roughly sorting high-resolution remote sensing image scene

A remote sensing image, high-resolution technology, applied in the field of remote sensing image processing, can solve the problem of pixel-level classification efficiency and accuracy that does not meet actual needs

Inactive Publication Date: 2012-07-04
HUAZHONG UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, remote sensing images do not have semantic meaning on a small scale, because ground object scenes are usually large-scale areas, so pixel-level classification does not meet actual needs in terms of efficiency and accuracy

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
  • Method for roughly sorting high-resolution remote sensing image scene
  • Method for roughly sorting high-resolution remote sensing image scene
  • Method for roughly sorting high-resolution remote sensing image scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] In this embodiment, a visible light remote sensing image with a resolution of about 3000*3000 is taken as an example to describe the scene classification of the present invention in detail.

[0051] (1) Image initial segmentation

[0052] Firstly, the original image is decomposed by wavelet, using Daubechies 4-point wavelet for first-level decomposition, and 4 sets of wavelet coefficient matrices with doubled resolution are obtained, which are the approximate coefficients of the original image and 3 sets of detail coefficients.

[0053] Next, the Laws texture operator operation is performed on these four groups of wavelet coefficient matrices to obtain the feature vector group describing the original image. This process is roughly as follows: the number of texture categories contained in the image is known, and then all frequency bands LL, HL, LH, HH of the largest scale are decomposed from the wavelet, and a 4-dimensional vector is constructed for each position, and th...

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 method for roughly sorting a high-resolution remote sensing image scene, which is used for providing context information for target recognition of a remote sensing image. The method is characterized by comprising the following steps of: (1) initially partitioning an image; (2) sorting context; (3) performing regional integration; and (4) performing post-processing. The remote sensing image scene is sorted by combining context classification which is initially partitioned rapidly and is integrated with semantic information with object-oriented sectional sorting; and the method can be used for image preprocessing of various types of satellite target recognition.

Description

technical field [0001] The invention belongs to the field of remote sensing image processing, in particular to a method for scene classification of high-resolution remote sensing images, which is used for providing context information for target recognition of remote sensing images. Background technique [0002] High-resolution remote sensing images generally refer to visible light aerial remote sensing images of 1m to 5m. The data volume of high-resolution remote sensing images is large. If the method of feature expression, feature clustering and segmentation is directly used for target recognition, it will consume a lot of time. computing resources, resulting in inefficient processing. Therefore, the idea of ​​coarse scene classification for remote sensing images on a large scale is proposed, an image is divided into limited areas associated with the target we are interested in, and then the target is extracted in the dependent area according to the nature of the target. ...

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 Patents(China)
IPC IPC(8): G06K9/62
Inventor 王岳环唐为林桑农姚玮宋云峰吴剑剑
Owner HUAZHONG UNIV OF SCI & TECH
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