Unlock instant, AI-driven research and patent intelligence for your innovation.

Remote sensing image residential area extraction method and device

A technology of remote sensing image and extraction method, which is applied in the directions of instruments, character and pattern recognition, scene recognition, etc., and can solve the problem of low extraction accuracy

Active Publication Date: 2019-10-22
PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method and device for extracting residential areas from remote sensing images to solve the problem of low accuracy in the current extraction of residential areas from remote sensing images based on texture features

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 image residential area extraction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] Such as figure 1 Shown is a flow chart of a method for extracting residential areas from remote sensing images of the present invention, specifically:

[0053] 1. Construct a scale image.

[0054] The entire remote sensing image I with a scale of 1m is reduced by three different scale coefficients to obtain three scale images with different resolutions. The corresponding scales of the three scale images are 5m, 7m and 9m respectively.

[0055] Here, the reduced scale factor depends on the resolution of the original image to be processed. The higher the resolution, the worse the texture, and the larger the scale factor that needs to be reduced. Combined with the texture statistical attributes of block-style residential areas and the topographic map surveying specifications, the resolution of the reduced image should be controlled at three scales of 4m-5m, 6m-7m and 9m-10m.

[0056] 2. Calculate the residential attribute labeling results of all pixels on the image of ea...

Embodiment 2

[0098] The specific steps of this embodiment mainly include:

[0099] 1. Construct a scale image.

[0100] 2. Calculate the residential attribute labeling results of all pixels on the image of each scale.

[0101] 3. Comprehensive judgment to obtain the final residential property labeling results of all pixels in the remote sensing image I.

[0102] 4. Extract the contour boundary of the residential area in the remote sensing image I.

[0103] The difference between this embodiment and Embodiment 1 is only in the method of calculating the residential attribute labeling results of all pixels on each scale image. This embodiment uses the method of Fourier transform to calculate all the pixels on the scale image The result of marking the residential place attribute.

[0104] The Fourier transform method used in this embodiment belongs to a prior art. For details, refer to "Research on Residential Area Extraction Technology from Remote Sensing Image Based on Texture Features" m...

Embodiment 3

[0106] This embodiment is a device for extracting residential areas from remote sensing images, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the program, Embodiment 1 and Embodiment 1 are realized. 2. The extraction method of remote sensing image settlements. And when carrying out specific programming, because the knowledge such as the grammar of programming language is the common knowledge of this field, technician is fully capable of using existing programming language (such as C language, JAVA, assembly language, C#, C++, etc.) to perform corresponding programming, and this process will not be repeated here.

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 image residential area extraction method and device, and belongs to the field of remote sensing image processing application. The remote sensing image is zoomed into scale images with different resolutions, then attribute marks of all pixel points in each scale image are obtained through calculation, multiple attribute mark results of all pixel points on the remote sensing image can be obtained through conversion, and finally resident place information is extracted through comprehensive judgment. The principle that the texture features of the low-resolution scale images are clear is utilized, the low-resolution multi-scale remote sensing images are selected to replace the high-resolution original remote sensing images to extract the residential area, finally, the residential area attribute marking result is obtained through comprehensive judgment, and the accuracy of the extraction result is improved.

Description

technical field [0001] The invention relates to a method and device for extracting residential areas from remote sensing images, and belongs to the application field of remote sensing image processing. Background technique [0002] At present, domestic and foreign descriptions of remote sensing image features mainly focus on three aspects: spectrum, texture and geometric shape information. With the improvement of remote sensing image resolution, the shape diversity and spectral complexity of ground objects tend to be more obvious, the phenomenon of "same spectrum and different objects" and "different objects with the same spectrum" are more obvious, with higher intra-class variation and lower inter-class differences It greatly weakens the pattern separability of different surface features in the spectral domain, and the recognition and extraction of ground objects cannot be achieved by relying solely on spectral information; geometric features mainly use information such as ...

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): G06K9/00G06K9/46
CPCG06V20/13G06V10/462G06V10/44
Inventor 金飞刘智芮杰王淑香袁璐温锐孙启松李润生张昊
Owner PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com