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

A Method for Functional Classification of Urban Buildings in High Resolution Remote Sensing Images

A remote sensing image, high-resolution technology, applied in the field of remote sensing image classification and recognition, can solve the problems of difficult urban buildings, classification and recognition, etc., and achieve the effect of high classification accuracy

Active Publication Date: 2019-12-06
INST OF REMOTE SENSING & DIGITAL EARTH CHINESE ACADEMY OF SCI
View PDF10 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, only relying on the current remote sensing automatic classification and extraction technology is still difficult to carry out semantic-level functional classification and identification of urban buildings.

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
  • A Method for Functional Classification of Urban Buildings in High Resolution Remote Sensing Images
  • A Method for Functional Classification of Urban Buildings in High Resolution Remote Sensing Images
  • A Method for Functional Classification of Urban Buildings in High Resolution Remote Sensing Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] according to figure 1 It can be seen that a method for functional classification of urban buildings in high-resolution remote sensing images, the steps are:

[0063] A. For a given high-resolution remote sensing image A( figure 2 ) using the CNN method to extract buildings from Quickbird multi-spectral (resolution up to 2.5m) remote sensing image data, and obtain the extraction results of buildings (such as Figure 5 ). Proceed as follows:

[0064] Preprocessing of remote sensing images 100: preprocessing of remote sensing images, including radiometric calibration, atmospheric correction, and geometric correction.

[0065] Establishment of building sample database 101: Select 80 typical building samples with high pixel purity (the number of samples used in this case) from the above remote sensing images to establish a building sample database.

[0066] Building 102 of CNN urban building extraction model: the sample bank in the building sample bank is established (...

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 classifying functions of urban buildings in high-resolution remote sensing images, the steps of which are: A. using CNN method to extract buildings in high-resolution remote sensing images to obtain building extraction results; B. according to attributes Organize and classify the POI data, and estimate the kernel density of the POI of commercial service facility land, public management and public service land, and residential land, respectively, and obtain the kernel density maps of these land types; C. Using the above-mentioned CNN's remote sensing image building information extraction results and kernel density map to calculate the average kernel density of a single building. This method is easy to implement and easy to operate, and effectively solves the difficult problem of using remote sensing information extraction technology to realize the classification and identification of building functions at the semantic level. The dynamic data of functional area classification serves for urban management and rational planning.

Description

technical field [0001] The invention relates to the technical field of classification and recognition of remote sensing images, and more specifically relates to a method for classifying functions of urban buildings in high-resolution remote sensing images, especially for high-resolution remote sensing images with a resolution not lower than 5m. Background technique [0002] Urban buildings are an important part of the city. As a stable space for human living and activities, their transformation and renewal always affect the development of the city and the changes in human life. According to the use function of the building, the building can be divided into various types such as commercial service facility land, public management and public service land, residential land, and industrial, mining and storage land. The functional classification of urban buildings can provide a favorable basis for the division of urban functional areas, assist government departments in the manage...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/08G06V20/176G06F18/2415
Inventor 刘亚岚曲畅任玉环
Owner INST OF REMOTE SENSING & DIGITAL EARTH CHINESE ACADEMY OF SCI
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