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

SVM-based recognition method of building angular points in high-resolution optical image

A high-resolution, optical image technology, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as gaps, achieve the effect of improving accuracy and generalization ability

Active Publication Date: 2017-03-22
GUILIN UNIVERSITY OF TECHNOLOGY
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Remote sensing technology is becoming more and more mature, and its application fields are constantly expanding. However, the computer interpretation and interpretation technology of high-resolution remote sensing images still has a large gap with the needs of practical applications.

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
  • SVM-based recognition method of building angular points in high-resolution optical image
  • SVM-based recognition method of building angular points in high-resolution optical image
  • SVM-based recognition method of building angular points in high-resolution optical image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0027] (1) Perform orthorectification processing on the obtained high-resolution remote sensing images and corresponding DEM images through ENVI and Erdas remote sensing image digital processing software to obtain corrected high-resolution remote sensing images containing elevation information.

[0028] (2) Since plant leaves have strong absorption properties in the visible red band and strong reflection properties in the near-infrared band, according to this feature, the vegetation water body is separated from the image first to improve the classification accuracy. Therefore, the vegetation in the high-resolution remote sensing image is separated from the image by NDVI (Normalized Difference Vegetation Index) to improve the classification accuracy of the following step (3). Among them, NIR is the reflection value of the near-infrared band, and R is the reflection value of the red band.

[0029] NDVI=(NIR-R) / (NIR+R) (-1<=NDVI<=1) (1)

[0030] A negative value of NDVI means 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 an SVM-based recognition method of building angular points in a high-resolution optical image. The process of the method comprises the steps that the high-resolution optical image is subjected to ortho-rectification, the influences of vegetation on a classification result are removed through an NDVI, a binary support vector machine (SVM) is used for marking out building blocks in the image in a classified mode, a candy operator is used for performing edge detection on the area where the building blocks are located, a structure chart of point sets of building nodes is obtained through hough transformation, and the SVM is used for classifying the point sets to obtain the building angular points. Through the method, the recognition precision of the building angular points in the optical image can be greatly improved, and the information extraction rate of buildings and other artificial objects in the image with a high spatial resolution is increased.

Description

technical field [0001] The invention relates to the field of high resolution remote sensing image recognition, in particular to a method for recognition and extraction of building corners in high spatial resolution optical images. Background technique [0002] The extraction and shape mapping of buildings in high-resolution remote sensing images are key factors in the construction of future smart cities, and in the process of building extraction, building corner recognition is an important part. In recent years, the spatial resolution of satellite remote sensing images has reached the sub-meter level, and the support vector machine developed from statistical theory has also achieved good promotion and application in the field of pattern recognition and classification. The rapid development of computer algorithm technology provides a new research method for the recognition of building corners. [0003] Remote sensing technology is becoming more and more mature, and its appli...

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 Applications(China)
IPC IPC(8): G06K9/62G06K9/00G06K9/46
CPCG06V20/176G06V10/44G06F18/2411
Inventor 李百寿李灵芝张强
Owner GUILIN UNIVERSITY OF TECHNOLOGY
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