A City Boundary Extraction Method Fused with Multispectral Remote Sensing Data and Night Light Remote Sensing Data

A technology of remote sensing data and night lights, which is applied in image data processing, character and pattern recognition, image enhancement, etc., can solve the problem of failing to extract city boundaries more quickly and accurately, and achieve the effect of reducing the phenomenon of false extraction

Active Publication Date: 2018-10-26
CENT SOUTH UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention proposes a city boundary extraction method that integrates multi-spectral remote sensing data and night light remote sensing data. This kind of feature, in order to achieve rapid and automatic extraction of city boundaries, improve the accuracy of city boundaries, and reduce the effect of false extraction rate

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 City Boundary Extraction Method Fused with Multispectral Remote Sensing Data and Night Light Remote Sensing Data
  • A City Boundary Extraction Method Fused with Multispectral Remote Sensing Data and Night Light Remote Sensing Data
  • A City Boundary Extraction Method Fused with Multispectral Remote Sensing Data and Night Light Remote Sensing Data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0092] Embodiment 1: process schematic diagram sees figure 2 .

[0093] (1) Image preprocessing

[0094] right figure 2 (a) and (b), use ENVI software to transform the coordinates of multi-spectral remote sensing images and night light remote sensing images into a UTM projection coordinate system, and resample the night light remote sensing images to 30 meters, as figure 2(c) shown.

[0095] (2) Impervious Surface Extraction

[0096] After the multispectral remote sensing image is processed in step 1, the impermeable surface can be extracted. The extraction process is as follows:

[0097] ① Use ENVI software to perform radiometric correction on the multi-spectral remote sensing image, and convert the DN value on the image into reflectance;

[0098] ② Calculate the normalized difference water index MNDWI, the calculation formula is:

[0099]

[0100] Among them, Green and MIR 1 is the reflectance of green band and mid-infrared1.

[0101] ③Near-infrared, mid-infrar...

Embodiment 2

[0123] Embodiment 2: process schematic diagram sees image 3 .

[0124] Its processing step is identical with embodiment 1, and final result figure is as follows image 3 (g) shown.

[0125] The test results of Example 1 and Example 2 are all marked in the figure by solid lines.

[0126] It can be seen that the overall detection effect of the present invention is ideal. In addition, the existing technology (references: Xiao P, WangX, Feng X, et al. Detecting China's Urban Expansion Over the Past Three Decades Using Nighttime Light Data [J]. IEEE Journal of Selected Topics in AppliedEarth Observations & Remote Sensing, 2014, 7 (10): 4095-4106.) test results ( figure 2 (h), image 3 (h)) and the results of the present invention ( figure 2 (g), image 3 (g)) for contrast, by statistical correct rate, error rate and kappa coefficient, comparative analysis the present invention is with the advantage of prior art, statistical result sees the following table:

[0127] Embod...

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 extracting urban boundaries by combining multi-spectral remote sensing data and nighttime light remote sensing data. By combining the impermeable surface index and the light index extracted from nighttime light remote sensing data, the city boundary can be located more accurately and errors can be reduced. Extraction phenomenon. At the same time, by fusing multispectral remote sensing data with higher spatial resolution than nighttime light remote sensing data, the characteristics of the two data are used as the distinguishing features of urban areas and non-urban areas at the same time, which ensures that the extracted urban boundaries are better than nighttime light remote sensing data alone. more refined. A large number of experimental results show that the correct extraction rate of the city boundary of the present invention has reached more than 90%, which is nearly 10% higher than that of the prior art, and the false extraction rate is as low as below 10%, which solves the problems existing in the prior art and is suitable for land planning , geographical conditions monitoring, urban expansion analysis and other urban remote sensing applications.

Description

technical field [0001] The invention belongs to the field of urban planning, in particular to a method for extracting city boundaries by fusing multispectral remote sensing data and night light remote sensing data. Background technique [0002] The automatic extraction of city boundaries is the key to grasping the extent of urban expansion in time, and the extent of urban expansion has become a key concern in the field of urban planning. At the same time, the rapid and automatic extraction of city boundaries can reduce the manpower and material resources of traditional monitoring methods. However, when the resolution of remote sensing images is not high enough, the automatic extraction method is easy to mistakenly classify some ground objects into the city boundary. Therefore, the extraction of city boundaries from medium and low resolution remote sensing images is more challenging. At present, the newer and better urban boundary extraction methods are based on remote sensi...

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): G06K9/00
CPCG06T3/40G06T3/4007G06T2207/20004G06T2207/10032G06T2207/20221G06V20/176G06V10/20G06V10/40G06F18/22G06F18/241G06F18/25
Inventor 陶超柯文聪邹滨马进龙刘莹邹峥嵘
Owner CENT SOUTH UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap