CN115018859A - Urban built-up area remote sensing extraction method and system based on multi-scale space nesting - Google Patents

Urban built-up area remote sensing extraction method and system based on multi-scale space nesting Download PDF

Info

Publication number
CN115018859A
CN115018859A CN202210392975.8A CN202210392975A CN115018859A CN 115018859 A CN115018859 A CN 115018859A CN 202210392975 A CN202210392975 A CN 202210392975A CN 115018859 A CN115018859 A CN 115018859A
Authority
CN
China
Prior art keywords
urban
area
index
remote sensing
built
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210392975.8A
Other languages
Chinese (zh)
Inventor
李治
傅俏燕
黄树松
王冠珠
高廷
李娅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Center for Resource Satellite Data and Applications CRESDA
Original Assignee
China Center for Resource Satellite Data and Applications CRESDA
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Center for Resource Satellite Data and Applications CRESDA filed Critical China Center for Resource Satellite Data and Applications CRESDA
Priority to CN202210392975.8A priority Critical patent/CN115018859A/en
Publication of CN115018859A publication Critical patent/CN115018859A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/176—Urban or other man-made structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20128—Atlas-based segmentation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • Y02A30/60—Planning or developing urban green infrastructure

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a multi-scale space nesting-based urban built-up area remote sensing extraction method and system, wherein the method comprises the following steps: constructing an urban index VANUI according to MODIS NDVI data and NPP-VIIRS noctilucent data; self-adaptive segmentation is carried out on the city index VANUI by utilizing the statistical data of the urban built-up area to obtain a boundary B1 of the urban built-up area; calculating a morphological construction index (MBI) according to a boundary B1 of the urban construction district; constructing a self-adaptive segmentation model, segmenting the morphological building index MBI, and acquiring urban building information O; performing cluster analysis on the city building information O to obtain regular building information S; and (4) calculating a convex hull of the regular building information S, and acquiring the boundary range of the urban built-up area. The invention realizes nesting of multi-scale spaces, restricts and continuously optimizes the extraction result of urban construction urban areas, and finally realizes automatic extraction of urban construction urban areas.

Description

Urban built-up area remote sensing extraction method and system based on multi-scale space nesting
Technical Field
The invention belongs to the technical field of high-resolution remote sensing image processing and information extraction, and particularly relates to a multi-scale space nesting-based urban built-up area remote sensing extraction method and system.
Background
The area of the urban built-up area is an important judgment standard for comprehensively measuring the economic development stage of one city and one area, and plays an important role in the development planning, spatial layout and management optimization of the city. On the one hand, the area of the built-up area reflects the industrial structure of the corresponding area and the stage of the urbanization process. On the other hand, the area of the built-up area is powerful in the economic strength of the area. Compared with methods such as on-site debugging and drawing, the remote sensing image can quickly and accurately acquire the boundary information of the built-up area of the city, so that the method is widely researched and applied.
According to the attribute characteristics of urban built-up areas, the current urban built-up area extraction based on remote sensing mainly adopts 4 methods, which specifically comprise: a) a spectral feature extraction method based on the medium-resolution remote sensing image; b) a spatial feature extraction method based on the high-resolution remote sensing image; c) a method for extracting based on noctilucent data and d) a method for combining based on the above method. However, since spatial information of a city is an important attribute of a built-up area of the city, it is not considered in the index of the built-up area of the city. In addition, the manual selection of the threshold value also restricts the high efficiency and stability of the urban construction area information extraction result.
Disclosure of Invention
The technical problem solved by the invention is as follows: the method and the system for remotely sensing and extracting the urban built-up area based on the nesting of the multi-scale space are provided, the nesting of the multi-scale space is realized, the extraction result of the urban built-up area is restrained and continuously optimized, and the automatic extraction of the urban built-up area is finally realized.
The purpose of the invention is realized by the following technical scheme: a remote sensing extraction method for urban built-up areas based on multi-scale space nesting comprises the following steps: constructing a city index VANUI according to MODIS NDVI data and NPP-VIIRS noctilucent data; self-adaptive segmentation is carried out on the city index VANUI by utilizing the statistical data of the urban built-up area to obtain an urban built-up area boundary B1; calculating a morphological construction index MBI according to a boundary B1 of the urban construction district; constructing a self-adaptive segmentation model, segmenting the morphological building index MBI, and acquiring urban building information O; performing cluster analysis on the city building information O to obtain regular building information S; and (4) calculating a convex hull of the regular building information S, and acquiring the boundary range of the urban built-up area.
In the above urban built-up area remote sensing extraction method based on multi-scale spatial nesting, the urban index VANUI is obtained by the following formula:
VANUI＝DN NPP ×(1-NDVI mean )；
wherein DN NPP DN value of NPP-VIIRS noctilucent data; NDVI mean The average value of the MODIS NDVI data after filtering processing is obtained; vanui is a city index.
In the above remote sensing extraction method for urban built-up areas based on multi-scale spatial nesting, the urban built-up area boundary B1 is obtained by the following formula:
Figure BDA0003596274180000021
wherein, B1 is the boundary of urban construction area; DN VANUI The pixel values of the city index feature image are obtained; t is a pixel value interval of the city index characteristic image; area (VANUI) is the area of the segmentation result of the corresponding city index characteristic image when the pixel value interval of the city index characteristic image is t.
In the urban built-up area remote sensing extraction method based on multi-scale spatial nesting, the morphological building index MBI is obtained through the following formula:
Figure BDA0003596274180000022
wherein, DMP W-TH (d,s)＝|MP W-TH (d,(s+Δs))-MP W-TH (d,s)|；
Figure BDA0003596274180000023
DMP W-TH (d, s) represent differential morphological contours based on top-hat transforms; d and S respectively represent the number of multi-angles and the number of multi-scales; MP (moving Picture experts group) W-TH (d, s) represents a morphological contour based on a top-hat transformation;
Figure BDA0003596274180000024
representing a b-based morphological open reconstruction; b represents the maximum brightness value in each wave band of the remote sensing image pixel points; d, s and Δ s respectively represent direction, scale and scale increment parameters; k represents the wave band of the remote sensing image; k represents the maximum value of the applied remote sensing image wave band; x represents the pixel value of the remote sensing image.
In the remote sensing extraction method for the urban built-up area based on multi-scale space nesting, the urban building information O is obtained through the following formula:
Figure BDA0003596274180000031
wherein p is a pixel value interval of the morphological architectural index MBI; area p (MBI) is the area of the segmentation result of the corresponding morphological construction index when the pixel value interval of the morphological construction index MBI is p; area GUF Area of global city footprint data; mask is the information Mask model.
In the urban built-up area remote sensing extraction method based on multi-scale spatial nesting, an information Mask model Mask is as follows:
Figure BDA0003596274180000032
wherein, GlobeLand30 (water,bare) Representing "water type" and "open land type" in GlobeLand30 surface covering products, OSM being "road type" for openstreet map products, and Hansen being Hansen products"vegetation type".
In the urban built-up area remote sensing extraction method based on multi-scale spatial nesting, a Kmeans clustering algorithm is adopted to perform clustering analysis on urban building information O to obtain regular building information S.
In the urban built-up area remote sensing extraction method based on multi-scale space nesting, the regular building information S is obtained through the following formula:
Figure BDA0003596274180000033
wherein k represents the number of clusters; ci represents the type of cluster; c represents the specific type obtained from the types of the clusters; mu.s i Representing the ith cluster center; f represents the selected characteristic information; DN F Pixel values are obtained for the feature information.
In the urban built-up area remote sensing extraction method based on multi-scale spatial nesting, a Graham scanning method is adopted to calculate the convex hull of regular building information S.
A remote sensing extraction system for urban built-up areas based on multi-scale spatial nesting comprises: the first module is used for constructing an urban index VANUI according to MODIS NDVI data and NPP-VIIRS noctilucent data; the second module is used for carrying out self-adaptive segmentation on the city index VANUI by utilizing the statistical data of the city built-up area to obtain a city built-up area boundary B1; the third module is used for calculating a morphological construction index MBI according to a boundary B1 of the urban construction area; the fourth module is used for constructing a self-adaptive segmentation model, segmenting the morphological building index MBI and acquiring urban building information O; the fifth module is used for carrying out clustering analysis on the urban building information O to obtain regular building information S; and the sixth module is used for calculating the convex hull of the regular building information S and acquiring the boundary range of the urban built-up area.
Compared with the prior art, the invention has the following beneficial effects:
(1) according to the method, the noctilucent data is automatically segmented through the urban construction area statistical data to obtain the urban construction area coarse boundary, so that the potential area range of the urban construction area can be preliminarily determined; in the region range, based on the high-resolution remote sensing image and the medium-resolution thematic information product, urban regularization building information is extracted, and the potential region range of the urban building boundary is further refined; the potential area ranges of the urban building boundaries are automatically connected through Graham scanning, the robustness of the method is improved, and the automatic information extraction of urban construction areas is finally realized;
(2) the invention has better robustness for urban construction areas, especially under the condition of medium and large-sized cities, and has automatic extraction capability under different urban scenes.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart of a multi-scale spatial information nesting-based urban built-up area high-resolution remote sensing automatic extraction method provided by the embodiment of the invention;
FIG. 2(a) is a graph of 2016 NPP-VIIRS night-luminous data (400 meters) provided by an embodiment of the present invention;
FIG. 2(b) is a 2016 model MOD13Q1 product data (250 meters) chart provided by an embodiment of the present invention;
fig. 2(c) is a water body type and bare land type information product (30 m) diagram of GlobeLand30 in 2010 according to an embodiment of the present invention;
fig. 2(d) is a 2013 Hansen vegetation type information product diagram provided by an embodiment of the invention;
fig. 2(e) is a 2015 openstreet map road type information product diagram provided by the embodiment of the present invention;
fig. 2(f) is a 2011 GUF architecture information product diagram provided by an embodiment of the present invention;
fig. 2(g) is a diagram of a high resolution one-high spatial resolution remote sensing image (2 meters) of 2016, 4, 9 and 9 days according to an embodiment of the present invention;
FIG. 3 is a VANUI index feature graph corresponding to 2016 year NPP-VIIRS night light data (400 meters) and 2016 year MODIS MOD13Q1 product data (250 meters) provided by an embodiment of the present invention;
fig. 4 is a result diagram of obtaining a city built-up area boundary B1 by adaptively segmenting the vauui by using the statistical data of the city built-up area according to the embodiment of the present invention;
FIG. 5 is a diagram illustrating the result of calculating the MBI of the high resolution image within the boundary B1 of the urban area according to the embodiment of the present invention;
FIG. 6 is a result diagram of an urban building information result obtained by constructing an adaptive segmentation model based on a multi-source mesoscale thematic information product, segmenting an MBI index, and providing the adaptive segmentation model;
FIG. 7 is a schematic illustration of a rule building information result provided by an embodiment of the present invention;
fig. 8 is a diagram of a final extraction result of an urban area building provided by the embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
In the embodiment of the present invention, the adopted multi-scale spatial data includes: 1) macro scale remote sensing data: NPP-VIIRS night light data (400 meters) in 2016 (fig. 2 (a)) and MODIS MOD13Q1 product data (250 meters) in 2016 (fig. 2 (b)); 2) and a mesoscale remote sensing data product: water type and bare land type information products of GlobeLand30 in 2010 (30 meters) (shown in fig. 2 (c)), Hansen vegetation type information products in 2013 (shown in fig. 2 (d)), openstreet map road type information products in 2015 (shown in fig. 2 (e)), and building information products in 2011 GUF (shown in fig. 2 (f)); 3) and a high-resolution one-high spatial resolution remote sensing image (2 m) of the high-spatial resolution remote sensing image 2016 (4 months, 9 days) (shown in fig. 2 (g)). The multispectral resolution and the panchromatic resolution of the remote sensing data of the high-resolution first-grade satellite are respectively 8 meters and 2 meters, the remote sensing data of the high-resolution first-grade satellite comprises four wave bands, namely a blue wave band (0.45-0.52 mu m), a green wave band (0.52-0.59 mu m), a red wave band (0.63-0.69 mu m), a near infrared wave band (0.77-0.89 mu m), the radiation quantization level is 16 bits, and a high-resolution orthographic fusion remote sensing image with the spatial resolution of 2 meters is obtained through RPC model and Gram-Schmidt fusion processing. The spatial resolution of an MODIS MOD13Q1 product is 250 meters, the time resolution is 16 days, projection change, mosaic and cutting are carried out through MRT, MODIS NDVI time sequence data are obtained, an SG filtering algorithm is used for reconstructing the MODIS NDVI time sequence, influences of factors such as atmosphere, solar illumination and observation visual angle are eliminated, and a reconstructed MODIS NDVI time sequence product is obtained.
Fig. 1 is a flowchart of an urban built-up area high-resolution remote sensing automatic extraction method based on multi-scale spatial information nesting according to an embodiment of the invention. As shown in fig. 1, the method comprises the steps of:
1) constructing an urban index VANUI based on 250m MODIS NDVI data and 400m NPP-VIIRS noctilucent data;
VANUI＝DN NPP ×(1-NDVI mean )
in the formula, DN NPP DN value of NPP-VIIRS luminous data; NDVI mean The mean value of MODIS NDVI time sequence data after filtering processing; VANUI is a city index. The result of the VANUI index profile of this example is shown in FIG. 3.
2) Carrying out self-adaptive segmentation on the VANUI by utilizing statistical data of the urban built-up area to obtain an urban built-up area boundary B1;
Figure BDA0003596274180000061
wherein, B1 is urban building area; DN VANUI Pixel values of the VANUI characteristic image; t is the pixel value of the VANUI characteristicThe interval, t in this embodiment, is [0,1 ]](ii) a Area is the Area of a VANUI characteristic image segmentation result corresponding to the VANUI characteristic pixel value interval t; and N is a parameter and represents the area in the city built-up area statistical yearbook of the research city. According to the 'statistics of the Chinese cities annual book 2016', the area value of the built-up area in Shanghai city in 2016 is 998.6km 2 . The result of the city urban area boundary B1 of the embodiment is shown in FIG. 4.
3) Calculating a morphological construction index MBI of the high-resolution image for an area in a boundary B1 of the urban construction area;
Figure BDA0003596274180000071
wherein the content of the first and second substances,
Figure BDA0003596274180000072
the calculation method comprises the following steps:
DMP W-TH (d,s)＝|MP W-TH (d,(s+Δs))-MP W-TH (d,s)|
wherein, MP W-TH The calculation method of (d, s) is as follows:
Figure BDA0003596274180000073
wherein, the calculation method of b is as follows:
Figure BDA0003596274180000074
in the formula, DMP W-TH Representing a differential morphological profile based on a top-hat transform; d and S respectively represent the number of multiple angles and the number of multiple scales, and the number of the multiple angles and the number of the multiple scales are respectively 4 and 6 through experiments in the research; MP (moving Picture experts group) W-TH Representing a morphological contour based on a top-hat transformation;
Figure BDA0003596274180000076
representing a b-based morphological open reconstruction; b represents the brightness of each wave band of the remote sensing image pixel pointA large value; d, s and Δ s represent the direction, scale and scale increment parameters, respectively, which the study experimentally set to {0 °, 45 °, 90 ° and 135 ° }, {11, 19, 27, 35, 43, 51, 59}, 8, respectively; k represents the wave band of the remote sensing image; k represents the maximum value of the applied remote sensing image wave band, and the parameter of the high-resolution remote sensing image with the high resolution of the high resolution grade one number adopted in the research is 4; x represents a pixel value of the remote sensing image. The morphological architectural index MBI results of this example are shown in FIG. 5.
4) Constructing a self-adaptive segmentation model based on the multi-source mesoscale thematic information product, and segmenting the MBI index to obtain urban building information O;
Figure BDA0003596274180000075
the Mask calculation method comprises the following steps:
Figure BDA0003596274180000081
where p is the pixel value interval of the MBI index, the interval of p in this study is [0,255%]；Area p Is the area of the region of the MBI segmentation result when the threshold is p; area GUF Area of a topical information product GUF (Global Urban Footprint (GUF)); mask is an information Mask model; GlobeLand30 (water,bare) OSM and Hansen denote "water body type", "bare land type" in GlobeLand30 ground cover products, "road type" in openstreet map products, and "vegetation type" in Hansen products, respectively. The map of the result of obtaining the city building information of the embodiment is shown in fig. 6.
5) Performing clustering analysis on the extracted urban building result O by adopting a Kmeans clustering algorithm to obtain a regular building information result S;
Figure BDA0003596274180000082
wherein, mu i The calculation method comprises the following steps:
Figure BDA0003596274180000083
in the formula, k represents the number of clusters, and the parameter is 2; ci represents the type of the cluster, and the parameter is 2, which represents two types; c represents the specific type obtained in the types of clusters, namely: regular buildings and irregular buildings; mu.s i Representing the ith cluster center; f represents the selected characteristic information, and MBI characteristics, rectangular geometric characteristics and texture characteristics are adopted through experiments in the research; DN F Pixel values are obtained for the feature information. The regular building information result S of the present embodiment is shown in fig. 7.
6) And calculating the convex hull of the regular building information S by adopting a Graham scanning method, and obtaining the final boundary range of the urban built-up area.
a) First, select a point set S (S) 0 ,s 1 ,s 2 ,s 3 ,……,s n ) The point with the smallest y coordinate is marked as s 0 If the y coordinates are the same, the x coordinate of the same point is the minimum; it should be understood that the regular building information S is a set of points S (S) 0 ,s 1 ,s 2 ,s 3 ,……,s n ) Wherein s is 0 Is the first building information, s 1 For the second building information, s 2 Is the third building information, s 3 Is the fourth building information, s n The (n + 1) th building information;
b) handle(s) 0 ,s 1 ,s 2 ,s 3 ,……,s n ) In order of polar angle from small to large (in s) 0 Pole) is pressed to s 0 The distances of (a) are sorted from small to large;
c) handle s 0 ,s 1 ,s 2 Pushing the stack;
d) traverse the remaining points s 3 ,s 4 ,……,s n By calculating the cross product(s) between two points n -s 0 )×(s n-1 -s 0 )＝(x n -x 0 )×(y n -y 0 )-(x n-1 -x 0 )×(y n-1 -y 0 ) When the cross product between two points is less than 0, indicating a counter-clockwise direction, the vertex remains. When the cross product between two points is greater than 0, indicating a clockwise direction, then the vertex is removed;
e) and finally obtaining the final boundary range of the built-up area of the city through traversal. The final extraction result of the urban area is shown in fig. 8.
The embodiment also provides a remote sensing extraction system for urban built-up areas based on multi-scale space nesting, which comprises: the first module is used for constructing a city index VANUI according to MODIS NDVI data and NPP-VIIRS noctilucent data; the second module is used for carrying out self-adaptive segmentation on the city index VANUI by utilizing the statistical data of the urban built-up area to obtain an urban built-up area boundary B1; the third module is used for calculating a morphological construction index MBI according to a boundary B1 of the urban construction area; the fourth module is used for constructing a self-adaptive segmentation model, segmenting the morphological building index MBI and acquiring urban building information O; the fifth module is used for carrying out cluster analysis on the urban building information O to obtain regular building information S; and the sixth module is used for calculating the convex hull of the regular building information S and acquiring the boundary range of the urban built-up area.
The method fully exerts the thematic information advantage of large-scale noctilucent data, the attribute advantage of medium-scale optical remote sensing thematic and the spatial information advantage of high-resolution remote sensing images, and constructs an adaptive segmentation model by applying the prior information technologies such as unstructured statistical data, a clustering method, adaptive segmentation and the like around the comprehensive attributes of urban construction areas, associates large-medium-small scale spatial information, realizes nesting of multi-scale spaces, restricts and continuously optimizes the extraction result of the urban construction areas, and finally realizes automatic extraction of the urban construction areas.
According to the method, the noctilucent data is automatically segmented through the urban construction area statistical data to obtain the urban construction area coarse boundary, so that the potential area range of the urban construction area can be preliminarily determined; in the region range, based on the high-resolution remote sensing image and the medium-resolution thematic information product, urban regularization building information is extracted, and the potential region range of the urban building boundary is further refined; the potential area ranges of the urban building boundaries are automatically connected through Graham scanning, the robustness of the method is improved, and the automatic information extraction of urban construction areas is finally realized; the method has better robustness for urban construction areas, especially under the condition of medium and large cities, and has automatic extraction capability under different urban scenes.
Although the present invention has been described with reference to the preferred embodiments, it is not intended to limit the present invention, and those skilled in the art can make variations and modifications of the present invention without departing from the spirit and scope of the present invention by using the methods and technical contents disclosed above.

Claims (10)

1. A remote sensing extraction method for urban built-up areas based on multi-scale spatial nesting is characterized by comprising the following steps:
constructing an urban index according to MODIS NDVI data and NPP-VIIRS noctilucent data;
self-adaptive segmentation is carried out on the city index by utilizing the statistical data of the urban built-up area to obtain the boundary of the urban built-up area;
calculating a morphological building index according to the boundary of the urban construction area;
constructing a self-adaptive segmentation model, segmenting the morphological building index, and acquiring urban building information;
performing clustering analysis on the urban building information to obtain regular building information;
and calculating a convex hull of the regular building information to obtain the boundary range of the urban built-up area.
2. The urban built-up area remote sensing extraction method based on multi-scale space nesting according to claim 1, characterized in that: the city index VANUI is obtained by the following formula:
VANUI＝DN NPP ×(1-NDVI mean )；
wherein DN NPP DN value of NPP-VIIRS noctilucent data; NDVI mean The average value of the MODIS NDVI data after filtering processing is obtained; VANUI is a city index.
3. The urban built-up area remote sensing extraction method based on multi-scale space nesting according to claim 1, characterized in that: the urban construction area boundary B1 is obtained by the following formula:
Figure FDA0003596274170000011
wherein, B1 is the boundary of urban construction area; DN VANUI Pixel values of the city index feature image; t is a pixel value interval of the city index characteristic image; area t And (VANUI) is the area of the segmentation result of the city index characteristic image corresponding to the pixel value interval of the city index characteristic image.
4. The urban built-up area remote sensing extraction method based on multi-scale space nesting according to claim 1, characterized in that: the morphological architectural index MBI is obtained by the following formula:
Figure FDA0003596274170000012
wherein, DMP W-TH (d,s)＝|MP W-TH (d,(s+Δs))-MP W-TH (d,s)|；
Figure FDA0003596274170000021
DMP W-TH (d, s) represents a differential morphological contour based on a top hat transform; d and S respectively represent the number of multi-angles and the number of multi-scales; MP (moving Picture experts group) W-TH (d, s) represents a morphological contour based on a top-hat transformation;
Figure FDA0003596274170000022
representing a b-based morphological open reconstruction; b represents the maximum brightness value in each wave band of the remote sensing image pixel points; d, s and Δ s represent direction, scale and scale increment parameters, respectively; k represents the wave band of the remote sensing image; k represents the maximum value of the applied remote sensing image wave band; x represents a pixel value of the remote sensing image.
5. The urban built-up area remote sensing extraction method based on multi-scale space nesting according to claim 1, characterized in that: the city building information O is obtained by the following formula:
Figure FDA0003596274170000023
wherein, p is a pixel value interval of the morphological building index; area p (MBI) is the area of the morphological building index segmentation result corresponding to the morphological building index MBI pixel value interval; area GUF Area of global city footprint data; mask is the information Mask model.
6. The urban built-up area remote sensing extraction method based on multi-scale spatial nesting according to claim 5, characterized by comprising the following steps: the information Mask model Mask is:
Figure FDA0003596274170000024
wherein, GlobeLand30 (water,bare) Indicating "water type" and "bare land type" in GlobeLand30 surface covering products, OSM being "road type" for openstreet map products, and Hansen being "vegetation type" for Hansen products.
7. The urban built-up area remote sensing extraction method based on multi-scale space nesting according to claim 1, characterized in that: and (5) carrying out clustering analysis on the urban building information O by adopting a Kmeans clustering algorithm to obtain regular building information S.
8. The urban built-up area remote sensing extraction method based on multi-scale spatial nesting according to claim 7, characterized by comprising the following steps: the regular building information S is obtained by the following formula:
Figure FDA0003596274170000025
wherein k represents the number of clusters; ci represents the type of cluster; c represents the specific type obtained from the types of the clusters; mu.s i Representing the ith cluster center; f represents the selected characteristic information; DN F Pixel values are obtained for the feature information.
9. The urban built-up area remote sensing extraction method based on multi-scale spatial nesting according to claim 1, characterized by comprising the following steps: and calculating the convex hull of the regular building information S by adopting a Graham scanning method.
10. A remote sensing extraction system for built-up areas of cities based on multi-scale space nesting is characterized by comprising:
the first module is used for constructing an urban index according to MODIS NDVI data and NPP-VIIRS luminous data;
the second module is used for carrying out self-adaptive segmentation on the city index VANUI by utilizing the statistical data of the urban built-up area to obtain the boundary of the urban built-up area;
the third module is used for calculating a morphological building index according to the boundary of the urban building area;
the fourth module is used for constructing a self-adaptive segmentation model, segmenting the morphological building index and acquiring urban building information;
the fifth module is used for carrying out clustering analysis on the urban building information to obtain regular building information;
and the sixth module is used for calculating the convex hull of the regular building information and acquiring the boundary range of the urban built-up area.
CN202210392975.8A 2022-04-14 2022-04-14 Urban built-up area remote sensing extraction method and system based on multi-scale space nesting Pending CN115018859A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210392975.8A CN115018859A (en) 2022-04-14 2022-04-14 Urban built-up area remote sensing extraction method and system based on multi-scale space nesting

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210392975.8A CN115018859A (en) 2022-04-14 2022-04-14 Urban built-up area remote sensing extraction method and system based on multi-scale space nesting

Publications (1)

Publication Number Publication Date
CN115018859A true CN115018859A (en) 2022-09-06

Family

ID=83067673

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210392975.8A Pending CN115018859A (en) 2022-04-14 2022-04-14 Urban built-up area remote sensing extraction method and system based on multi-scale space nesting

Country Status (1)

Country Link
CN (1) CN115018859A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117612003A (en) * 2023-11-27 2024-02-27 通友微电(四川)有限公司 Urban built-up area green land change identification method based on multi-source remote sensing image

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117612003A (en) * 2023-11-27 2024-02-27 通友微电(四川)有限公司 Urban built-up area green land change identification method based on multi-source remote sensing image

Similar Documents

Publication Publication Date Title
CN108596103B (en) High-resolution remote sensing image building extraction method based on optimal spectral index selection
CN107610164B (en) High-resolution four-number image registration method based on multi-feature mixing
CN107067405B (en) Remote sensing image segmentation method based on scale optimization
CN112396128B (en) Automatic labeling method for railway external environment risk source sample
CN111008664B (en) Hyperspectral sea ice detection method based on space-spectrum combined characteristics
Huang et al. Automatic extraction of impervious surfaces from high resolution remote sensing images based on deep learning
CN107491758A (en) Yangtze river basin water body information and its space encoding method
CN107688777B (en) Urban green land extraction method for collaborative multi-source remote sensing image
CN110390255A (en) High-speed rail environmental change monitoring method based on various dimensions feature extraction
CN112017160A (en) Multi-strategy combination-based multi-source remote sensing image road material fine extraction method
CN101980317A (en) Method for predicting traffic flow extracted by improved C-V model-based remote sensing image road network
CN113744249B (en) Marine ecological environment damage investigation method
CN112241661A (en) Urban ground feature fine classification method combining airborne LiDAR point cloud data and aerial image
CN112669459A (en) Satellite image optimal mosaic line generation method based on feature library intelligent decision
CN113780307A (en) Method for extracting blue-green space information with maximum regional year
CN112037244B (en) Landsat-8 image culture pond extraction method combining index and contour indicator SLIC
CN113362359A (en) Building automatic extraction method of oblique photography data fused with height and spectrum information
CN109598202A (en) A kind of object-based satellite image multi objective built-up areas extraction method
CN113505842A (en) Automatic extraction method suitable for large-scale regional remote sensing image urban building
CN116363522A (en) Coastal zone reclamation sea change remote sensing monitoring method based on deep learning
CN115862010A (en) High-resolution remote sensing image water body extraction method based on semantic segmentation model
CN115018859A (en) Urban built-up area remote sensing extraction method and system based on multi-scale space nesting
CN115527027A (en) Remote sensing image ground object segmentation method based on multi-feature fusion mechanism
CN114119630A (en) Coastline deep learning remote sensing extraction method based on coupling map features
Yang et al. An Improved Method for Individual Tree Segmentation in Complex Urban Scene Based on Using Multispectral LiDAR by Deep Learning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination