CN114550005A - Method and system for identifying buildings in natural protection area - Google Patents
Method and system for identifying buildings in natural protection area Download PDFInfo
- Publication number
- CN114550005A CN114550005A CN202210166403.8A CN202210166403A CN114550005A CN 114550005 A CN114550005 A CN 114550005A CN 202210166403 A CN202210166403 A CN 202210166403A CN 114550005 A CN114550005 A CN 114550005A
- Authority
- CN
- China
- Prior art keywords
- area
- index
- building
- data
- spectral
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000003595 spectral effect Effects 0.000 claims abstract description 85
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 34
- 238000012545 processing Methods 0.000 claims description 24
- 238000012937 correction Methods 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 20
- 230000000873 masking effect Effects 0.000 claims description 16
- 239000002689 soil Substances 0.000 claims description 13
- 238000010586 diagram Methods 0.000 claims description 12
- 230000003750 conditioning effect Effects 0.000 claims description 11
- 238000001228 spectrum Methods 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 208000027066 STING-associated vasculopathy with onset in infancy Diseases 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 4
- 238000005260 corrosion Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 4
- 238000002310 reflectometry Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 2
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 3
- 235000017491 Bambusa tulda Nutrition 0.000 description 3
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 241001330002 Bambuseae Species 0.000 description 2
- 239000011425 bamboo Substances 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 241000209128 Bambusa Species 0.000 description 1
- 101100356682 Caenorhabditis elegans rho-1 gene Proteins 0.000 description 1
- 235000002566 Capsicum Nutrition 0.000 description 1
- 239000006002 Pepper Substances 0.000 description 1
- 235000016761 Piper aduncum Nutrition 0.000 description 1
- 235000017804 Piper guineense Nutrition 0.000 description 1
- 244000203593 Piper nigrum Species 0.000 description 1
- 235000008184 Piper nigrum Nutrition 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to a method and a system for identifying buildings in a natural protection area, wherein the method comprises the following steps: preprocessing the satellite image of the target area to obtain preprocessed multispectral data; calculating a spectral index according to the preprocessed multispectral data; building identification rules of the target area are constructed based on the satellite images, the typical wave band characteristics and the typical index samples, and building areas are determined according to the spectral indexes and the building identification rules; closing the building area to obtain a closed building; and drawing according to the closed building and the preprocessed multispectral data to obtain a result graph. The building identification method integrates the characteristic information such as the image wave band, the spectral index and the like, so that the building identification efficiency is improved.
Description
Technical Field
The invention relates to the technical field of building identification in forest farm crossing areas, in particular to a building identification method and system in a natural conservation area.
Background
For a long time, how to automatically, quickly and accurately identify buildings by using high-spatial-resolution optical satellite images is a research hotspot for high-spatial satellite remote sensing application. In recent years, researchers at home and abroad use high-spatial-resolution satellite remote sensing data such as Quickbird, IKONOS, ZY-3 and the like to research and form a city (town) area building identification method with pixel level, object level and combination of the pixel level and the object level. The pixel level identification method takes a pixel as a basic unit, but the method can generate obvious salt and pepper phenomena to cause low identification precision; with the rapid development of artificial intelligence, the pixel-level building identification by using a deep learning method is concerned more and more, but the method has the limitations that a large number of training samples are required, the computer configuration requirement is high, and the like; the object level identification method divides the high-resolution image into a plurality of homogeneous areas (objects) with multiple pixels, so that the urban building identification result with higher precision can be obtained, but the search for the optimal segmentation scale is a challenge; in order to overcome the defects of the pixel level and the object level in building identification by using high-score data, some scholars try to combine the pixel level and the object level, firstly perform building initial extraction from pixels, and then perform post-identification by using an object level method.
Most of the existing building identification methods at home and abroad are developed by aiming at the characteristics of buildings in urban (town) areas, and the buildings in natural conservation areas generally have the characteristics of dispersion, small aggregation scale and the like compared with the buildings in the urban (town) areas, are shielded by mountains and trees, and influence the identification precision due to the interference of farmlands, bare lands, shadows and the like. .
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a building identification method and system in a natural reserve area.
In order to achieve the purpose, the invention provides the following scheme:
a building identification method in a nature reserve comprises the following steps:
preprocessing the satellite image of the target area to obtain preprocessed multispectral data;
calculating a spectral index according to the preprocessed multispectral data;
building identification rules of the target area are constructed based on the satellite images, the typical wave band characteristics and the typical index samples, and building areas are determined according to the spectral indexes and the building identification rules;
closing the building area to obtain a closed building;
and drawing according to the closed building and the preprocessed multispectral data to obtain a result graph.
Preferably, the preprocessing the satellite image of the target region to obtain preprocessed multispectral data includes:
acquiring the satellite image of a target area; the satellite image comprises multispectral data and panchromatic data;
carrying out absolute radiometric calibration and atmospheric correction on the multispectral data in sequence to obtain first spectral data, and carrying out absolute radiometric calibration on the panchromatic data to obtain first panchromatic data;
sequentially performing orthorectification on the first spectral data and the first panchromatic data respectively by using RPC information to obtain second spectral data and second panchromatic data;
respectively carrying out geometric fine correction on the second spectral data and the second panchromatic data by using a reference image to obtain third spectral data and third panchromatic data;
performing image processing on the third spectral data and the third panchromatic data based on Gram-Schmidt Pan Sharpening algorithm to obtain preprocessed multispectral data covering the target area; the image processing comprises fusion, splicing and cutting.
Preferably, said calculating a spectral index from said preprocessed multispectral data comprises:
extracting spectral indexes to be calculated according to vegetation information, water body information, bare land information and building information based on a preset correlation index; the spectral indexes to be calculated comprise a normalized vegetation index, a soil conditioning index, a ratio index, a normalized water body index, a fire passing index and a global environment vegetation index;
and calculating the spectral index according to the spectral index and the preprocessed multispectral data.
Wherein, eta is an intermediate parameter,rho 1, rho 2, rho 3 and rho 4 are respectively the reflectivity of a first wave band, a second wave band, a third wave band and a fourth wave band of the satellite image in sequence; NDVI is the normalized vegetation index; SAVI is the soil conditioning index; RI is the ratio index; NDWI is the normalized water body index; BAI is the index of excessive internal heat; GEMI is the global environmental vegetation index.
Preferably, the building identification rule for the target area is constructed based on the satellite imagery, the typical band features and the typical index samples, and the building area is determined according to the spectral index and the building identification rule, including:
when the formula is satisfiedDetermining a target pixel as a vegetation, masking an area where the vegetation is located, and reserving a non-vegetation area;
in the satellite image of the non-vegetation area, when the value of a target pixel meets a formulaDetermining that the target pixel is a water body, and masking the area where the water body is located;
in the image of the non-vegetation area after the area where the water body is covered, when the value of the target pixel meets the formulaDetermining that the target pixel is a shadow, and masking the area where the shadow is located;
in the satellite image of the non-vegetation area after the area where the shadow is located is masked, when the value of a target pixel meets a formulaDetermining a target pixel as a road, and masking the area where the road is located;
in the satellite image of the non-vegetation area after the area where the road is covered, when the value of a target pixel meets a formulaORThen, determining the target pixel as bare ground, and aligning the bare groundMasking the region where the ground is located;
in the satellite image of the non-vegetation area after the area where the bare land is covered, when the value of a target pixel meets a formulaDetermining a target pixel as a candidate building;
taking the candidate building as a center, adopting an 8-neighborhood search analysis method to judge the connectivity of the detected single building pixel to obtain the number of the connectivity pixels of each area;
removing the area with the connectivity pixel number smaller than a preset threshold value, setting the value of the building as 1 and setting other category values as 0, and forming a binary grid map; and the area where the building image element in the binary grid map is located is the building area.
Preferably, the closing process of the building area to obtain a closed building includes:
taking building pixels in the binaryzation grid map as seed points, performing expansion corrosion treatment on a 7 multiplied by 7 window, filling the whole area with 1, marking all non-boundary points as 0, marking each connected area, and counting the number of the pixels;
filtering the image according to a preset pixel number threshold, reserving a connected region larger than the preset pixel number threshold, and deleting a connected region smaller than or equal to the preset pixel number threshold;
and performing edge smoothing treatment on the filtered image to obtain the closed building which forms a continuous closed region.
Preferably, the mapping according to the closed building and the preprocessed multispectral data to obtain a result map includes:
outputting the binaryzation closed building based on a function of the grid-to-vector conversion to obtain a vector diagram;
and carrying out image superposition according to the vector diagram and the preprocessed multispectral data to obtain the result diagram.
A system for identifying buildings in a natural reserve, comprising:
the preprocessing unit is used for preprocessing the satellite image of the target area to obtain preprocessed multispectral data;
the spectrum calculating unit is used for calculating a spectrum index according to the preprocessed multispectral data;
the identification unit is used for constructing a building identification rule of the target area based on the satellite image, the typical wave band characteristics and the typical index sample, and determining a building area according to the spectral index and the building identification rule;
the closing processing unit is used for performing closing processing on the building area to obtain a closed building;
and the drawing unit is used for drawing according to the closed building and the preprocessed multispectral data to obtain a result graph.
Preferably, the pretreatment unit specifically includes:
the acquisition module is used for acquiring the satellite image of the target area; the satellite image comprises multispectral data and panchromatic data;
the first correction module is used for sequentially carrying out absolute radiometric calibration and atmospheric correction on the multispectral data to obtain first spectral data;
the second correction module is used for sequentially performing orthorectification on the first spectral data and the panchromatic data respectively by utilizing RPC information to obtain second spectral data and first panchromatic data;
the third correction module is used for respectively carrying out geometric fine correction on the second spectral data and the first panchromatic data by utilizing a reference image to obtain third spectral data and second panchromatic data;
an image processing module, configured to perform image processing on the third spectral data and the second panchromatic data based on Gram-Schmidt Pan Sharpening algorithm to obtain the preprocessed multispectral data that covers the target region; the image processing comprises fusion, splicing and cutting.
Preferably, the spectrum calculating unit specifically includes:
the index extraction module is used for extracting spectral indexes to be calculated according to vegetation information, water body information, bare land information and building information based on a preset correlation index; the spectral indexes to be calculated comprise a normalized vegetation index, a soil conditioning index, a ratio index, a normalized water body index, a fire passing index and a global environment vegetation index;
and the calculation module is used for calculating the spectral index according to the spectral index and the preprocessed multispectral data.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention discloses a method and a system for identifying buildings in a natural protection area, wherein the method comprises the following steps: preprocessing the satellite image of the target area to obtain preprocessed multispectral data; calculating a spectral index according to the preprocessed multispectral data; building identification rules of the target area are constructed based on the satellite images, the typical wave band characteristics and the typical index samples, and building areas are determined according to the spectral indexes and the building identification rules; closing the building area to obtain a closed building; and drawing according to the closed building and the preprocessed multispectral data to obtain a result graph. The building identification method integrates the characteristic information such as the image wave band, the spectral index and the like, so that the building identification efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a method in an embodiment provided by the present invention;
FIG. 2 is a schematic process flow diagram of an automatic building identification technique according to an embodiment of the present invention;
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, the inclusion of a list of steps, processes, methods, etc. is not limited to only those steps recited, but may alternatively include additional steps not recited, or may alternatively include additional steps inherent to such processes, methods, articles, or devices.
At present, the distribution condition of buildings in a natural protection area is accurately mastered, so that the method is indispensable information for forest disturbance monitoring, land utilization investigation and the like, and meanwhile, the method can provide technical service for rapidly and conveniently processing illegal building events in the protection area. Therefore, the high-resolution remote sensing identification method for buildings in the natural protection area with pertinence in the application range is researched and formed, and the method has important practical significance for the protection of the natural protection area.
The invention aims to provide a method and a system for identifying buildings in a natural protection area, which can improve the efficiency of identifying the buildings in the natural protection area.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a flowchart of a method in an embodiment of the present invention, and as shown in fig. 1, the present invention provides a method for identifying a building in a natural reserve, including:
step 100: preprocessing the satellite image of the target area to obtain preprocessed multispectral data;
step 200: calculating a spectral index according to the preprocessed multispectral data;
step 300: building identification rules of the target area are constructed based on the satellite images, the typical wave band characteristics and the typical index samples, and building areas are determined according to the spectral indexes and the building identification rules;
step 400: closing the building area to obtain a closed building;
step 500: and drawing according to the closed building and the preprocessed multispectral data to obtain a result graph.
Preferably, the preprocessing the satellite image of the target region to obtain preprocessed multispectral data includes:
acquiring the satellite image of a target area; the satellite image comprises multispectral data and panchromatic data;
carrying out absolute radiometric calibration and atmospheric correction on the multispectral data in sequence to obtain first spectral data; carrying out absolute radiometric calibration on the panchromatic data to obtain first panchromatic data;
sequentially performing orthorectification on the first spectral data and the first panchromatic data respectively by using RPC information to obtain second spectral data and second panchromatic data;
respectively carrying out geometric fine correction on the second spectral data and the second panchromatic data by using a reference image to obtain third spectral data and third panchromatic data;
performing image processing on the third spectral data and the third panchromatic data based on Gram-Schmidt Pan Sharpening algorithm to obtain preprocessed multispectral data covering the target area; the image processing comprises fusion, splicing and cutting.
Fig. 2 is a schematic diagram of a processing flow of an automatic building identification technology in an embodiment provided by the present invention, and as shown in fig. 2, in order to meet the technical requirements of automatic building identification in a natural protection area of the bamboo sea, Changning in Sichuan, the present embodiment provides a method for remotely identifying a building in a natural protection area by comprehensively utilizing characteristic information such as a wave band and a spectral index of a domestic high-resolution second (GF-2) satellite image, so as to serve for monitoring artificial disturbance information in the natural protection area.
The first step in the embodiment is image preprocessing, firstly absolute radiometric calibration and atmospheric correction are carried out on multispectral data of a high-resolution second (GF-2) satellite image L1A level of a natural protection area of the national level of the bamboo sea without cloud coverage, then the multispectral data and the panchromatic data are respectively subjected to orthorectification based on RPC information carried by product data, geometric fine correction is carried out by using a reference image, and then fusion, splicing, cutting and other processing are carried out on the multispectral data and the panchromatic data subjected to orthorectification by adopting a Gram-Schmidt Pan shading algorithm, so that the multispectral image and the panchromatic image with the spatial resolution of 1m covering an area to be detected are obtained.
Preferably, said calculating a spectral index from said preprocessed multispectral data comprises:
extracting spectral indexes to be calculated according to vegetation information, water body information, bare land information and building information based on a preset correlation index; the spectral indexes to be calculated comprise a normalized vegetation index, a soil conditioning index, a ratio index, a normalized water body index, a fire passing index and a global environment vegetation index;
and calculating the spectral index according to the spectral index and the preprocessed multispectral data.
Wherein eta is an intermediate parameter,ρ1、ρ2rho 3 and rho 4 are the reflectivities of a first wave band, a second wave band, a third wave band and a fourth wave band of the satellite image in sequence; NDVI is the normalized vegetation index; SAVI is the soil conditioning index; RI is the ratio index; NDWI is the normalized water body index; BAI is the index of excessive internal heat; GEMI is the global environmental vegetation index.
Further, in the embodiment, the second step is spectral index calculation, and by using the preprocessed GF-2 multispectral data, 6 spectral indexes, such as normalized vegetation index (NDVI), soil conditioning index (SAVI), Ratio Index (RI), normalized water index (NDWI), fire index (BAI), and global environment vegetation index (GEMI), which have high correlation with information extraction such as vegetation, water, bare land, and buildings, are selected, and the calculation formulas are respectively shown in formulas (1) to (7).
Wherein: η is an intermediate parameter and is calculated by equation (7).
In the formula: rho1、ρ2、ρ3And ρ4The reflectivities of band 1, band 2, band 3 and band 4 of GF-2 data are in that order.
Preferably, the building identification rule for the target area is constructed based on the satellite imagery, the typical band features and the typical index samples, and the building area is determined according to the spectral index and the building identification rule, including:
when the formula is satisfiedDetermining a target pixel as a vegetation, masking an area where the vegetation is located, and reserving a non-vegetation area;
in the satellite image of the non-vegetation area, when the value of a target pixel meets a formulaDetermining that the target pixel is a water body, and masking the area where the water body is located;
in the image of the non-vegetation area after the area where the water body is covered, when the value of the target pixel meets the formulaDetermining that the target pixel is a shadow, and masking the area where the shadow is located;
in the satellite image of the non-vegetation area after the area where the shadow is located is masked, when the value of a target pixel meets a formulaDetermining a target pixel as a road, and masking the area where the road is located;
in the satellite image of the non-vegetation area after the area where the road is covered, when the value of a target pixel meets a formulaORDetermining a target pixel as a bare area, and masking the area where the bare area is located;
in the satellite image of the non-vegetation area after the area where the bare land is covered, when the value of a target pixel meets a formulaDetermining a target pixel as a candidate building;
taking the candidate building as a center, adopting an 8-neighborhood search analysis method to judge the connectivity of the detected single building pixel to obtain the number of the connectivity pixels of each area;
removing the area with the connectivity pixel number smaller than a preset threshold value, setting the value of the building as 1 and setting other category values as 0, and forming a binary grid map; and the area where the building image element in the binary grid map is located is the building area.
Specifically, the third step in this embodiment is building identification rules, and building identification rules of the natural protection area are built by analyzing band features and index samples of typical categories such as selected vegetation, water, open land, buildings and the like by using GF-2 images of national natural protection areas of bamboos, changning, cahai, and the like, and mainly include the following seven aspects:
(1) non-vegetation area extraction
Constructing a vegetation pixel discriminant by using the calculated NDVI and GF-2 wave band feature combinations; and when the value of the pixel satisfies the formula (8), judging the pixel as vegetation, masking the vegetation area and reserving the non-vegetation area.
(2) Water mask
In the non-vegetation area image, when the value of the pixel satisfies the formula (9), the pixel is judged as a water body pixel, and the water body area is masked.
(3) Shadow mask
In the non-vegetation area image after the water body area is masked, when the value of the pixel satisfies the formula (10), the pixel is judged as a shadow area, and the shadow area is masked.
(4) Road mask
In the image of the non-vegetation area masked with the shadow pixel and the like, when the value of the pixel satisfies the formula (11), the pixel is judged as a road area and is masked.
(5) Bare ground mask
In the non-vegetation area image after the road pixel is masked, when the value of the pixel meets the formula (12), the pixel is judged as a bare area pixel, and the pixel is masked.
(6) Building candidate picture element
In the image of the non-vegetation area obtained by masking the bare land and other pixels, when the value of the pixel satisfies the formula (13), the pixel is determined as a candidate building.
(7) Building image element confirmation
And taking the candidate building as a center, adopting an 8-neighborhood search analysis method to judge the connectivity of the detected single building pixel, removing the area with smaller number of the connectivity pixels, setting the value of the building to be 1, and setting other category values to be 0, and forming a binary grid map.
Preferably, the closing process of the building area to obtain a closed building includes:
taking the building pixels in the binary grid map as seed points, performing expansion corrosion treatment on a 7 multiplied by 7 window, filling the whole area with 1, marking all non-boundary points as 0, marking each connected area, and counting the number of the pixels;
filtering the image according to a preset pixel number threshold, reserving a connected region larger than the preset pixel number threshold, and deleting a connected region smaller than or equal to the preset pixel number threshold;
and performing edge smoothing treatment on the filtered image to obtain the closed building which forms a continuous closed region.
Optionally, the fourth step in this embodiment is a building area closing process, and since the distribution of buildings in a forest is usually relatively dispersed and continuously covers a floor area of most dozens of square meters, and is also blocked by surrounding trees, when a building area is identified through an algorithm program under such conditions, a phenomenon of sporadic pixels occurs.
Taking the detected building pixels in the binary image as seed points, performing expansion corrosion treatment on a 7 multiplied by 7 window, filling the whole area with 1, marking all non-boundary (background) points as 0, labeling each connected area, and counting the number of the pixels; then, filtering the image according to the set number of pixels (threshold value for short), completely reserving the connected region exceeding the threshold value, and deleting the connected region if the number of pixels is less than the threshold value; and finally, performing edge smoothing treatment to form a continuous building with closed regional property.
Preferably, the drawing according to the closed building and the preprocessed multispectral data to obtain a result graph includes:
outputting the binaryzation closed building based on a function of the grid-to-vector conversion to obtain a vector diagram;
and carrying out image superposition according to the vector diagram and the preprocessed multispectral data to obtain the result diagram.
As an optional implementation manner, in this embodiment, the fifth step is to output the result of drawing, and output the binarized building as a vector diagram by using a function of grid vector conversion; and superposing the preprocessed GF-2 multispectral image to perform drawing.
The embodiment also provides a system for identifying buildings in a natural reserve area, which comprises:
the preprocessing unit is used for preprocessing the satellite image of the target area to obtain preprocessed multispectral data;
the spectrum calculating unit is used for calculating a spectrum index according to the preprocessed multispectral data;
the identification unit is used for constructing a building identification rule of the target area based on the satellite image, the typical wave band characteristics and the typical index sample, and determining a building area according to the spectral index and the building identification rule;
the closing processing unit is used for performing closing processing on the building area to obtain a closed building;
and the drawing unit is used for drawing according to the closed building and the preprocessed multispectral data to obtain a result graph.
Preferably, the pretreatment unit specifically includes:
the acquisition module is used for acquiring the satellite image of the target area; the satellite image comprises multispectral data and panchromatic data;
the first correction module is used for sequentially carrying out absolute radiometric calibration and atmospheric correction on the multispectral data to obtain first spectral data and is also used for carrying out absolute radiometric calibration on the panchromatic data to obtain first panchromatic data;
the second correction module is used for sequentially performing orthorectification on the first spectral data and the first panchromatic data respectively by utilizing RPC information to obtain second spectral data and second panchromatic data;
the third correction module is used for respectively carrying out geometric fine correction on the second spectral data and the second panchromatic data by utilizing a reference image to obtain third spectral data and third panchromatic data;
an image processing module, configured to perform image processing on the third spectral data and the third panchromatic data based on a Gram-schmidtpa shaping algorithm to obtain preprocessed multispectral data that covers the target region; the image processing comprises fusion, splicing and cutting.
Preferably, the spectrum calculating unit specifically includes:
the index extraction module is used for extracting spectral indexes to be calculated according to vegetation information, water body information, bare land information and building information based on a preset correlation index; the spectral indexes to be calculated comprise normalized vegetation indexes, soil regulation indexes, ratio indexes, normalized water body indexes, fire indexes and global environment vegetation indexes;
and the calculation module is used for calculating the spectral index according to the spectral index and the preprocessed multispectral data.
The invention has the following beneficial effects:
(1) the invention researches and forms a high-resolution remote sensing identification method of buildings in a natural protected area, and has important practical significance for the protection of the natural protected area.
(2) The invention provides a building identification method integrating characteristic information such as image wave band, spectral index and the like, and provides technical support for monitoring artificial disturbance information of a natural protected area.
(3) The building identification method integrates the characteristic information such as the image wave band, the spectral index and the like, so that the building identification efficiency is improved.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (10)
1. A method and a system for identifying buildings in a natural conservation area are characterized by comprising the following steps:
preprocessing the satellite image of the target area to obtain preprocessed multispectral data;
calculating a spectral index according to the preprocessed multispectral data;
building identification rules of the target area are constructed based on the satellite images, the typical wave band characteristics and the typical index samples, and building areas are determined according to the spectral indexes and the building identification rules;
closing the building area to obtain a closed building;
and drawing according to the closed building and the preprocessed multispectral data to obtain a result graph.
2. The method for identifying buildings in natural reserve according to claim 1, wherein the preprocessing the satellite image of the target area to obtain the preprocessed multispectral data comprises:
acquiring the satellite image of a target area; the satellite image comprises multispectral data and panchromatic data;
carrying out absolute radiometric calibration and atmospheric correction on the multispectral data in sequence to obtain first spectral data, and carrying out absolute radiometric calibration on the panchromatic data to obtain first panchromatic data;
sequentially performing orthorectification on the first spectral data and the first panchromatic data respectively by using RPC information to obtain second spectral data and second panchromatic data;
respectively carrying out geometric fine correction on the second spectral data and the second panchromatic data by using a reference image to obtain third spectral data and third panchromatic data;
performing image processing on the third spectral data and the third panchromatic data based on Gram-Schmidt Pan Sharpening algorithm to obtain preprocessed multispectral data covering the target area; the image processing comprises fusion, splicing and cutting.
3. The method for identifying buildings within natural conservation zones as claimed in claim 1, wherein said calculating a spectral index from said preprocessed multispectral data comprises:
extracting spectral indexes to be calculated according to vegetation information, water body information, bare land information and building information based on a preset correlation index; the spectral indexes to be calculated comprise a normalized vegetation index, a soil conditioning index, a ratio index, a normalized water body index, a fire passing index and a global environment vegetation index;
and calculating the spectral index according to the spectral index and the preprocessed multispectral data.
4. The method for identifying buildings in a natural protected area according to claim 3, wherein the normalized vegetation index is calculated by the formula:
Wherein eta is an intermediate parameter,ρ1、ρ2、ρ3and ρ4The reflectivities of a first wave band, a second wave band, a third wave band and a fourth wave band of the satellite image are sequentially recorded; NDVI is the normalized vegetation index; SAVI is the soil conditioning index; RI is the ratio index; NDWI is the normalized water body index; BAI is the index of excessive internal heat; GEMI is the global environmental vegetation index.
5. The method for identifying buildings in natural protection areas according to claim 4, wherein the building identification rule of the target area is constructed based on the satellite images, the typical wave band characteristics and the typical index samples, and the building area is determined according to the spectral index and the building identification rule, and the method comprises the following steps:
when the formula is satisfiedDetermining a target pixel as a vegetation, masking an area where the vegetation is located, and reserving a non-vegetation area;
in the satellite image of the non-vegetation area, when the value of a target pixel meets a formulaDetermining that the target pixel is a water body, and masking the area where the water body is located;
in the image of the non-vegetation area after the area where the water body is covered, when the value of the target pixel meets the formulaDetermining that the target pixel is a shadow, and masking the area where the shadow is located;
in the satellite image of the non-vegetation area after the area where the shadow is located is masked, when the value of a target pixel meets a formulaDetermining a target pixel as a road, and masking the area where the road is located;
in the satellite image of the non-vegetation area after the area where the road is covered, when the value of a target pixel meets a formulaDetermining a target pixel as a bare area, and masking the area where the bare area is located;
in the satellite image of the non-vegetation area after the area where the bare land is covered, when the value of a target pixel meets a formulaDetermining a target pixel as a candidate building;
taking the candidate building as a center, adopting an 8-neighborhood search analysis method to judge the connectivity of the detected single building pixel to obtain the number of the connectivity pixels of each area;
removing the area with the connectivity pixel number smaller than a preset threshold value, setting the value of the building as 1 and setting other category values as 0, and forming a binary grid map; and the area where the building image element in the binary grid map is located is the building area.
6. The method for identifying buildings in natural protection areas according to claim 5, wherein the step of closing the building areas to obtain a closed building comprises the following steps:
taking the building pixels in the binary grid map as seed points, performing expansion corrosion treatment on a 7 multiplied by 7 window, filling the whole area with 1, marking all non-boundary points as 0, marking each connected area, and counting the number of the pixels;
filtering the image according to a preset pixel number threshold, reserving a connected region larger than the preset pixel number threshold, and deleting a connected region smaller than or equal to the preset pixel number threshold;
and performing edge smoothing treatment on the filtered image to obtain the closed building which forms a continuous closed region.
7. The method for identifying buildings within natural conservation zones as claimed in claim 6, wherein said mapping based on said closed buildings and said preprocessed multispectral data to obtain a result map comprises:
outputting the binaryzation closed building based on a function of the grid rotation vector to obtain a vector diagram;
and carrying out image superposition according to the vector diagram and the preprocessed multispectral data to obtain the result diagram.
8. A system for identifying buildings in a natural reserve, comprising:
the preprocessing unit is used for preprocessing the satellite image of the target area to obtain preprocessed multispectral data;
the spectrum calculating unit is used for calculating a spectrum index according to the preprocessed multispectral data;
the identification unit is used for constructing a building identification rule of the target area based on the satellite image, the typical wave band characteristics and the typical index sample, and determining a building area according to the spectral index and the building identification rule;
the closing processing unit is used for performing closing processing on the building area to obtain a closed building;
and the drawing unit is used for drawing according to the closed building and the preprocessed multispectral data to obtain a result graph.
9. The system for identifying buildings in natural reserve according to claim 8, wherein the preprocessing unit comprises:
the acquisition module is used for acquiring the satellite image of the target area; the satellite image comprises multispectral data and panchromatic data;
the first correction module is used for sequentially carrying out absolute radiometric calibration and atmospheric correction on the multispectral data to obtain first spectral data and is also used for carrying out absolute radiometric calibration on the panchromatic data to obtain first panchromatic data;
the second correction module is used for sequentially performing orthorectification on the first spectral data and the first panchromatic data respectively by utilizing RPC information to obtain second spectral data and second panchromatic data;
the third correction module is used for respectively carrying out geometric fine correction on the second spectral data and the second panchromatic data by utilizing a reference image to obtain third spectral data and third panchromatic data;
an image processing module, configured to perform image processing on the third spectral data and the third panchromatic data based on Gram-Schmidt Pan Sharpening algorithm to obtain the preprocessed multispectral data that covers the target region; the image processing comprises fusion, splicing and cutting.
10. The system for identifying buildings in natural conservation areas as claimed in claim 8, wherein the spectrum calculation unit specifically comprises:
the index extraction module is used for extracting a spectrum index to be calculated according to vegetation information, water body information, bare land information and building information based on a preset correlation index; the spectral indexes to be calculated comprise normalized vegetation indexes, soil regulation indexes, ratio indexes, normalized water body indexes, fire indexes and global environment vegetation indexes;
and the calculation module is used for calculating the spectral index according to the spectral index and the preprocessed multispectral data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210166403.8A CN114550005A (en) | 2022-02-23 | 2022-02-23 | Method and system for identifying buildings in natural protection area |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210166403.8A CN114550005A (en) | 2022-02-23 | 2022-02-23 | Method and system for identifying buildings in natural protection area |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114550005A true CN114550005A (en) | 2022-05-27 |
Family
ID=81678004
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210166403.8A Pending CN114550005A (en) | 2022-02-23 | 2022-02-23 | Method and system for identifying buildings in natural protection area |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114550005A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117576572A (en) * | 2024-01-16 | 2024-02-20 | 杭州稻道农业科技有限公司 | Comprehensive planting and raising paddy rice planting coverage extraction method, device and medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108596103A (en) * | 2018-04-26 | 2018-09-28 | 吉林大学 | High resolution ratio satellite remote-sensing image building extracting method based on optimal spectrum Index selection |
CN110796001A (en) * | 2019-09-23 | 2020-02-14 | 武汉珈和科技有限公司 | Satellite image film-covering farmland identification and extraction method and system |
CN111345214A (en) * | 2020-03-13 | 2020-06-30 | 武汉禾大科技有限公司 | Xinjiang cotton region identification method and system based on satellite image data |
-
2022
- 2022-02-23 CN CN202210166403.8A patent/CN114550005A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108596103A (en) * | 2018-04-26 | 2018-09-28 | 吉林大学 | High resolution ratio satellite remote-sensing image building extracting method based on optimal spectrum Index selection |
CN110796001A (en) * | 2019-09-23 | 2020-02-14 | 武汉珈和科技有限公司 | Satellite image film-covering farmland identification and extraction method and system |
CN111345214A (en) * | 2020-03-13 | 2020-06-30 | 武汉禾大科技有限公司 | Xinjiang cotton region identification method and system based on satellite image data |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117576572A (en) * | 2024-01-16 | 2024-02-20 | 杭州稻道农业科技有限公司 | Comprehensive planting and raising paddy rice planting coverage extraction method, device and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kaplan et al. | Mapping and monitoring wetlands using Sentinel-2 satellite imagery | |
Avitabile et al. | Capabilities and limitations of Landsat and land cover data for aboveground woody biomass estimation of Uganda | |
Jain et al. | Monitoring land use change and its drivers in Delhi, India using multi-temporal satellite data | |
Conrad et al. | Measuring rural settlement expansion in Uzbekistan using remote sensing to support spatial planning | |
Im et al. | A change detection model based on neighborhood correlation image analysis and decision tree classification | |
CN109919875B (en) | High-time-frequency remote sensing image feature-assisted residential area extraction and classification method | |
CN107247927B (en) | Method and system for extracting coastline information of remote sensing image based on tassel cap transformation | |
Chen et al. | The application of the tasseled cap transformation and feature knowledge for the extraction of coastline information from remote sensing images | |
Rasmussen et al. | Tree survey and allometric models for tiger bush in northern Senegal and comparison with tree parameters derived from high resolution satellite data | |
CN111046613B (en) | Optimal river channel calculation method based on path tracking and river network extraction method based on multi-temporal remote sensing image | |
Verhulp et al. | Transferability of decision trees for land cover classification in a heterogeneous area | |
Chen et al. | Urban land use mapping using high resolution SAR data based on density analysis and contextual information | |
CN113780307A (en) | Method for extracting blue-green space information with maximum regional year | |
Thompson et al. | Applying object-based segmentation in the temporal domain to characterise snow seasonality | |
CN114550005A (en) | Method and system for identifying buildings in natural protection area | |
CN105894006A (en) | Space-time probability model rice remote sensing recognition method | |
Solaimani et al. | Land use/cover change detection based on remote sensing data (A case study; Neka Basin) | |
Sun et al. | Identifying terraces in the hilly and gully regions of the Loess Plateau in China | |
Bektas Balcik et al. | Determination of magnitude and direction of land use/land cover changes in Terkos Water Basin, Istanbul | |
Asmat et al. | Automated house detection and delineation using optical remote sensing technology for informal human settlement | |
CN115063437B (en) | Mangrove canopy visible light image index feature analysis method and system | |
Ai et al. | Mapping of native plant species and noxious weeds to investigate grassland degradation in the Three-River Headwaters region using HJ-1A/HSI imagery | |
Whiteside et al. | Vegetation map for Magela Creek floodplain using WorldView-2 multispectral image data | |
Yue et al. | The extraction of water information based on SPOT5 image using object-oriented method | |
Taha | Assessment of urbanization encroachment over Al-Monib island using fuzzy post classification comparison and urbanization metrics |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220527 |
|
RJ01 | Rejection of invention patent application after publication |