CN111797720B - Drainage basin water body extraction method combining spectral characteristics and confluence cumulant - Google Patents
Drainage basin water body extraction method combining spectral characteristics and confluence cumulant Download PDFInfo
- Publication number
- CN111797720B CN111797720B CN202010554443.0A CN202010554443A CN111797720B CN 111797720 B CN111797720 B CN 111797720B CN 202010554443 A CN202010554443 A CN 202010554443A CN 111797720 B CN111797720 B CN 111797720B
- Authority
- CN
- China
- Prior art keywords
- water body
- confluence
- cumulant
- wave band
- confluence cumulant
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a drainage basin water body extraction method combining spectral characteristics and confluence cumulant, which is characterized in that a sentinel No. 2 multispectral image is used for identifying a drainage basin water body and outputting a corresponding water body image; calculating the average gradient and confluence cumulant of the corresponding basin by using DEM data and analyzing the correlation between the average gradient and confluence cumulant of the basin; and finally, correcting the water body diagram by taking the confluence cumulant at the first turning point of the correlation of the average gradient and the confluence cumulant as the minimum limit of forming the water body to obtain a more accurate watershed water body diagram. The method has the advantages of high calculation precision, wide application range, more scientific and reasonable results and the like, and is favorable for accurately acquiring the water body distribution condition of the watershed.
Description
Technical Field
The invention relates to the technical field of interpretation of water body information of remote sensing images, in particular to a drainage basin water body extraction method combining spectral characteristics and confluence cumulant.
Background
The surface water body is an important component of the earth water circulation, and acquisition of the surface water body distribution of the watershed is of great importance to hydrological analysis. Due to the enormous workload of field labeling, watershed surface water extraction is generally performed by a digital method. At present, optical remote sensing images become a conventional means for monitoring surface water, and acquired data can provide macroscopic, real-time and dynamic water distribution information and have high cost benefit.
McFeeters proposed a Normalized Difference Water Index (NDWI) in 1996, which utilizes the Difference of the reflectances of Water bodies in different bands to form the NDWI through the contrast of visible and near infrared bands. The NDWI can quickly extract the water body information in the image, but the method is interfered by dense buildings, so that the practical application of the method is limited. In xu equ autumn, a corrected Normalized Difference Water Index (MNDWI) is proposed in 2006, a short-wave infrared band is used for replacing a near-infrared band, vegetation information can be better restrained, meanwhile, spectrum confusion between Water and buildings can be reduced, extraction of urban Water is facilitated, but shadows, roads and other dark objects cannot be effectively distinguished. Feyisa proposed an Automatic Water Extraction Index (AWEI) in 2014, which can be formally transformed according to different background conditions, so that the precision in urban and mountainous areas is superior to MNDWI.
Although the water body index is an intuitive and concise water body extraction method, because the water body index cannot completely separate the water body from other ground objects, a large number of errors are often generated when a certain threshold value is directly applied to water body extraction. Aiming at the problem, Isikdog gan provides an automatic water system extraction engine (RivaMap) in 2017, and the model is based on the Canny edge detection theory, and uses a multi-scale singular index to strengthen a water body index map, so that the influence of bare rocks and vegetation on water body extraction is effectively reduced. However, the application of RivaMap to the 10m resolution Sentinel-2 image recognizes a large number of terrestrial units as water body units, and generates a large error.
Watershed Digital water system extraction can also be completed through a Digital Elevation Model (DEM), and a common method is to process the DEM to obtain the confluence accumulation amount and then set a threshold value for water system extraction. The method is simple and easy to implement, and can directly generate a connected river network, but the optimal threshold value of the extracted water system is often difficult to determine and limited by DEM precision, and the extracted water system by the method often cannot well reflect the condition of actual water system distribution. The existing water body extraction method based on spectral features can generate a large amount of False Positive errors (FP).
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide the drainage basin water body extraction method combining the spectral characteristics and the confluence cumulant, and the invention improves the accuracy and the scientificity of drainage basin water body extraction.
The invention adopts the following technical scheme for solving the technical problems:
the watershed water body extraction method combining the spectral characteristics and the confluence cumulant, provided by the invention, comprises the following steps of:
step 1, acquiring the 3 rd wave band, the 8 th wave band, the 11 th wave band and the 12 th wave band of the sentinel No. 2 multispectral image, preprocessing the wave bands and generating automatic waterBody extraction exponential graph AWEI nsh (ii) a Wherein, the 3 rd wave band is a green wave band, the 8 th wave band is a near infrared wave band, the 11 th wave band is a short wave infrared 1 wave band, and the 12 th wave band is a short wave infrared 2 wave band;
As a further optimization scheme of the watershed water body extraction method combining the spectral characteristics and the confluence cumulant, the pretreatment process in the step 1 is as follows:
the short wave infrared 1 band and the short wave infrared 2 band are resampled to the same spatial resolution as the green band and the near infrared band using bilinear interpolation.
As a further optimization scheme of the watershed water body extraction method combining spectral characteristics and confluence cumulant, the AWEI is subjected to step 2 nsh Analyzing and extracting the water body distribution of the basin, and outputting a water body distribution central line graph W of the basin Origin The method comprises the following steps:
mixing AWEI nsh Inputting the water body water Origin ；
As a further optimization scheme of the watershed water body extraction method combining spectral characteristics and confluence cumulant, step 3 calculates the gradient and confluence cumulant of each grid in the watershed by using DEM data and establishesCumulative amount of vertical convergence A and average gradient
The correlation curve of (2) is as follows:
step 3.1, calculating the gradient S and the convergence cumulant A of each grid unit of the drainage basin;
A＝{A 1 ，A 2 ，...，A N }
wherein N is the total number of grid units with different confluence cumulants, A j J is the jth confluence accumulation amount, 1,2.. N;
step 3.2, calculating the average gradient of the units with the same confluence cumulant according to the descending order of the numerical values of the confluence cumulant of each grid unit
Where i is the grid number of the n grid cells corresponding to a certain confluence accumulation amount, S i Is the slope corresponding to the i-th grid cell at the confluence accumulation amount, j is the number corresponding to the N confluence accumulation amounts,
is the average gradient corresponding to the jth confluence accumulation amount;
step 3.3, adopting a double logarithmic coordinate to draw a confluence cumulant A-average gradient
And (5) a correlation curve.
As a further optimization scheme of the watershed water body extraction method combining the spectral characteristics and the confluence cumulant, the step 4 is specifically as follows:
step 4.1, observing a confluence cumulant-average gradient correlation curve, and taking the confluence cumulant at the first turning point of the correlation curve as the minimum confluence cumulant A of the formed water body Critical ；
Step 4.2, with A Critical Generating a critical water body diagram W as a threshold value of confluence accumulation amount Critical Wherein W is Critical Is shown as
Step 4.3, utilize bilinear interpolation to get W Critical Resampling to and Origin the same spatial resolution;
step 4.4, outputting the final water body distribution central line graph W Revised The calculation method is as follows
W Revised ＝W Origin ×W Critical 。
Compared with the prior art, the invention adopting the technical scheme has the following technical effects:
(1) the method determines the minimum confluence cumulant requirement of the watershed generation water body through the digital elevation model so as to correct the water body extracted based on the spectral characteristics, thus effectively reducing false positives of water body extraction and obtaining a more accurate watershed water body diagram;
(2) the invention has high precision and good applicability; by utilizing the sentinel No. 2 multispectral image with the resolution of 10m, more precise water body distribution can be extracted, and meanwhile, the invention can accurately and effectively extract the water body distribution of drainage basins of different types and sizes;
(3) the data applied by the invention is public, reliable and easy to obtain; the sentry No. 2 multispectral image and the digital elevation model data are all covered globally, meanwhile, the method is simple in involved flow and clear in relation, calculation efficiency is guaranteed, and objective rules are met.
Drawings
FIG. 1 is an overall flow chart of the present invention.
FIG. 2 is a diagram of the AWEI calculated in accordance with the present invention nsh Figure (a).
FIG. 3 is a calculated initial water centerline map generated by the present invention.
FIG. 4 is a calculated grade map of the present invention.
FIG. 5 is a calculated total amount of conflux chart according to the present invention.
Fig. 6 is a graph showing the average gradient-confluence accumulation amount correlation established by the present invention.
FIG. 7 is a calculated critical water body map generated by the present invention.
FIG. 8 is a corrected water centerline map generated by the calculation of the present invention.
FIG. 9 is a schematic diagram of the comparison between the calculation result of the valley-deprived drain basin and the number 2 RGB image of the sentinel.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
Aiming at the problems in the background art, the discussion that the first turning point of the gradient-confluence cumulant correlation diagram symbolizes the transition from divergent terrain to convergent terrain and also shows the change of the water body dominant generation process (Kirkby, 1986; Tarboton et al, 1992; Georgiou, 1993) is combined, and the confluence cumulant at the first turning point of the gradient-confluence cumulant correlation diagram represents the minimum confluence cumulant limit of the generated water body, so that the water body diagram generated based on the spectral characteristics is corrected, the recognition error in the water body diagram can be reduced, and the accuracy and the scientificity of water body recognition can be increased.
As shown in fig. 1, the watershed water body extraction method combining spectral features and confluence cumulant provided by the invention comprises the following steps:
s1, acquiring the No. 3 wave band, the No. 8 wave band, the No. 11 wave band and the No. 12 wave band of the sentinel No. 2 multispectral image through a Google Earth Engine (GEE), preprocessing the wave bands and generating an automatic water body extraction index map AWEI nsh Wherein, the 3 rd waveThe band is green wave band, and the 8 th wave band is near infrared wave band, and the 11 th wave band is the infrared 1 wave band of shortwave, and the 12 th wave band is the infrared 2 wave bands of shortwave, includes the following step:
resampling short wave infrared 1 wave band and short wave infrared 2 wave band to be the same as the spatial resolution of green wave band and near infrared wave band by using bilinear interpolation method
② calculating water body index AWEI nsh Combining the 3 rd wave band-green wave band, the 8 th wave band-near infrared wave band, the 11 th wave band-short wave infrared 1 wave band and the 12 th wave band-short wave infrared 2 wave band to highlight the water body and inhibit noise, and the calculation formula is as follows
Step S2 for AWEI nsh Analyzing and extracting the water body distribution of the basin, and outputting a water body distribution central line graph W of the basin Origin (see fig. 3), comprising the steps of:
mixing AWEI nsh Inputting the water body water Origin ；
Step S3, calculating the gradient (shown in figure 4) and confluence accumulation amount (shown in figure 5) of each grid in the basin by using DEM data and establishing average gradient
A correlation curve with the confluence accumulation amount a (see fig. 6) comprising the steps of:
calculating the gradient S and the confluence accumulation amount A of each grid unit of the drainage basin.
A＝{A 1 ，A 2 ，...，A N } (2)
Wherein N is the total number of grid units with different confluence cumulants, A j J is the jth confluence accumulation amount, 1,2.. N.
Secondly, the confluence cumulant of each grid unit is orderly processed from small to large according to the numerical value, and the gradient average value of the unit with the same confluence cumulant is obtained
Where i is the grid number of the n grid cells corresponding to a certain confluence accumulation amount, S i Is the slope corresponding to the i-th grid cell at the confluence accumulation amount, j is the number corresponding to the N confluence accumulation amounts,
is the average gradient corresponding to the jth confluence accumulation amount.
Third, the average gradient is drawn by adopting double logarithmic coordinates
-confluence accumulation a correlation curve.
Step S4, correcting the water body diagram by taking the confluence cumulant at the first turning point of the correlation curve as the minimum limit (as shown in figure 7) for forming the water body, and outputting the final water body distribution center line diagram W Revised (see fig. 8), comprising the steps of:
firstly, observing a correlation curve of average gradient and confluence cumulant, and taking the confluence cumulant at the first turning point of the correlation curve as the minimum confluence cumulant A of the formed water body Critical 。
② with A Critical Generating a critical water body diagram W as a threshold value of confluence accumulation amount Critical Wherein W is Critical Can be expressed as
Utilizing twoLinear interpolation will be W Critical Resampling to and Origin the same spatial resolution.
Fourthly, outputting a final water body distribution central line graph W Revised The calculation method is as follows
W Revised ＝W Origin ×W Critical (6)
Taking the rassa bottom ditch drainage basin as an example, the area of the drainage basin is 68.1km 2 . The Sentinel-2MSI 10m/20m resolution optical images and SRTM 30m resolution digital elevation data from Google Earth Engine (R) ((R))https://earthengine.google.com/)。
Step one, acquiring the 3 rd wave band, the 8 th wave band, the 11 th wave band and the 12 th wave band of the sentinel No. 2 multispectral image through a Google Earth Engine (GEE), preprocessing the wave bands and generating an automatic water body extraction index map AWEI nsh Wherein, the 3 rd wave band is green wave band, the 8 th wave band is near infrared wave band, the 11 th wave band is the infrared 1 wave band of shortwave, the 12 th wave band is the infrared 2 wave bands of shortwave, include the following step:
introducing a boundary of a sink drain basin into GEE, acquiring data of a green wave band, a near infrared wave band, a short wave infrared 1 wave band, a short wave infrared 2 wave band and SRTM DEM 30m of a Sentinel-2MSI Level-2A of a corresponding area of the GEE, and performing bilinear interpolation on the short wave infrared 1 wave band and the short wave infrared 2 wave band to enable the resolution of the band to be consistent with the green wave band (20m → 10 m).
Calculating the AWEI according to the formula (1) nsh (see fig. 2).
Step two, for AWEI nsh Analyzing and extracting the water body distribution of the basin, and outputting a water body distribution central line graph W of the basin Origin (fig. 3), comprising the steps of:
mixing AWEI nsh Inputting RivaMap to replace default MNDWI, defaulting the size and processing scale of a Gaussian convolution kernel, setting output options, and generating a watershed water body distribution central line graph w Origin 。
Step three, calculating the gradient (shown in figure 4) and the confluence cumulant (shown in figure 5) of each grid in the basin by using the DEM data and establishing an average gradient
-correlation curve of the confluence accumulation amount a (see fig. 6), comprising the steps of:
the method comprises the steps of firstly, importing DEM data by using ArcGIS, filling a hole, then generating a water flow graph by using a D8 flow algorithm, calculating a confluence accumulation amount, and then calculating the gradient of a grid unit by using a gradient tool.
And secondly, deriving the confluence accumulation amount and gradient value of each grid unit of the drainage basin, sequencing the confluence accumulation amounts according to formulas (2), (3) and (4), and calculating the average value of gradients corresponding to the same confluence accumulation amounts.
And thirdly, generating a scatter diagram according to the average gradient and the corresponding confluence cumulant, and adopting a double logarithmic coordinate.
Step four, correcting the water body diagram by taking the confluence cumulant at the first turning point of the correlation curve as the minimum limit (as shown in fig. 7) for forming the water body, and outputting a final water body distribution diagram W Revised (see fig. 8), comprising the steps of:
analyzing a first turning point of a correlation diagram of average gradient and confluence cumulant, wherein the first turning point generally appears at a position with small confluence cumulant and represents that a leading process for controlling water flow generation changes, and the confluence cumulant at the position is taken as a lowest threshold value A of a generated water body Critical 。
② with A Critical Generating W for a threshold Critical The calculation formula is shown in (5), and the calculation result is shown in fig. 7.
③ mixing W Critical Multiplying the water body distribution central line graph generated by RivaMap to generate a final water body distribution graph W Revised (see fig. 8), the calculation formula is (6).
Fourthly, mixing W Revised Compared with the RGB image of sentinel No. 2 corresponding to the drainage basin (as shown in FIG. 9), the method disclosed by the invention can be found out to effectively reduce the false positive of the original water body distribution center line and keep the accuracy of water body distribution.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (5)
1. A watershed water body extraction method combining spectral characteristics and confluence cumulant is characterized by comprising the following steps:
step 1, acquiring the 3 rd wave band, the 8 th wave band, the 11 th wave band and the 12 th wave band of the sentinel No. 2 multispectral image, preprocessing the wave bands and generating an automatic water body extraction index map AWEI nsh (ii) a Wherein, the 3 rd wave band is a green wave band, the 8 th wave band is a near infrared wave band, the 11 th wave band is a short wave infrared 1 wave band, and the 12 th wave band is a short wave infrared 2 wave band;
step 2, for AWEI nsh Analyzing and extracting the water body distribution of the basin, and outputting a water body distribution central line graph W of the basin Origin ；
Step 3, calculating the gradient and convergence cumulant of each grid in the drainage basin by using DEM data and establishing convergence cumulant A and average gradient
The correlation curve of (1);
step 4, taking the confluence cumulant at the first turning point of the correlation curve as the minimum limit of forming the water body to carry out a water body distribution central line graph W Origin The final water body distribution central line graph W is output Revised 。
2. The method for extracting the watershed water body by combining the spectral characteristics and the confluence cumulant according to claim 1, wherein the pretreatment process in the step 1 is as follows:
the short wave infrared 1 band and the short wave infrared 2 band are resampled to the same spatial resolution as the green band and the near infrared band using bilinear interpolation.
3. A combined spectrum according to claim 1The watershed water body extraction method based on sum and confluence cumulant is characterized in that AWEI is subjected to the step 2 nsh Analyzing and extracting the water body distribution of the basin, and outputting a water body distribution central line graph W of the basin Origin The method comprises the following steps:
mixing AWEI nsh Inputting the water body water Origin 。
4. The method for extracting watershed water body by combining spectral characteristics and confluence cumulant as claimed in claim 1, wherein the step 3 calculates the gradient and confluence cumulant of each grid in the watershed by using DEM data and establishes confluence cumulant A and average gradient
The correlation curve of (2) is as follows:
step 3.1, calculating the gradient S and the convergence cumulant A of each grid unit of the drainage basin;
A＝{A 1 ，A 2 ，...，A N }
wherein N is the total number of grid units with different confluence cumulant, A j J is the jth confluence accumulation amount, 1,2.. N;
step 3.2, calculating the average gradient of the units with the same confluence cumulant according to the descending order of the numerical values of the confluence cumulant of each grid unit
Wherein i isGrid number, S, of n grid cells corresponding to a certain amount of accumulation of confluence i Is the slope corresponding to the i-th grid cell at the confluence accumulation amount, j is the number corresponding to the N confluence accumulation amounts,
is the average gradient corresponding to the jth confluence accumulation amount;
step 3.3, adopting a double logarithmic coordinate to draw a confluence cumulant A-average gradient
And (5) a correlation curve.
5. The method for extracting a watershed water body according to claim 1, wherein the step 4 comprises the following specific steps:
step 4.1, observing a confluence cumulant-average gradient correlation curve, and taking the confluence cumulant at the first turning point of the correlation curve as the minimum confluence cumulant A of the formed water body Critical ；
Step 4.2, with A Critical Generating a critical water body diagram W as a threshold value of confluence accumulation amount Critical Wherein W is Critical Is shown as
Step 4.3, utilize bilinear interpolation to get W Critical Resampling to and Origin the same spatial resolution;
step 4.4, outputting the final water body distribution central line graph W Revised The calculation method is as follows
W Revised ＝W Origin ×W Critical 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010554443.0A CN111797720B (en) | 2020-06-17 | 2020-06-17 | Drainage basin water body extraction method combining spectral characteristics and confluence cumulant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010554443.0A CN111797720B (en) | 2020-06-17 | 2020-06-17 | Drainage basin water body extraction method combining spectral characteristics and confluence cumulant |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111797720A CN111797720A (en) | 2020-10-20 |
| CN111797720B true CN111797720B (en) | 2022-08-05 |
Family
ID=72804075
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010554443.0A Active CN111797720B (en) | 2020-06-17 | 2020-06-17 | Drainage basin water body extraction method combining spectral characteristics and confluence cumulant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111797720B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399309A (en) * | 2018-03-16 | 2018-08-14 | 中国水利水电科学研究院 | A kind of watershed partitioning method of large scale complex topographic area hydrological distribution model |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160328498A1 (en) * | 2015-05-06 | 2016-11-10 | International Business Machines Corporation | Topology-Based Method to Assess the Environmental Impact of Deicing Sodium Chloride |
-
2020
- 2020-06-17 CN CN202010554443.0A patent/CN111797720B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399309A (en) * | 2018-03-16 | 2018-08-14 | 中国水利水电科学研究院 | A kind of watershed partitioning method of large scale complex topographic area hydrological distribution model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111797720A (en) | 2020-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109446992B (en) | Remote sensing image building extraction method and system based on deep learning, storage medium and electronic equipment | |
| CN107895376A (en) | Based on the solar panel recognition methods for improving Canny operators and contour area threshold value | |
| CN104751478A (en) | Object-oriented building change detection method based on multi-feature fusion | |
| CN109919070B (en) | Coastline remote sensing calculation method with profile shape self-adaptive fitting function | |
| CN108984771B (en) | River channel width extraction method based on Mann-Kendall mutation test of river channel section gradient value | |
| CN105118090A (en) | Adaptive point-cloud filtering method for complex terrain structure | |
| TW201022708A (en) | Method of change detection for building models | |
| CN112285710B (en) | Multi-source remote sensing reservoir water storage capacity estimation method and device | |
| CN110287898A (en) | A kind of optical satellite remote sensing image cloud detection method of optic | |
| CN104574512A (en) | Multi-scale DEM (digital elevation model) construction method considering topographical semantic information | |
| CN111027446A (en) | Coastline automatic extraction method of high-resolution image | |
| CN103839267A (en) | Building extracting method based on morphological building indexes | |
| CN104850853B (en) | City rapid extracting method and device | |
| CN111597930A (en) | Coastline extraction method based on remote sensing cloud platform | |
| CN110889840A (en) | Effectiveness detection method of high-resolution 6 # remote sensing satellite data for ground object target | |
| CN110569733B (en) | Lake long time sequence continuous water area change reconstruction method based on remote sensing big data platform | |
| CN111881801A (en) | Newly-added construction land remote sensing monitoring method and equipment based on invariant detection strategy | |
| CN106940782A (en) | High score SAR based on variogram increases construction land newly and extracts software | |
| CN108537116B (en) | Multi-scale feature-based coastline secondary type extraction method and system | |
| CN112037244B (en) | Landsat-8 image culture pond extraction method combining index and contour indicator SLIC | |
| CN111797720B (en) | Drainage basin water body extraction method combining spectral characteristics and confluence cumulant | |
| CN112033937A (en) | Method for evaluating water body extraction precision | |
| CN106250687B (en) | Go the deposit gravel roundness calculation method of fasciation IPP | |
| CN110276270B (en) | High-resolution remote sensing image building area extraction method | |
| CN107977968A (en) | The building layer detection method excavated based on buildings shadow information |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |