CN114863053A - Method and device for improving precision of digital elevation model - Google Patents
Method and device for improving precision of digital elevation model Download PDFInfo
- Publication number
- CN114863053A CN114863053A CN202210788504.9A CN202210788504A CN114863053A CN 114863053 A CN114863053 A CN 114863053A CN 202210788504 A CN202210788504 A CN 202210788504A CN 114863053 A CN114863053 A CN 114863053A
- Authority
- CN
- China
- Prior art keywords
- digital elevation
- elevation model
- srtm
- model
- data
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C5/00—Measuring height; Measuring distances transverse to line of sight; Levelling between separated points; Surveyors' levels
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—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
- G06T2207/10—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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- Remote Sensing (AREA)
- General Health & Medical Sciences (AREA)
- Computer Graphics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Architecture (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Radar, Positioning & Navigation (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method for improving the precision of a digital elevation model, which comprises the following steps: s1: acquiring an SRTM digital elevation model and Landsat 8 satellite remote sensing multispectral image data; s2: acquiring a reference digital elevation model of a predetermined area, extracting an SRTM digital elevation model and Landsat 8 satellite remote sensing multispectral image data of the predetermined area, taking the SRTM digital elevation model data and the Landsat 8 satellite remote sensing multispectral image data of the predetermined area as input, taking the reference digital elevation model data of the predetermined area as output, and training to obtain an artificial neural network model, wherein the precision of the reference digital elevation model is higher than that of the SRTM digital elevation model; s3: and improving the SRTM digital elevation model in S1 by using the artificial neural network model and Landsat 8 satellite remote sensing multispectral image data. The invention also provides a device for improving the precision of the digital elevation model. The invention has controllable cost, and can effectively improve the precision of the digital elevation model in large area and large scale.
Description
Technical Field
The invention relates to the technical field related to surveying and mapping. More particularly, the present invention relates to a method and apparatus for improving the accuracy of digital elevation models.
Background
Digital Elevation Models (DEM) have wide application in modern geology, hydrology, ecology and climate. The traditional method of obtaining digital elevation models is through on-site manual surveys; this approach, particularly for remote areas of high vegetation coverage, not only requires significant manpower and material resources, but also has an impact on its widespread acquisition and use due to impractically high costs and inefficiencies. The digital elevation model based on the satellite Remote Sensing technology (Remote Sensing) solves the above problems to some extent, but there are still many challenges and problems, such as: low accuracy of open source data, high cost of commercial data, etc.
SRTM (shutdown Radar Topographic Session) is the open source digital elevation model which is the most widely used and has the highest overall precision at present. SRTM provides global coverage (56) using dual radar antennas to acquire interferometric radar data, processed into digital terrain data o S-60 o N), and the spatial resolution is 92 m. However, since the 5.6cm wavelength used by the SRTM sensor is notThe method can well penetrate through the tree crown, is limited by the spatial resolution of 92m, and is generally low in SRTM precision. Research shows that in an open area, the vertical error of the SRTM is 10m, and in a forest zone, the vertical error of the SRTM can reach 20 m.
NEXTMap @ World 30 @ are commercial digital elevation models developed by Intermap, Inc. The model integrates various open source data through a data fusion technology, and provides elevation data which cover the global range and have the spatial resolution of 30 m. Although the NEXTMap World 30 has a low cost (0.15 US $/km 2), the data precision is close to that of SRTM after simple noise reduction treatment, and the vertical error is 12 m. GeoElevation10 is another commercial digital elevation model developed and sold by airbus service-preventive space companies. The model is derived from satellite data of a Terras SAR-X radar, and the limitation of ground control points is eliminated. The spatial resolution of GeoElevation10 is 10m, and the vertical error is controlled to be 5-10 m. Although the data is highly accurate, the selling price is also high: 30 [/km ] of 2 And a minimum purchase area of 500km 2. Such high costs have exceeded the budget of many research projects and have also directly limited the use of this data in large scale areas.
Therefore, it is desirable to design a technical solution that can overcome the above technical problems to some extent.
Disclosure of Invention
An object of the present invention is to provide a method and an apparatus for improving the accuracy of a digital elevation model, which are cost-controllable and can effectively improve the accuracy of the digital elevation model in a large area and a large scale.
To achieve these objects and other advantages and in accordance with the purpose of the invention, as embodied and broadly described herein, there is provided a method for improving accuracy of a digital elevation model, comprising: s1: acquiring an SRTM digital elevation model and Landsat 8 satellite remote sensing multispectral image data; s2: acquiring a reference digital elevation model of a predetermined area, extracting an SRTM digital elevation model and Landsat 8 satellite remote sensing multispectral image data of the predetermined area, taking the SRTM digital elevation model data and the Landsat 8 satellite remote sensing multispectral image data of the predetermined area as input, taking the reference digital elevation model data of the predetermined area as output, and training to obtain an artificial neural network model, wherein the precision of the reference digital elevation model is higher than that of the SRTM digital elevation model; s3: and improving the SRTM digital elevation model in S1 by using the artificial neural network model and Landsat 8 satellite remote sensing multispectral image data.
Further, selecting preset areas of multiple land cover types, and respectively establishing a plurality of artificial neural network models.
Further, the land cover types at least comprise vegetation cover, building cover and water body cover.
Further, before improving the SRTM digital elevation model data in S1, dividing an area to be improved into a plurality of grids, performing a land cover type determination on each grid, and selecting a corresponding artificial neural network model according to the land cover type to perform improvement on each grid.
Further in accordance with、 Andperforming land cover type judgment on each grid whenIf the soil coverage type is larger than a first preset value, judging that the soil coverage type is vegetation coverage, and if the soil coverage type is larger than the first preset value, judging that the soil coverage type is vegetation coverageIf the land coverage type is larger than a second preset value, judging that the land coverage type is building coverage, and if the land coverage type is larger than the second preset value, judging that the land coverage type is building coverageIf the water body covering type is larger than the third preset value, judging that the land covering type is water body covering; wherein the content of the first and second substances,
、 、 andthe reflectivity values of the near infrared band, the red band, the short wave infrared band and the green band in the Landsat 8 multispectral image data are respectively.
Further, still include: carrying out evaluation on the artificial neural network model whenIf the artificial neural network model is in the first preset range, r is in the second preset range and the Bias is in the third preset range, the artificial neural network model is used for improving the SRTM digital elevation model; wherein the content of the first and second substances,
in the above formula, the first and second carbon atoms are,for the improved SRTM digital elevation model data at grid i,for the reference digital elevation model data at grid i,andrespectively representing the average values of the improved SRTM digital elevation model data and the reference digital elevation model data, wherein n is the grid number.
Furthermore, the Landsat 8 satellite remote sensing multispectral image data are 11 wave band data of the Landsat 8 satellite, and the SRTM digital elevation model data and the reference digital elevation model data are both elevation values.
Further, the artificial neural network model is obtained by training an ANN model.
Further, the reference digital elevation model is WorldDEM.
According to another aspect of the present invention, there is provided an apparatus for improving accuracy of a digital elevation model, comprising: a processor; a memory storing executable instructions; wherein the processor is configured to execute the executable instructions to perform the method of improving the accuracy of a digital elevation model.
The invention at least comprises the following beneficial effects:
the method organically combines the multispectral image data of Landsat 8 satellite remote sensing and the mode recognition function of the artificial neural network together, can correct the existing digital elevation model, effectively improves the precision of the digital elevation model in a large area and a large scale, and has controllable cost.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic illustration of various types of land cover of the present invention;
FIG. 3 is a diagram illustrating the effect of improving the accuracy of a digital elevation model according to the present invention.
Detailed Description
The present invention is further described in detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
It will be understood that terms such as "having," "including," and "comprising," as used herein, do not preclude the presence or addition of one or more other elements or groups thereof.
The embodiment of the application provides a method for improving the precision of a digital elevation model, which comprises the following steps:
s1: acquiring an SRTM digital elevation model and Landsat 8 satellite remote sensing multispectral image data; the Digital Elevation Model (DEM) is a discrete mathematical expression of the topography of the earth surface; DEM represents a finite sequence of three-dimensional vectors over an area D, described in functional form as: v i =X i ,Y i ,Z i ;i=1,2……n,X i ,Y i Is a plane coordinate, Z i Is (X) i ,Y i ) Corresponding elevation values; SRTM is an open source digital elevation model, but the precision is not high; the Landsat 8 satellite comprises an OLI land imager and a thermal infrared sensor, the Landsat 8 satellite remote sensing multispectral image data is earth surface reflectivity data obtained by the OLI land imager and the thermal infrared sensor, the OLI land imager comprises 9 wave bands, and the thermal infrared sensor TIRS comprises 2 independent thermal infrared wave bands, specifically, Band 1 coast (coast wave Band), Band 2 Blue (Blue wave Band), Band 3 Green (Green wave Band), Band 4 Red (Red wave Band), Band 5 NIR (near infrared wave Band), Band 6 SWIR 1 (short wave infrared 1), Band 7 SWIR 2 (short wave infrared 2), Band 8 Pan (panchromatic wave Band), Band 9 Cirrus (rolling cloud wave Band), Band 10 TIRS 1 (thermal infrared 1), Band 11 TIRS 2 (thermal infrared 2);
s2: acquiring a reference digital elevation model of a predetermined area, extracting an SRTM digital elevation model and Landsat 8 satellite remote sensing multispectral image data of the predetermined area, taking the SRTM digital elevation model data and the Landsat 8 satellite remote sensing multispectral image data of the predetermined area as input, taking the reference digital elevation model data of the predetermined area as output, and training to obtain an artificial neural network model, wherein the precision of the reference digital elevation model is higher than that of the SRTM digital elevation model; the reference digital elevation model is a high-precision digital elevation model, and various commercial digital elevation models can be selected; the reference digital elevation model only needs to acquire a preset area with a smaller area without acquiring all areas, and the preset area can be selected from areas with rich land coverage types; extracting SRTM digital elevation model data, Landsat 8 satellite remote sensing multispectral image data and reference digital elevation model data in a preset area, training to obtain an artificial neural network model, wherein the SRTM digital elevation model data and the reference digital elevation model data can be selected as elevation values of coordinates; optionally, part of data in the predetermined area is used as a training set to train the artificial neural network model, and part of data is used as a test set to test the artificial neural network model;
s3: improving the SRTM digital elevation model in S1 by using the artificial neural network model and Landsat 8 satellite remote sensing multispectral image data; inputting the elevation value of each coordinate of the SRTM digital elevation model in the S1 and Landsat 8 satellite remote sensing multispectral image data into the artificial neural network model obtained in the S2 to obtain an improved elevation value, and realizing improvement and correction of the SRTM digital elevation model, so that the precision of all areas of the SRTM digital elevation model can reach and approach the precision of the reference digital elevation model, and the reference digital elevation model of all areas does not need to be purchased, thereby reducing the cost; optionally, the improvement and correction is to improve and correct elevation values of each coordinate; comparing fig. 3 (b), (c), and (d), it can be known that the accuracy and detail of the SRTM digital elevation model can be significantly improved by the improvement and correction of the present application, and approach to the level of the reference digital elevation model.
In other embodiments, a predetermined area of a plurality of land cover types is selected, and a plurality of artificial neural network models are respectively established; by subdividing different land cover types, the correction and improvement effects of the SRTM digital elevation model are improved.
In other embodiments, as shown in FIG. 2, the types of land cover include at least vegetation cover, building cover, water cover; the three land cover types comprise most areas, and the vegetation cover artificial neural network model, the building cover artificial neural network model and the water body cover artificial neural network model are established by the method of the embodiment, so that the three land cover types can be improved and corrected.
In other embodiments, before improving the SRTM digital elevation model data in S1, dividing an area to be improved into a plurality of grids, performing a land cover type determination on each grid, and selecting a corresponding artificial neural network model according to the land cover type to perform improvement on each grid; here, each network comprises a plurality of coordinates, and the height values of the SRTM digital elevation model data in each grid range are regarded as consistent, so that the calculation amount can be reduced; optionally, selecting an average value or a median value of elevation values of coordinates in the grid as the elevation value of the grid, selecting a reflectivity value with the largest occupied area from the Landsat 8 satellite remote sensing multispectral image data, and inputting the reflectivity value into the artificial neural network model; judging the land coverage type of each grid, improving and correcting the elevation value of the SRTM digital elevation model in each grid by using an artificial neural network model respectively, and then combining the elevation values into an integral improved digital elevation model; the more and more the grids are, the finer the grids are, and the number of the grids can be selected according to actual precision requirements.
In other embodiments, according to、Andperforming land cover type judgment on each grid whenIf the soil coverage type is larger than a first preset value, judging that the soil coverage type is vegetation coverage, and if the soil coverage type is larger than the first preset value, judging that the soil coverage type is vegetation coverageIf the value is larger than a second preset value, the judgment is madeThe type of land cover is architectural cover whenIf the water body covering type is larger than the third preset value, judging that the land covering type is water body covering; wherein, the first and the second end of the pipe are connected with each other,
、 、 and respectively reflecting rate values of a near infrared band, a red band, a short wave infrared band and a green band in Landsat 8 multispectral image data; NDVI is a normalized vegetation index, NDBI is a normalized construction index, NDWI is a normalized water body index,、 andall values of (A) are [ -1, 1 [)]And the higher the numerical value is, the more the land coverage of the area is respectively the vegetation, the building and the water body are dominant; the first predetermined value, the second predetermined value and the third predetermined value can be determined by experience or trial and error according to the requirement of precision when、Andif the current grid is larger than the first preset value, the second preset value and the third preset value respectively, which type of land cover the current grid belongs to can be basically judged, and then the corresponding artificial neural network model is selected.
In other embodiments, further comprising: carrying out evaluation on the artificial neural network model whenIf the artificial neural network model is in the first preset range, r is in the second preset range and the Bias is in the third preset range, the artificial neural network model is used for improving the SRTM digital elevation model; wherein the content of the first and second substances,
in the above formula, the first and second carbon atoms are,for the improved SRTM digital elevation model data at grid i,for the reference digital elevation model data at grid i,andrespectively representing the average values of the improved SRTM digital elevation model data and the reference digital elevation model data, wherein n is the number of grids; in the above embodiment, the obtained artificial neural network model is evaluated, and the evaluated data includes data generated by the artificial neural network modelThe improved SRTM digital elevation model data and the reference digital elevation model data of (a), which may not be used for training of the artificial neural network model; mean square errorCorrelation coefficient r, deviationWhen the conditions are all met, the artificial neural network model can meet the requirements on the correction and improvement of the SRTM digital elevation model; RMSE: [0, + ∞); r: [ -1,+1](ii) a And (3) Bias: (∞, infinity); the smaller the RMSE is, the closer the improved SRTM digital elevation model data and the reference digital elevation model data are; the closer the absolute value of r is to 1, the stronger the linear relationship between the improved SRTM digital elevation model data and the reference digital elevation model data is; the closer the Bias is to 1, the closer the improved SRTM digital elevation model data and the reference digital elevation model data are; the specific first predetermined range, second predetermined range, and third predetermined range may be determined empirically and by trial and error, depending on the accuracy requirements.
In other embodiments, the Landsat 8 satellite remote sensing multispectral image data is 11 wave band data of a Landsat 8 satellite, and both the SRTM digital elevation model data and the reference digital elevation model data are elevation values; namely, the elevation values of each grid are regarded as consistent, the elevation values of each grid are corrected and improved, and finally the improvements of all the grids are combined into an improved digital elevation model.
In other embodiments, the artificial neural network model is trained from an ANN model; the ANN model structure form generally comprises an input layer, a hidden layer and an output layer, wherein the input items are 11 wave bands of SRTM topographic data and Landsat 8 satellite remote sensing data, and the output item is a reference digital elevation model; i.e. the ANN employed will contain 12 input neurons and 1 output neuron and by default 10 hidden neurons.
In other embodiments, the reference digital elevation model is WorldDEM, which is the highest global accuracy satellite remote sensing digital elevation model currently, and has higher accuracy than SRTM.
An embodiment of the present application further provides a device for improving accuracy of a digital elevation model, including: a processor; a memory storing executable instructions; wherein the processor is configured to execute the executable instructions to perform the method of improving the accuracy of a digital elevation model; in this embodiment, a relevant program may be configured in a cloud server or a local server, a reference digital elevation model of a predetermined area is obtained, an SRTM digital elevation model and Landsat 8 satellite remote sensing multispectral image data of the predetermined area are extracted, the SRTM digital elevation model data and Landsat 8 satellite remote sensing multispectral image data of the predetermined area are used as input, the reference digital elevation model data of the predetermined area are used as output, and an artificial neural network model is obtained through training; and correcting and improving the SRTM digital elevation model by using the artificial neural network model and the Landsat 8 satellite remote sensing multispectral image data.
The number of apparatuses and the scale of the process described herein are intended to simplify the description of the present invention. Applications, modifications and variations of the method of the present invention for improving the accuracy of digital elevation models will be apparent to those skilled in the art.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.
Claims (10)
1. The method for improving the accuracy of the digital elevation model is characterized by comprising the following steps:
s1: acquiring an SRTM digital elevation model and Landsat 8 satellite remote sensing multispectral image data;
s2: acquiring a reference digital elevation model of a predetermined area, extracting an SRTM digital elevation model and Landsat 8 satellite remote sensing multispectral image data of the predetermined area, taking the SRTM digital elevation model data and the Landsat 8 satellite remote sensing multispectral image data of the predetermined area as input, taking the reference digital elevation model data of the predetermined area as output, and training to obtain an artificial neural network model, wherein the precision of the reference digital elevation model is higher than that of the SRTM digital elevation model;
s3: and improving the SRTM digital elevation model in S1 by using the artificial neural network model and Landsat 8 satellite remote sensing multispectral image data.
2. The method for improving accuracy of a digital elevation model according to claim 1, wherein predetermined areas of a plurality of land cover types are selected and a plurality of the artificial neural network models are created separately.
3. The method of improving accuracy of a digital elevation model of claim 2, wherein the land cover types include at least vegetation cover, building cover, water cover.
4. The method for improving accuracy of a digital elevation model of claim 2, wherein prior to refining the SRTM digital elevation model data in S1, dividing an area to be refined into a plurality of meshes, performing a land cover type determination for each mesh, and selecting the corresponding artificial neural network model based on the land cover type to perform the refining for each mesh.
5. The method for improving accuracy of a digital elevation model of claim 4, wherein the method is based on、Andis executed for each gridThe type of land cover is judged whenIf the soil coverage type is larger than a first preset value, judging that the soil coverage type is vegetation coverage, and if the soil coverage type is larger than the first preset value, judging that the soil coverage type is vegetation coverageIf the land coverage type is larger than a second preset value, judging that the land coverage type is building coverage, and if the land coverage type is larger than the second preset value, judging that the land coverage type is building coverageIf the water body covering type is larger than the third preset value, judging that the land covering type is water body covering; wherein the content of the first and second substances,
6. The method for improving accuracy of a digital elevation model of claim 5, further comprising:
carrying out evaluation on the artificial neural network model whenIf the artificial neural network model is in the first preset range, r is in the second preset range and the Bias is in the third preset range, the artificial neural network model is used for improving the SRTM digital elevation model; wherein the content of the first and second substances,
in the above formula, the first and second carbon atoms are,for the improved SRTM digital elevation model data at grid i,for the reference digital elevation model data at grid i,andrespectively representing the average values of the improved SRTM digital elevation model data and the reference digital elevation model data, wherein n is the number of grids;is the root mean square error, r is the correlation coefficient,Is a deviation.
7. The method of claim 6, wherein the Landsat 8 satellite remote sensing multispectral image data is 11-waveband data of a Landsat 8 satellite, and the SRTM digital elevation model data and the reference digital elevation model data are elevation values.
8. The method for improving accuracy of a digital elevation model of claim 1, wherein the artificial neural network model is trained from an ANN model.
9. The method for improving accuracy of a digital elevation model according to claim 1, wherein the reference digital elevation model is WorldDEM.
10. Apparatus for improving the accuracy of a digital elevation model, comprising:
a processor;
a memory storing executable instructions;
wherein the processor is configured to execute the executable instructions to perform the method of improving accuracy of a digital elevation model of any of claims 1-9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210788504.9A CN114863053B (en) | 2022-07-06 | 2022-07-06 | Method and device for improving precision of digital elevation model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210788504.9A CN114863053B (en) | 2022-07-06 | 2022-07-06 | Method and device for improving precision of digital elevation model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114863053A true CN114863053A (en) | 2022-08-05 |
CN114863053B CN114863053B (en) | 2023-02-03 |
Family
ID=82626683
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210788504.9A Active CN114863053B (en) | 2022-07-06 | 2022-07-06 | Method and device for improving precision of digital elevation model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114863053B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104573239A (en) * | 2015-01-09 | 2015-04-29 | 河海大学 | High spatial resolution remote sense image-based tidal flat DEM (Digital Elevation Model) optimization method |
CN105787457A (en) * | 2016-03-08 | 2016-07-20 | 浙江工商大学 | Evaluation method for improving vegetation classified remote sensing precision through integration of MODIS satellite and DEM |
CN109584364A (en) * | 2018-11-27 | 2019-04-05 | 福建经纬测绘信息有限公司 | A kind of generation method and device of the 2.5 dimension electronic maps based on inclination threedimensional model |
CN110097505A (en) * | 2019-05-16 | 2019-08-06 | 中国人民解放军海军工程大学 | A kind of Law of DEM Data processing method and processing device |
US20200151504A1 (en) * | 2018-11-09 | 2020-05-14 | International Business Machines Corporation | Scalable Feature Classification for Laser Scanning Data and Digital Elevation Models |
CN111428942A (en) * | 2020-04-16 | 2020-07-17 | 贵州电网有限责任公司 | Line icing thickness prediction method for extracting micro-terrain factors based on variable grid technology |
CN113358091A (en) * | 2021-06-02 | 2021-09-07 | 自然资源部国土卫星遥感应用中心 | Method for producing digital elevation model by using three-linear array three-dimensional satellite image |
CN114137567A (en) * | 2021-11-26 | 2022-03-04 | 自然资源部国土卫星遥感应用中心 | Glacier elevation change monitoring method based on satellite remote sensing data |
CN114387408A (en) * | 2021-12-02 | 2022-04-22 | 浙江大华技术股份有限公司 | Method and device for generating digital elevation model and computer readable storage medium |
-
2022
- 2022-07-06 CN CN202210788504.9A patent/CN114863053B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104573239A (en) * | 2015-01-09 | 2015-04-29 | 河海大学 | High spatial resolution remote sense image-based tidal flat DEM (Digital Elevation Model) optimization method |
CN105787457A (en) * | 2016-03-08 | 2016-07-20 | 浙江工商大学 | Evaluation method for improving vegetation classified remote sensing precision through integration of MODIS satellite and DEM |
US20200151504A1 (en) * | 2018-11-09 | 2020-05-14 | International Business Machines Corporation | Scalable Feature Classification for Laser Scanning Data and Digital Elevation Models |
CN109584364A (en) * | 2018-11-27 | 2019-04-05 | 福建经纬测绘信息有限公司 | A kind of generation method and device of the 2.5 dimension electronic maps based on inclination threedimensional model |
CN110097505A (en) * | 2019-05-16 | 2019-08-06 | 中国人民解放军海军工程大学 | A kind of Law of DEM Data processing method and processing device |
CN111428942A (en) * | 2020-04-16 | 2020-07-17 | 贵州电网有限责任公司 | Line icing thickness prediction method for extracting micro-terrain factors based on variable grid technology |
CN113358091A (en) * | 2021-06-02 | 2021-09-07 | 自然资源部国土卫星遥感应用中心 | Method for producing digital elevation model by using three-linear array three-dimensional satellite image |
CN114137567A (en) * | 2021-11-26 | 2022-03-04 | 自然资源部国土卫星遥感应用中心 | Glacier elevation change monitoring method based on satellite remote sensing data |
CN114387408A (en) * | 2021-12-02 | 2022-04-22 | 浙江大华技术股份有限公司 | Method and device for generating digital elevation model and computer readable storage medium |
Non-Patent Citations (3)
Title |
---|
杨帅; 胡保健; 胡占占; 张志号: "对ASTER GDEM数字高程模型的精度评价及修正", 《北京测绘》 * |
秦臣臣等: "基于ICESat/GLAS的山东省SRTM与ASTER GDEM高程精度评价与修正", 《地球信息科学学报》 * |
马雨阳; 官海翔; 杨昊轩; 邵帅; 邵逸群; 刘焕军: "利用地形、土壤和作物信息辅助提高东北漫岗地数字高程模型精度的新方法", 《中国农业科学》 * |
Also Published As
Publication number | Publication date |
---|---|
CN114863053B (en) | 2023-02-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106226260B (en) | A kind of Soil Moisture Inversion method of combination microwave and infrared remote sensing image | |
Xiao et al. | Use of general regression neural networks for generating the GLASS leaf area index product from time-series MODIS surface reflectance | |
CN104613944B (en) | Distributed water depth prediction method based on GWR (geographically weighted regression) and BP (back propagation) neural network | |
CN108268735A (en) | Soil moisture NO emissions reduction method based on multi-source remote sensing satellite fused data | |
CN105004320B (en) | A kind of high score satellite data land table vegetation coverage inversion method and system | |
CN107609526A (en) | Rule-based fine dimension city impervious surface rapid extracting method | |
CN107909607A (en) | A kind of year regional vegetation coverage computational methods | |
CN102982538B (en) | Nature color simulating method of resource satellite multi-spectral image | |
CN109885959B (en) | A kind of surface temperature robust NO emissions reduction method | |
CN112711989B (en) | Corn straw coverage estimation method based on radar remote sensing and optical remote sensing | |
CN112348812B (en) | Forest stand age information measurement method and device | |
CN114926748A (en) | Soybean remote sensing identification method combining Sentinel-1/2 microwave and optical multispectral images | |
CN113780097B (en) | Cultivated land extraction method based on knowledge graph and deep learning | |
CN107229913A (en) | Density of population analysis system based on high score satellite remote sensing date combination building height | |
CN113205014B (en) | Time sequence data farmland extraction method based on image sharpening | |
CN109784300A (en) | A kind of crops science survey production method and system | |
CN109816542A (en) | A kind of crop production reduction Claims Resolution method and system | |
Xu et al. | Retrieving global leaf chlorophyll content from MERIS data using a neural network method | |
Erasmi et al. | Mapping deforestation and land cover conversion at the rainforest margin in Central Sulawesi, Indonesia | |
CN114881620B (en) | Territorial space monitoring method and system based on satellite remote sensing | |
Jin et al. | Combining 3D radiative transfer model and convolutional neural network to accurately estimate Forest canopy cover from very high-resolution satellite images | |
Nguyen et al. | Mapping Land use/land cover using a combination of Radar Sentinel-1A and Sentinel-2A optical images | |
CN117115669B (en) | Object-level ground object sample self-adaptive generation method and system with double-condition quality constraint | |
Wang et al. | Research on cropping intensity mapping of the Huai River Basin (China) based on multi-source remote sensing data fusion | |
Kang et al. | Construction of multidimensional features to identify tea plantations using multisource remote sensing data: A case study of Hangzhou city, China |
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 |