CN117994460A - Three-dimensional geological refinement modeling method and device based on air-ground combination - Google Patents
Three-dimensional geological refinement modeling method and device based on air-ground combination Download PDFInfo
- Publication number
- CN117994460A CN117994460A CN202410224753.4A CN202410224753A CN117994460A CN 117994460 A CN117994460 A CN 117994460A CN 202410224753 A CN202410224753 A CN 202410224753A CN 117994460 A CN117994460 A CN 117994460A
- Authority
- CN
- China
- Prior art keywords
- refinement
- region
- data
- area
- aerial vehicle
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000010801 machine learning Methods 0.000 claims description 40
- 238000004590 computer program Methods 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000012163 sequencing technique Methods 0.000 claims description 12
- 238000007405 data analysis Methods 0.000 claims description 8
- 230000015572 biosynthetic process Effects 0.000 claims description 5
- 238000003786 synthesis reaction Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 4
- 238000011835 investigation Methods 0.000 description 4
- 238000012876 topography Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30184—Infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computer Graphics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The application relates to a three-dimensional geological fine modeling method and device based on air-ground combination, wherein the method comprises the steps of obtaining unmanned aerial vehicle survey data and laser scanning data, and carrying out three-dimensional processing on the unmanned aerial vehicle survey data and the laser scanning data based on a preset map model to obtain unmanned aerial vehicle survey three-dimensional data and laser scanning three-dimensional data; comparing the unmanned aerial vehicle survey three-dimensional data with the laser scanning three-dimensional data to obtain an unmanned aerial vehicle area, a laser area and a combined coverage area; analyzing the unmanned plane area, the laser area and the combined coverage area respectively to obtain a refined designated area; acquiring a refinement coefficient based on the combined coverage area; and carrying out refinement compensation on the data corresponding to the refinement specified region according to the refinement coefficient to generate a three-dimensional geological model. The method has the effect of improving the combination degree of unmanned aerial vehicle survey data and laser scanning data, and further improving the refinement degree of the three-dimensional geological model.
Description
Technical Field
The invention relates to the technical field of geological modeling, in particular to a three-dimensional geological refined modeling method and device based on air-ground combination.
Background
In the geological field, fine three-dimensional geological modeling has important significance for resource exploration, environmental protection and geological disaster prediction. The three-dimensional geological refinement modeling method based on air-ground combination fuses advanced technologies such as unmanned aerial vehicle aerial photography and handheld laser scanning, and provides a powerful tool for geological science. At present, the wide application of unmanned aerial vehicle aerial photography technology provides high-resolution image data for geological investigation, so that scientists can know the surface characteristics more comprehensively and in more detail. Meanwhile, the handheld laser scanner can acquire the ground point cloud data with high precision, so that the accuracy of the geological model is further enhanced.
However, these techniques still have some drawbacks when dealing with some complex scenarios. First, unmanned aerial vehicle aerial photography is limited by natural conditions such as weather, wind speed, etc., and may not be able to complete tasks in certain extreme environments. Second, due to the limited flying height of the unmanned aerial vehicle, it may be difficult to cover high mountain areas, vertical cliffs, etc. In addition, the scanning range of a handheld laser scanner is relatively limited, requiring manual operations at multiple locations, increasing the complexity of data acquisition.
Therefore, in the related art, through combining unmanned aerial vehicle aerial photography and handheld laser scanning data, richer geological information can be obtained in a wider geographical range, so that the accuracy and coverage range of the data are improved, and the data processing is performed through an artificial intelligence algorithm, so that the speed and efficiency of geological modeling are accelerated. However, the combination degree of the unmanned aerial vehicle aerial photographing and the handheld laser scanning data is not high, and the refinement degree of the three-dimensional geological model cannot be improved by combining the unmanned aerial vehicle aerial photographing and the handheld laser scanning data.
Disclosure of Invention
The application provides a three-dimensional geological fine modeling method and device based on air-ground combination in order to improve the combination degree of unmanned aerial vehicle survey data and laser scanning data and further improve the fine degree of a three-dimensional geological model.
In a first aspect, the above object of the present application is achieved by the following technical solutions:
a three-dimensional geological refinement modeling method based on air-ground combination comprises the following steps:
acquiring unmanned aerial vehicle survey data and laser scanning data, and performing three-dimensional processing on the unmanned aerial vehicle survey data and the laser scanning data based on a preset map model to obtain unmanned aerial vehicle survey three-dimensional data and laser scanning three-dimensional data;
comparing the unmanned aerial vehicle survey three-dimensional data with the laser scanning three-dimensional data to obtain an unmanned aerial vehicle area, a laser area and a combined coverage area;
Analyzing the unmanned plane area, the laser area and the combined coverage area respectively to obtain a refined designated area;
acquiring a refinement coefficient based on the combined coverage area;
And carrying out refinement compensation on the data corresponding to the refinement specified region according to the refinement coefficient to generate a three-dimensional geological model.
By adopting the technical scheme, the unmanned aerial vehicle survey data and the laser scanning data are subjected to three-dimensional processing, and the unmanned aerial vehicle survey data and the laser scanning data are corresponding, so that the unmanned aerial vehicle survey area and the laser scanning area are corresponding in the same coordinate system, and the unmanned aerial vehicle survey data and the laser scanning data are convenient to comprehensively analyze in the follow-up process; in the combined three-dimensional modeling method of the unmanned aerial vehicle and the laser scanner, most of the areas surveyed by the unmanned aerial vehicle and the areas scanned by the laser scanner are not overlapped, for example, the areas which are difficult to reach by the unmanned aerial vehicle or are difficult to be surveyed by a worker by using the laser scanner are not overlapped, and the areas which are complicated in part of geological conditions are surveyed by using the unmanned aerial vehicle and the laser scanner at the same time, so that whether the data of different areas have the conditions of being surveyed by the unmanned aerial vehicle and the laser scanner at the same time is judged, the characteristics of the unmanned aerial vehicle and the laser scanner are further judged, the areas with lower definition degree in the target area are further judged, and then targeted definition compensation processing is carried out, so that the combination degree of the unmanned aerial vehicle survey data and the laser scanning data is improved, and the effect of the definition degree of the three-dimensional geological model is improved is realized.
The present application may be further configured in a preferred example to: the analyzing the unmanned aerial vehicle area, the laser area and the combined coverage area to obtain a refined designated area specifically comprises the following steps:
inputting data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into a blank machine learning model, and obtaining a first refined specified region based on the blank machine learning model;
Inputting data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into a geological exploration model, and obtaining a second refined specified region based on the geological exploration model;
and obtaining a refinement specified region according to the first refinement specified region and the second refinement specified region.
By adopting the technical scheme, the blank machine learning model refers to a machine learning model which is not trained, the machine learning model which is not trained is not influenced by other data or features, but is only analyzed by starting with the characteristics of the current data, and the difference of the current data can be more accurately analyzed, so that the unmanned plane area, the laser area and the data corresponding to the combined coverage area are input into the blank machine learning model, and the positions with different fineness of the survey data corresponding to the different areas are respectively judged by the analysis of the blank machine learning model, so that the area needing to be subjected to refinement processing is obtained; the geological survey model is a machine learning model trained by unmanned aerial vehicle survey data and laser scanning data of a plurality of different areas, and a second fine designated area which represents the need of carrying out fine processing according with general logic is judged through the geological survey model, so that the first fine designated area and the second fine designated area are combined to obtain a more accurate fine designated area, and the three-dimensional geological model of the target area is finer.
The present application may be further configured in a preferred example to: the obtaining the refinement specified region according to the first refinement specified region and the second refinement specified region specifically includes:
comparing the data corresponding to the first refined specified region and the second refined specified region to obtain a region comparison result;
And obtaining a refined designated area according to the area comparison result.
By adopting the technical scheme, the first refinement specified region is acquired through the blank machine learning model, the second refinement specified region is acquired through the geological survey model, so that the first refinement specified region and the second refinement specified region are different, but the first refinement specified region and the second refinement specified region are all regions needing refinement, so that the first refinement specified region and the second refinement specified region are compared and combined, and the combined regions are taken as refinement specified regions, so that the region needing refinement processing is increased, and the accuracy of the region needing refinement processing is ensured.
The present application may be further configured in a preferred example to: the analyzing the unmanned aerial vehicle area, the laser area and the combined coverage area to obtain a refined designated area specifically comprises the following steps:
inputting data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into an expert experience model, a geological learning model and an edge model to obtain an expert experience refined specified region, a geological learning refined specified region and an edge refined specified region;
And sequencing the expert experience refinement region, the geological learning refinement region and the edge refinement region based on a preset credibility sequencing, and obtaining the refinement region according to a sequencing result.
By adopting the technical scheme, the expert experience model is that an expert analyzes survey data of the unmanned aerial vehicle and the laser scanner, and judges that the unmanned aerial vehicle and the laser scanner are likely to generate areas with insufficient data refinement degree when in survey, the geological learning model is an area which is judged by combining geological characteristics of a target area and is likely to cause insufficient survey data of the unmanned aerial vehicle and the laser scanner, the edge model is that historical survey data of the unmanned aerial vehicle and the laser scanner are analyzed, geological characteristics of the area with insufficient survey data are judged, and then the area with insufficient refinement degree of the current target area is judged, the preset reliability ranking is sequence information for selecting results of different models for different areas, for example, the reliability ranking corresponding to the unmanned aerial vehicle area is expressed in the expert experience refinement specification area, the geological learning refinement specification area and the edge refinement specification area, and the reliability of the edge refinement specification area is highest, so that the edge refinement specification area obtained by inputting the unmanned aerial vehicle area into the edge model is taken as the refinement specification area, and the accuracy of the selected processing area is further ensured.
The present application may be further configured in a preferred example to: the acquiring the refinement coefficient based on the combined coverage area specifically includes:
Inputting the data corresponding to the combined coverage area into a geological comparison model to obtain a geological comparison result;
and obtaining a refinement coefficient according to the geological comparison result.
Through adopting above-mentioned technical scheme, combine the coverage area to refer to the area that uses unmanned aerial vehicle and laser scanner to survey simultaneously, consequently, through the data input geology contrast model that corresponds to this combine the coverage area is analyzed, judge the difference of unmanned aerial vehicle survey data and laser scanning data of same position department, judge the fineness difference of presuming unmanned aerial vehicle survey data and laser scanning data according to this difference again, and then the generation needs to combine the fineness coefficient of coverage area, namely the unmanned aerial vehicle survey data and the laser scanning data that will combine the coverage area carry out the coefficient of refinement, realize the refinement of unmanned aerial vehicle survey data and laser scanning data to current target area through this fineness coefficient, and then make the three-dimensional geological model of target area more meticulous.
The present application may be further configured in a preferred example to: performing refinement compensation on the data corresponding to the refinement specified region according to the refinement coefficient to generate a three-dimensional geological model, wherein the method specifically comprises the following steps:
obtaining a refinement compensation coefficient according to the refinement coefficient and a preset compensation coefficient;
and carrying out fine compensation on the data corresponding to the fine designated area according to the fine compensation coefficient to generate a three-dimensional geological model.
Through adopting above-mentioned technical scheme, the coefficient of compensation that presets is to the holistic unmanned aerial vehicle survey data of target area and the coefficient of carrying out the fine compensation of laser scanning data, through combining fine coefficient and preset compensation coefficient, further improves the holistic unmanned aerial vehicle survey data of target area and the degree of refinement of laser scanning data, and then makes the three-dimensional geological model of formation finer.
In a second aspect, the above object of the present application is achieved by the following technical solutions:
a three-dimensional geology refinement modeling device based on air-ground combination, the three-dimensional geology refinement modeling device based on air-ground combination comprises:
the data three-dimensional module is used for acquiring unmanned aerial vehicle survey data and laser scanning data, and carrying out three-dimensional processing on the unmanned aerial vehicle survey data and the laser scanning data based on a preset map model to acquire unmanned aerial vehicle survey three-dimensional data and laser scanning three-dimensional data;
the area dividing module is used for comparing the unmanned aerial vehicle survey three-dimensional data with the laser scanning three-dimensional data to obtain an unmanned aerial vehicle area, a laser area and a combined coverage area;
The area data analysis module is used for respectively analyzing the unmanned aerial vehicle area, the laser area and the combined coverage area to obtain a refined designated area;
a refinement coefficient acquisition module, configured to acquire a refinement coefficient based on the combined coverage area;
And the three-dimensional model generation module is used for carrying out refinement compensation on the data corresponding to the refinement specified region according to the refinement coefficient to generate a three-dimensional geological model.
Optionally, the area data analysis module includes:
The first analysis submodule is used for inputting data corresponding to the unmanned plane area, the laser area and the combined coverage area into a blank machine learning model, and obtaining a first refined specified area based on the blank machine learning model;
The second analysis submodule is used for inputting data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into a geological exploration model, and obtaining a second refined specified region based on the geological exploration model;
And the result synthesis submodule is used for obtaining the refinement specified region according to the first refinement specified region and the second refinement specified region.
In a third aspect, the above object of the present application is achieved by the following technical solutions:
A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the above-described three-dimensional geological refinement modeling method based on air-ground association when the computer program is executed.
In a fourth aspect, the above object of the present application is achieved by the following technical solutions:
a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the above-described three-dimensional geological refinement modeling method based on air-ground union.
In summary, the present application includes at least one of the following beneficial technical effects:
1. Carrying out three-dimensional processing on unmanned aerial vehicle survey data and laser scanning data, and corresponding the unmanned aerial vehicle survey data and the laser scanning data, so that the unmanned aerial vehicle survey area and the laser scanning area are corresponding in the same coordinate system, and subsequent comprehensive analysis of the unmanned aerial vehicle survey data and the laser scanning data is facilitated; in the combined three-dimensional modeling method of the unmanned aerial vehicle and the laser scanner, most of areas surveyed by the unmanned aerial vehicle and areas scanned by the laser are not overlapped, for example, for areas which are difficult to reach by the unmanned aerial vehicle or are difficult to be surveyed by workers by using the laser scanner, the areas surveyed by the unmanned aerial vehicle and the areas scanned by the laser scanner are not overlapped, and partial areas with complex geological conditions are surveyed by using the unmanned aerial vehicle and the laser scanner at the same time, so that whether the data of different areas have the condition that the unmanned aerial vehicle and the laser scanner are surveyed simultaneously is judged, and therefore, the characteristics of the unmanned aerial vehicle and the laser scanner are further judged, and further, the areas with lower surveying degree in the target areas are judged, and then targeted refined compensation processing is carried out, so that the combination degree of the unmanned aerial vehicle surveying data and the laser scanning data is improved, and the effect of the three-dimensional geological model is improved;
2. The blank machine learning model is a machine learning model which is not trained, the untrained machine learning model is not influenced by other data or features, but is analyzed only by starting from the characteristics of the current data, and the difference of the current data can be more accurately analyzed, so that the unmanned plane region, the laser region and the data corresponding to the combined coverage region are input into the blank machine learning model, and the positions with different fineness of the survey data corresponding to the different regions are respectively judged through the analysis of the blank machine learning model, so that the region needing to be subjected to refinement processing is obtained; the geological survey model is a machine learning model trained by unmanned aerial vehicle survey data and laser scanning data of a plurality of different areas, and a second refinement specified area which is required to be subjected to refinement processing and accords with general logic is judged through the geological survey model, so that the first refinement specified area and the second refinement specified area are combined to obtain a more accurate refinement specified area, and the three-dimensional geological model of the target area is finer;
3. The first refinement specified region is acquired through a blank machine learning model, the second refinement specified region is acquired through a geological survey model, and therefore the first refinement specified region and the second refinement specified region are different, but the first refinement specified region and the second refinement specified region are all regions needing refinement, and therefore the first refinement specified region and the second refinement specified region are compared and combined, and the combined regions are taken as refinement specified regions, so that the regions needing refinement processing are increased, and the accuracy of selecting the regions needing refinement processing is guaranteed.
Drawings
FIG. 1 is a flow chart of an implementation of a three-dimensional geological refinement modeling method based on air-ground association in an embodiment of the application;
FIG. 2 is a first implementation flowchart of S30 of a three-dimensional geological refinement modeling method based on air-ground association in an embodiment of the application;
FIG. 3 is a flowchart of an implementation of S303 of a three-dimensional geological refinement modeling method based on air-ground association in an embodiment of the application;
FIG. 4 is a second implementation flowchart of S30 of a three-dimensional geological refinement modeling method based on air-ground association in an embodiment of the application;
FIG. 5 is a flowchart of an implementation of S40 of a three-dimensional geological refinement modeling method based on air-ground association in an embodiment of the application;
FIG. 6 is a flowchart of an implementation of S50 of a three-dimensional geological refinement modeling method based on air-ground association in an embodiment of the application;
FIG. 7 is a schematic block diagram of a three-dimensional geological refinement modeling apparatus based on air-ground association in an embodiment of the present application;
FIG. 8 is an internal block diagram of a three-dimensional geologic refinement modeling computer device based on air-ground association in an embodiment of the application.
Detailed Description
The application is described in further detail below with reference to fig. 1-8.
In one embodiment, as shown in fig. 1, the application discloses a three-dimensional geological refinement modeling method based on air-ground combination, which specifically comprises the following steps:
s10: and acquiring unmanned aerial vehicle survey data and laser scanning data, and performing three-dimensional processing on the unmanned aerial vehicle survey data and the laser scanning data based on a preset map model to obtain unmanned aerial vehicle survey three-dimensional data and laser scanning three-dimensional data.
In this embodiment, the target area of the survey is a residential area. Unmanned survey data refers to image data obtained by unmanned survey of a target area. The laser scanning data refers to point cloud data obtained by a laser scanner surveying a target area. The drone survey three-dimensional data refers to three-dimensional position coordinate data generated from the drone survey data. The laser scanning three-dimensional data refers to three-dimensional position coordinate data generated by the laser scanning data.
Specifically, when planning a survey plan for a target area, a laser scanning area, an unmanned aerial vehicle aerial survey route and the like are determined according to the topographic features of the target area, but in an actual survey process, the actual laser scanning area and the unmanned aerial vehicle survey area are often changed due to various factors, so that after the actual survey is finished, image data obtained by the unmanned aerial vehicle survey of the target area and point cloud data obtained by the laser scanner survey of the target area, namely unmanned aerial vehicle survey data and laser scanning data, are obtained. The preset map model refers to an integral three-dimensional space model of a target area formed by using a geographic coordinate system on the earth as a reference, the laser scanning data comprises point cloud data obtained by surveying the target area by a laser scanner, the laser scanning data also comprises geographic position data of the laser scanner through a global positioning system, the unmanned aerial vehicle surveying data also comprises geographic position data of the unmanned aerial vehicle through the global positioning system, and therefore, the unmanned aerial vehicle surveying data and the laser scanning data are subjected to three-dimensional processing through the preset map model to generate unmanned aerial vehicle surveying three-dimensional data representing the three-dimensional space of the unmanned aerial vehicle surveying area and laser scanning three-dimensional data representing the three-dimensional space of the laser scanning area, and the unmanned aerial vehicle surveying area and the laser scanning area correspond to the same coordinate system in the same three-dimensional space.
S20: and comparing the unmanned aerial vehicle survey three-dimensional data with the laser scanning three-dimensional data to obtain an unmanned aerial vehicle area, a laser area and a combined coverage area.
In this embodiment, the unmanned aerial vehicle region refers to a three-dimensional space in which only the unmanned aerial vehicle surveys among the three-dimensional spaces of the target region. The laser region refers to a three-dimensional space in which only the laser scanner surveys in the three-dimensional space of the target region. The combined coverage area refers to a three-dimensional space which is surveyed by the unmanned aerial vehicle and the laser scanner and exists in the three-dimensional space of the target area.
Specifically, in the combined three-dimensional modeling method of the unmanned aerial vehicle and the laser scanner, most of the areas surveyed by the unmanned aerial vehicle and the areas scanned by the laser are not overlapped, for example, for the areas which are difficult for the unmanned aerial vehicle to reach or for the staff to survey by using the laser scanner, the areas surveyed by the unmanned aerial vehicle and the areas scanned by the laser are not overlapped, and the areas with complex geological conditions are surveyed by using the unmanned aerial vehicle and the laser scanner at the same time, therefore, the three-dimensional data surveyed by the unmanned aerial vehicle and the three-dimensional data scanned by the laser scanner are compared, only the three-dimensional space surveyed by the unmanned aerial vehicle is judged in the three-dimensional space of the target area, only the three-dimensional space surveyed by the laser scanner is judged, and the three-dimensional space surveyed by the unmanned aerial vehicle and the laser scanner is simultaneously available in the three-dimensional space of the target area, so that the unmanned aerial vehicle area, the laser area and the combined coverage area are respectively obtained.
S30: and respectively analyzing the unmanned aerial vehicle area, the laser area and the combined coverage area to obtain a refined designated area.
In the present embodiment, the refinement specification region refers to a region in which refinement processing is performed.
Specifically, the unmanned aerial vehicle region, the laser region and the combined coverage region are respectively analyzed, the unmanned aerial vehicle region, the laser region and the partial region which needs to be subjected to refinement treatment in the combined coverage region are respectively judged, a refinement designated region is obtained, for example, the unmanned aerial vehicle investigation data (i.e. investigation measurement data of the target region in the early stage, such as the height of each building in the target region, and the like) are combined through the aerial photographing height of the unmanned aerial vehicle and the resolution ratio of the aerial photographing image of the unmanned aerial vehicle, and the data with insufficient refinement degree in the unmanned aerial vehicle investigation three-dimensional data corresponding to the unmanned aerial vehicle region are judged, so that the refinement designated region corresponding to the unmanned aerial vehicle region is obtained; according to the parameters such as the action range, the scanning speed, the resolution, the point cloud density and the like of the laser region, the self position of the laser scanner and the heights of different objects are combined when the laser scanning is carried out, the defect of insufficient refinement degree in the laser scanning three-dimensional data corresponding to the higher object is judged, so that the data of insufficient refinement degree in the laser scanning three-dimensional data corresponding to the laser region is judged, and further a refinement designated region corresponding to the laser region is obtained; for the combined coverage area, the corresponding fine designated area can be obtained through the corresponding laser scanning three-dimensional data and the average fine degree of the unmanned aerial vehicle surveying three-dimensional data and the unmanned aerial vehicle surveying three-dimensional data which are lower than the average value.
S40: based on the combined coverage area, refinement coefficients are obtained.
In the present embodiment, the refinement coefficient refers to a coefficient for adjusting data corresponding to the refinement specification region.
Specifically, the combined coverage area refers to an area surveyed by using an unmanned aerial vehicle and a laser scanner at the same time, therefore, unmanned aerial vehicle surveyed data and laser scanning data corresponding to the combined coverage area are analyzed, the fineness degree of the current target area surveyed by the current unmanned aerial vehicle and the laser scanning is respectively judged, the fineness degree of the current target area surveyed by the current unmanned aerial vehicle and the fineness degree of the current target area surveyed by the laser scanning are combined, the number of difference values of the fineness degrees of the current target area surveyed by the current unmanned aerial vehicle is comprehensively judged, for example, the precision of the image data of the current target area surveyed by the current unmanned aerial vehicle is 10mm, the precision of the point cloud data of the current target area surveyed by the laser scanning is 5mm, the precision gap of the current unmanned aerial vehicle and the laser scanning is 5mm, and in order to reduce the precision gap and ensure the accuracy of three-dimensional position data, half of the precision gap of 5mm is taken as the refinement coefficient of the corresponding area.
S50: and carrying out refinement compensation on the data corresponding to the refinement specified region according to the refinement coefficient to generate a three-dimensional geological model.
In this embodiment, the three-dimensional geologic model refers to a three-dimensional geologic model of the target area.
Specifically, the adjacent unmanned aerial vehicle surveying data and the laser scanning data at the same position generate fine compensation data at an intermediate position, for example, the distance between the adjacent two unmanned aerial vehicles and the image data surveyed by the current target area is 10mm, the point cloud data surveyed by the laser scanner and the current target area are arranged at the position represented by the image data surveyed by the adjacent two unmanned aerial vehicles, then according to the fine coefficient, the average value of the point cloud data surveyed by the laser scanning and the image data surveyed by the next unmanned aerial vehicle and the image data surveyed by the current target area is generated, the position of the generated average value is marked at the midpoint of the image data surveyed by the next unmanned aerial vehicle and the current target area by the laser scanning, thereby realizing fine compensation on the data corresponding to the fine designated area, and after all fine compensation data are generated, the three-dimensional geological model of the target area is generated based on the fine compensation data, the image data surveyed by the unmanned aerial vehicle and the point cloud data surveyed by the laser scanner.
In an embodiment, as shown in fig. 2, in step S30, the unmanned plane area, the laser area and the combined coverage area are respectively analyzed to obtain a refined designated area, which specifically includes:
S301: inputting data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into a blank machine learning model, and obtaining a first refined specified region based on the blank machine learning model.
In the present embodiment, the blank machine learning model refers to a machine learning model that is not trained. The first refinement specification region refers to a refinement specification region generated based on a blank machine learning model.
Specifically, the blank machine learning model is a machine learning model which is not trained, the untrained machine learning model is not affected by other data or features, but only analyzed based on the characteristics of the current data, and differences of the current data can be more accurately analyzed, so that data corresponding to an unmanned aerial vehicle region, a laser region and a combined coverage area are respectively input into the blank machine learning model, based on the blank machine learning model, the data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage area are respectively analyzed, positions with different fineness of survey data corresponding to different regions are determined, and the positions are used as first refined designated regions, for example, positions and the like, where cloud density in laser scanning data corresponding to the laser region is obviously smaller than that in laser scanning data corresponding to other laser scanning data, and positions and the like, where the distance between a laser scanner and an object in the target region is not corresponding to the point cloud density (i.e., the point cloud density is obviously smaller), where the accuracy of image data in unmanned aerial vehicle survey data corresponding to the unmanned aerial vehicle region is obviously smaller than that in other unmanned aerial vehicle survey data, and the positions and the distances between the unmanned aerial vehicle and the object in the target region are not corresponding to the image data are determined.
S302: inputting the data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into a geological exploration model, and obtaining a second refined specified region based on the geological exploration model.
In this embodiment, the geological survey model refers to a trained machine learning model of unmanned survey data and laser scan data over a plurality of different regions. The second refined designated area refers to a refined designated area generated based on the geological survey model.
Specifically, the geological survey model is a machine learning model trained by unmanned aerial vehicle survey data and laser scanning data of a plurality of different areas, the unmanned aerial vehicle area, the laser area and the data corresponding to the combined coverage area are input into the geological survey model, the data corresponding to the unmanned aerial vehicle area, the laser area and the combined coverage area are respectively analyzed based on the geological survey model, positions with different fineness of the survey data corresponding to the different areas are judged, and the positions are used as second fine designated areas.
S303: and obtaining the refinement specified region according to the first refinement specified region and the second refinement specified region.
Specifically, according to the first refinement specification region and the second refinement specification region, the regions included in the first refinement specification region and the second refinement specification region are combined to obtain the refinement specification region.
In one embodiment, as shown in fig. 3, in step S303, obtaining the refinement specification region according to the first refinement specification region and the second refinement specification region specifically includes:
S3031: and comparing the data corresponding to the first refined specified region and the second refined specified region to obtain a region comparison result.
In this embodiment, the region comparison result refers to the comparison result of the first refinement specified region and the second refinement specified region.
Specifically, the first refinement specified region is acquired through a blank machine learning model, and the second refinement specified region is acquired through a geological survey model, so that the first refinement specified region and the second refinement specified region are different, data corresponding to the first refinement specified region and the second refinement specified region are compared, and the difference of the areas of the first refinement specified region and the second refinement specified region is judged, so that a region comparison result is obtained.
S3032: and obtaining a refined designated area according to the area comparison result.
Specifically, the area comparison result, that is, the difference between the area sizes of the first and second specified areas is compared with a preset area difference threshold, if the difference between the area sizes of the first and second specified areas is greater than the preset area difference threshold, the learning result of the blank machine learning model is abnormal, the second specified area is taken as the specified area (because the learning result of the geological survey model, which indicates the area with low degree of refinement, is more accurate, and the blank machine learning model can find the difference of data, the learning result of the blank machine learning model is more detailed, if the difference between the area sizes of the first and second specified areas is greater than the preset area difference threshold, the learning result of the second specified area should be taken as the reference, and if the difference between the area sizes of the first and second specified areas is less than the preset area difference threshold, the first and second specified areas are combined to obtain the specified area.
In an embodiment, as shown in fig. 4, in step S30, the unmanned plane area, the laser area and the combined coverage area are respectively analyzed to obtain a refined designated area, which specifically includes:
S311: and inputting data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into an expert experience model, a geological learning model and an edge model to obtain an expert experience refined specified region, a geological learning refined specified region and an edge refined specified region.
In this embodiment, the expert experience model refers to a model for judging an area where insufficient data refinement is likely to occur when the unmanned aerial vehicle and the laser scanner are surveyed, based on analysis of survey data of the unmanned aerial vehicle and the laser scanner and the topography of the current target area by an expert. The geology learning model is a model for judging an area which easily causes insufficient refinement of survey data of the unmanned aerial vehicle and the laser scanner by the geology characteristics of the target area. The edge model is a model for analyzing historical survey data of the unmanned aerial vehicle and the laser scanner and judging geological features when areas with insufficient refinement of the survey data appear.
Specifically, the data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region are input into an expert experience model, a geological learning model and an edge model, wherein the expert experience model is a model for judging the region where insufficient data refinement degree easily occurs when the unmanned aerial vehicle and the laser scanner are surveyed according to the analysis of the survey data of the unmanned aerial vehicle and the laser scanner and the topography of the current target region by an expert, the geological learning model is a model for judging the region where insufficient survey data refinement degree easily occurs when the unmanned aerial vehicle and the laser scanner are surveyed according to the geological characteristics of the target region, and the edge model is a model for analyzing the historical survey data of the unmanned aerial vehicle and the laser scanner and judging the geological characteristics when the region where insufficient survey data refinement degree occurs so as to obtain the expert experience refinement specification region, the geological learning refinement specification region and the edge refinement specification region.
It should be noted that the expert experience refinement specification region includes an expert experience refinement specification region corresponding to the unmanned aerial vehicle region, an expert experience refinement specification region corresponding to the laser region, and an expert experience refinement specification region corresponding to the combined coverage region, the geological learning refinement specification region includes a geological learning refinement specification region corresponding to the unmanned aerial vehicle region, a geological learning refinement specification region corresponding to the laser region, and a geological learning refinement specification region corresponding to the combined coverage region, and the edge refinement specification region includes an edge refinement specification region corresponding to the unmanned aerial vehicle region, an edge refinement specification region corresponding to the laser region, and an edge refinement specification region corresponding to the combined coverage region.
In the present embodiment, the geosteering model refers to a model learned by geological survey data, seismic exploration, electromagnetic exploration, geochemical data, seismic wave propagation, and electromagnetic field variation data of a target area.
S312: and sequencing the expert experience refinement region, the geological learning refinement region and the edge refinement region based on a preset credibility sequencing, and obtaining the refinement region according to a sequencing result.
In this embodiment, the preset confidence ranking refers to sequence information of results for selecting different models for different regions.
Specifically, the preset reliability ranking refers to order information for selecting results of different models for different regions, for example, reliability ranking corresponding to an unmanned aerial vehicle region indicates that among learning results of an expert experience refinement region, a geological learning refinement region and an edge refinement region, reliability of the learning results of the edge refinement region is highest, that is, the ranking of the learning results of the edge refinement region is first, because topography of the unmanned aerial vehicle region is more complex and has a large variation range, accuracy of the learning results of the expert experience model is relatively poor, and learning data of the geological learning model for the topography type of the unmanned aerial vehicle region is less, and therefore accuracy of the learning results of the geological learning model is relatively poor, and therefore the edge refinement region is selected as the refinement region.
In one embodiment, as shown in fig. 5, in step S40, the refinement coefficients are obtained based on the combined coverage area, which specifically includes:
s41: and inputting the data corresponding to the combined coverage area into a geological comparison model to obtain a geological comparison result.
In this embodiment, the geologic contrast model refers to a model for comparing unmanned survey data and laser scan data in combination with coverage areas. The geologic comparison result refers to the output result of the geologic comparison model.
Specifically, unmanned aerial vehicle survey data and laser scanning data corresponding to the coverage area are input into a geological comparison model, unmanned aerial vehicle survey data and laser scanning data are correspondingly compared through the geological comparison model, the difference between the unmanned aerial vehicle survey data and the laser scanning data at the same position is judged, the difference is used as an output result of the geological comparison model, and a geological comparison result is obtained.
S42: and obtaining the refinement coefficient according to the geological comparison result.
Specifically, according to the geological comparison result, namely the difference between unmanned aerial vehicle survey data and laser scanning data at the same position, a notch of the current target area refinement degree is judged according to the difference, and further a refinement coefficient of the combined coverage area is generated, namely, the unmanned aerial vehicle survey data and the laser scanning data of the combined coverage area are refined.
In one embodiment, as shown in fig. 6, in step S50, the refinement compensation is performed on the refinement specification area according to the refinement coefficients, so as to generate a three-dimensional geological model, which specifically includes:
S51: and obtaining the refinement compensation coefficient according to the refinement coefficient and a preset compensation coefficient.
In this embodiment, the preset compensation coefficient refers to a coefficient for performing fine compensation on the unmanned aerial vehicle survey data and the laser scanning data of the entire target area.
Specifically, the preset compensation coefficient refers to a coefficient for performing refinement compensation on the unmanned aerial vehicle survey data and the laser scanning data of the whole target area, and the preset compensation coefficient can be set by a difference value between the refinement degree of the historical unmanned aerial vehicle survey data and the laser scanning data and the target refinement degree. According to the refinement coefficient and the preset compensation coefficient, the refinement compensation coefficient is generated, for example, an average value of the refinement coefficient and the preset compensation coefficient is calculated.
S52: and carrying out fine compensation on the data corresponding to the fine designated area according to the fine compensation coefficient to generate a three-dimensional geological model.
Specifically, data corresponding to the specified area is subjected to fine compensation according to the fine compensation coefficient, fine compensation data are generated, and a three-dimensional geological model is generated based on the fine compensation data, image data surveyed by the unmanned aerial vehicle and point cloud data surveyed by the laser scanner.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present application.
In an embodiment, a three-dimensional geological refinement modeling device based on air-ground combination is provided, and the three-dimensional geological refinement modeling device based on air-ground combination corresponds to the three-dimensional geological refinement modeling method based on air-ground combination in the embodiment one by one. As shown in fig. 7, the three-dimensional geological refinement modeling device based on the air-ground combination comprises a data three-dimensional module, a region dividing module, a region data analysis module, a refinement coefficient acquisition module and a three-dimensional model generation module. The functional modules are described in detail as follows:
The data three-dimensional module is used for acquiring unmanned aerial vehicle survey data and laser scanning data, and carrying out three-dimensional processing on the unmanned aerial vehicle survey data and the laser scanning data based on a preset map model to acquire unmanned aerial vehicle survey three-dimensional data and laser scanning three-dimensional data;
The area dividing module is used for comparing the unmanned aerial vehicle survey three-dimensional data with the laser scanning three-dimensional data to obtain an unmanned aerial vehicle area, a laser area and a combined coverage area;
the area data analysis module is used for respectively analyzing the unmanned aerial vehicle area, the laser area and the combined coverage area to obtain a refined designated area;
The refinement coefficient acquisition module is used for acquiring the refinement coefficient based on the combined coverage area;
and the three-dimensional model generation module is used for carrying out refinement compensation on the data corresponding to the refinement specified region according to the refinement coefficient to generate a three-dimensional geological model.
Optionally, the area data analysis module includes:
The first analysis submodule is used for inputting data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into a blank machine learning model, and obtaining a first refined specified region based on the blank machine learning model;
The second analysis submodule is used for inputting data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into a geological exploration model, and obtaining a second refined specified region based on the geological exploration model;
And the result synthesis submodule is used for obtaining the refinement specified region according to the first refinement specified region and the second refinement specified region.
Optionally, the result synthesis submodule includes:
The comparison unit is used for comparing the data corresponding to the first refined specified area and the second refined specified area to obtain an area comparison result;
and the region specifying unit is used for obtaining a refined specified region according to the region comparison result.
Optionally, the area data analysis module includes:
the multi-model analysis submodule is used for inputting data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into an expert experience model, a geological learning model and an edge model to obtain an expert experience refined specified region, a geological learning refined specified region and an edge refined specified region;
And the multi-model selection sub-module is used for sequencing the expert experience refinement specified region, the geological learning refinement specified region and the edge refinement specified region based on the preset credibility sequencing, and obtaining the refinement specified region according to the sequencing result.
Optionally, the refinement coefficient acquisition module includes:
The geological comparison sub-module is used for inputting data corresponding to the combined coverage area into a geological comparison model to obtain a geological comparison result;
and the refinement coefficient acquisition submodule is used for acquiring the refinement coefficient according to the geological comparison result.
Optionally, the three-dimensional model generating module includes:
The compensation coefficient acquisition submodule is used for acquiring the refinement compensation coefficient according to the refinement coefficient and a preset compensation coefficient;
And the model generation submodule is used for carrying out fine compensation on the data corresponding to the fine designated area according to the fine compensation coefficient to generate a three-dimensional geological model.
For specific limitation of the three-dimensional geological refinement modeling device based on the air-ground combination, reference may be made to the limitation of the three-dimensional geological refinement modeling method based on the air-ground combination hereinabove, and the description thereof will not be repeated here. The modules in the three-dimensional geological fine modeling device based on the air and ground combination can be fully or partially realized by software, hardware and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing unmanned aerial vehicle survey three-dimensional data, laser scanning three-dimensional data, unmanned aerial vehicle areas, laser areas, combined coverage areas, refined specified areas, refined coefficients and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a three-dimensional geological refinement modeling method based on air-ground association.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of when executing the computer program:
acquiring unmanned aerial vehicle survey data and laser scanning data, and performing three-dimensional processing on the unmanned aerial vehicle survey data and the laser scanning data based on a preset map model to acquire unmanned aerial vehicle survey three-dimensional data and laser scanning three-dimensional data;
Comparing the unmanned aerial vehicle survey three-dimensional data with the laser scanning three-dimensional data to obtain an unmanned aerial vehicle area, a laser area and a combined coverage area;
Respectively analyzing the unmanned aerial vehicle area, the laser area and the combined coverage area to obtain a refined designated area;
acquiring a refinement coefficient based on the combined coverage area;
and carrying out refinement compensation on the data corresponding to the refinement specified region according to the refinement coefficient to generate a three-dimensional geological model.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring unmanned aerial vehicle survey data and laser scanning data, and performing three-dimensional processing on the unmanned aerial vehicle survey data and the laser scanning data based on a preset map model to acquire unmanned aerial vehicle survey three-dimensional data and laser scanning three-dimensional data;
Comparing the unmanned aerial vehicle survey three-dimensional data with the laser scanning three-dimensional data to obtain an unmanned aerial vehicle area, a laser area and a combined coverage area;
Respectively analyzing the unmanned aerial vehicle area, the laser area and the combined coverage area to obtain a refined designated area;
acquiring a refinement coefficient based on the combined coverage area;
and carrying out refinement compensation on the data corresponding to the refinement specified region according to the refinement coefficient to generate a three-dimensional geological model.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (10)
1. The three-dimensional geological refinement modeling method based on the air-ground combination is characterized by comprising the following steps of:
acquiring unmanned aerial vehicle survey data and laser scanning data, and performing three-dimensional processing on the unmanned aerial vehicle survey data and the laser scanning data based on a preset map model to obtain unmanned aerial vehicle survey three-dimensional data and laser scanning three-dimensional data;
comparing the unmanned aerial vehicle survey three-dimensional data with the laser scanning three-dimensional data to obtain an unmanned aerial vehicle area, a laser area and a combined coverage area;
Analyzing the unmanned plane area, the laser area and the combined coverage area respectively to obtain a refined designated area;
acquiring a refinement coefficient based on the combined coverage area;
And carrying out refinement compensation on the data corresponding to the refinement specified region according to the refinement coefficient to generate a three-dimensional geological model.
2. The three-dimensional geological refinement modeling method based on air-ground combination according to claim 1, wherein the analyzing the unmanned aerial vehicle region, the laser region and the combined coverage region respectively to obtain a refinement specified region specifically comprises:
inputting data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into a blank machine learning model, and obtaining a first refined specified region based on the blank machine learning model;
Inputting data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into a geological exploration model, and obtaining a second refined specified region based on the geological exploration model;
and obtaining a refinement specified region according to the first refinement specified region and the second refinement specified region.
3. The three-dimensional geological refinement modeling method based on air-ground combination according to claim 2, wherein the obtaining a refinement specification region according to the first refinement specification region and the second refinement specification region specifically comprises:
comparing the data corresponding to the first refined specified region and the second refined specified region to obtain a region comparison result;
And obtaining a refined designated area according to the area comparison result.
4. The three-dimensional geological refinement modeling method based on air-ground combination according to claim 1, wherein the analyzing the unmanned aerial vehicle region, the laser region and the combined coverage region respectively to obtain a refinement specified region specifically comprises:
inputting data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into an expert experience model, a geological learning model and an edge model to obtain an expert experience refined specified region, a geological learning refined specified region and an edge refined specified region;
And sequencing the expert experience refinement region, the geological learning refinement region and the edge refinement region based on a preset credibility sequencing, and obtaining the refinement region according to a sequencing result.
5. The three-dimensional geological refinement modeling method based on air-ground combination according to claim 1, wherein the obtaining refinement coefficients based on the combined coverage area specifically comprises:
Inputting the data corresponding to the combined coverage area into a geological comparison model to obtain a geological comparison result;
and obtaining a refinement coefficient according to the geological comparison result.
6. The three-dimensional geological refinement modeling method based on air-ground combination according to claim 1, wherein the performing refinement compensation on the data corresponding to the refinement specified region according to the refinement coefficient to generate a three-dimensional geological model specifically comprises:
obtaining a refinement compensation coefficient according to the refinement coefficient and a preset compensation coefficient;
and carrying out fine compensation on the data corresponding to the fine designated area according to the fine compensation coefficient to generate a three-dimensional geological model.
7. The three-dimensional geological refinement modeling device based on the air-ground combination is characterized by comprising:
the data three-dimensional module is used for acquiring unmanned aerial vehicle survey data and laser scanning data, and carrying out three-dimensional processing on the unmanned aerial vehicle survey data and the laser scanning data based on a preset map model to acquire unmanned aerial vehicle survey three-dimensional data and laser scanning three-dimensional data;
the area dividing module is used for comparing the unmanned aerial vehicle survey three-dimensional data with the laser scanning three-dimensional data to obtain an unmanned aerial vehicle area, a laser area and a combined coverage area;
The area data analysis module is used for respectively analyzing the unmanned aerial vehicle area, the laser area and the combined coverage area to obtain a refined designated area;
a refinement coefficient acquisition module, configured to acquire a refinement coefficient based on the combined coverage area;
And the three-dimensional model generation module is used for carrying out refinement compensation on the data corresponding to the refinement specified region according to the refinement coefficient to generate a three-dimensional geological model.
8. The three-dimensional geological refinement modeling device based on air-ground combination according to claim 7, wherein the region data analysis module comprises:
The first analysis submodule is used for inputting data corresponding to the unmanned plane area, the laser area and the combined coverage area into a blank machine learning model, and obtaining a first refined specified area based on the blank machine learning model;
The second analysis submodule is used for inputting data corresponding to the unmanned aerial vehicle region, the laser region and the combined coverage region into a geological exploration model, and obtaining a second refined specified region based on the geological exploration model;
And the result synthesis submodule is used for obtaining the refinement specified region according to the first refinement specified region and the second refinement specified region.
9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of the three-dimensional geological refinement modeling method based on air-ground association as claimed in any one of claims 1 to 6.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the three-dimensional geological refinement modeling method based on air-ground association as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410224753.4A CN117994460B (en) | 2024-02-29 | 2024-02-29 | Three-dimensional geological refinement modeling method and device based on air-ground combination |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410224753.4A CN117994460B (en) | 2024-02-29 | 2024-02-29 | Three-dimensional geological refinement modeling method and device based on air-ground combination |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117994460A true CN117994460A (en) | 2024-05-07 |
| CN117994460B CN117994460B (en) | 2024-10-15 |
Family
ID=90890987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410224753.4A Active CN117994460B (en) | 2024-02-29 | 2024-02-29 | Three-dimensional geological refinement modeling method and device based on air-ground combination |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117994460B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110127517A (en) * | 2010-05-19 | 2011-11-25 | (주)넥스지오 | Method for geological investigation of large scaled foundation |
| US20210311504A1 (en) * | 2020-04-01 | 2021-10-07 | Nec Laboratories America, Inc. | Near real-time reconstruction using drones |
| CN113538668A (en) * | 2020-04-17 | 2021-10-22 | 中国石油化工股份有限公司 | Geological model construction method, geological model construction system, storage medium and electronic equipment |
| CN116129064A (en) * | 2022-11-25 | 2023-05-16 | 广东卓维网络有限公司 | Electronic map generation method, device, equipment and storage medium |
| CN116778105A (en) * | 2023-08-17 | 2023-09-19 | 云南高阳科技有限公司 | Fusion modeling method based on multi-precision three-dimensional mapping data |
| CN116844068A (en) * | 2023-09-01 | 2023-10-03 | 山东省地质矿产勘查开发局第五地质大队（山东省第五地质矿产勘查院） | Building mapping method, system, computer equipment and storage medium |
-
2024
- 2024-02-29 CN CN202410224753.4A patent/CN117994460B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110127517A (en) * | 2010-05-19 | 2011-11-25 | (주)넥스지오 | Method for geological investigation of large scaled foundation |
| US20210311504A1 (en) * | 2020-04-01 | 2021-10-07 | Nec Laboratories America, Inc. | Near real-time reconstruction using drones |
| CN113538668A (en) * | 2020-04-17 | 2021-10-22 | 中国石油化工股份有限公司 | Geological model construction method, geological model construction system, storage medium and electronic equipment |
| CN116129064A (en) * | 2022-11-25 | 2023-05-16 | 广东卓维网络有限公司 | Electronic map generation method, device, equipment and storage medium |
| CN116778105A (en) * | 2023-08-17 | 2023-09-19 | 云南高阳科技有限公司 | Fusion modeling method based on multi-precision three-dimensional mapping data |
| CN116844068A (en) * | 2023-09-01 | 2023-10-03 | 山东省地质矿产勘查开发局第五地质大队（山东省第五地质矿产勘查院） | Building mapping method, system, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117994460B (en) | 2024-10-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111160302B (en) | Obstacle information identification method and device based on automatic driving environment | |
| CN110443786B (en) | Laser radar point cloud filtering method and device, computer equipment and storage medium | |
| US11222204B2 (en) | Creation of a 3D city model from oblique imaging and lidar data | |
| US11657533B2 (en) | Computer vision systems and methods for ground surface condition detection and extraction from digital images | |
| CN109683175B (en) | Laser radar configuration method, device, equipment and storage medium | |
| WO2020068784A1 (en) | Active learning framework for machine-assisted tasks | |
| WO2022099511A1 (en) | Method and apparatus for ground segmentation based on point cloud data, and computer device | |
| CN111353969A (en) | Method and device for determining drivable area of road and computer equipment | |
| CN111144304A (en) | Vehicle target detection model generation method, vehicle target detection method and device | |
| WO2021134285A1 (en) | Image tracking processing method and apparatus, and computer device and storage medium | |
| CN112102375B (en) | Point cloud registration reliability detection method and device and mobile intelligent equipment | |
| CN116168246A (en) | Method, device, equipment and medium for identifying waste slag field for railway engineering | |
| CN114792338A (en) | Vision fusion positioning method based on prior three-dimensional laser radar point cloud map | |
| CN117994460B (en) | Three-dimensional geological refinement modeling method and device based on air-ground combination | |
| CN113808142B (en) | Ground identification recognition method and device and electronic equipment | |
| CN113433568B (en) | Laser radar observation simulation method and device | |
| CN113593026B (en) | Lane line labeling auxiliary map generation method, device and computer equipment | |
| Li et al. | Geometric object based building reconstruction from satellite imagery derived point clouds | |
| CN115953604A (en) | Real estate geographic information mapping data acquisition method | |
| Widyaningrum et al. | Tailored features for semantic segmentation with a DGCNN using free training samples of a colored airborne point cloud | |
| CN111366172B (en) | Quality detection method and device of digital elevation model and storage medium | |
| WO2022021209A9 (en) | Electronic map generation method and apparatus, computer device, and storage medium | |
| Kim et al. | Automatic classification of drone images using deep learning and SVM with multiple grid sizes | |
| Akbulut et al. | An Analysis of Neighbourhood Types for POINTNET++ in Semantic Segmentation of Airborne Laser Scanning Data | |
| KR102512222B1 (en) | Method and System for Verifying Outside Manure Pile Volume based on Unmanned Aerial Vehicle |
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 |