A method for 3D digitization of ancient buildings based on multi-source data fusion of surveying and mapping geographic information

Abstract

The present invention relates to the field of ancient building protection and digitization technology, a method and device for 3D digitization of real scenes of ancient buildings by fusion of multi-source data of surveying and mapping geographic information, comprising: after confirming that accurate image acquisition of ancient buildings can be performed using an acquisition parameter set and a reference occlusion area set, fitting an acquisition path and coordinates for acquiring images of ancient buildings based on the acquisition parameter set and a reference coordinate system, photographing a target ancient building using an image collector to obtain an acquired image set, confirming that the acquired image set is a preset target image set, generating a first 3D point cloud map for characterizing outdoor features of the ancient building using the target image set, obtaining a second 3D point cloud map for characterizing indoor features of the ancient building, fusing the first 3D point cloud map and the second 3D point cloud map to obtain an optimized 3D point cloud map, and constructing a target ancient building model based on the optimized 3D point cloud map. The present invention can improve the accuracy and intelligence of 3D digitization of real scenes of ancient buildings.

Description

Technical Field

[0001] The present invention relates to the field of ancient building protection and digitization technology, and in particular to a method, device, electronic equipment and computer-readable storage medium for 3D digitization of ancient building real scenes by fusing multi-source data of surveying and mapping geographic information. Background Art

[0002] As an important part of cultural heritage, ancient buildings carry rich historical information and artistic value. Therefore, how to construct a three-dimensional model that can represent the indoor and outdoor characteristics of ancient buildings is of great significance to the research and protection of ancient buildings.

[0003] At present, the three-dimensional digitization of ancient buildings mostly relies on manual point measurement of the dimensions of the indoor and outdoor components of the ancient buildings, and the three-dimensional model of each component is constructed using the measured dimensions. The assembly relationship or positioning relationship between different components of the ancient building is used to assemble each combined component in the ancient building, thereby realizing the three-dimensional integrated modeling of the indoor and outdoor of the ancient building.

[0004] Although the above method can realize the 3D digitization of the interior and exterior of ancient buildings, it is difficult to ensure the accuracy of manual point measurement, and a large number of positioning relationships or assembly relationships need to be measured to realize the assembly of indoor components or outdoor components. In addition, when manually measuring the size of indoor components or outdoor components of ancient buildings, the positioning relationship or assembly relationship of indoor components or outdoor components, a large amount of time and human resources are required. Therefore, the intelligence level and accuracy of the 3D digitization of ancient buildings need to be improved. Summary of the invention

[0005] The present invention provides a three-dimensional digitization method for ancient building real scenes by fusing multi-source data of surveying and mapping geographic information and a computer-readable storage medium, the main purpose of which is to improve the accuracy and intelligence of the three-dimensional digitization of ancient building real scenes.

[0006] To achieve the above-mentioned purpose, the present invention provides a method for 3D digitization of ancient building real scene by fusing multi-source data of surveying and mapping geographic information, comprising:

[0007] receiving a three-dimensional digitization instruction, and confirming a three-dimensional digitization environment based on the three-dimensional digitization instruction, wherein the three-dimensional digitization environment includes: one or more ancient buildings to be modeled, an image collector and a building scanner, wherein the image collector is composed of an aircraft and a shooting unit;

[0008] Perform the following operations on each of one or more ancient buildings:

[0009] Acquire a satellite image of the ancient building, acquire a fitting circle center of the ancient building based on the satellite image, construct a reference coordinate system with the fitting circle center as the origin, acquire an envelope hemispherical surface of the ancient building based on the fitting circle center, and acquire a route hemispherical surface based on the envelope hemispherical surface, wherein the distance between the route hemispherical surface and the envelope hemispherical surface is equal to a preset safe flight distance;

[0010] Acquire a reference occlusion region set using the route hemisphere, wherein the reference occlusion region set includes H reference occlusion regions, wherein H is an integer greater than or equal to 0;

[0011] Acquire a horizontal acquisition interval angle based on a preset heading overlap, acquire an image acquisition height based on a preset lateral overlap, match the horizontal acquisition interval angle with the image acquisition height to obtain an acquisition parameter group, summarize the acquisition parameter group to obtain an acquisition parameter group set, wherein the lowest height of the image collector is preset as the initial height;

[0012] After confirming that the ancient building is a preset target ancient building by using the acquisition parameter set and the reference occlusion area set, an initial camera inclination angle is calculated based on the reference occlusion area set;

[0013] Based on the acquisition parameter set, a plurality of fitting acquisition orientation points are confirmed in the reference coordinate system, an acquisition path is fitted according to the plurality of fitting acquisition orientation points, a camera inclination angle for image acquisition is set as an initial camera inclination angle, an image collector after the camera inclination angle is set is driven according to the acquisition path, and the target ancient building is photographed by the image collector to obtain an acquired image set, wherein the acquired image set includes a plurality of acquired images;

[0014] After confirming that the acquired image set is a preset target image set, a first three-dimensional point cloud image is acquired based on the target image set, and a second three-dimensional point cloud image is acquired using the building scanner and the ancient building;

[0015] Matching the first three-dimensional point cloud image with the second three-dimensional point cloud image to obtain an optimized three-dimensional point cloud image, and constructing an initial ancient building model based on the optimized three-dimensional point cloud image and the pre-constructed reconstruction model;

[0016] A rendering operation is performed on the initial ancient building model to obtain a target ancient building model, and the real-scene three-dimensional digitization of the ancient building is achieved based on the target ancient building model.

[0017] Optionally, obtaining the fitting center of the ancient building based on the satellite image includes:

[0018] Performing a grayscale operation on the satellite image to obtain a grayscale image;

[0019] An image segmentation model set for segmenting an image is obtained, wherein the image segmentation model set includes a plurality of image segmentation models, image segmentation models are sequentially extracted from the image segmentation model set, and the following operations are performed on the extracted image segmentation models:

[0020] Performing a segmentation operation on the grayscale image based on the extracted image segmentation model to obtain an initial building image;

[0021] Summarizing the initial building images to obtain an initial building image set;

[0022] Match each initial building image in the initial building image set to a pre-constructed image coordinate system to obtain a mapping image;

[0023] Extract pixel points from the mapped image in sequence, and perform the following operations on the extracted pixel points:

[0024] The mapping times are obtained based on the extracted pixel points, and the mapping frequency is calculated using the mapping times. The calculation formula is as follows:

[0025] ;

[0026] in, represents the mapping frequency, Indicates the number of mappings, Represents the number of image segmentation models in the image segmentation model set;

[0027] comparing the mapped frequency with a preset frequency threshold;

[0028] If the mapping frequency is greater than or equal to the frequency threshold, retain the pixel point corresponding to the mapping frequency;

[0029] Otherwise, the pixel points corresponding to the mapping frequency are removed from the mapping image;

[0030] The retained pixel points are aggregated to obtain a target pixel point set, and the target pixel point set is used to obtain the fitting center.

[0031] Optionally, the step of using the acquisition parameter set and the reference occlusion area set to confirm that the ancient building is a preset target ancient building includes:

[0032] Sorting the acquisition parameter groups in the acquisition parameter group set in the order of image acquisition height from small to large to obtain an acquisition parameter group sequence;

[0033] Extracting acquisition parameter groups from the acquisition parameter group sequence in sequence, and performing the following operations on the extracted acquisition parameter groups:

[0034] Acquire an initial occlusion angle set based on the image acquisition height corresponding to the extracted acquisition parameter group and the reference occlusion area set, wherein the initial occlusion angle set includes L initial occlusion angles, wherein L is an integer greater than or equal to 0;

[0035] Acquire a target occlusion angle based on the initial occlusion angle set, wherein the target occlusion angle is the largest initial occlusion angle in the initial occlusion angle set;

[0036] Comparing the target occlusion angle with the horizontal acquisition interval angle corresponding to the extracted acquisition parameter group;

[0037] If the target occlusion angle is less than the horizontal acquisition interval angle corresponding to the extracted acquisition parameter group, the ancient building is confirmed to be the target ancient building, and the initial camera inclination is calculated using a pre-constructed inclination evaluation relationship, wherein the inclination evaluation relationship is as follows:

[0038] ;

[0039] in, is the initial camera tilt angle, Indicates the height of the image collector. Indicates the radius of the route hemisphere;

[0040] If there is only one target occlusion angle greater than or equal to the horizontal acquisition interval angle corresponding to the extracted acquisition parameter group and the image acquisition height corresponding to the extracted acquisition parameter group is the initial height, then the target horizontal acquisition interval angle is obtained based on the acquisition parameter group sequence, wherein the target horizontal acquisition interval angle is the horizontal acquisition interval angle corresponding to the second acquisition parameter group in the acquisition parameter group sequence;

[0041] Based on the target horizontal acquisition interval angle, a height value corresponding to the target occlusion interval angle is centrally confirmed in the reference occlusion area, wherein the target occlusion interval angle is equal to the target horizontal acquisition interval angle;

[0042] If the height value is less than or equal to the preset height threshold, the height value is used as the initial height, and the process returns to the step of obtaining the image acquisition height based on the preset lateral overlap;

[0043] Otherwise, it is confirmed that the ancient building is not the target ancient building.

[0044] Optionally, fitting a collection path according to a plurality of fitting collection orientation points includes:

[0045] A fitting model set for fitting the path is obtained, wherein the fitting model set includes a plurality of fitting models, fitting models are sequentially extracted from the fitting model set, and the following operations are performed on the extracted fitting models:

[0046] An initial path is acquired using the extracted fitting model and a plurality of fitting acquisition azimuth points, wherein the initial path is composed of a plurality of first paths and K second paths, K is an integer greater than or equal to 0, and a start point and an end point of the initial path are preset;

[0047] The evaluation energy consumption is calculated based on the initial path and the pre-constructed energy consumption evaluation relationship, the evaluation energy consumption is summarized to obtain an evaluation energy consumption set, and the collection path is confirmed based on the evaluation energy consumption set, wherein the collection path is the initial path corresponding to the smallest evaluation energy consumption in the evaluation energy consumption set.

[0048] Optionally, the energy consumption evaluation equation is as follows:

[0049] ;

[0050] in, represents the energy consumption evaluation, Indicates that the image collector is the first one in multiple first paths The average energy consumption of the first path is Indicates the first path among multiple first paths The distance of the first path, Indicates that the image collector is the first one in multiple first paths The average speed of the first path, Indicates that the first path has indivual, Indicates that the image collector is The second path The average energy consumption of the second path is express The second path The distance of the second path, Indicates that the image collector is The second path The average speed of the second path is Indicates shared A second path.

[0051] Optionally, confirming that the acquired image set is a preset target image set includes:

[0052] Extracting collected images from the collected image set in sequence, and performing the following operations on the extracted collected images:

[0053] Confirming acquisition coordinates based on the extracted acquisition image, the reference coordinate system and the plurality of fitted acquisition orientation points, and performing a marking operation on the acquisition image using the acquisition coordinates to obtain a marked image;

[0054] Summarizing the identification images to obtain an identification image set;

[0055] Extract logo images from the logo image set in sequence, and perform the following operations on the extracted logo images:

[0056] Based on the acquisition coordinates corresponding to the extracted identification image, a reference image set is retrieved from the identification image set, wherein the reference image set includes a plurality of reference images, and the Euclidean distances between the acquisition coordinates corresponding to the reference images and the acquisition coordinates corresponding to the extracted identification image are both less than or equal to a preset distance threshold;

[0057] Performing a grayscale operation on the extracted identification image to obtain an identification grayscale image, and obtaining a reference grayscale image set using a reference image set, wherein the reference grayscale image set includes a plurality of reference grayscale images, and the reference grayscale images correspond to the reference images one by one;

[0058] The first comprehensive grayscale value is calculated based on the identification grayscale image and the pre-constructed comprehensive grayscale relationship formula, wherein the comprehensive grayscale relationship formula is as follows:

[0059] ;

[0060] in, represents the first integrated gray value, , are all preset coefficients. Indicates the mean value of the grayscale value corresponding to the pixel in the grayscale image. Indicates the variance of the grayscale value corresponding to the pixel in the grayscale image;

[0061] Using a reference grayscale image set to obtain a comprehensive evaluation range;

[0062] If the first comprehensive grayscale value corresponding to the identification image satisfies the comprehensive evaluation range, the acquired image set is confirmed to be the target image set.

[0063] Optionally, the obtaining a comprehensive evaluation range by using a reference grayscale image set includes:

[0064] The comprehensive grayscale value is calculated based on the reference grayscale image set and the pre-constructed comprehensive grayscale relationship, and the comprehensive evaluation range is formulated using the comprehensive grayscale value, wherein the comprehensive grayscale relationship is as follows:

[0065] ;

[0066] in, represents the comprehensive gray value, Indicates that the reference grayscale image set has A reference grayscale image, , They represent the first A reference grayscale image, The Euclidean distance corresponding to the reference grayscale image, Represents the first The mean of the grayscale values ​​corresponding to the pixels in the reference grayscale image, Represents the first The variance of the grayscale value corresponding to the pixel in the reference grayscale image, is the preset coefficient;

[0067] The scope of comprehensive assessment is as follows:

[0068] ;

[0069] in, Indicates the scope of comprehensive assessment, Indicates the preset coefficient.

[0070] Optionally, matching the first three-dimensional point cloud image and the second three-dimensional point cloud image to obtain an optimized three-dimensional point cloud image includes:

[0071] A target feature point set is obtained based on the first three-dimensional point cloud image, and an optimized three-dimensional point cloud image is obtained using the target feature point set, a pre-constructed feature matching matrix and the second three-dimensional point cloud image, wherein the feature matching matrix is ​​as follows:

[0072] ;

[0073] in, represents the feature matching matrix, represents the target feature point set, represents the point cloud rotation matrix, represents the point cloud translation matrix, Indicates the first The coordinates corresponding to the target feature points, Indicates the second 3D point cloud image. The coordinates corresponding to the points, represents the Euclidean norm.

[0074] Optionally, the reconstruction model is a neural network model.

[0075] To achieve the above-mentioned purpose, the present invention also provides a three-dimensional digitization device for ancient building real scene by fusing multi-source data of surveying and mapping geographic information, comprising:

[0076] The ancient building three-dimensional digital environment confirmation module is used to receive a three-dimensional digital instruction and confirm a three-dimensional digital environment based on the three-dimensional digital instruction, wherein the three-dimensional digital environment includes: one or more ancient buildings to be modeled, an image collector and a building scanner, wherein the image collector is composed of an aircraft and a shooting unit;

[0077] The ancient building image acquisition module is used to perform the following operations on each of one or more ancient buildings:

[0078] Acquire a satellite image of the ancient building, acquire a fitting circle center of the ancient building based on the satellite image, construct a reference coordinate system with the fitting circle center as the origin, acquire an envelope hemispherical surface of the ancient building based on the fitting circle center, and acquire a route hemispherical surface based on the envelope hemispherical surface, wherein the distance between the route hemispherical surface and the envelope hemispherical surface is equal to a preset safe flight distance;

[0079] Acquire a reference occlusion region set using the route hemisphere, wherein the reference occlusion region set includes H reference occlusion regions, wherein H is an integer greater than or equal to 0;

[0080] Acquire a horizontal acquisition interval angle based on a preset heading overlap, acquire an image acquisition height based on a preset lateral overlap, match the horizontal acquisition interval angle with the image acquisition height to obtain an acquisition parameter group, summarize the acquisition parameter group to obtain an acquisition parameter group set, wherein the lowest height of the image collector is preset as the initial height;

[0081] After confirming that the ancient building is a preset target ancient building by using the acquisition parameter set and the reference occlusion area set, an initial camera inclination angle is calculated based on the reference occlusion area set;

[0082] Based on the acquisition parameter set, a plurality of fitting acquisition orientation points are confirmed in the reference coordinate system, an acquisition path is fitted according to the plurality of fitting acquisition orientation points, a camera inclination angle for image acquisition is set as an initial camera inclination angle, an image collector after the camera inclination angle is set is driven according to the acquisition path, and the target ancient building is photographed by the image collector to obtain an acquired image set, wherein the acquired image set includes a plurality of acquired images;

[0083] The ancient building three-dimensional point cloud map construction module is used to obtain a first three-dimensional point cloud map based on the target image set after confirming that the collected image set is a preset target image set, and obtain a second three-dimensional point cloud map using the building scanner and the ancient building;

[0084] The ancient building three-dimensional digital construction module is used to match the first three-dimensional point cloud image with the second three-dimensional point cloud image to obtain an optimized three-dimensional point cloud image, and to construct an initial ancient building model based on the optimized three-dimensional point cloud image and the pre-constructed reconstruction model;

[0085] A rendering operation is performed on the initial ancient building model to obtain a target ancient building model, and the real-scene three-dimensional digitization of the ancient building is achieved based on the target ancient building model.

[0086] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising:

[0087] a memory storing at least one instruction; and

[0088] The processor executes the instructions stored in the memory to implement the above-mentioned method for 3D digitization of ancient building real scene by fusing multi-source data of surveying and mapping geographic information.

[0089] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned method for three-dimensional digitization of real scenes of ancient buildings by fusing multi-source data of surveying and mapping geographic information.

[0090] The present invention is to solve the problem described in the background technology. The present invention obtains a satellite image of an ancient building, obtains a fitting center of the ancient building based on the satellite image, constructs a reference coordinate system with the fitting center as the origin, obtains an envelope hemisphere of the ancient building based on the fitting center, and obtains a route hemisphere based on the envelope hemisphere. It can be seen that the embodiment of the present invention takes into account the possible differences in obtaining the fitting center using satellite images when obtaining the fitting center. Therefore, an image segmentation model set is used to obtain the fitting center, thereby improving the accuracy of obtaining the fitting center, and laying a foundation for accurately fitting the acquisition path for collecting ancient building images. The present invention uses the route hemisphere to obtain a reference occlusion area set. It can be seen that the present invention takes into account the possibility of other buildings or vegetation around the ancient building before formulating the acquisition path, which may cause the acquisition path to be unable to be fitted normally. Furthermore, the present invention obtains a horizontal acquisition interval angle based on a preset heading overlap, obtains an image acquisition height based on a preset lateral overlap, matches the horizontal acquisition interval angle with the image acquisition height, obtains an acquisition parameter group, summarizes the acquisition parameter group, obtains an acquisition parameter group set, and uses the acquisition parameter group set and the reference occlusion area set to confirm that the ancient building is a preset target ancient building. Then, the initial camera inclination angle is calculated based on the reference occlusion area set. It can be seen that the present invention uses the route hemisphere to realize image acquisition of the ancient building, so that the acquired image can better characterize the characteristics of the ancient building, thereby improving the accuracy of three-dimensional digitization of the ancient building, and before confirming the fitting azimuth point, it is considered that different acquisition parameter groups may have different occlusion situations. Furthermore, under certain conditions, the image collector can be adaptively adjusted so that the image collected by the image collector can better characterize the characteristics of the ancient building and improve the practicality of the embodiment of the present invention. Based on the acquisition parameter set, the present invention confirms multiple fitting acquisition orientation points in the reference coordinate system, fits an acquisition path according to the multiple fitting acquisition orientation points, sets the camera inclination angle of image acquisition to the initial camera inclination angle, drives the image collector after the camera inclination angle is set according to the acquisition path, and uses the image collector to shoot the target ancient building to obtain an acquired image set. It can be seen that the present invention also considers the problem of energy consumption of the initial path. Therefore, the acquisition path with the minimum energy consumption is obtained through the initial path. After the present invention confirms that the acquired image set is a preset target image set, a first three-dimensional point cloud map is obtained based on the target image set, a second three-dimensional point cloud map is obtained using the building scanner and the ancient building, the first three-dimensional point cloud map and the second three-dimensional point cloud map are matched to obtain an optimized three-dimensional point cloud map, an initial ancient building model is constructed based on the optimized three-dimensional point cloud map and a pre-constructed reconstruction model, and a rendering operation is performed on the initial ancient building model to obtain a target ancient building model.It can be seen that the present invention not only uses the acquisition image set to obtain the first three-dimensional point cloud map but also uses the building scanner to obtain the second three-dimensional point cloud map, and the first three-dimensional point cloud map and the second three-dimensional point cloud map have different characteristics of the ancient building, that is, the first three-dimensional point cloud map can represent the outdoor characteristics of the ancient building, and the second three-dimensional point cloud map can represent the indoor characteristics of the ancient building, and the two three-dimensional point clouds are matched, so that the matched optimized three-dimensional point cloud map can represent the indoor and outdoor characteristics of the ancient building, and the three-dimensional integrated modeling of the indoor and outdoor of the ancient building can be realized by optimizing the three-dimensional point cloud map, and the initial ancient building model constructed by using the optimized three-dimensional point cloud map is rendered, so that the rendered initial ancient building model can better represent the ancient building. Therefore, the present invention can improve the accuracy and intelligence of the three-dimensional digitization of the real scene of the ancient building. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] Figure 1 A schematic diagram of a flow chart of a method for 3D digitization of real scenes of ancient buildings by fusing multi-source data of surveying and mapping geographic information provided by an embodiment of the present invention;

[0092] Figure 2 A functional module diagram of a three-dimensional digitization device for ancient building real scene by fusing multi-source data of surveying and mapping geographic information provided by an embodiment of the present invention;

[0093] Figure 3 A schematic diagram of the structure of an electronic device for implementing the method for three-dimensional digitization of real scenes of ancient buildings by fusing multi-source data of surveying and mapping geographic information provided by an embodiment of the present invention.

[0094] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0095] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0096] The embodiment of the present application provides a method for three-dimensional digitization of real scenes of ancient buildings by fusion of multi-source data of surveying and mapping geographic information. The execution subject of the method for three-dimensional digitization of real scenes of ancient buildings by fusion of multi-source data of surveying and mapping geographic information includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for three-dimensional digitization of real scenes of ancient buildings by fusion of multi-source data of surveying and mapping geographic information can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0097] Reference Figure 1FIG. 1 is a flow chart of a method for 3D digitizing a real scene of an ancient building by fusing multi-source data of surveying and mapping geographic information provided by an embodiment of the present invention. In this embodiment, the method for 3D digitizing a real scene of an ancient building by fusing multi-source data of surveying and mapping geographic information includes:

[0098] S1. Receive a three-dimensional digitization instruction, and confirm a three-dimensional digitization environment based on the three-dimensional digitization instruction, wherein the three-dimensional digitization environment includes: one or more ancient buildings to be modeled, an image collector and a building scanner, wherein the image collector is composed of an aircraft and a shooting unit.

[0099] It is understandable that the three-dimensional digitization instruction is an instruction issued by the ancient building protection personnel or the ancient building reconstruction personnel, and the ancient building protection personnel or the ancient building reconstruction personnel confirm the necessary environment for the three-dimensional digitization of the real scene of the ancient building, which is a three-dimensional digitization environment. The function of the image collector is to collect images of the ancient building in all directions and angles. The function of the building scanner is to collect three-dimensional point cloud images of the ancient building. Optionally, a laser scanner is used as the building scanner, and other technologies can achieve the same effect, which will not be repeated here. Optionally, a camera is used as the shooting unit, and other technologies can achieve the same effect, which will not be repeated here.

[0100] For example, Xiao Zhang, as an ancient building protection worker, initiates the three-dimensional digitization command and confirms the three-dimensional numerical digitization environment in order to record the characteristics of the ancient building to facilitate subsequent repair and maintenance of the ancient building.

[0101] S2. Obtain a satellite image of the ancient building, obtain the fitting center of the ancient building based on the satellite image, construct a reference coordinate system with the fitting center as the origin, obtain the envelope hemisphere of the ancient building based on the fitting center, and obtain the route hemisphere based on the envelope hemisphere, wherein the distance between the route hemisphere and the envelope hemisphere is equal to a preset safe flight distance.

[0102] It should be explained that the obtaining of the fitting center of the ancient building based on the satellite image includes:

[0103] Performing a grayscale operation on the satellite image to obtain a grayscale image;

[0104] An image segmentation model set for segmenting an image is obtained, wherein the image segmentation model set includes a plurality of image segmentation models, image segmentation models are sequentially extracted from the image segmentation model set, and the following operations are performed on the extracted image segmentation models:

[0105] Performing a segmentation operation on the grayscale image based on the extracted image segmentation model to obtain an initial building image;

[0106] Summarizing the initial building images to obtain an initial building image set;

[0107] Match each initial building image in the initial building image set to a pre-constructed image coordinate system to obtain a mapping image;

[0108] Extract pixel points from the mapped image in sequence, and perform the following operations on the extracted pixel points:

[0109] The mapping times are obtained based on the extracted pixel points, and the mapping frequency is calculated using the mapping times. The calculation formula is as follows:

[0110] ;

[0111] in, represents the mapping frequency, Indicates the number of mappings, Represents the number of image segmentation models in the image segmentation model set;

[0112] comparing the mapped frequency with a preset frequency threshold;

[0113] If the mapping frequency is greater than or equal to the frequency threshold, retain the pixel point corresponding to the mapping frequency;

[0114] Otherwise, the pixel points corresponding to the mapping frequency are removed from the mapping image;

[0115] The retained pixel points are aggregated to obtain a target pixel point set, and the target pixel point set is used to obtain the fitting center.

[0116] It should be noted that satellite images refer to earth observation images containing ancient buildings. The grayscale operation performed on the satellite image refers to the operation of converting a color satellite image into a grayscale image, and the grayscale operation is a prior art and will not be described in detail here. The image segmentation model refers to a model or algorithm that can segment the area corresponding to the ancient building in the grayscale image. Optionally, the Canndy algorithm is used as the image segmentation model, and other technologies can achieve the same effect, which will not be described in detail here. The initial building image refers to a grayscale image containing only ancient buildings. Optionally, a pixel coordinate system is used as the image coordinate system. The operation of mapping the initial building image to the image coordinate system is: obtaining the number of rows and columns of pixel points in the initial building image, and using the number of rows and columns as the horizontal axis coordinate and the vertical axis coordinate of the pixel coordinate system, superimposing each initial building image in the initial building image set, and obtaining the mapped image. The fitting center of the circle refers to the center of the circle corresponding to the minimum circumscribed circle of the initial building image. Optionally, the problem of obtaining the center of a fitting circle using a target pixel point set is converted into a problem of solving a minimum covering circle, and the technology for obtaining the center of a minimum covering circle is an existing technology and will not be described in detail here.

[0117] For example, the frequency threshold is 0.6, the area corresponding to the satellite image is an area composed of 25 squares with a side length of 1, and the area surrounded by the 25 squares with a side length of 1 is: a square area with (0, 0), (5, 5), (5, 0) and (0, 5) as vertices. The area obtained after the satellite image is segmented by the first image segmentation model is an area surrounded by 8 squares with a side length of 1 that include (3, 3) and are adjacent to (3, 3). This area is the initial building image. The area of ​​the initial building image should be the area enclosed by the eight squares with a side length of 1 adjacent to (3, 3). The area of ​​the initial building image corresponding to the third image segmentation model is consistent with the area of ​​the initial building image corresponding to the first image segmentation model. Then the target pixel point sets obtained by these three image segmentation models are: eight squares with a side length of 1 containing (3, 3) and adjacent to (3, 3). Among the eight squares with a side length of 1 containing (3, 3) and adjacent to (3, 3), the square with a side length of 1 refers to the target pixel point.

[0118] It is understandable that there are differences in the structures and parameters corresponding to the image segmentation models in the image segmentation model set, so different image segmentation models may be used to process the same grayscale image, resulting in different processing results. The method of matching each initial building image in the initial building image set can improve the accuracy of obtaining the fitting center using satellite images, and then improve the accuracy of the actual three-dimensional digitization of ancient buildings. Optionally, a Cartesian coordinate system is used as the reference coordinate system. The method for obtaining the envelope hemispherical surface of the ancient building based on the fitting center is: obtaining the smallest cuboid based on the ancient building, and obtaining the envelope hemispherical surface based on the smallest cuboid and the fitting center. The envelope hemispherical surface refers to the spherical surface of the hemisphere that wraps the smallest cuboid, and the technology of obtaining the envelope hemispherical surface using the fitting center is a prior art and will not be repeated here. The smallest cuboid refers to the smallest cuboid that wraps the ancient building. Obviously, in the embodiment of the present invention, the route hemispherical surface is hemispherical. The purpose of using a hemispherical route in the embodiment of the present invention is to more accurately collect image information of the ancient building, and then improve the accuracy of constructing a three-dimensional point cloud map of the ancient building.

[0119] S3. Acquire a reference occlusion area set using the route hemisphere, wherein the reference occlusion area set includes H reference occlusion areas, wherein H is an integer greater than or equal to 0.

[0120] It should be understood that the reference occlusion area refers to the area intersecting with the hemispherical route hemispherical surface, including but not limited to the intersection of buildings and the hemispherical route hemispherical surface and the intersection of vegetation and the hemispherical route hemispherical surface. Optionally, a sensor is used to obtain the reference occlusion area with the route hemispherical surface as the detection object.

[0121] Exemplarily, for ease of understanding, taking the Cartesian coordinate system as an example, the path hemisphere is a hemisphere with the origin as the center and a radius of 2, and the vertical axis corresponding to the path hemisphere is greater than or equal to 0. There is a cube with a side length of 1 at (1, 1, 0), then the part where the cube intersects with the path hemisphere is the reference occlusion area.

[0122] S4. Acquire a horizontal acquisition interval angle based on a preset heading overlap, acquire an image acquisition height based on a preset lateral overlap, match the horizontal acquisition interval angle with the image acquisition height to obtain an acquisition parameter group, summarize the acquisition parameter groups to obtain an acquisition parameter group set, wherein the lowest height of the image collector is preset as the initial height.

[0123] It is understandable that heading overlap refers to: the degree of overlap of the ground corresponding to two adjacent images taken along the same route. Lateral overlap refers to: the degree of overlap of the same ground image portion corresponding to two adjacent photographs taken. Image acquisition height refers to the height at which images of ancient buildings are acquired. The horizontal acquisition interval angle refers to the angle between two adjacent image acquisition points and the vertical axis in the reference coordinate system at a certain image acquisition height. For example: in a Cartesian coordinate system, when the vertical axes are both 1, the coordinates of two adjacent image acquisition points are respectively: (1, 0, 1) and (0, 1, 1), then the horizontal acquisition interval angle corresponding to these two image acquisition points is 90 degrees. The techniques of obtaining the horizontal acquisition interval angle using heading overlap and obtaining the image acquisition height using lateral overlap are both existing technologies and will not be repeated here.

[0124] It should be explained that the purpose of matching the horizontal acquisition interval angle with the image acquisition height to obtain the acquisition parameter group is to obtain the horizontal acquisition interval angle required for image acquisition at different heights. For example, the acquisition parameter group set includes three acquisition parameter groups, and the three acquisition parameter groups are (5m, 5 degrees), (8m, 4 degrees) and (12m, 3 degrees), among which the first acquisition parameter group (5m, 5 degrees) means that when the image acquisition height of the image collector is 5m, the horizontal acquisition interval angle is 5 degrees.

[0125] S5. After confirming that the ancient building is the preset target ancient building by using the acquisition parameter set and the reference occlusion area set, an initial camera inclination angle is calculated based on the reference occlusion area set.

[0126] Furthermore, the step of using the acquisition parameter set and the reference occlusion area set to confirm that the ancient building is a preset target ancient building includes:

[0127] Sorting the acquisition parameter groups in the acquisition parameter group set in the order of image acquisition height from small to large to obtain an acquisition parameter group sequence;

[0128] Extracting acquisition parameter groups from the acquisition parameter group sequence in sequence, and performing the following operations on the extracted acquisition parameter groups:

[0129] Acquire an initial occlusion angle set based on the image acquisition height corresponding to the extracted acquisition parameter group and the reference occlusion area set, wherein the initial occlusion angle set includes L initial occlusion angles, wherein L is an integer greater than or equal to 0;

[0130] Acquire a target occlusion angle based on the initial occlusion angle set, wherein the target occlusion angle is the largest initial occlusion angle in the initial occlusion angle set;

[0131] Comparing the target occlusion angle with the horizontal acquisition interval angle corresponding to the extracted acquisition parameter group;

[0132] If the target occlusion angle is less than the horizontal acquisition interval angle corresponding to the extracted acquisition parameter group, the ancient building is confirmed to be the target ancient building, and the initial camera inclination is calculated using a pre-constructed inclination evaluation relationship, wherein the inclination evaluation relationship is as follows:

[0133] ;

[0134] in, is the initial camera tilt angle, Indicates the height of the image collector. Indicates the radius of the route hemisphere;

[0135] If there is only one target occlusion angle greater than or equal to the horizontal acquisition interval angle corresponding to the extracted acquisition parameter group and the image acquisition height corresponding to the extracted acquisition parameter group is the initial height, then the target horizontal acquisition interval angle is obtained based on the acquisition parameter group sequence, wherein the target horizontal acquisition interval angle is the horizontal acquisition interval angle corresponding to the second acquisition parameter group in the acquisition parameter group sequence;

[0136] Based on the target horizontal acquisition interval angle, a height value corresponding to the target occlusion interval angle is centrally confirmed in the reference occlusion area, wherein the target occlusion interval angle is equal to the target horizontal acquisition interval angle;

[0137] If the height value is less than or equal to the preset height threshold, the height value is used as the initial height, and the process returns to the step of obtaining the image acquisition height based on the preset lateral overlap;

[0138] Otherwise, it is confirmed that the ancient building is not the target ancient building.

[0139] It is understandable that each acquisition parameter group includes different acquisition parameters of the image collector. For example: when the acquisition parameter group is (5m, 5 degrees), it means that the image collector needs to have a total of 72 acquisition points at a height of 5m, and the angle interval between adjacent acquisition points is 5 degrees. When the reference occlusion area set has a target occlusion angle greater than or equal to the horizontal acquisition interval angle corresponding to a certain acquisition parameter group in the image acquisition height corresponding to the acquisition parameter group other than the initial height, it indicates that the image collector cannot complete the image acquisition operation of the ancient building at this height. For example: when the acquisition parameter group is (8m, 4 degrees), at a height of 8m, the target occlusion angle corresponding to the reference occlusion area set is 5 degrees, indicating that at a height of 8m, it is impossible to achieve the image acquisition operation at this height by proposing different acquisition points. Confirming that an ancient building is not a target ancient building means that: the expected image cannot be completely captured at the ancient building. Furthermore, confirming that the ancient building is a target ancient building means that: the image representing the outdoor features of the ancient building can be accurately captured according to preset parameters. The set of images that can represent the outdoor features of the ancient building is the captured image set. Here, the parameters include but are not limited to: heading overlap and lateral overlap. For specific steps of obtaining the captured image set, please refer to the subsequent embodiments.

[0140] It should be understood that when there is only a horizontal acquisition interval angle corresponding to the target occlusion angle greater than or equal to the initial height, the image acquisition operation can be completed by using the image collector by adjusting the camera inclination angle of the image acquisition unit. Based on the target horizontal acquisition interval angle, the height value corresponding to the target occlusion interval angle is confirmed in the reference occlusion area, which means: confirming the height value when the target occlusion interval angle is equal to the target horizontal acquisition interval angle. For example: the acquisition parameter group sequence is: (5m, 5 degrees), (8m, 4 degrees) and (12m, 3 degrees), the target horizontal acquisition interval angle is 4 degrees, then the height value when the interval angle is 4 degrees is confirmed in the reference occlusion area with 4 degrees as the reference, and the height value is 6.5m, the preset height threshold is 7m, then the height value is less than or equal to the height threshold, 6.5m is used as the initial height, and the acquisition parameter group set with an initial height of 6.5m is recalculated. The purpose of setting the height threshold is to expand the applicable conditions of the embodiment of the present invention while ensuring that the proposed camera inclination angle is reasonable, thereby improving the accuracy of the proposed three-dimensional model of the ancient building.

[0141] It is understandable that the camera tilt refers to the angle change of the image collector relative to the horizontal plane. When the camera tilt is too large, the image of the ancient building collected will be blocked. For example, when the camera tilt is 90 degrees, that is, when the image collector is perpendicular to the horizontal plane, only the top view of the ancient building can be collected.

[0142] S6. Based on the acquisition parameter set, multiple fitting acquisition orientation points are confirmed in the reference coordinate system, an acquisition path is fitted according to the multiple fitting acquisition orientation points, the camera inclination angle of image acquisition is set to the initial camera inclination angle, the image collector after the camera inclination angle is set is driven according to the acquisition path, and the target ancient building is photographed by the image collector to obtain an acquired image set, wherein the acquired image set includes multiple acquired images.

[0143] It is understandable that the acquisition parameter set includes multiple acquisition parameter groups, and multiple fitting acquisition points can be identified in the reference coordinate system using different acquisition parameter groups. For example: when the acquisition parameter group is (5m, 5 degrees), it means that when the vertical axis height of the reference coordinate system is 5m, 72 fitting acquisition points can be obtained in the route hemisphere, and the angle between two adjacent fitting acquisition points and the vertical axis is 5 degrees. The fitting acquisition azimuth point refers to the acquisition azimuth point after considering the use of the horizontal acquisition interval angle in the route hemisphere to avoid the occlusion area, and the fitting acquisition azimuth point is composed of the horizontal coordinate, the vertical coordinate and the vertical coordinate. For example: when the height of the route hemisphere is 5m, there is an occlusion area corresponding to an angle of 4 degrees, then the fitting acquisition azimuth point can be the 72 fitting acquisition points corresponding to any angle when crossing the angle corresponding to the occlusion area, and at different heights, the position of the proposed fitting acquisition point may be different.

[0144] It should be explained that the step of fitting a collection path according to a plurality of fitting collection orientation points includes:

[0145] A fitting model set for fitting the path is obtained, wherein the fitting model set includes a plurality of fitting models, fitting models are sequentially extracted from the fitting model set, and the following operations are performed on the extracted fitting models:

[0146] An initial path is acquired using the extracted fitting model and a plurality of fitting acquisition azimuth points, wherein the initial path is composed of a plurality of first paths and K second paths, K is an integer greater than or equal to 0, and a start point and an end point of the initial path are preset;

[0147] The evaluation energy consumption is calculated based on the initial path and the pre-constructed energy consumption evaluation relationship, the evaluation energy consumption is summarized to obtain an evaluation energy consumption set, and the collection path is confirmed based on the evaluation energy consumption set, wherein the collection path is the initial path corresponding to the smallest evaluation energy consumption in the evaluation energy consumption set.

[0148] Furthermore, the fitting model refers to an algorithm or model used for fitting the path. Optionally, an ant colony algorithm is used as the fitting model, and other technologies can achieve the same effect, which will not be described in detail here.

[0149] It is understandable that the difference between the first path and the second path is that the first path is a line segment between two fitting acquisition orientation points, and the second path is a curve formed by taking one of the two fitting acquisition orientation points as the starting point and the other as the end point. For example, when there is an occlusion area between the first fitting acquisition orientation point and the second fitting acquisition orientation point, the path of the image collector needs to be planned to cross the occlusion area.

[0150] It should be understood that the energy consumption evaluation relationship is as follows:

[0151] ;

[0152] in, represents the energy consumption evaluation, Indicates that the image collector is the first one in multiple first paths The average energy consumption of the first path is Indicates the first path among multiple first paths The distance of the first path, Indicates that the image collector is the first one in multiple first paths The average speed of the first path, Indicates that the first path has indivual, Indicates that the image collector is The second path The average energy consumption of the second path is express The second path The distance of the second path, Indicates that the image collector is The second path The average speed of the second path is Indicates shared A second path.

[0153] S7. After confirming that the acquired image set is a preset target image set, a first three-dimensional point cloud image is obtained based on the target image set, and a second three-dimensional point cloud image is obtained using the building scanner and the ancient building.

[0154] It is understandable that the confirming that the acquired image set is a preset target image set includes:

[0155] Extracting collected images from the collected image set in sequence, and performing the following operations on the extracted collected images:

[0156] Confirming acquisition coordinates based on the extracted acquisition image, the reference coordinate system and the plurality of fitted acquisition orientation points, and performing a marking operation on the acquisition image using the acquisition coordinates to obtain a marked image;

[0157] Summarizing the identification images to obtain an identification image set;

[0158] Extract logo images from the logo image set in sequence, and perform the following operations on the extracted logo images:

[0159] Based on the acquisition coordinates corresponding to the extracted identification image, a reference image set is retrieved from the identification image set, wherein the reference image set includes a plurality of reference images, and the Euclidean distances between the acquisition coordinates corresponding to the reference images and the acquisition coordinates corresponding to the extracted identification image are both less than or equal to a preset distance threshold;

[0160] Performing a grayscale operation on the extracted identification image to obtain an identification grayscale image, and obtaining a reference grayscale image set using a reference image set, wherein the reference grayscale image set includes a plurality of reference grayscale images, and the reference grayscale images correspond to the reference images one by one;

[0161] The first comprehensive grayscale value is calculated based on the identification grayscale image and the pre-constructed comprehensive grayscale relationship formula, wherein the comprehensive grayscale relationship formula is as follows:

[0162] ;

[0163] in, represents the first integrated gray value, , are all preset coefficients. Indicates the mean value of the grayscale value corresponding to the pixel in the grayscale image. Indicates the variance of the grayscale value corresponding to the pixel in the grayscale image;

[0164] Using a reference grayscale image set to obtain a comprehensive evaluation range;

[0165] If the first comprehensive grayscale value corresponding to the identification image satisfies the comprehensive evaluation range, the acquired image set is confirmed to be the target image set.

[0166] It should be explained that the acquisition coordinates refer to the coordinates corresponding to the acquisition orientation points fitted by the image collector in the reference coordinate system when the acquisition image is taken. The operation of marking the acquisition image using the acquisition coordinates refers to: marking the coordinates of the acquisition image, which is used to filter out the reference grayscale image set corresponding to the extracted acquisition image in the acquisition image set. For example, the coordinates corresponding to the acquisition image are (1, 1, 1), and the acquisition image is marked to obtain 1-1-1-acquisition image, where 1-1-1 means that the coordinates corresponding to the acquisition image are (1, 1, 1). Other technologies can achieve the same effect, which will not be repeated here.

[0167] It should be understood that the Euclidean distance is the distance calculated using the coordinates corresponding to the two identification images, and the calculation of the Euclidean distance is a prior art and will not be described in detail here. The reference grayscale image refers to the grayscale image obtained by graying the reference image. When the first comprehensive grayscale value meets the comprehensive evaluation range, it means that the identification image corresponding to the first comprehensive grayscale value does not have overexposure or underexposure, that is, the identification image corresponding to the first comprehensive grayscale value can represent the characteristics of the ancient building.

[0168] Furthermore, the obtaining of the comprehensive evaluation range by using the reference grayscale image set includes:

[0169] The comprehensive grayscale value is calculated based on the reference grayscale image set and the pre-constructed comprehensive grayscale relationship, and the comprehensive evaluation range is formulated using the comprehensive grayscale value, wherein the comprehensive grayscale relationship is as follows:

[0170] ;

[0171] in, represents the comprehensive gray value, Indicates that the reference grayscale image set has A reference grayscale image, , They represent the first A reference grayscale image, The Euclidean distance corresponding to the reference grayscale image, Represents the first The mean of the grayscale values ​​corresponding to the pixels in the reference grayscale image, Represents the first The variance of the grayscale value corresponding to the pixel in the reference grayscale image, is the preset coefficient;

[0172] The scope of comprehensive assessment is as follows:

[0173] ;

[0174] in, Indicates the scope of comprehensive assessment, Indicates the preset coefficient.

[0175] It should be explained that, due to the existence of lateral overlap and heading overlap, there is a certain correlation between the reference grayscale images in the reference grayscale image set and the extracted identification image. For example, when the heading overlap is 60%, it means that there are two reference grayscale images adjacent to the extracted identification image in the route, and the overlap between these two reference grayscale images and the extracted identification image is 60%, that is, both reference grayscale images have a 60% overlap with the area captured by the extracted identification image.

[0176] Furthermore, different shooting angles and different positions may result in different results when shooting the same position. For example, when shooting a mirror, when the shooting angle is opposite to the angle at which the mirror reflects sunlight, the image captured is overexposed, and the image cannot be used to characterize the features of the mirror. Therefore, a comprehensive evaluation range is constructed using the comprehensive grayscale value, and the comprehensive evaluation range can be used to ensure that the images in the target image set are not overexposed or underexposed. Thus, the target image set can more accurately characterize the features of the outdoor structure of the ancient building. Therefore, the target image set can be used to construct a more accurate first three-dimensional point cloud map that characterizes the outdoor features of the ancient building, thereby avoiding problems such as model holes, model fragmentation, lack of texture, and uneven color when constructing a three-dimensional model of the ancient building using the first three-dimensional point cloud map.

[0177] It is understandable that the first three-dimensional point cloud map refers to a three-dimensional point cloud map of the ancient building constructed using the collected image set. The technology of obtaining the first three-dimensional point cloud map using the collected image set is existing technology and will not be repeated here.

[0178] It should be understood that the second three-dimensional point cloud map corresponds to the same ancient building as the first three-dimensional point cloud map. The difference between the first three-dimensional point cloud map and the second three-dimensional point cloud map is that the first three-dimensional point cloud map is constructed by a set of collected images, and the second three-dimensional point cloud map is acquired by a building scanner.

[0179] It is understandable that the second three-dimensional point cloud map can not only supplement the first three-dimensional point cloud map, but also measure the size, positioning relationship or assembly relationship of the internal components of the ancient building. Then, after matching the first three-dimensional point cloud map with the second three-dimensional point cloud map, the obtained optimized three-dimensional point cloud map can realize the integrated three-dimensional digitization of the interior and exterior of the ancient building. For the specific steps of matching the first three-dimensional point cloud map with the second three-dimensional point cloud map, please refer to the subsequent embodiments.

[0180] Exemplarily, a camera is used as the building scanner, and a series of stations for collecting images are set inside and outside the ancient building. The heading overlap, lateral overlap and angle of image collection are considered at each station, and image collection is performed at each station in the series of stations for collecting images to obtain indoor and outdoor collection image sets, and the second three-dimensional point cloud map is obtained using the indoor and outdoor collection image sets.

[0181] S8. Match the first three-dimensional point cloud image and the second three-dimensional point cloud image to obtain an optimized three-dimensional point cloud image, and construct an initial ancient building model based on the optimized three-dimensional point cloud image and the pre-constructed reconstruction model.

[0182] Furthermore, matching the first three-dimensional point cloud image with the second three-dimensional point cloud image to obtain an optimized three-dimensional point cloud image includes:

[0183] A target feature point set is obtained based on the first three-dimensional point cloud image, and an optimized three-dimensional point cloud image is obtained using the target feature point set, a pre-constructed feature matching matrix and the second three-dimensional point cloud image, wherein the feature matching matrix is ​​as follows:

[0184] ;

[0185] in, represents the feature matching matrix, represents the target feature point set, represents the point cloud rotation matrix, represents the point cloud translation matrix, Indicates the first The coordinates corresponding to the target feature points, Indicates the second 3D point cloud image. The coordinates corresponding to the points, represents the Euclidean norm.

[0186] It is understandable that the first three-dimensional point cloud map and the second three-dimensional point cloud map have different sources and characterize the features of the ancient building at different positions. By matching the first three-dimensional point cloud map with the second three-dimensional point cloud map, a three-dimensional point cloud map that characterizes more detailed features of the ancient building can be obtained, thereby improving the accuracy of the initial ancient building model construction. Optionally, a convolutional neural network is used to identify feature points from the first three-dimensional point cloud map. Other methods can achieve the same effect, which will not be repeated here. The matching of the first three-dimensional point cloud map and the second three-dimensional point cloud map refers to: converting the first three-dimensional point cloud map to the second three-dimensional point cloud map or converting the second three-dimensional point cloud map to the first three-dimensional point cloud map, so that the first three-dimensional point cloud map and the second three-dimensional point cloud map can be combined to jointly characterize the features of the ancient building.

[0187] It should be understood that the reconstruction model is a neural network model.

[0188] S9, performing a rendering operation on the initial ancient building model to obtain a target ancient building model, and realizing three-dimensional digitization of the real scene of the ancient building based on the target ancient building model.

[0189] It can be understood that the rendering operation refers to obtaining rendering information corresponding to the ancient building, wherein the rendering information includes but is not limited to: color, material, texture, etc. After rendering the initial ancient building model using the rendering information, the rendered initial ancient building model is more in line with the characteristics of the ancient building, so as to facilitate the subsequent use of the target ancient building model to realize monitoring, restoration and other tasks of the ancient building.

[0190] The present invention is to solve the problem described in the background technology. The present invention obtains a satellite image of an ancient building, obtains a fitting center of the ancient building based on the satellite image, constructs a reference coordinate system with the fitting center as the origin, obtains an envelope hemisphere of the ancient building based on the fitting center, and obtains a route hemisphere based on the envelope hemisphere. It can be seen that the embodiment of the present invention takes into account the possible differences in obtaining the fitting center using satellite images when obtaining the fitting center. Therefore, an image segmentation model set is used to obtain the fitting center, thereby improving the accuracy of obtaining the fitting center, and laying a foundation for accurately fitting the acquisition path for collecting ancient building images. The present invention uses the route hemisphere to obtain a reference occlusion area set. It can be seen that the present invention takes into account the possibility of other buildings or vegetation around the ancient building before formulating the acquisition path, which may cause the acquisition path to be unable to be fitted normally. Furthermore, the present invention obtains a horizontal acquisition interval angle based on a preset heading overlap, obtains an image acquisition height based on a preset lateral overlap, matches the horizontal acquisition interval angle with the image acquisition height, obtains an acquisition parameter group, summarizes the acquisition parameter group, obtains an acquisition parameter group set, and uses the acquisition parameter group set and the reference occlusion area set to confirm that the ancient building is a preset target ancient building. Then, the initial camera inclination angle is calculated based on the reference occlusion area set. It can be seen that the present invention uses the route hemisphere to realize image acquisition of the ancient building, so that the acquired image can better characterize the characteristics of the ancient building, thereby improving the accuracy of three-dimensional digitization of the ancient building, and before confirming the fitting azimuth point, it is considered that different acquisition parameter groups may have different occlusion situations. Furthermore, under certain conditions, the image collector can be adaptively adjusted so that the image collected by the image collector can better characterize the characteristics of the ancient building and improve the practicality of the embodiment of the present invention. Based on the acquisition parameter set, the present invention confirms multiple fitting acquisition orientation points in the reference coordinate system, fits an acquisition path according to the multiple fitting acquisition orientation points, sets the camera inclination angle of image acquisition to the initial camera inclination angle, drives the image collector after the camera inclination angle is set according to the acquisition path, and uses the image collector to shoot the target ancient building to obtain an acquired image set. It can be seen that the present invention also considers the problem of energy consumption of the initial path. Therefore, the acquisition path with the minimum energy consumption is obtained through the initial path. After the present invention confirms that the acquired image set is a preset target image set, a first three-dimensional point cloud map is obtained based on the target image set, a second three-dimensional point cloud map is obtained using the building scanner and the ancient building, the first three-dimensional point cloud map and the second three-dimensional point cloud map are matched to obtain an optimized three-dimensional point cloud map, an initial ancient building model is constructed based on the optimized three-dimensional point cloud map and a pre-constructed reconstruction model, and a rendering operation is performed on the initial ancient building model to obtain a target ancient building model.It can be seen that the present invention not only uses the acquisition image set to obtain the first three-dimensional point cloud map but also uses the building scanner to obtain the second three-dimensional point cloud map, and the first three-dimensional point cloud map and the second three-dimensional point cloud map have different characteristics of the ancient building, that is, the first three-dimensional point cloud map can represent the outdoor characteristics of the ancient building, and the second three-dimensional point cloud map can represent the indoor characteristics of the ancient building, and the two three-dimensional point clouds are matched, so that the matched optimized three-dimensional point cloud map can represent the indoor and outdoor characteristics of the ancient building, and the three-dimensional integrated modeling of the indoor and outdoor of the ancient building can be realized by optimizing the three-dimensional point cloud map, and the initial ancient building model constructed by using the optimized three-dimensional point cloud map is rendered, so that the rendered initial ancient building model can better represent the ancient building. Therefore, the present invention can improve the accuracy and intelligence of the three-dimensional digitization of the real scene of the ancient building.

[0191] like Figure 2 The figure shows a functional module diagram of a three-dimensional digitization device for real scenes of ancient buildings by fusing multi-source data of surveying and mapping geographic information provided by an embodiment of the present invention.

[0192] The three-dimensional digitization device 100 for real scenes of ancient buildings by fusion of surveying and mapping geographic information multi-source data of the present invention can be installed in an electronic device. According to the functions to be implemented, the three-dimensional digitization device 100 for real scenes of ancient buildings by fusion of surveying and mapping geographic information multi-source data can include a three-dimensional digitized environment confirmation module 101 for ancient buildings, an image acquisition module 102 for ancient buildings, a three-dimensional point cloud map construction module 103 for ancient buildings, and a three-dimensional digitized construction module 104 for ancient buildings. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and is stored in the memory of the electronic device.

[0193] The ancient building three-dimensional digital environment confirmation module 101 is used to receive a three-dimensional digitalization instruction and confirm a three-dimensional digital environment based on the three-dimensional digitalization instruction, wherein the three-dimensional digital environment includes: one or more ancient buildings to be modeled, an image collector and a building scanner, wherein the image collector is composed of an aircraft and a shooting unit;

[0194] The ancient building image acquisition module 102 is used to perform the following operations on each of the one or more ancient buildings:

[0195] Acquire a satellite image of the ancient building, acquire a fitting circle center of the ancient building based on the satellite image, construct a reference coordinate system with the fitting circle center as the origin, acquire an envelope hemispherical surface of the ancient building based on the fitting circle center, and acquire a route hemispherical surface based on the envelope hemispherical surface, wherein the distance between the route hemispherical surface and the envelope hemispherical surface is equal to a preset safe flight distance;

[0196] Acquire a reference occlusion region set using the route hemisphere, wherein the reference occlusion region set includes H reference occlusion regions, wherein H is an integer greater than or equal to 0;

[0197] Acquire a horizontal acquisition interval angle based on a preset heading overlap, acquire an image acquisition height based on a preset lateral overlap, match the horizontal acquisition interval angle with the image acquisition height to obtain an acquisition parameter group, summarize the acquisition parameter group to obtain an acquisition parameter group set, wherein the lowest height of the image collector is preset as the initial height;

[0198] After confirming that the ancient building is a preset target ancient building by using the acquisition parameter set and the reference occlusion area set, an initial camera inclination angle is calculated based on the reference occlusion area set;

[0199] Based on the acquisition parameter set, a plurality of fitting acquisition orientation points are confirmed in the reference coordinate system, an acquisition path is fitted according to the plurality of fitting acquisition orientation points, a camera inclination angle for image acquisition is set as an initial camera inclination angle, an image collector after the camera inclination angle is set is driven according to the acquisition path, and the target ancient building is photographed by the image collector to obtain an acquired image set, wherein the acquired image set includes a plurality of acquired images;

[0200] The ancient building three-dimensional point cloud image construction module 103 is used to obtain a first three-dimensional point cloud image based on the target image set after confirming that the collected image set is a preset target image set, and obtain a second three-dimensional point cloud image using the building scanner and the ancient building;

[0201] The ancient building three-dimensional digital construction module 104 is used to match the first three-dimensional point cloud image and the second three-dimensional point cloud image to obtain an optimized three-dimensional point cloud image, and to construct an initial ancient building model based on the optimized three-dimensional point cloud image and the pre-constructed reconstruction model;

[0202] A rendering operation is performed on the initial ancient building model to obtain a target ancient building model, and the real-scene three-dimensional digitization of the ancient building is achieved based on the target ancient building model.

[0203] In detail, the modules in the ancient building real scene three-dimensional digitization device 100 for fusion of multi-source data of surveying and mapping geographic information in the embodiment of the present invention are used in the same manner as above. Figure 1 The same technical means are used as the method for three-dimensional digitization of real scenes of ancient buildings by fusing multi-source data of surveying and mapping geographic information described in the text, and can produce the same technical effects, so I will not go into details here.

[0204] like Figure 3 , which is a schematic diagram of the structure of an electronic device for implementing a method for digitizing the real scene of ancient buildings in three dimensions by fusing multi-source data of surveying and mapping geographic information provided by an embodiment of the present invention.

[0205] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a method program for three-dimensional digitization of real scenes of ancient buildings by fusing multi-source data of surveying and mapping geographic information.

[0206] The memory 11 includes at least one type of readable storage medium, including flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the ancient building real scene three-dimensional digitization method program for multi-source data fusion of surveying and mapping geographic information, but also can be used to temporarily store data that has been output or is to be output.

[0207] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as a program for a method for 3D digitization of ancient buildings with multi-source data fusion of surveying and mapping geographic information, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0208] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0209] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0210] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0211] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0212] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0213] The program of the method for 3D digitization of ancient buildings by fusing multi-source data of surveying and mapping geographic information stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0214] receiving a three-dimensional digitization instruction, and confirming a three-dimensional digitization environment based on the three-dimensional digitization instruction, wherein the three-dimensional digitization environment includes: one or more ancient buildings to be modeled, an image collector and a building scanner, wherein the image collector is composed of an aircraft and a shooting unit;

[0215] Perform the following operations on each of one or more ancient buildings:

[0216] Acquire a satellite image of the ancient building, acquire a fitting circle center of the ancient building based on the satellite image, construct a reference coordinate system with the fitting circle center as the origin, acquire an envelope hemispherical surface of the ancient building based on the fitting circle center, and acquire a route hemispherical surface based on the envelope hemispherical surface, wherein the distance between the route hemispherical surface and the envelope hemispherical surface is equal to a preset safe flight distance;

[0217] Acquire a reference occlusion region set using the route hemisphere, wherein the reference occlusion region set includes H reference occlusion regions, wherein H is an integer greater than or equal to 0;

[0218] Acquire a horizontal acquisition interval angle based on a preset heading overlap, acquire an image acquisition height based on a preset lateral overlap, match the horizontal acquisition interval angle with the image acquisition height to obtain an acquisition parameter group, summarize the acquisition parameter group to obtain an acquisition parameter group set, wherein the lowest height of the image collector is preset as the initial height;

[0219] After confirming that the ancient building is a preset target ancient building by using the acquisition parameter set and the reference occlusion area set, an initial camera inclination angle is calculated based on the reference occlusion area set;

[0220] Based on the acquisition parameter set, a plurality of fitting acquisition orientation points are confirmed in the reference coordinate system, an acquisition path is fitted according to the plurality of fitting acquisition orientation points, a camera inclination angle for image acquisition is set as an initial camera inclination angle, an image collector after the camera inclination angle is set is driven according to the acquisition path, and the target ancient building is photographed by the image collector to obtain an acquired image set, wherein the acquired image set includes a plurality of acquired images;

[0221] After confirming that the acquired image set is a preset target image set, a first three-dimensional point cloud image is acquired based on the target image set, and a second three-dimensional point cloud image is acquired using the building scanner and the ancient building;

[0222] Matching the first three-dimensional point cloud image with the second three-dimensional point cloud image to obtain an optimized three-dimensional point cloud image, and constructing an initial ancient building model based on the optimized three-dimensional point cloud image and the pre-constructed reconstruction model;

[0223] A rendering operation is performed on the initial ancient building model to obtain a target ancient building model, and the real-scene three-dimensional digitization of the ancient building is achieved based on the target ancient building model.

[0224] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0225] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0226] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0227] receiving a three-dimensional digitization instruction, and confirming a three-dimensional digitization environment based on the three-dimensional digitization instruction, wherein the three-dimensional digitization environment includes: one or more ancient buildings to be modeled, an image collector and a building scanner, wherein the image collector is composed of an aircraft and a shooting unit;

[0228] Perform the following operations on each of one or more ancient buildings:

[0229] Acquire a satellite image of the ancient building, acquire a fitting circle center of the ancient building based on the satellite image, construct a reference coordinate system with the fitting circle center as the origin, acquire an envelope hemispherical surface of the ancient building based on the fitting circle center, and acquire a route hemispherical surface based on the envelope hemispherical surface, wherein the distance between the route hemispherical surface and the envelope hemispherical surface is equal to a preset safe flight distance;

[0230] Acquire a reference occlusion region set using the route hemisphere, wherein the reference occlusion region set includes H reference occlusion regions, wherein H is an integer greater than or equal to 0;

[0231] Acquire a horizontal acquisition interval angle based on a preset heading overlap, acquire an image acquisition height based on a preset lateral overlap, match the horizontal acquisition interval angle with the image acquisition height to obtain an acquisition parameter group, summarize the acquisition parameter group to obtain an acquisition parameter group set, wherein the lowest height of the image collector is preset as the initial height;

[0232] After confirming that the ancient building is a preset target ancient building by using the acquisition parameter set and the reference occlusion area set, an initial camera inclination angle is calculated based on the reference occlusion area set;

[0233] Based on the acquisition parameter set, a plurality of fitting acquisition orientation points are confirmed in the reference coordinate system, an acquisition path is fitted according to the plurality of fitting acquisition orientation points, a camera inclination angle for image acquisition is set as an initial camera inclination angle, an image collector after the camera inclination angle is set is driven according to the acquisition path, and the target ancient building is photographed by the image collector to obtain an acquired image set, wherein the acquired image set includes a plurality of acquired images;

[0234] After confirming that the acquired image set is a preset target image set, a first three-dimensional point cloud image is acquired based on the target image set, and a second three-dimensional point cloud image is acquired using the building scanner and the ancient building;

[0235] Matching the first three-dimensional point cloud image with the second three-dimensional point cloud image to obtain an optimized three-dimensional point cloud image, and constructing an initial ancient building model based on the optimized three-dimensional point cloud image and the pre-constructed reconstruction model;

[0236] A rendering operation is performed on the initial ancient building model to obtain a target ancient building model, and the real-scene three-dimensional digitization of the ancient building is achieved based on the target ancient building model.

[0237] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, and actual implementation may have other division methods.

[0238] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0239] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0240] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0241] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for 3D digitization of ancient building scenes by fusing multi-source data of surveying and mapping geographic information, characterized in that: The method comprises: receiving a three-dimensional digitization instruction, and confirming a three-dimensional digitization environment based on the three-dimensional digitization instruction, wherein the three-dimensional digitization environment includes: one or more ancient buildings to be modeled, an image collector and a building scanner, wherein the image collector is composed of an aircraft and a shooting unit; Perform the following operations on each of the one or more ancient buildings: Acquire a satellite image of the ancient building, acquire a fitting circle center of the ancient building based on the satellite image, construct a reference coordinate system with the fitting circle center as the origin, acquire an envelope hemispherical surface of the ancient building based on the fitting circle center, and acquire a route hemispherical surface based on the envelope hemispherical surface, wherein the distance between the route hemispherical surface and the envelope hemispherical surface is equal to a preset safe flight distance; Acquire a reference occlusion region set using the route hemisphere, wherein the reference occlusion region set includes H reference occlusion regions, wherein H is an integer greater than or equal to 0; Acquire a horizontal acquisition interval angle based on a preset heading overlap, acquire an image acquisition height based on a preset lateral overlap, match the horizontal acquisition interval angle with the image acquisition height to obtain an acquisition parameter group, summarize the acquisition parameter group to obtain an acquisition parameter group set, wherein the lowest height of the image collector is preset as the initial height; After confirming that the ancient building is a preset target ancient building by using the acquisition parameter set and the reference occlusion area set, an initial camera inclination angle is calculated based on the reference occlusion area set; Based on the acquisition parameter set, a plurality of fitting acquisition orientation points are confirmed in the reference coordinate system, an acquisition path is fitted according to the plurality of fitting acquisition orientation points, a camera inclination angle for image acquisition is set as an initial camera inclination angle, an image collector after the camera inclination angle is set is driven according to the acquisition path, and the target ancient building is photographed by the image collector to obtain an acquired image set, wherein the acquired image set includes a plurality of acquired images; After confirming that the acquired image set is a preset target image set, a first three-dimensional point cloud image is acquired based on the target image set, and a second three-dimensional point cloud image is acquired using the building scanner and the ancient building; Matching the first three-dimensional point cloud image with the second three-dimensional point cloud image to obtain an optimized three-dimensional point cloud image, and constructing an initial ancient building model based on the optimized three-dimensional point cloud image and the pre-constructed reconstruction model; A rendering operation is performed on the initial ancient building model to obtain a target ancient building model, and the real-scene three-dimensional digitization of the ancient building is achieved based on the target ancient building model.

2. The method for 3D digitization of ancient building scenes by fusion of multi-source data of surveying and mapping geographic information as claimed in claim 1, characterized in that: The step of obtaining the fitting center of the ancient building based on the satellite image includes: Performing a grayscale operation on the satellite image to obtain a grayscale image; An image segmentation model set for segmenting an image is obtained, wherein the image segmentation model set includes a plurality of image segmentation models, image segmentation models are sequentially extracted from the image segmentation model set, and the following operations are performed on the extracted image segmentation models: Performing a segmentation operation on the grayscale image based on the extracted image segmentation model to obtain an initial building image; Summarizing the initial building images to obtain an initial building image set; Match each initial building image in the initial building image set to a pre-constructed image coordinate system to obtain a mapping image; Extract pixel points from the mapped image in sequence, and perform the following operations on the extracted pixel points: The mapping times are obtained based on the extracted pixel points, and the mapping frequency is calculated using the mapping times. The calculation formula is as follows: ； in, represents the mapping frequency, Indicates the number of mappings, Represents the number of image segmentation models in the image segmentation model set; comparing the mapped frequency with a preset frequency threshold; If the mapping frequency is greater than or equal to the frequency threshold, the pixel point corresponding to the mapping frequency is retained; Otherwise, the pixel points corresponding to the mapping frequency are removed from the mapping image; The retained pixel points are aggregated to obtain a target pixel point set, and the target pixel point set is used to obtain the fitting center.

3. The method for 3D digitization of ancient building scenes by fusion of multi-source data of surveying and mapping geographic information as claimed in claim 2, characterized in that: The method of using the acquisition parameter set and the reference occlusion area set to confirm that the ancient building is a preset target ancient building includes: Sorting the acquisition parameter groups in the acquisition parameter group set in the order of image acquisition height from small to large to obtain an acquisition parameter group sequence; Extracting acquisition parameter groups from the acquisition parameter group sequence in sequence, and performing the following operations on the extracted acquisition parameter groups: Acquire an initial occlusion angle set based on the image acquisition height corresponding to the extracted acquisition parameter group and the reference occlusion area set, wherein the initial occlusion angle set includes L initial occlusion angles, wherein L is an integer greater than or equal to 0; Acquire a target occlusion angle based on the initial occlusion angle set, wherein the target occlusion angle is the largest initial occlusion angle in the initial occlusion angle set; Comparing the target occlusion angle with the horizontal acquisition interval angle corresponding to the extracted acquisition parameter group; If the target occlusion angle is less than the horizontal acquisition interval angle corresponding to the extracted acquisition parameter group, the ancient building is confirmed to be the target ancient building, and the initial camera inclination is calculated using a pre-constructed inclination evaluation relationship, wherein the inclination evaluation relationship is as follows: ； in, is the initial camera tilt angle, Indicates the height of the image collector. Indicates the radius of the route hemisphere; If there is only one target occlusion angle greater than or equal to the horizontal acquisition interval angle corresponding to the extracted acquisition parameter group and the image acquisition height corresponding to the extracted acquisition parameter group is the initial height, then the target horizontal acquisition interval angle is obtained based on the acquisition parameter group sequence, wherein the target horizontal acquisition interval angle is the horizontal acquisition interval angle corresponding to the second acquisition parameter group in the acquisition parameter group sequence; Based on the target horizontal acquisition interval angle, a height value corresponding to the target occlusion interval angle is centrally confirmed in the reference occlusion area, wherein the target occlusion interval angle is equal to the target horizontal acquisition interval angle; If the height value is less than or equal to the preset height threshold, the height value is used as the initial height, and the process returns to the step of obtaining the image acquisition height based on the preset lateral overlap; Otherwise, it is confirmed that the ancient building is not the target ancient building.

4. The method for 3D digitization of ancient building real scene by fusion of multi-source data of surveying and mapping geographic information as claimed in claim 3, characterized in that: The step of fitting a collection path according to a plurality of fitting collection orientation points includes: A fitting model set for fitting the path is obtained, wherein the fitting model set includes a plurality of fitting models, fitting models are sequentially extracted from the fitting model set, and the following operations are performed on the extracted fitting models: An initial path is acquired using the extracted fitting model and a plurality of fitting acquisition azimuth points, wherein the initial path is composed of a plurality of first paths and K second paths, K is an integer greater than or equal to 0, and a start point and an end point of the initial path are preset; The evaluation energy consumption is calculated based on the initial path and the pre-constructed energy consumption evaluation relationship, the evaluation energy consumption is summarized to obtain an evaluation energy consumption set, and the collection path is confirmed based on the evaluation energy consumption set, wherein the collection path is the initial path corresponding to the smallest evaluation energy consumption in the evaluation energy consumption set.

5. The method for 3D digitization of ancient building scenes by fusion of multi-source data of surveying and mapping geographic information as claimed in claim 4, characterized in that: The energy consumption evaluation relationship is as follows: ； in, represents the energy consumption evaluation, Indicates that the image collector is the first one in multiple first paths The average energy consumption of the first path is Indicates the first path among multiple first paths The distance of the first path, Indicates that the image collector is the first one in multiple first paths The average speed of the first path, Indicates that the first path has indivual, Indicates that the image collector is The second path The average energy consumption of the second path is express The second path The distance of the second path, The image collector is shown in The second path The average speed of the second path is Indicates shared A second path.

6. The method for 3D digitization of ancient building scenes by fusion of multi-source data of surveying and mapping geographic information as claimed in claim 5, characterized in that: The step of confirming that the acquired image set is a preset target image set includes: Extracting collected images from the collected image set in sequence, and performing the following operations on the extracted collected images: Confirming acquisition coordinates based on the extracted acquisition image, the reference coordinate system and the plurality of fitted acquisition orientation points, and performing a marking operation on the acquisition image using the acquisition coordinates to obtain a marked image; Aggregating the identification images to obtain an identification image set; Extract logo images from the logo image set in sequence, and perform the following operations on the extracted logo images: Based on the acquisition coordinates corresponding to the extracted identification image, a reference image set is retrieved from the identification image set, wherein the reference image set includes a plurality of reference images, and the Euclidean distances between the acquisition coordinates corresponding to the reference images and the acquisition coordinates corresponding to the extracted identification image are both less than or equal to a preset distance threshold; Performing a grayscale operation on the extracted identification image to obtain an identification grayscale image, and obtaining a reference grayscale image set using a reference image set, wherein the reference grayscale image set includes a plurality of reference grayscale images, and the reference grayscale images correspond to the reference images one by one; The first comprehensive grayscale value is calculated based on the identification grayscale image and the pre-constructed comprehensive grayscale relationship formula, wherein the comprehensive grayscale relationship formula is as follows: ； in, represents the first integrated gray value, , are all preset coefficients. Indicates the mean value of the grayscale value corresponding to the pixel in the grayscale image. Indicates the variance of the grayscale value corresponding to the pixel in the grayscale image; Using a reference grayscale image set to obtain a comprehensive evaluation range; If the first comprehensive grayscale value corresponding to the identification image satisfies the comprehensive evaluation range, the acquired image set is confirmed to be the target image set.

7. The method for 3D digitization of ancient building scenes by fusion of multi-source data of surveying and mapping geographic information as claimed in claim 6, characterized in that: The method of obtaining a comprehensive evaluation range by using a reference grayscale image set includes: The comprehensive grayscale value is calculated based on the reference grayscale image set and the pre-constructed comprehensive grayscale relationship, and the comprehensive evaluation range is formulated using the comprehensive grayscale value, wherein the comprehensive grayscale relationship is as follows: ； in, represents the comprehensive gray value, Indicates that the reference grayscale image set has A reference grayscale image, , They represent the first A reference grayscale image, The Euclidean distance corresponding to the reference grayscale image, Represents the first The mean of the grayscale values ​​corresponding to the pixels in the reference grayscale image, Represents the first The variance of the grayscale value corresponding to the pixel in the reference grayscale image, is the preset coefficient; The scope of comprehensive assessment is as follows: ； in, Indicates the scope of comprehensive assessment, Indicates the preset coefficient.

8. The method for 3D digitization of ancient building scenes by fusion of multi-source data of surveying and mapping geographic information as claimed in claim 7, characterized in that: The matching of the first three-dimensional point cloud image and the second three-dimensional point cloud image to obtain an optimized three-dimensional point cloud image includes: A target feature point set is obtained based on the first three-dimensional point cloud image, and an optimized three-dimensional point cloud image is obtained using the target feature point set, a pre-constructed feature matching matrix and the second three-dimensional point cloud image, wherein the feature matching matrix is ​​as follows: ； in, represents the feature matching matrix, represents the target feature point set, represents the point cloud rotation matrix, represents the point cloud translation matrix, Indicates the first The coordinates corresponding to the target feature points, Indicates the second 3D point cloud image. The coordinates corresponding to the points, represents the Euclidean norm.

9. The method for 3D digitization of ancient building scenes by fusion of multi-source data of surveying and mapping geographic information as claimed in claim 8, characterized in that: The reconstruction model is a neural network model.

10. A three-dimensional digitization device for ancient building real scene by integrating multi-source data of surveying and mapping geographic information, characterized in that: The device comprises: The ancient building three-dimensional digital environment confirmation module is used to receive a three-dimensional digital instruction and confirm a three-dimensional digital environment based on the three-dimensional digital instruction, wherein the three-dimensional digital environment includes: one or more ancient buildings to be modeled, an image collector and a building scanner, wherein the image collector is composed of an aircraft and a shooting unit; The ancient building image acquisition module is used to perform the following operations on each of one or more ancient buildings: Acquire a satellite image of the ancient building, acquire a fitting circle center of the ancient building based on the satellite image, construct a reference coordinate system with the fitting circle center as the origin, acquire an envelope hemispherical surface of the ancient building based on the fitting circle center, and acquire a route hemispherical surface based on the envelope hemispherical surface, wherein the distance between the route hemispherical surface and the envelope hemispherical surface is equal to a preset safe flight distance; Acquire a reference occlusion region set using the route hemisphere, wherein the reference occlusion region set includes H reference occlusion regions, wherein H is an integer greater than or equal to 0; Acquire a horizontal acquisition interval angle based on a preset heading overlap, acquire an image acquisition height based on a preset lateral overlap, match the horizontal acquisition interval angle with the image acquisition height to obtain an acquisition parameter group, summarize the acquisition parameter group to obtain an acquisition parameter group set, wherein the lowest height of the image collector is preset as the initial height; After confirming that the ancient building is a preset target ancient building by using the acquisition parameter set and the reference occlusion area set, an initial camera inclination angle is calculated based on the reference occlusion area set; Based on the acquisition parameter set, a plurality of fitting acquisition orientation points are confirmed in the reference coordinate system, an acquisition path is fitted according to the plurality of fitting acquisition orientation points, a camera inclination angle for image acquisition is set as an initial camera inclination angle, an image collector after the camera inclination angle is set is driven according to the acquisition path, and the target ancient building is photographed by the image collector to obtain an acquired image set, wherein the acquired image set includes a plurality of acquired images; The ancient building three-dimensional point cloud map construction module is used to obtain a first three-dimensional point cloud map based on the target image set after confirming that the collected image set is a preset target image set, and obtain a second three-dimensional point cloud map using the building scanner and the ancient building; The ancient building three-dimensional digital construction module is used to match the first three-dimensional point cloud image with the second three-dimensional point cloud image to obtain an optimized three-dimensional point cloud image, and to construct an initial ancient building model based on the optimized three-dimensional point cloud image and the pre-constructed reconstruction model; A rendering operation is performed on the initial ancient building model to obtain a target ancient building model, and the real-scene three-dimensional digitization of the ancient building is achieved based on the target ancient building model.

Images