Method, apparatus, computer device, and readable storage medium for generating a three-dimensional model

Abstract

An embodiment of the present application discloses a method, device, computer device, and readable storage medium for generating a three-dimensional model. The method includes obtaining multiple sets of three-line array pushbroom data within a target area; extracting corresponding points between each set of the three-line array pushbroom data, and fusing the corresponding points to obtain multiple sets of fused points; fusing and connecting each set of the three-line array pushbroom data according to the fused points to obtain a corresponding stereo image pair set for the target area; extracting white film buildings corresponding to the stereo image pair set; constructing a textureless model of the target area according to multiple sets of the three-line array pushbroom data, and attaching the white film buildings to the textureless model to generate the three-dimensional model. The method for generating a three-dimensional model provided by the embodiment of the present application can improve the accuracy of model generation.

Description

Technical Field

[0001] This application relates to the technical field of model generation, and particularly to a method, apparatus, computer device, and readable storage medium for generating a three-dimensional model. Background Art

[0002] In the prior art, three-dimensional models are mainly generated through image matching, aerial triangulation, multi-view image dense matching, and texture mapping. Due to the large number of random factors in the generation process, the accuracy of the generated models is relatively low. Therefore, how to improve the accuracy of model generation is a technical problem that urgently needs to be solved at present. Summary of the Invention

[0003] One of the purposes of this application is to provide a method, apparatus, computer device, and readable storage medium for generating a three-dimensional model to solve the problem of how to improve the accuracy of model generation.

[0004] In a first aspect, an embodiment of this application provides a method for generating a three-dimensional model, including:

[0005] Obtain multiple groups of three-line array pushbroom data within a target area;

[0006] Extract corresponding points between each group of the three-line array pushbroom data, and fuse the corresponding points to obtain multiple groups of fused points;

[0007] Fuse and connect multiple groups of the three-line array pushbroom data according to the fused points to obtain a stereo image pair group corresponding to the target area;

[0008] Extract the white film building corresponding to the stereo image pair group;

[0009] Construct a textureless model of the target area according to multiple groups of the three-line array pushbroom data, and attach the white film building to the textureless model to generate the three-dimensional model.

[0010] In an optional implementation manner, the constructing a textureless model of the target area according to multiple groups of the three-line array pushbroom data includes:

[0011] Determine the terrain within the target area according to multiple groups of the three-line array pushbroom data;

[0012] Construct a rough model of the target area;

[0013] Filter the rough model to obtain a filtered rough model;

[0014] Fill the filtered rough model according to the terrain to obtain the textureless model of the target area.

[0015] In an optional implementation manner, the constructing a rough model of the target area includes:

[0016] Determine the range of the grid and construct the grid according to the preset parameters;

[0017] Construct a rough model of the target area based on the range of the grid and the grid.

[0018] In an alternative embodiment, the terrain includes urban areas and mountainous areas. Filling the filtered rough model according to the terrain includes:

[0019] If the terrain is the urban area, fill the filtered rough model by using the minimum value filling method;

[0020] If the terrain is the mountainous area, fill the filtered rough model by using the smooth filling method.

[0021] In an alternative embodiment, extracting the white film buildings corresponding to the stereo image pair group includes:

[0022] Construct a co-occurrence matrix corresponding to the stereo image pair group according to the grayscale image corresponding to the stereo image pair group, wherein the co-occurrence matrix is obtained by statistically analyzing the situation where two pixels maintaining a preset distance on the grayscale image respectively have preset grayscales;

[0023] Calculate the eigenvalues of the co-occurrence matrix according to the co-occurrence matrix, and use the eigenvalues as the white film buildings corresponding to the stereo image pair group.

[0024] In an alternative embodiment, after obtaining the stereo image pair group corresponding to the target area, it further includes:

[0025] Obtain the information of multiple image control points arranged in the target area;

[0026] Perform precision measurement of the fusion points on the information of multiple image control points and the fusion points by using measurement solution to obtain the precision of the target area.

[0027] In an alternative embodiment, extracting the corresponding same-name points of each group of the three-line array pushbroom data includes:

[0028] Detect multiple groups of the three-line array pushbroom data according to the Hessian matrix to obtain the initial same-name points corresponding to multiple groups of the three-line array pushbroom data, wherein the Hessian matrix is a square matrix composed of the second-order partial derivatives of a multivariate function;

[0029] Perform non-maximum suppression on the initial same-name points to obtain the same-name points of each group of the three-line array pushbroom data.

[0030] In a second aspect, an embodiment of the present application provides a three-dimensional model generation device, including:

[0031] An acquisition module, configured to acquire multiple groups of three-line array pushbroom data within a target area;

[0032] A fusion module, configured to extract corresponding points between each group of the three-line array pushbroom data, and fuse the corresponding points to obtain multiple groups of fused points;

[0033] A connection module, configured to perform fusion connection on multiple groups of the three-line array pushbroom data according to the fused points to obtain a stereo image pair group corresponding to the target area;

[0034] An extraction module, configured to extract white film buildings corresponding to the stereo image pair group;

[0035] A generation module, configured to construct a textureless model of the target area according to multiple groups of the three-line array pushbroom data, and attach the white film buildings to the textureless model to obtain the three-dimensional model.

[0036] In a third aspect, an embodiment of the present application provides a computer device, which includes a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the method for generating a three-dimensional model as described in the first aspect is implemented.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for generating a three-dimensional model as described in the first aspect is implemented.

[0038] The method, device, computer device, and readable storage medium for generating a three-dimensional model provided by the embodiments of the present application. The method includes acquiring multiple groups of three-line array pushbroom data within a target area; extracting corresponding points between each group of the three-line array pushbroom data, and fusing the corresponding points to obtain multiple groups of fused points; performing fusion connection on multiple groups of the three-line array pushbroom data according to the fused points to obtain a stereo image pair group corresponding to the target area; extracting white film buildings corresponding to the stereo image pair group; constructing a textureless model of the target area according to multiple groups of the three-line array pushbroom data, and attaching the white film buildings to the textureless model to generate the three-dimensional model. By the method of corresponding point fusion, the accuracy of model generation can be improved. At the same time, through the establishment of a textureless model of the target area and the method of pasting white film buildings, the generation of the three-dimensional model can be realized automatically and quickly, and the generation efficiency of the three-dimensional model can be improved. Description of the Drawings

[0039] To more clearly illustrate the technical solutions of the present application, the following will briefly introduce the accompanying drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and should not be regarded as limiting the protection scope of the present application. In each of the drawings, similar components are numbered similarly.

[0040] Figure 1 It shows a schematic block diagram of the steps of a method for generating a three-dimensional model provided by an embodiment of the present application;

[0041] Figure 2 It shows the three-line array pushbroom data before preprocessing provided by an embodiment of the present application;

[0042] Figure 3 It shows the three-line array pushbroom data after preprocessing provided by an embodiment of the present application;

[0043] Figure 4 It shows the three-line array pushbroom data after the automatic adjustment of 16-bit data provided by an embodiment of the present application;

[0044] Figure 5 It shows a schematic diagram of the stereo pair corresponding to the three-line array pushbroom data within the target area provided by an embodiment of the present application;

[0045] Figure 6 It shows a schematic diagram of the image control points arranged within the target area provided by an embodiment of the present application;

[0046] Figure 7 It shows a schematic diagram of the checkpoint residuals provided by an embodiment of the present application;

[0047] Figure 8 It shows a schematic diagram of the three-dimensional model provided by an embodiment of the present application;

[0048] Figure 9 It shows a schematic diagram of the rough model within the target area provided by an embodiment of the present application;

[0049] Figure 10 It shows a schematic diagram of the rough model after filtering with mountain filling provided by an embodiment of the present application;

[0050] Figure 11 It shows a schematic block diagram of the structure of a device for generating a three-dimensional model provided by an embodiment of the present application. Specific Embodiments

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0052] The components of the embodiments of the present application that are usually described and illustrated in the accompanying drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the claimed present application, but merely represents selected embodiments of the present application. All other embodiments obtained by those skilled in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0053] Hereinafter, the terms "including", "having" and their cognates that can be used in various embodiments of the present application are only intended to represent specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be construed as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or the possibility of adding one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0054] In addition, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0055] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as that commonly understood by those of ordinary skill in the art to which the various embodiments of the present application belong. The terms (such as those defined in a commonly used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning unless clearly defined in the various embodiments of the present application.

[0056] Embodiment 1

[0057] Please refer to Figure 1 , Figure 1 which shows a schematic block diagram of the steps of a method for generating a three-dimensional model provided by an embodiment of the present application.

[0058] As Figure 1 shown, a method for generating a three-dimensional model provided by an embodiment of the present application can be applied to a server, and the method includes S110 to S150.

[0059] S110: Obtain multiple sets of three-line array pushbroom data within a target area.

[0060] In this embodiment, the three-line array pushbroom has 12 charge coupled device (CCD) line pairs, which are arranged in three groups according to the front view, top view, and rear view. The front view group includes a single panchromatic CCD line pair. The top view group includes a pair of panchromatic CCD line pairs staggered by half a pixel and one CCD line pair each for red, green, blue, and near-infrared. The rear view group includes a single panchromatic CCD line pair and one CCD line pair each for red, green, blue, and near-infrared. Among them, the charge coupled device can convert an optical image into a digital signal. The front view angle is 27°, the top view angle is 0°, and the rear view angle is 14°. The three-dimensional array pushbroom data is the data obtained by performing three-dimensional array pushbroom, including navigation and positioning information and camera file information. Among them, the navigation and positioning information is the coordinate information of the three-line array pushbroom data, and the camera file information includes the model, pixel size, pixels, and focal length of the camera.

[0061] Furthermore, calculated according to the base-height ratio of the stereo image pairs formed by each viewing angle, the front view and the rear view form a stereo with the highest accuracy. However, considering that the top view RGB data is required for orthorectification, generally when loading data, it is necessary to load the top view RGB data and the panchromatic band (Pan) of another viewing angle, or it is necessary to load the top view RGB data and the G-band data. This can effectively save the data loading time, and the quality of the coarse model extracted from RGB and the panchromatic band is better than that of the coarse model extracted from the panchromatic band and the panchromatic band. Among them, the panchromatic band generally refers to a single band of about 0.5 to 0.75 microns, that is, the visible light band starting from green. The G-band refers to the electromagnetic frequency between 220 GHz and 325 GHz.

[0062] It can be understood that, considering that the quality of the three-line array pushbroom data may vary due to aerial photography environment, weather, and other uncertain factors, the three-line array pushbroom data can also be preprocessed. The preprocessing methods include 16-bit data automatic adjustment, color adjustment, brightness, contrast, gamma value, etc. Please refer to Figure 2 and Figure 3 , Figure 2 shows the three-line array pushbroom data before preprocessing provided by the embodiment of the present application, Figure 3 shows the three-line array pushbroom data after preprocessing provided by the embodiment of the present application. Obviously, the three-line array pushbroom data after preprocessing is clearer than that before preprocessing.

[0063] Specifically, taking the 16-bit data automatic adjustment in preprocessing as an example, when the three-line array pushbroom data is acquired, the loaded data can simultaneously include 16-bit data and 8-bit data. In order to retain more color recognition, imaging is performed with a 16-bit color depth. After the three-line pushbroom data is acquired, the data color appears as pure black. It is necessary to perform 16-bit data automatic adjustment before the normal color of the data can be displayed and the next operation can be carried out. When adjusting the color of the three-line array pushbroom data, it is not necessary to adjust the three-line array pushbroom data to a suitable color in the 16-bit data automatic adjustment for each line pair. Taking non-overexposure as the criterion, the color can be darker. The three-line array pushbroom data can also be adjusted to a suitable color through at least one curve adjustment. For the same line pair, the adjusted color is consistent. For the three-line array pushbroom data of the same flight mission, the camera calibration and light are relatively consistent. Therefore, the quality and color of the three-line pushbroom data of the same flight mission are relatively consistent. Therefore, the template after the 16-bit data automatic adjustment of the three-line pushbroom data is applicable to the three-line pushbroom data of the same flight mission and not applicable to the three-line pushbroom data of other flight missions. For the three-line pushbroom data of different flight missions, the templates need to be adjusted separately for processing. Please refer to Figure 4 , Figure 4 which shows the three-line array pushbroom data after the 16-bit data automatic adjustment provided by the embodiment of the present application.

[0064] It should be noted that the three-line array pushbroom data obtained from the camera belongs to L0 (level 0 data) level data. In order to improve the accuracy of the three-line array pushbroom data and the convenience of operation, processing starts from L1 (level 1 data) level data. During the data preparation process, it is necessary to reorganize and specify the path files, copy the necessary data in any one of the forms of.ads,.odf,.odf.obj,.sup,.tif to the data preparation folder, and correct the file paths. Among them, L0 level data is the data directly detected by the spaceborne detector received by the ground system and has not been processed, and L1 level data is the basic data obtained through quality inspection, image positioning, and radiometric calibration processing.

[0065] S120: Extract the homologous points between each group of the three-line array pushbroom data, and fuse the homologous points to obtain multiple groups of fused points.

[0066] In this embodiment, by extracting the homologous points between each group of the three-line array pushbroom data and fusing the homologous points to obtain multiple groups of fused points, the accuracy of model generation can be improved.

[0067] In an optional implementation manner, the extraction of the homologous points of each group of the three-line array pushbroom data includes:

[0068] Detect multiple groups of the pushbroom data of the three-line array according to the Hessian matrix to obtain initial corresponding points corresponding to multiple groups of the pushbroom data of the three-line array, where the Hessian matrix is a square matrix composed of second-order partial derivatives of a multivariate function;

[0069] Perform non-maximum suppression on the initial corresponding points to obtain corresponding points of each group of the pushbroom data of the three-line array.

[0070] Specifically, the Hessian matrix is a square matrix composed of second-order partial derivatives of a multivariate function, which is used to describe the local curvature of the function. The process of non-maximum suppression (NMS) is as follows: sort the initial corresponding points according to the confidence score; select the initial corresponding point with the highest confidence and add it to the final output list, and delete it from the initial corresponding point list; calculate the IoU (Intersection over Union) between the initial corresponding point with the highest confidence and the initial corresponding points; delete the initial corresponding points with IoU greater than the threshold; repeat the above process until the initial corresponding point list is empty. Among them, IoU is a standard for measuring the accuracy of detecting corresponding objects in a specific dataset.

[0071] In another alternative embodiment, the SIFT matching method combining the nearest neighbor distance and the second nearest neighbor distance can be used. Take the first preset number of SIFI key points of the first group of the pushbroom data of the three-line array, and find the first second preset number of key points with the closest Euclidean distance to them in the second group of the pushbroom data of the three-line array. Among the first second preset number of key points, if the ratio of the closest distance to the second closest distance is less than the preset threshold, extract this pair of key points and use this pair of key points as corresponding points. In this way, while ensuring the fusion speed, the accuracy and feasibility of the fusion can be improved.

[0072] S130: Perform fusion connection on multiple groups of the pushbroom data of the three-line array according to the fusion points to obtain a group of stereo image pairs corresponding to the target area.

[0073] In this embodiment, for multiple groups of the pushbroom data of the three-line array, the areas where the fusion points of two adjacent groups of the pushbroom data of the three-line array are located should be overlapping and consistent. Therefore, the fusion points of any two groups of the pushbroom data of the three-line array can realize the fusion connection of multiple groups of the pushbroom data of the three-line array in the target area, so as to obtain the stereo image pairs of the pushbroom data of the three-line array. Please refer to Figure 5 , Figure 5 which shows a schematic diagram of the stereo image pairs corresponding to the pushbroom data of the three-line array in the target area provided by the embodiment of the present application.

[0074] In an alternative embodiment, after obtaining the stereo image pair group corresponding to the target area, the method further includes:

[0075] Obtaining information of a plurality of image control points arranged in the target area;

[0076] Performing accuracy measurement of the fusion points by using measurement solution on the information of the plurality of image control points and the fusion points, to obtain the accuracy of the target area.

[0077] Specifically, a plurality of control points are arranged in the target area through field operations, and the three-dimensional coordinates and azimuth of the control points can be obtained through field measurement. Please refer to Figure 6 , Figure 6 which shows a schematic diagram of the image control points arranged in the target area provided by the embodiment of the present application. As shown in Figure 6 , 1, 2, 3, 4, 5, and 6 respectively represent the first image control point, the second image control point, the third image control point, the fourth image control point, the fifth image control point, and the sixth image control point. The information of the image control points includes the three-dimensional coordinates, coordinate accuracy, and standard deviation of the image control points. It can be understood that when selecting image control points, image control points on the roof or higher than the ground should be avoided to prevent the influence of ground object changes on the overall accuracy.

[0078] In an alternative embodiment, the preset formula corresponding to the measurement solution is:

[0079]

[0080] where represents the j-th feature point on the i-th frame. X j represents the maximum likelihood estimate value of the three-dimensional coordinates; P i represents the camera transformation matrix.

[0081] It can be understood that according to the distribution of the image control points in the target area, appropriate image control points are selected as check points to check the accuracy of the target area. Performing accuracy measurement of the fusion points by using measurement solution on the information of the plurality of image control points and the fusion points to obtain a measurement solution report. By finding the check point residuals in the measurement solution report, the accuracy status of the target area can be judged according to the check point residuals in the measurement solution report. If there are points with relatively large residuals, manual inspection can be carried out to confirm whether there are measurement errors in the check points. If the residuals of the check points are within the preset range, it is determined that the check points are normal; if the residuals of the check points are not within the preset range, it is determined that the check points are abnormal.

[0082] Please refer to Figure 7 , Figure 7The figure shows a schematic diagram of the checkpoint residuals provided by the embodiments of the present application. The residual of the checkpoint Xm - Xg is 0.007, the residual of the checkpoint Ym - Yg is 0.168, and the residual of the checkpoint Zm - Zg is 0.360.

[0083] S140: Extract the white film building corresponding to the stereo image pair group.

[0084] In this embodiment, the white film building is obtained by stretching the building outline according to a preset height.

[0085] In an alternative embodiment, the extracting the white film building corresponding to the stereo image pair group includes:

[0086] According to the grayscale images corresponding to the stereo image pair group, construct the co-occurrence matrix corresponding to the stereo image pair group, where the co-occurrence matrix is obtained by statistically analyzing the situation where two pixels with a preset distance on the grayscale image respectively have a preset grayscale;

[0087] According to the co-occurrence matrix, calculate the eigenvalues of the co-occurrence matrix, and use the eigenvalues as the white film building corresponding to the stereo image pair group.

[0088] Specifically, the co-occurrence matrix can reflect the comprehensive information of the image grayscale regarding direction, adjacent interval, and change amplitude, and is the basis for analyzing the local patterns and arrangement rules of the image. In this embodiment, according to the co-occurrence matrix, calculate some of the eigenvalues of the co-occurrence matrix, and use the some of the eigenvalues as the white film building corresponding to the stereo image pair group, where the some of the eigenvalues represent the texture features of the image.

[0089] S150: According to multiple groups of the pushbroom data of the three-line array, construct a textureless model of the target area, and attach the white film building to the textureless model to generate the three-dimensional model.

[0090] In this embodiment, please also refer to Figure 8 , Figure 8 The figure shows a schematic diagram of the three-dimensional model provided by the embodiments of the present application. By establishing the textureless model of the target area and the method of pasting the white film building, the generation of the three-dimensional model can be automatically and quickly realized, improving the generation efficiency of the three-dimensional model.

[0091] In an alternative embodiment, the constructing the textureless model of the target area according to multiple groups of the pushbroom data of the three-line array includes:

[0092] According to multiple groups of the pushbroom data of the three-line array, determine the terrain within the target area;

[0093] Construct a rough model of the target area;

[0094] Filter the rough model to obtain a filtered rough model;

[0095] Fill the filtered rough model according to the terrain to obtain a textureless model of the target area.

[0096] In this embodiment, the terrain includes urban areas and mountainous areas. The process of filtering the rough model includes: removing the deleted points and non-testable points in the rough model, and only selecting the points remaining after filtering the buildings and vegetation. It can be understood that for the data of mountainous areas, if the default building and vegetation filtering parameters are used, a large range of points on the mountains will often be filtered out. Because if the vegetation is lush in mountainous areas, the extracted rough model will be uneven with the undulations of the vegetation, resulting in the filtering out of these high and low points.

[0097] In an alternative embodiment, the construction of the rough model of the target area includes:

[0098] Determine the range of the grid and construct the grid according to preset parameters;

[0099] Based on the range of the grid and the grid, construct the rough model of the target area.

[0100] Specifically, taking the shape of the constructed grid as a quadrilateral as an example, the preset parameters include a first step length and a second step length, where both the first step length and the second step length are determined by the terrain and the scale. In specific implementation, the shape of the constructed grid can be other shapes such as triangles and circles, and the preset parameters are the side lengths corresponding to triangles, the radii or diameters corresponding to circles, which are not limited herein. Please refer to Figure 8 , Figure 8 shows a schematic diagram of the rough model in the target area provided by the embodiment of the present application. In this embodiment, the rough model of the constructed target area is as Figure 8 shown.

[0101] It can be understood that after the rough model is constructed, contour lines with the first step length and / or the second step length as the contour interval will be automatically generated, and the quality of the rough model can be preliminarily judged from the contour lines. The specific judgment process is as follows: if the overall terrain is too natural without various protrusions and / or depressions, the quality of the rough model is good; if the terrain is distorted or deformed, the quality of the rough model is poor. When the quality of the rough model is poor, the unfiltered building and vegetation points can be manually deleted to improve the quality of the rough model.

[0102] In an alternative embodiment, the filling of the filtered rough model according to the terrain includes:

[0103] If the terrain is the urban area, fill the filtered rough model in a minimum value filling manner;

[0104] If the terrain is the mountainous area, the filtered rough model is filled in a smooth filling manner.

[0105] Specifically, please refer to Figure 9 , Figure 9 which shows a schematic diagram of the filtered rough model after filling in the mountainous area provided by the embodiment of the present application. Taking the terrain as the mountainous area as an example in this embodiment, the filtered rough model obtained is as Figure 9 shown.

[0106] The method for generating a three-dimensional model provided by the embodiment of the present application includes obtaining multiple sets of three-line array pushbroom data in a target area; extracting corresponding points between each set of the three-line array pushbroom data, and fusing the corresponding points to obtain multiple sets of fused points; fusing and connecting multiple sets of the three-line array pushbroom data according to the fused points to obtain a corresponding stereo pair group of the target area; extracting a white film building corresponding to the stereo pair group; constructing a textureless model of the target area according to multiple sets of the three-line array pushbroom data, and attaching the white film building to the textureless model to generate the three-dimensional model. By the method of corresponding point fusion, the accuracy of model generation can be improved. At the same time, by establishing the textureless model of the target area and pasting the white film building, the generation of the three-dimensional model can be automatically and quickly realized, and the generation efficiency of the three-dimensional model is improved.

[0107] Embodiment 2

[0108] Please refer to Figure 11 , Figure 11 which shows a structural schematic block diagram of a three-dimensional model generation device provided by the embodiment of the present application. The three-dimensional model generation device 500 can be applied to a server and includes an acquisition module 510, a fusion module 520, a connection module 530, an extraction module 540, and a generation module 550.

[0109] Among them, the acquisition module 510 is configured to obtain multiple sets of three-line array pushbroom data in a target area;

[0110] The fusion module 520 is configured to extract corresponding points between each set of the three-line array pushbroom data, and fuse the corresponding points to obtain multiple sets of fused points;

[0111] The connection module 530 is configured to fuse and connect multiple sets of the three-line array pushbroom data according to the fused points to obtain a corresponding stereo pair group of the target area;

[0112] The extraction module 540 is configured to extract a white film building corresponding to the stereo pair group;

[0113] The generation module 550 is configured to construct a textureless model of the target area according to multiple sets of the three-line array pushbroom data, and attach the white film building to the textureless model to obtain the three-dimensional model.

[0114] The above device is used to execute the method provided in Embodiment 1, and its implementation principle and technical effects are similar, which will not be elaborated here.

[0115] An embodiment of the present application also discloses a computer device, which includes a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, it implements the method for generating a three-dimensional model as described in Embodiment 1.

[0116] An embodiment of the present application also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the method for generating a three-dimensional model as described in Embodiment 1.

[0117] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are only illustrative. For example, the flowcharts and structure diagrams in the drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the blocks may occur in a different order from that marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the structure diagram and / or flowchart, as well as the combination of blocks in the structure diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0118] In addition, in each embodiment of the present application, the various functional modules or units may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.

[0119] When the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0120] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application.

Claims

1. A method for generating a three-dimensional model, characterized in that, it includes: Obtain multiple sets of pushbroom data of three-line arrays within the target area; Extract corresponding points of each set of the three-line array pushbroom data, and fuse the corresponding points to obtain multiple sets of fused points; Fusion-connect multiple sets of the three-line array pushbroom data according to the fused points to obtain a corresponding stereo image pair set of the target area; Extract the white film buildings corresponding to the stereo image pair set; Construct a textureless model of the target area according to multiple sets of the three-line array pushbroom data, and attach the white film buildings to the textureless model to generate the three-dimensional model.

2. The method according to claim 1, characterized in that, The constructing a textureless model of the target area according to multiple sets of the three-line array pushbroom data includes: Determine the terrain within the target area according to multiple sets of the three-line array pushbroom data; Construct a rough model of the target area; Filter the rough model to obtain a filtered rough model; Fill the filtered rough model according to the terrain to obtain the textureless model of the target area.

3. The method according to claim 2, characterized in that, The constructing a rough model of the target area includes: Determine the range of the grid and construct the grid according to preset parameters; Construct a rough model of the target area based on the range of the grid and the grid.

4. The method according to claim 2, characterized in that, The terrain includes urban areas and mountainous areas. The filling the filtered rough model according to the terrain includes: If the terrain is the urban area, fill the filtered rough model by using the minimum filling method; If the terrain is the mountainous area, fill the filtered rough model by using the smooth filling method.

5. The method according to claim 1, characterized in that, The extracting the white film buildings corresponding to the stereo image pair set includes: Construct a co-occurrence matrix corresponding to the stereo image pair set according to the grayscale image corresponding to the stereo image pair set, where the co-occurrence matrix is obtained by statistically counting the situation where two pixels with a preset distance on the grayscale image respectively have a preset grayscale; Calculate the eigenvalues of the co-occurrence matrix according to the co-occurrence matrix, and use the eigenvalues as the white film buildings corresponding to the stereo image pair set.

6. The method according to claim 1, characterized in that, After obtaining the corresponding stereo image pair set of the target area, it further includes: Obtain information of multiple image control points arranged within the target area; Perform precision measurement of the fused points on the information of multiple image control points and the fused points by using measurement solution to obtain the precision of the target area.

7. The method according to claim 1, characterized in that, The extracting the corresponding points of each set of the three-line array pushbroom data includes: Detect multiple sets of the three-line array pushbroom data according to the Hessian matrix to obtain initial corresponding points corresponding to multiple sets of the three-line array pushbroom data, where the Hessian matrix is a square matrix composed of second-order partial derivatives of a multivariate function; Perform non-maximum suppression on the initial corresponding points to obtain the corresponding points of each set of the three-line array pushbroom data.

8. A device for generating a three-dimensional model, It is characterized in that including: an acquisition module, configured to acquire multiple groups of three-line array pushbroom data within a target area; a fusion module, configured to extract corresponding points between each group of the three-line array pushbroom data and fuse the corresponding points to obtain multiple groups of fused points; a connection module, configured to perform fusion connection on multiple groups of the three-line array pushbroom data according to the fused points to obtain a corresponding stereo image pair group of the target area; an extraction module, configured to extract white film buildings corresponding to the stereo image pair group; a generation module, configured to construct a textureless model of the target area according to multiple groups of the three-line array pushbroom data and attach the white film buildings to the textureless model to obtain the three-dimensional model.

9. A computer device It is characterized in that the computer device includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, it implements a method for generating a three-dimensional model according to any one of claims 1 to 7.

10. A computer-readable storage medium It is characterized in that the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements a method for generating a three-dimensional model according to any one of claims 1 to 7.

Images