A regional monitoring method, device, equipment and storage medium

Abstract

The present application provides a regional monitoring method, apparatus, device, and storage medium, relating to the field of photographic monitoring technology. A first image of a monitoring area in a first time period is photographically measured and solved to obtain a first three-dimensional model of a monitored object within the monitoring area. Based on the first three-dimensional model and the first two-dimensional coordinates of multiple registration points in the first image, the first three-dimensional coordinates of multiple registration points are obtained. Based on the first three-dimensional coordinates of the multiple registration points, a second image of the monitoring area in a second time period is photographically measured and solved to obtain a second three-dimensional model of the monitored object. The first three-dimensional model and the second three-dimensional model are in the same three-dimensional coordinate system. The first three-dimensional model and the second three-dimensional model are registered to obtain a registration analysis result, thereby realizing automated regional monitoring and reducing labor costs. Complete surface information of the monitoring area is obtained through photogrammetry, improving the comprehensiveness and accuracy of the automated registration analysis results, and improving regional monitoring efficiency.

Description

Technical Field

[0001] The present application relates to the field of photographic monitoring technology, and more specifically, to a method, apparatus, device, and storage medium for regional monitoring. Background Art

[0002] When geotechnical engineers monitor geotechnical engineering projects, they need to monitor the position, status and other information of the objects under test in a monitoring area at different times, so as to analyze the spatial information at different times and obtain the changes of the monitored objects in the monitoring area to ensure the safety of geotechnical engineering projects.

[0003] In conventional technology, users can go to the monitoring area every day, compare the inspection conditions at different times based on the real-time inspection every day, and record the comparison results. However, the labor cost is high, and the manual comparison method has the problems of low efficiency and low accuracy of the comparison results. Manual comparison depends on the user's level, and the quality of the comparison results obtained is uneven, which affects the safety of geotechnical engineering. Users can also select a limited number of points in the monitoring area and install monitoring instruments and equipment at the positions corresponding to the limited points. Users can compare and analyze multiple point information in the monitoring area transmitted by the monitoring instruments and equipment at different times. This method divides the information of the monitoring area into multiple independent point information. When comparing and analyzing, multiple independent point information needs to be integrated into the same benchmark. The calculation steps are cumbersome and inefficient. At the same time, due to the fixed position of the monitoring instruments and equipment, multiple independent point information cannot completely cover the blind spots of the monitoring area, making the monitoring range incomplete and the accuracy of the comparative analysis results poor. Summary of the Invention

[0004] The purpose of the present invention is to provide a regional monitoring method, device, equipment and storage medium to address the deficiencies of the above-mentioned existing technologies, so as to solve the technical problems in the existing technologies such as incomplete monitoring range, poor accuracy of regional changes, and low efficiency in monitoring data processing.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of the present application are as follows:

[0006] In a first aspect, an embodiment of the present application provides a method for regional monitoring, the method comprising:

[0007] Performing camera measurement and calculation on a first image of the monitoring area in a first time period to obtain a first three-dimensional model of the monitoring object within the monitoring area;

[0008] Obtaining first three-dimensional coordinates of the plurality of registration points according to the first three-dimensional model and first two-dimensional coordinates of the plurality of registration points in the first image;

[0009] performing photogrammetric calculation on a second image of the monitoring area in a second time period according to the first three-dimensional coordinates of the plurality of registration points to obtain a second three-dimensional model of the monitoring object, wherein the first three-dimensional model and the second three-dimensional model are in the same three-dimensional coordinate system;

[0010] The first three-dimensional model and the second three-dimensional model are registered to obtain a registration analysis result, where the registration analysis result is used to indicate changes in the monitored object from the first time period to the second time period.

[0011] Optionally, before obtaining the first three-dimensional coordinates of the plurality of registration points based on the first three-dimensional model and the first two-dimensional coordinates of the plurality of registration points in the first image, the method further includes:

[0012] In response to a plurality of registration point selection operations input through the first image, pixel positions of the plurality of registration points on the first image are respectively determined as first two-dimensional coordinates of the plurality of registration points.

[0013] Optionally, obtaining the first three-dimensional coordinates of the plurality of registration points according to the first three-dimensional model and the first two-dimensional coordinates of the plurality of registration points in the first image includes:

[0014] Projecting the first two-dimensional coordinates of the plurality of registration points onto the first three-dimensional model along a preset projection direction to obtain intersection points of the plurality of registration points and the first three-dimensional model;

[0015] The three-dimensional coordinates of the intersections of the plurality of registration points and the first three-dimensional model are determined as first three-dimensional coordinates of the plurality of registration points.

[0016] Optionally, performing photogrammetric calculation on a second image of the monitoring area in a second time period according to the first three-dimensional coordinates of the plurality of registration points to obtain a second three-dimensional model of the monitoring object includes:

[0017] performing photogrammetric calculation on the second image based on the first three-dimensional coordinates of the plurality of registration points to obtain an initial three-dimensional model of the monitored object and a point cloud rotation matrix; the point cloud rotation matrix includes rotation parameters of a plurality of point cloud data, the plurality of point cloud data including the plurality of registration points;

[0018] The plurality of point cloud data in the initial three-dimensional model are rotated and translated according to the point cloud rotation matrix to obtain the second three-dimensional model.

[0019] Optionally, performing photogrammetric calculation on the second image according to the first three-dimensional coordinates of the plurality of registration points to obtain an initial three-dimensional model of the monitored object and a point cloud rotation matrix includes:

[0020] performing photogrammetric calculation on the second image to obtain the initial three-dimensional model;

[0021] Obtaining second three-dimensional coordinates of the plurality of registration points according to the initial three-dimensional model and the second two-dimensional coordinates of the plurality of registration points in the second image;

[0022] The point cloud rotation matrix is ​​obtained according to the first three-dimensional coordinates and the second three-dimensional coordinates.

[0023] Optionally, obtaining the point cloud rotation matrix according to the first three-dimensional coordinates and the second three-dimensional coordinates includes:

[0024] Obtaining a rotation matrix of the plurality of registration points according to the first three-dimensional coordinates and the second three-dimensional coordinates;

[0025] The point cloud rotation matrix is ​​generated according to the rotation matrices of the multiple registration points.

[0026] Optionally, registering the first three-dimensional model and the second three-dimensional model to obtain a registration analysis result includes:

[0027] Using a preset three-dimensional ruler, scaling the first three-dimensional model and the second three-dimensional model respectively to obtain a first twin model and a second twin model of the monitored object;

[0028] The first twin model and the second twin model are registered to obtain the registration analysis result.

[0029] In a second aspect, an embodiment of the present application provides an area monitoring device, comprising:

[0030] A first solving module is used to perform camera measurement and solving on a first image of a monitoring area in a first time period to obtain a first three-dimensional model of a monitoring object in the monitoring area;

[0031] an obtaining module, configured to obtain first three-dimensional coordinates of the plurality of registration points according to the first three-dimensional model and the first two-dimensional coordinates of the plurality of registration points in the first image;

[0032] a second solving module, configured to perform photogrammetric solving on a second image of the monitoring area in a second time period based on the first three-dimensional coordinates of the plurality of registration points, to obtain a second three-dimensional model of the monitored object, wherein the first three-dimensional model and the second three-dimensional model are in the same three-dimensional coordinates;

[0033] The registration module is used to register the first three-dimensional model and the second three-dimensional model to obtain a registration analysis result, wherein the registration analysis result is used to indicate the change of the monitored object from the first time period to the second time period.

[0034] In a third aspect, an embodiment of the present application provides a computer device comprising: a storage medium and a processor, wherein the storage medium stores a computer program executable by the processor, and when the processor executes the computer program, an area monitoring method according to the first aspect is implemented.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is read and executed, the area monitoring method of the first aspect described above is implemented.

[0036] Compared with the prior art, this application has the following beneficial effects:

[0037] The present application provides a method, apparatus, equipment and storage medium for regional monitoring, which obtains a first 3D model of a monitored object in the monitored area by performing photographic measurement and solution on a first image of a monitored area in a first time period, obtains the first 3D coordinates of multiple registration points according to the first 2D model and the first 2D coordinates of multiple registration points, obtains the second 3D model of the monitored object according to the first 3D coordinates of the multiple registration points, wherein the first 3D model and the second 3D model are in the same 3D coordinate system, and the first 3D model and the second 3D model are registered to obtain a registration analysis result, which is used to indicate the change of the monitored object from the first time period to the second time period. The method monitors geotechnical engineering objects through close-range photography, does not require users to conduct on-site inspections, and does not require users to install monitoring instruments and equipment at positions corresponding to a limited number of points in the monitored area, which can save users time. The quantitative solution can obtain the three-dimensional model of all monitored objects in the monitoring area, that is, the surface information of the monitoring area, so that the monitoring range is more comprehensive. Through the model registration of the two models, the automation of regional monitoring is realized, and there is no need for manual field comparison, which improves the efficiency of regional monitoring and reduces labor costs. In addition, the close-up photography of geotechnical engineering is more comprehensive. Both models correspond to the complete surface information of the monitoring area. Compared with conventional monitoring, which may ignore the details and blind spots in the monitoring area, this method improves the comprehensiveness of the automatic registration analysis results and the accuracy of the registration analysis results, thereby improving the automation level of geotechnical engineering surface deformation monitoring and early warning. At the same time, the changes in the monitoring area are obtained through the surface information of the monitoring area at two different times. Compared with the changes in the monitoring area obtained through multiple independent point information, the traditional total station measurement control point process corresponding to the monitoring instrument equipment is simplified, effectively improving the processing efficiency of the image file, thereby improving the efficiency of regional monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 A schematic diagram of a flow chart of a regional monitoring method provided in an embodiment of the present application;

[0040] Figure 2 A schematic diagram of a flow chart of another regional monitoring method provided in an embodiment of the present application;

[0041] Figure 3 A schematic diagram of a flow chart of another regional monitoring method provided in an embodiment of the present application;

[0042] Figure 4 A schematic diagram of a flow chart of another regional monitoring method provided in an embodiment of the present application;

[0043] Figure 5 A schematic diagram of a flow chart of another regional monitoring method provided in an embodiment of the present application;

[0044] Figure 6 A schematic diagram of a flow chart of another regional monitoring method provided in an embodiment of the present application;

[0045] Figure 7 A schematic diagram of an area monitoring device provided in an embodiment of the present application;

[0046] Figure 8 A schematic diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0048] 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 present application for protection, but merely represents selected embodiments of the present application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0049] In addition, the terms "first", "second", etc., if used, are merely used to distinguish and describe, and should not be understood as indicating or implying relative importance.

[0050] It should be noted that, in the absence of conflict, the features in the embodiments of the present invention may be combined with each other.

[0051] When geotechnical engineers monitor geotechnical engineering projects, they can compare the objects under test in the monitoring area with the conditions of the previous inspection during each on-site operation and record the changes in the objects under test in the monitoring area. This method has high labor costs, and the field inspection takes up a lot of time and resources, resulting in low monitoring efficiency. In addition, conventional monitoring may ignore the details in the monitoring area, making the recorded changes in the objects under test less accurate. By setting up multiple monitoring instruments and equipment at multiple locations in the monitoring area, multiple monitoring instruments and equipment can collect and transmit their corresponding multiple independent point information, and then analyze the multiple point information. This method has cumbersome calculation steps and low efficiency. In addition, the multiple independent point information cannot completely cover the blind spots in the monitoring area, making the monitoring range incomplete and the accuracy of the analysis results poor. Therefore, in this application, images of the monitoring area at different times are automatically analyzed to obtain the changes in all objects under test in the monitoring area. That is, all objects under test in the monitoring area and their changes can be obtained, thereby improving regional monitoring efficiency and reducing labor costs. At the same time, the comprehensiveness of the monitoring range is ensured, and the details and blind spots of the monitoring area are not missed, thereby improving the accuracy of regional changes.

[0052] In order to improve monitoring efficiency, ensure the comprehensiveness of the monitoring scope, and improve the accuracy of regional changes, the technical solution of this application provides a regional monitoring method. The following is an explanation of a regional monitoring method provided in an embodiment of this application through specific examples. Figure 1 A flow chart of a regional monitoring method provided in an embodiment of the present application is shown as follows: Figure 1 As shown, the method includes:

[0053] S101 , performing camera measurement and calculation on a first image of a monitoring area in a first time period to obtain a first three-dimensional model of a monitoring object in the monitoring area.

[0054] This application uses close-up photography to monitor geotechnical engineering, wherein geotechnical engineering monitoring is a systematic and serial observation and analysis process of the deformation of the rock and soil mass caused by the construction and use of the project, and the changes in the safety and stability of the surrounding environment and the building itself.

[0055] When monitoring geotechnical engineering projects using close-range photography, the present application first captures a first image of the monitored area during a first time period. This first image can be a two-dimensional image. Based on this first image, a first three-dimensional model corresponding to all monitored objects within the monitored area can be obtained through photogrammetry. This first three-dimensional model of the monitored area can also be referred to as the first surface information of the monitored area.

[0056] Photogrammetry can use the image of the object to reconstruct the spatial position and three-dimensional shape of the object. Its basic principle is to simulate the photographic process based on the idea of ​​geometric inversion of the photographic process. Two projectors are used to simulate the spatial position, posture and relationship of two adjacent images during photography, forming an optical geometric model that is smaller than the actual object.

[0057] In this embodiment of the present application, two images with a 60% overlap can be used to restore a reduced-scale stereoscopic model of the photographed terrain using optical and electromechanical instruments. Measurements can then be performed on this model to determine the spatial coordinates of the photographed object. The photogrammetric results can be output in graphical or numerical form. In this embodiment of the present application, the photogrammetric solution is displayed as a three-dimensional model. The optical and electromechanical instruments can be designed and manufactured according to specific photogrammetric principles, and the photographed terrain can be the terrain of the monitoring area in this application.

[0058] S102 : Obtain first three-dimensional coordinates of multiple registration points according to the first three-dimensional model and the first two-dimensional coordinates of the multiple registration points in the first image.

[0059] There are multiple registration points in the first image. Since the first image is a two-dimensional image, the multiple registration points in the first image have multiple first two-dimensional coordinates.

[0060] When the first image of the monitoring area in the first time period is photographically measured and solved to obtain a first three-dimensional model, it can be understood that the multiple registration points in the first image have corresponding multiple first three-dimensional coordinates in the first three-dimensional model, that is, the multiple first three-dimensional coordinates corresponding to the multiple registration points can be obtained through the first two-dimensional coordinates of the multiple registration points in the first image and the first three-dimensional model.

[0061] S103 , performing photogrammetric calculation on a second image of the monitoring area in a second time period according to the first three-dimensional coordinates of the plurality of registration points to obtain a second three-dimensional model of the monitoring object.

[0062] In order to obtain the changes in the objects under test in the monitoring area, it is necessary to compare and analyze the information of all monitored objects in the monitoring area in multiple different time periods. Therefore, in addition to obtaining the information of the monitoring area in the first time period, it is also necessary to obtain the information of the monitoring area in the second time period, and then compare the two types of information.

[0063] Optionally, the first image of the first time period may be an image of the first period, and the second image of the second time period may be an image of the second period, wherein the first time period is before the second time period. Of course, information of the monitored area in multiple time periods may also be superimposed and compared or comprehensively compared, and the first time period may also be after the second time period, which is not specifically limited in the embodiments of the present application.

[0064] In this embodiment of the present application, a first 3D model of the monitored area during a first time period can be compared with a second 3D model of the monitored area during a second time period. Therefore, after obtaining the first 3D models of all monitored objects within the monitored area, the second 3D models must be obtained. The second 3D models of the monitored objects, i.e., the second 3D models corresponding to the monitored area, can also be referred to as the second surface information of the monitored area.

[0065] The first and second 3D models are in the same 3D coordinate system. If the second 3D model is obtained by performing photogrammetric calculations only on the second image of the monitored area during the second time period, the 3D coordinate system of the second 3D model may be different from that of the first 3D model. Therefore, when obtaining the second 3D model, it is necessary to align the first and second 3D models with the same 3D coordinate system based on the first 3D coordinates of the multiple registration points.

[0066] S104: Register the first three-dimensional model and the second three-dimensional model to obtain a registration analysis result.

[0067] The registration analysis result is used to indicate the changes of all monitored objects in the monitoring area from the first time period to the second time period, wherein some monitored objects do not change.

[0068] In the embodiment of the present application, the registration analysis results can be used to illustrate the specific changes in the surface information of the monitoring area at different times.

[0069] When the first three-dimensional model and the second three-dimensional model are in the same coordinate system, the two models or model data can be more accurately registered to obtain a registration analysis result.

[0070] The present application provides a regional monitoring method for monitoring geotechnical engineering objects through close-range photography. This method does not require users to conduct field surveys or install monitoring equipment at locations corresponding to a limited number of points within the monitoring area, saving users time. Photogrammetric calculations can generate a three-dimensional model of all monitored objects within the monitoring area, namely, the surface information of the monitoring area, making the monitoring range more comprehensive. By aligning two models, automated regional monitoring is achieved, eliminating the need for manual field comparison, improving the efficiency of regional monitoring and reducing labor costs. Furthermore, close-range photography of geotechnical engineering images is more comprehensive, and both models correspond to complete surface information of the monitoring area. Compared to conventional monitoring, which may overlook details and blind spots within the monitoring area, this method improves the comprehensiveness and accuracy of the automated alignment analysis results, thereby enhancing the automation level of geotechnical engineering surface deformation monitoring and early warning. Furthermore, by deriving changes in the monitoring area from surface information at two different times, compared to obtaining changes in the monitoring area from multiple independent point information, this method simplifies the traditional total station control point measurement process corresponding to the monitoring instrument and equipment, effectively improving the efficiency of image file processing, and thereby improving the efficiency of regional monitoring.

[0071] In the above Figure 1 Based on the region monitoring method shown above, the present application embodiment also provides another method for implementing the region monitoring method. Optionally, before the above method S102, before obtaining the first three-dimensional coordinates of the plurality of registration points based on the first three-dimensional model and the first two-dimensional coordinates of the plurality of registration points in the first image, the method further includes:

[0072] In response to a plurality of registration point selection operations inputted through a first image, pixel positions of the plurality of registration points on the first image are respectively determined as first two-dimensional coordinates of the plurality of registration points.

[0073] Optionally, to improve the accuracy of the registration analysis, the plurality of registration points may be at least four registration points. The plurality of registration points may be a plurality of easily distinguishable feature points within a stable region of the monitoring area. Of course, other numbers of registration points may also be used, and are not specifically limited in the embodiments of the present application.

[0074] For example, if there are four registration points, the four registration points may be distributed at the four corners of the first image, or distributed near the four corners of the first image.

[0075] For example, if the number of multiple registration points is greater than four, four of the registration points may be distributed at the four corners of the first image, or distributed near the four corners of the first image, and at least one other point may be distributed in the middle part of the first image. For easy distinction, at least one other point may be distributed at the junction of two obvious color blocks in the middle part of the first image.

[0076] The present application provides a regional monitoring method that responds to the selection operation of multiple registration points input through a first image, and respectively determines the pixel positions of the multiple registration points on the first image as the first two-dimensional coordinates of the multiple registration points. By selecting multiple registration points, the first three-dimensional model and the second three-dimensional model can be placed in the same three-dimensional coordinate system, so that the accuracy of the automated registration analysis results is higher, and the accuracy of regional changes is improved.

[0077] In the above Figure 1 Based on the region monitoring method shown, the embodiment of the present application also provides another method for implementing the region monitoring method. Optionally, Figure 2 A flow chart of another regional monitoring method provided in an embodiment of the present application is shown as follows: Figure 2 As shown, the above method S102 obtains the first three-dimensional coordinates of the plurality of registration points according to the first three-dimensional model and the first two-dimensional coordinates of the plurality of registration points in the first image, including:

[0078] S201 : Projecting first two-dimensional coordinates of a plurality of registration points onto a first three-dimensional model along a preset projection direction to obtain intersection points of the plurality of registration points and the first three-dimensional model.

[0079] The first two-dimensional coordinates of the multiple registration points are projected into multiple rays along a preset projection direction. The multiple rays intersect with the first three-dimensional model to obtain multiple intersection points of the multiple registration points and the first three-dimensional model.

[0080] Optionally, the first three-dimensional model may correspond to a plane formed by a model triangulation network. By calculating multiple intersection points of multiple rays and the plane, it is determined whether the multiple intersection points are within the triangulation network. If they are within the triangulation network, they are determined to be the intersection points of the first three-dimensional model and the rays, that is, the intersection points of the first three-dimensional model and the multiple alignment points.

[0081] Optionally, the preset projection direction may be a forward projection direction.

[0082] S202: Determine the three-dimensional coordinates of the intersections of the multiple registration points and the first three-dimensional model as first three-dimensional coordinates of the multiple registration points.

[0083] All points in the first three-dimensional model have three-dimensional coordinates. Therefore, the three-dimensional coordinates of the intersections of the first three-dimensional model and multiple registration points can be determined, and the three-dimensional coordinates of the intersections corresponding to each registration point are used as the first three-dimensional coordinates of the registration point.

[0084] The present application provides a method for regional monitoring, which projects the first two-dimensional coordinates of multiple registration points onto a first three-dimensional model along a preset projection direction to obtain the intersection points of the multiple registration points and the first three-dimensional model, and determines the three-dimensional coordinates at the intersection points of the multiple registration points and the first three-dimensional model as the first three-dimensional coordinates of the multiple registration points. Then, based on the first three-dimensional coordinates of the multiple registration points, the second three-dimensional model and the first three-dimensional model are placed in the same three-dimensional coordinate system, thereby making the accuracy of the automated registration analysis results higher and improving the accuracy of regional changes. At the same time, the registration analysis of the second three-dimensional model and the first three-dimensional model in the same coordinate system is more efficient, and it is also convenient for users to view the visually intuitive registration analysis results of the second three-dimensional model and the first three-dimensional model.

[0085] In the above Figure 1 Based on the region monitoring method shown, the embodiment of the present application also provides another method for implementing the region monitoring method. Optionally, Figure 3 A flow chart of another regional monitoring method provided in an embodiment of the present application is shown as follows: Figure 3 As shown, the above method S103 performs photogrammetric calculation on the second image of the monitoring area in the second time period according to the first three-dimensional coordinates of the plurality of registration points to obtain a second three-dimensional model of the monitoring object, including:

[0086] S301 , performing photogrammetric calculation on the second image according to the first three-dimensional coordinates of the plurality of registration points to obtain an initial three-dimensional model of the monitored object and a point cloud rotation matrix.

[0087] The point cloud rotation matrix includes rotation parameters of multiple point cloud data, and the multiple point cloud data includes multiple registration points. That is, the point cloud rotation matrix includes the rotation parameters of the multiple registration points. The point cloud rotation matrix can be calculated from the three-dimensional coordinate information of the multiple registration points.

[0088] In the embodiment of the present application, the rotation parameters may include a translation coefficient, a rotation coefficient, a scaling coefficient, and of course, may also include other coefficients, which are not specifically limited in the embodiment of the present application.

[0089] The initial three-dimensional model of the monitored object may be a three-dimensional model obtained by performing photogrammetry on the second image, that is, a three-dimensional model corresponding to the monitored area in the second time period.

[0090] S302 : rotating and translating a plurality of point cloud data in the initial three-dimensional model according to the point cloud rotation matrix to obtain a second three-dimensional model.

[0091] After calculating the point cloud rotation matrix through the three-dimensional coordinate information of multiple alignment points, the multiple point cloud data in the initial three-dimensional model are rotated and translated. At this time, the multiple point cloud data can represent all the point cloud data in the initial three-dimensional model, and can also represent part of the point cloud data in the initial three-dimensional model.

[0092] For example, when multiple point cloud data represent all point cloud data in an initial three-dimensional model, all point cloud data in the initial model can be multiplied by a rotation matrix to transform the three-dimensional coordinates corresponding to all point cloud data through the rotation parameters in the rotation matrix to obtain transformed point cloud data, which corresponds to a second three-dimensional model.

[0093] For example, when multiple point cloud data represent partial point cloud data in the initial three-dimensional model, multiple different point cloud rotation matrices can be obtained based on the first three-dimensional coordinates of multiple alignment points. For each point cloud rotation matrix, the multiple partial point cloud data in the initial three-dimensional model are rotated and translated to different degrees to obtain the transformed multiple partial point cloud data to constitute a second three-dimensional model.

[0094] In an embodiment of the present application, the point cloud rotation matrix can be understood as calculating the transformation relationship between multiple registration points in the first three-dimensional model and the initial three-dimensional model based on the three-dimensional coordinate information of multiple registration points. Through this change relationship, the second three-dimensional model after the registration points in the initial three-dimensional model are transformed through this transformation relationship is in the same coordinate system as the first three-dimensional model.

[0095] The present application provides a method for regional monitoring, which performs photogrammetric solution on a second image based on the first three-dimensional coordinates of multiple registration points to obtain an initial three-dimensional model of the monitored object and a point cloud rotation matrix. The point cloud rotation matrix includes: rotation parameters of multiple point cloud data, and the multiple point cloud data include: multiple registration points. According to the point cloud rotation matrix, the multiple point cloud data in the initial three-dimensional model are rotated and translated to obtain a second three-dimensional model, so that the second three-dimensional model and the first three-dimensional model are in the same three-dimensional coordinate system.

[0096] In the above Figure 3 Based on the region monitoring method shown, the embodiment of the present application also provides another method for implementing the region monitoring method. Optionally, Figure 4 A flow chart of another regional monitoring method provided in an embodiment of the present application is shown as follows: Figure 4 As shown, the above method S301 performs photogrammetric calculation on the second image according to the first three-dimensional coordinates of the plurality of registration points to obtain an initial three-dimensional model of the monitored object and a point cloud rotation matrix, including:

[0097] S401: Perform photogrammetric calculation on the second image to obtain an initial three-dimensional model.

[0098] The photogrammetry solution method is the same as the photogrammetry solution method in S101 above, and will not be described in detail here.

[0099] In an embodiment of the present application, the origin of the coordinate system of the three-dimensional model obtained by photogrammetry is randomly set, and the origin of the coordinate system of the three-dimensional model obtained each time is different. Therefore, the origin of the coordinate system of the initial three-dimensional model is different from that of the first three-dimensional model, that is, the first three-dimensional model and the initial three-dimensional model are not in the same three-dimensional coordinate system.

[0100] S402 : Obtain second three-dimensional coordinates of the plurality of registration points according to the initial three-dimensional model and the second two-dimensional coordinates of the plurality of registration points in the second image.

[0101] The multiple registration points in the second image are the multiple registration points in the first image. Due to the difference in image data, the first two-dimensional coordinates of the multiple registration points in the first image are different from the second two-dimensional coordinates of the multiple registration points in the second image.

[0102] After determining the second two-dimensional coordinates of multiple registration points in the second image, the second two-dimensional coordinates of the multiple registration points are projected into the initial three-dimensional model along a preset projection direction to obtain the intersection of the multiple registration points and the initial three-dimensional model, and the three-dimensional coordinates at the intersection of the multiple registration points and the initial three-dimensional model are determined as the second three-dimensional coordinates of the multiple registration points.

[0103] S403: Obtain a point cloud rotation matrix according to the first three-dimensional coordinates and the second three-dimensional coordinates.

[0104] According to the first three-dimensional coordinates of the multiple registration points and the second three-dimensional coordinates of the multiple registration points, a point cloud rotation matrix corresponding to the multiple registration points can be obtained.

[0105] The present application provides a method for regional monitoring, which performs photogrammetric calculation on a second image to obtain an initial three-dimensional model, obtains the second three-dimensional coordinates of multiple registration points based on the initial three-dimensional model and the second two-dimensional coordinates of multiple registration points in the second image, obtains a point cloud rotation matrix based on the first three-dimensional coordinates and the second three-dimensional coordinates, and then rotates and translates multiple point cloud data in the initial three-dimensional model based on the point cloud rotation matrix to obtain a second three-dimensional model in the same three-dimensional coordinate system as the first three-dimensional model.

[0106] In the above Figure 4 Based on the region monitoring method shown, the embodiment of the present application also provides another method for implementing the region monitoring method. Optionally, Figure 5 A flow chart of another regional monitoring method provided in an embodiment of the present application is shown as follows: Figure 5 As shown, the above method S403, obtaining the point cloud rotation matrix according to the first three-dimensional coordinates and the second three-dimensional coordinates, includes:

[0107] S501 : Obtain a rotation matrix of a plurality of registration points according to the first three-dimensional coordinates and the second three-dimensional coordinates.

[0108] For example, each registration point has a first three-dimensional coordinate and a second three-dimensional coordinate. The three coordinate values ​​in the second three-dimensional coordinate can be multiplied by corresponding coefficients to obtain the three coordinate values ​​in the first three-dimensional coordinate. In this case, the coefficients corresponding to the three coordinate values ​​in the second three-dimensional coordinate can constitute the rotation matrix of each registration point. Optionally, the coefficients corresponding to the three coordinate values ​​can be respectively referred to as the translation coefficient, the rotation coefficient, and the scaling coefficient.

[0109] According to the multiple first three-dimensional coordinates and the multiple second three-dimensional coordinates of the multiple registration points, multiple rotation matrices of the multiple registration points can be obtained through calculation.

[0110] S502: Generate a point cloud rotation matrix according to the rotation matrices of the multiple registration points.

[0111] For example, in one possible implementation, all point cloud data in the initial three-dimensional model are subjected to the same rotation and translation according to the point cloud rotation matrix to obtain a second three-dimensional model. At this time, a point cloud rotation matrix can be generated according to the rotation matrices of multiple registration points to rotate and translate all point cloud data in the initial three-dimensional model through the point cloud rotation matrix. For example, the same coefficient in the rotation matrix of multiple registration points can be averaged to obtain an average translation coefficient, an average rotation coefficient, and an average scaling coefficient. The point cloud rotation matrix is ​​constructed by these three average coefficients. Of course, a point cloud rotation matrix can also be obtained according to the rotation matrices of multiple registration points in other ways, which are not specifically limited in the present embodiment of the application, and the type of coefficients is not specifically limited in the present embodiment of the application.

[0112] For example, in another possible implementation, multiple rotations and translations are performed on multiple portions of point cloud data in the initial three-dimensional model based on a point cloud rotation matrix to obtain a second three-dimensional model. In this case, multiple point cloud rotation matrices can be generated based on the rotation matrices of multiple registration points, so that multiple rotations and translations can be performed on multiple portions of point cloud data in the initial three-dimensional model using the multiple point cloud rotation matrices. For example, the rotation matrix of each registration point can be used as the corresponding point cloud rotation matrix, and the point cloud data within a preset range of each registration point in the initial three-dimensional model can be rotated and translated using the point cloud rotation matrix corresponding to each registration point. For example, a corresponding point cloud rotation matrix can also be obtained based on the rotation matrices of two registration points whose distance meets a preset condition, and the point cloud data within the preset range of the two registration points in the initial three-dimensional model can be rotated and translated using the point cloud rotation matrix. The same coefficients in the rotation matrices of the two registration points whose distance meets the preset condition are averaged to obtain an average translation coefficient, an average rotation coefficient, and an average scaling coefficient. The same coefficients in the rotation matrices of the two registration points can be averaged using these three average coefficients to form the corresponding point cloud rotation matrix. Of course, the corresponding point cloud rotation matrix can also be obtained based on the rotation matrix of three alignment points whose distances meet the preset conditions. Therefore, multiple point cloud rotation matrices can be obtained based on the rotation matrix of at least one alignment point through other alignment point selection methods, and the corresponding point cloud rotation matrix can also be calculated based on at least one alignment point through other calculation methods. There are no specific restrictions in the embodiments of the present application, and the type of coefficients is not specifically restricted in the embodiments of the present application.

[0113] The present application provides an area monitoring method, which obtains a rotation matrix of multiple alignment points based on first three-dimensional coordinates and second three-dimensional coordinates, generates a point cloud rotation matrix based on the rotation matrix of the multiple alignment points, and then rotates and translates multiple point cloud data in the initial three-dimensional model based on the point cloud rotation matrix to obtain a second three-dimensional model in the same three-dimensional coordinate system as the first three-dimensional model.

[0114] In the above Figure 1 Based on the region monitoring method shown, the embodiment of the present application also provides another method for implementing the region monitoring method. Optionally, Figure 6 A flow chart of another regional monitoring method provided in an embodiment of the present application is shown as follows: Figure 6 As shown, the above method S104 registers the first three-dimensional model and the second three-dimensional model to obtain a registration analysis result, including:

[0115] S601 , using a preset three-dimensional ruler, scaling the first three-dimensional model and the second three-dimensional model respectively to obtain a first twin model and a second twin model of the monitored object.

[0116] In an embodiment of the present application, the three-dimensional models of all monitored objects in the monitoring area obtained by video measurement are different in size from the actual three-dimensional models corresponding to all actual monitored objects. In order to obtain more accurate registration analysis results and make the registration analysis results more in line with reality, it is necessary to convert the sizes of the three-dimensional models of all monitored objects in the monitoring area into actual sizes.

[0117] There is a corresponding scaling factor between the size of the three-dimensional models of all monitored objects in the monitoring area and their actual size. Through this scaling factor, the three-dimensional models of all monitored objects can be converted into three-dimensional models of actual size, that is, the first three-dimensional model corresponding to the monitoring area can be converted into a three-dimensional model of the same size as the actual size of the monitoring area.

[0118] For example, a preset three-dimensional ruler and a first three-dimensional model can be used to generate a first scaling matrix between one of the monitored objects in the first three-dimensional model and the corresponding actual monitored object. Simultaneously, a preset three-dimensional ruler and a second three-dimensional model can be used to generate a second scaling matrix between one of the monitored objects in the second three-dimensional model and the corresponding actual monitored object. The first scaling matrix and the second scaling matrix can be scaling coefficients. For example, the scaling matrix can include a horizontal coordinate scaling coefficient, a vertical coordinate scaling coefficient, and a height scaling coefficient, wherein the three scaling coefficients can be calculated by comparing the three-dimensional coordinates of any point in the first three-dimensional model with the actual three-dimensional coordinates corresponding to the point in the actual model. Optionally, the values ​​of the horizontal coordinate scaling coefficient, the vertical coordinate scaling coefficient, and the height scaling coefficient in the same scaling matrix can be the same.

[0119] After obtaining the first scaling matrix, the point cloud data in the first 3D model can be converted into a scaled first twin model. For example, the 3D coordinates of the point cloud data in the first 3D model can be multiplied by the first scaling matrix to obtain scaled point cloud data, forming the first twin model. After obtaining the second scaling matrix, the point cloud data in the second 3D model can be converted into a scaled second twin model. For example, the 3D coordinates of the point cloud data in the second 3D model can be multiplied by the second scaling matrix to obtain scaled point cloud data, forming the second twin model.

[0120] S602: Register the first twin model and the second twin model to obtain a registration analysis result.

[0121] The sizes of the first twin model and the second twin model are both actual sizes. By aligning the two twin models, the alignment analysis results are obtained, and then the actual changes of all monitored objects from the first time period to the second time period can be obtained, that is, the actual changes between the first and second surface information of the monitoring area. This improves the accuracy of the alignment analysis of the monitoring area and ensures the safety of geotechnical engineering.

[0122] For example, the three-dimensional coordinate information of all monitored objects in the first twin model can be aligned and compared with the corresponding three-dimensional coordinate information of the same monitored objects in the second twin model, thereby obtaining information such as the location and status of all monitored objects in the monitoring area at different times, and then predicting information such as the change trend of all monitored objects. Of course, other analysis results can also be used, and are not specifically limited in this embodiment of the application.

[0123] The present application provides a regional monitoring method, which uses a preset three-dimensional ruler to scale the first three-dimensional model and the second three-dimensional model respectively to obtain a first twin model and a second twin model of the monitored object, and aligns the first twin model and the second twin model to obtain an alignment analysis result. The alignment analysis result is the actual change of all monitored objects in the monitoring area from the first time period to the second time period, that is, the actual change of the surface information of the monitoring area from the first time period to the second time period, which improves the accuracy of the alignment analysis result of the monitoring area. When monitoring and warning the surface deformation of geotechnical engineering, geotechnical engineers can intuitively view the surface deformation of the geotechnical engineering that conforms to the actual size to ensure the safety of the geotechnical engineering.

[0124] The following describes an area monitoring device, equipment, and storage medium provided by the present application for execution. The specific implementation process and technical effects are described above and will not be repeated below.

[0125] Figure 7 A schematic diagram of a regional monitoring device provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the area monitoring device includes:

[0126] The first solving module 701 is configured to perform camera measurement and solving on a first image of a monitoring area in a first time period to obtain a first three-dimensional model of a monitoring object in the monitoring area.

[0127] The obtaining module 702 is configured to obtain first three-dimensional coordinates of a plurality of registration points according to the first three-dimensional model and the first two-dimensional coordinates of the plurality of registration points in the first image.

[0128] The second solving module 703 is used to perform photogrammetric solving on the second image of the monitoring area in the second time period according to the first three-dimensional coordinates of the multiple registration points to obtain a second three-dimensional model of the monitored object, wherein the first three-dimensional model and the second three-dimensional model are in the same three-dimensional coordinates.

[0129] The registration module 704 is used to register the first three-dimensional model and the second three-dimensional model to obtain a registration analysis result, where the registration analysis result is used to indicate changes in the monitored object from the first time period to the second time period.

[0130] Optionally, the obtaining module 702 is further configured to respond to a plurality of registration point selection operations inputted through the first image, and respectively determine pixel positions of the plurality of registration points on the first image as first two-dimensional coordinates of the plurality of registration points.

[0131] Optionally, module 702 is obtained, which is specifically used to project the first two-dimensional coordinates of multiple registration points into the first three-dimensional model along a preset projection direction to obtain the intersection points of the multiple registration points and the first three-dimensional model; and determine the three-dimensional coordinates at the intersection points of the multiple registration points and the first three-dimensional model as the first three-dimensional coordinates of the multiple registration points.

[0132] Optionally, the second solution module 703 is specifically used to perform photogrammetric solution on the second image based on the first three-dimensional coordinates of multiple alignment points to obtain an initial three-dimensional model of the monitored object and a point cloud rotation matrix; the point cloud rotation matrix includes: rotation parameters of multiple point cloud data, and the multiple point cloud data include: multiple alignment points; according to the point cloud rotation matrix, the multiple point cloud data in the initial three-dimensional model are rotated and translated to obtain a second three-dimensional model.

[0133] Optionally, the second solution module 703 is specifically used to perform photogrammetric solution on the second image to obtain an initial three-dimensional model; obtain the second three-dimensional coordinates of multiple registration points based on the initial three-dimensional model and the second two-dimensional coordinates of multiple registration points in the second image; and obtain the point cloud rotation matrix based on the first three-dimensional coordinates and the second three-dimensional coordinates.

[0134] Optionally, the second solving module 703 is specifically configured to obtain a rotation matrix of the plurality of registration points according to the first three-dimensional coordinates and the second three-dimensional coordinates; and generate a point cloud rotation matrix according to the rotation matrices of the plurality of registration points.

[0135] Optionally, the registration module 704 is specifically used to use a preset three-dimensional scale to scale the first three-dimensional model and the second three-dimensional model respectively to obtain a first twin model and a second twin model of the monitored object; and to align the first twin model and the second twin model to obtain a registration analysis result.

[0136] The above modules can be one or more integrated circuits configured to implement the above methods, such as one or more application specific integrated circuits (ASICs), one or more digital singnal processors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented by scheduling program code through a processing element, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0137] Figure 8 A schematic diagram of a computer device provided in an embodiment of the present application, which may be a computing device with computing processing capabilities.

[0138] The computer device includes: a processor 801 , a storage medium 802 , and a bus 803 . The processor 801 and the storage medium 802 are connected via the bus 803 .

[0139] The storage medium 802 is used to store programs, and the processor 801 calls the programs stored in the storage medium 802 to execute the above method embodiment. The specific implementation methods and technical effects are similar and will not be repeated here.

[0140] Optionally, the present invention further provides a program product, such as a computer-readable storage medium, comprising a program, which is used to perform the above method embodiment when executed by a processor.

[0141] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0142] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0143] In addition, the functional units in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional units.

[0144] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (English: Read-Only Memory, abbreviated: ROM), a random access memory (English: Random Access Memory, abbreviated: RAM), a magnetic disk or an optical disk, and other media that can store program code.

[0145] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited to them. Any changes or substitutions that can be easily conceived by any person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A regional monitoring method, characterized in that: The method comprises: Performing camera measurement and calculation on a first image of the monitoring area in a first time period to obtain a first three-dimensional model of the monitoring object within the monitoring area; Projecting the first two-dimensional coordinates of the plurality of registration points onto the first three-dimensional model along a preset projection direction to obtain intersections of the plurality of registration points and the first three-dimensional model; determining the three-dimensional coordinates of the intersections of the plurality of registration points and the first three-dimensional model as the first three-dimensional coordinates of the plurality of registration points; performing photogrammetric calculations on the second image based on the first three-dimensional coordinates of the plurality of registration points to obtain an initial three-dimensional model of the monitored object and a point cloud rotation matrix; the point cloud rotation matrix includes rotation parameters of a plurality of point cloud data, the plurality of point cloud data including the plurality of registration points; performing rotation and translation on the plurality of point cloud data in the initial three-dimensional model based on the point cloud rotation matrix to obtain a second three-dimensional model, wherein the first three-dimensional model and the second three-dimensional model are in the same three-dimensional coordinate system; performing registration on the first three-dimensional model and the second three-dimensional model to obtain a registration analysis result, wherein the registration analysis result is used to indicate a change of the monitored object from the first time period to the second time period; The performing of photogrammetric calculation on the second image according to the first three-dimensional coordinates of the plurality of registration points to obtain an initial three-dimensional model of the monitored object and a point cloud rotation matrix includes: performing photogrammetric calculation on the second image to obtain the initial three-dimensional model; Obtaining second three-dimensional coordinates of the plurality of registration points according to the initial three-dimensional model and the second two-dimensional coordinates of the plurality of registration points in the second image; Obtaining a rotation matrix of the plurality of registration points according to the first three-dimensional coordinates and the second three-dimensional coordinates; The point cloud rotation matrix is ​​generated according to the rotation matrices of the multiple registration points.

2. The regional monitoring method according to claim 1, characterized in that: Before obtaining the first three-dimensional coordinates of the plurality of registration points based on the first three-dimensional model and the first two-dimensional coordinates of the plurality of registration points in the first image, the method further includes: In response to a plurality of registration point selection operations input through the first image, pixel positions of the plurality of registration points on the first image are respectively determined as first two-dimensional coordinates of the plurality of registration points.

3. The regional monitoring method according to claim 1, characterized in that: The registering the first three-dimensional model and the second three-dimensional model to obtain a registration analysis result includes: Using a preset three-dimensional ruler, scaling the first three-dimensional model and the second three-dimensional model respectively to obtain a first twin model and a second twin model of the monitored object; The first twin model and the second twin model are registered to obtain the registration analysis result.

4. A regional monitoring device, characterized in that: include: A first solving module is used to perform camera measurement and solving on a first image of a monitoring area in a first time period to obtain a first three-dimensional model of a monitoring object in the monitoring area; an obtaining module, configured to project the first two-dimensional coordinates of the plurality of registration points onto the first three-dimensional model along a preset projection direction, and obtain intersection points of the plurality of registration points and the first three-dimensional model; Determining the three-dimensional coordinates of intersections of the plurality of registration points and the first three-dimensional model as first three-dimensional coordinates of the plurality of registration points; A second solving module is used to perform photogrammetric solving on the second image according to the first three-dimensional coordinates of the plurality of registration points to obtain an initial three-dimensional model of the monitored object and a point cloud rotation matrix; The point cloud rotation matrix includes rotation parameters of a plurality of point cloud data, wherein the plurality of point cloud data includes the plurality of registration points; the plurality of point cloud data in the initial three-dimensional model is rotated and translated according to the point cloud rotation matrix to obtain a second three-dimensional model, wherein the first three-dimensional model and the second three-dimensional model are in the same three-dimensional coordinate system; a registration module, configured to register the first three-dimensional model and the second three-dimensional model to obtain a registration analysis result, wherein the registration analysis result is used to indicate changes in the monitored object from the first time period to the second time period; Among them, the second solving module is specifically used to: perform photogrammetric solving on the second image to obtain the initial three-dimensional model; obtain the second three-dimensional coordinates of the multiple registration points based on the initial three-dimensional model and the second two-dimensional coordinates of the multiple registration points in the second image; obtain the rotation matrix of the multiple registration points based on the first three-dimensional coordinates and the second three-dimensional coordinates; and generate the point cloud rotation matrix based on the rotation matrix of the multiple registration points.

5. A computer device, characterized in that: include: A storage medium and a processor, wherein the storage medium stores a computer program executable by the processor, and when the processor executes the computer program, the area monitoring method according to any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is read and executed, the area monitoring method according to any one of claims 1 to 3 is implemented.

Images