Object extraction method, device, electronic device and storage medium

Abstract

The embodiments of the present application relate to the field of surveying and mapping technology, and provide an object extraction method, device, electronic device and storage medium. By configuring a data linkage interface in the electronic device, the data linkage interface includes a two-dimensional window for displaying a digital orthophoto and a three-dimensional window for displaying point cloud data. When the cartographer adjusts the interface, the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window are linked and adjusted so that the current digital orthophoto and the current point cloud data correspond to each other, so that the cartographer can see the corresponding elevation information in real time through the current point cloud data in the three-dimensional window. When the cartographer performs an information extraction operation, linkage drawing is performed in the current digital orthophoto and the current point cloud data, so that the cartographer can quickly and accurately identify the objects that need to be vectorized. Thus, accurate object information can be obtained, and the accuracy of the produced map is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of surveying and mapping technology, and more specifically, to an object extraction method, device, electronic device, and storage medium. Background Art

[0002] At present, when making high-precision maps, the commonly used data production systems are mainly based on digital orthophotos for drawing. The data production systems provide raster vectorization or manual vectorization tools. Cartographers can use raster vectorization or manual vectorization tools to select objects in digital orthophotos for vectorization to obtain corresponding object information.

[0003] However, since digital orthophotos express two-dimensional scenes and lack elevation information, the lack of elevation information makes it impossible to recover the height information of objects above the ground, such as power lines, cable wires, and windbreaks. This makes it impossible for cartographers to quickly and accurately identify objects that need to be vectorized, and thus it is impossible to obtain accurate object information, affecting the accuracy of the maps produced. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide an object extraction method, device, electronic device and storage medium to help map personnel quickly and accurately identify objects that need to be vectorized.

[0005] In order to achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows:

[0006] In a first aspect, an embodiment of the present application provides an object extraction method, which is applied to an electronic device, wherein the electronic device is pre-configured with a data linkage interface, wherein the data linkage interface includes a two-dimensional window and a three-dimensional window, wherein the two-dimensional window is used to display a digital orthophoto, and the three-dimensional window is used to display point cloud data;

[0007] The method comprises:

[0008] In response to the interface adjustment operation, the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window are adjusted in linkage, so that the map center of the current point cloud data is consistent with the map center of the current digital orthophoto and the display range of the current point cloud data is consistent with the map range of the current digital orthophoto;

[0009] In response to the information extraction operation, linkage drawing is performed on the current digital orthophoto and the current point cloud data to obtain drawing information of the object to be extracted;

[0010] Vectorization is performed based on the drawing information of the object to be extracted to obtain extracted object information.

[0011] Optionally, the interface adjustment operation includes a first adjustment operation on the point cloud data displayed in the three-dimensional window;

[0012] The step of adjusting the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window in a linked manner in response to the interface adjustment operation includes:

[0013] In response to the first adjustment operation, obtaining first canvas coordinates of the first adjustment operation in the three-dimensional window;

[0014] The digital orthophoto displayed in the two-dimensional window is adjusted in a linked manner according to the first canvas coordinates and the viewing angle parameters of the current point cloud data to obtain the current digital orthophoto.

[0015] Optionally, the step of adjusting the digital orthophoto displayed in the two-dimensional window in a linked manner according to the first canvas coordinates and the viewing angle parameters of the current point cloud data to obtain the current digital orthophoto includes:

[0016] Calculating the map center of the current digital orthophoto according to the viewing angle parameter of the current point cloud data;

[0017] Calculating the first scale pixel accuracy of the current digital orthophoto according to the viewing angle parameter of the current point cloud data and the map projection coordinate system corresponding to the current point cloud data;

[0018] Determining a map range of the current digital orthophoto according to the first canvas coordinates and the first scale pixel accuracy;

[0019] The current digital orthophoto is acquired according to the map range and displayed in the two-dimensional window according to the center of the map.

[0020] Optionally, the viewing angle parameters include camera center and viewing distance;

[0021] The step of calculating the map center of the current digital orthophoto according to the viewing angle parameter of the current point cloud data comprises:

[0022] Obtain the scene coordinates of the camera center in the current point cloud data;

[0023] Obtaining the world coordinates of the camera center according to the scene coordinates of the camera center and a preset conversion relationship between the scene coordinates and the world coordinates;

[0024] Calculate the world coordinates of the camera's sight point according to the world coordinates of the camera center and the visible distance;

[0025] The map center is obtained by using the abscissa and ordinate in the world coordinates of the camera viewpoint as the abscissa and ordinate of the map center respectively.

[0026] Optionally, the viewing angle parameters include a field of view angle and a viewing distance;

[0027] The step of calculating the first scale pixel accuracy of the current digital orthophoto according to the viewing angle parameter of the current point cloud data and the map projection coordinate system corresponding to the current point cloud data comprises:

[0028] According to the field of view angle and the visual distance, the visual range is calculated according to the formula EF=2*OO'*tan(fov / 2), wherein EF represents the visual range, OO' represents the visual distance, and fov represents the field of view angle;

[0029] Obtaining a unit value of a map projection coordinate system corresponding to the current point cloud data and a latitude band corresponding to the current point cloud data, wherein the unit value represents a geographical distance represented by each unit in the map projection coordinate system;

[0030] The relative circumference of the latitude band is calculated according to the formula cicum=cos(|latitude|), wherein cicum represents the relative circumference, latitude represents the latitude band, and || represents taking an absolute value;

[0031] Calculate the reference visible range according to the visible range, the unit value and the relative circumference according to the formula EF'=EF / metersPerUnit / cicum, where EF' represents the reference visible range and metersPerUnit represents the unit value;

[0032] According to the length and width of the two-dimensional window, the reference visible range is converted to the canvas coordinate system according to the formula R'=EF' / ((H+W) / 2) to obtain the first scale pixel accuracy, wherein R' represents the first scale pixel accuracy, H and W represent the length and width of the two-dimensional window respectively, and the first scale pixel accuracy represents the geographical distance represented by a pixel point in the two-dimensional window.

[0033] Optionally, the interface adjustment operation includes a second adjustment operation on the digital orthophoto displayed in the two-dimensional window;

[0034] The step of adjusting the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window in a linked manner in response to the interface adjustment operation includes:

[0035] In response to the second adjustment operation, obtaining second canvas coordinates of the second adjustment operation in the two-dimensional window;

[0036] The point cloud data displayed in the three-dimensional window are adjusted in a linked manner according to the second canvas coordinates and the map range and map center of the current digital orthophoto to obtain the current point cloud data.

[0037] Optionally, the step of adjusting the point cloud data displayed in the three-dimensional window in a linked manner according to the second canvas coordinates and the map range and map center of the current digital orthophoto to obtain the current point cloud data includes:

[0038] Acquire a second display level of the current digital orthophoto;

[0039] Determining a second scale pixel precision according to the second display level and a preset level correspondence relationship, wherein the level correspondence relationship represents a one-to-one correspondence between each scale pixel precision and each display level;

[0040] Calculating a scene display radius of the current point cloud data according to the pixel accuracy of the second scale and the length and width of the two-dimensional window;

[0041] Calculating the visible range of the current point cloud data according to the scene display radius and the map center of the current digital orthophoto;

[0042] Calculating the visible distance of the current point cloud data according to the scene display radius and the field of view of the point cloud data displayed in the three-dimensional window;

[0043] The point cloud data displayed in the three-dimensional window is adjusted according to the field of view angle, the visible range and the visible distance of the point cloud data displayed in the three-dimensional window to obtain current point cloud data.

[0044] Optionally, the second adjustment operation is a bird's-eye view operation on the digital orthophoto displayed in the two-dimensional window, and the current point cloud data is a three-dimensional bird's-eye view;

[0045] The step of adjusting the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window in a linked manner in response to the interface adjustment operation also includes:

[0046] Generate a side view corresponding to the current point cloud data according to the three-dimensional top view and the preset height, wherein the side view is used to indicate the elevation of the object;

[0047] The three-dimensional top view and the side view are displayed in the three-dimensional window.

[0048] Optionally, the information extraction operation is a boundary drawing operation; in response to the information extraction operation, the step of performing linkage drawing in the current digital orthophoto and the current point cloud data to obtain drawing information of the object to be extracted includes:

[0049] In response to the boundary drawing operation, synchronously and real-timely displaying a drawing process corresponding to the boundary drawing operation in the current digital orthophoto and the current point cloud data;

[0050] When it is detected that the boundary drawing operation stops, the two-dimensional boundary of the object to be extracted is displayed in the current digital orthophoto, and the three-dimensional boundary of the object to be extracted is displayed in the current point cloud data.

[0051] Optionally, the electronic device pre-stores a plurality of aerial photographs, the aerial photographs having shooting location information; the data linkage interface further comprises an aerial photograph window, the aerial photograph window being used to display the aerial photographs;

[0052] After the step of responding to the interface adjustment operation and linking the current digital orthophoto displayed in the two-dimensional window with the current point cloud data displayed in the three-dimensional window, the method further includes:

[0053] According to the map range and the map center, a current aerial photograph is obtained from the plurality of aerial photographs, and the current aerial photograph is displayed in the aerial photograph window;

[0054] The shooting location information of the current aerial photograph is located within the map range and is closest to the center of the map.

[0055] Optionally, the data linkage interface further includes a thumbnail window;

[0056] After the step of responding to the interface adjustment operation and linking the current digital orthophoto displayed in the two-dimensional window with the current point cloud data displayed in the three-dimensional window, the method further includes:

[0057] According to the map range, all reference aerial photographs are determined from the plurality of aerial photographs, and thumbnails of each of the reference aerial photographs are arranged and displayed in the thumbnail window; wherein the shooting location information of each of the reference aerial photographs is within the map range;

[0058] The thumbnail of the current aerial survey photograph is determined from all thumbnails displayed in the thumbnail window, and the thumbnail of the current aerial survey photograph is highlighted.

[0059] Optionally, before the step of adjusting the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window in a linkage manner in response to the interface adjustment operation, the method further comprises:

[0060] In response to the trigger operation, the digital orthophoto is displayed in the two-dimensional window, at least one view of the point cloud data is displayed in the three-dimensional window, and the aerial photograph whose shooting location information is within the map range and is closest to the map coordinates corresponding to the position of the mouse in the two-dimensional window or the three-dimensional window is displayed in the aerial photograph window;

[0061] The map center of the point cloud data is consistent with the map center of the digital orthophoto and the display range of the point cloud data is consistent with the map range of the digital orthophoto, and the at least one view includes at least one of a main view, a left view, a top view and a front view.

[0062] In a second aspect, an embodiment of the present application further provides an object extraction device, which is applied to an electronic device, wherein the electronic device is pre-configured with a data linkage interface, wherein the data linkage interface includes a two-dimensional window and a three-dimensional window, wherein the two-dimensional window is used to display a digital orthophoto, and the three-dimensional window is used to display point cloud data;

[0063] The device comprises:

[0064] A linkage adjustment module, for responding to the interface adjustment operation, linkage adjustment of the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window, so that the map center of the current point cloud data is consistent with the map center of the current digital orthophoto and the display range of the current point cloud data is consistent with the map range of the current digital orthophoto;

[0065] A linkage drawing module, used for responding to the information extraction operation, performing linkage drawing on the current digital orthophoto and the current point cloud data to obtain drawing information of the object to be extracted;

[0066] The vectorization module is used to perform vectorization based on the drawing information of the object to be extracted to obtain the extracted object information.

[0067] In a third aspect, an embodiment of the present application further provides an electronic device, comprising a processor and a memory, wherein the memory is used to store a program, and the processor is used to implement the object extraction method in the first aspect when executing the program.

[0068] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the object extraction method in the first aspect described above.

[0069] Compared with the prior art, the embodiments of the present application provide an object extraction method, device, electronic device and storage medium. By configuring a data linkage interface in the electronic device, the data linkage interface includes a two-dimensional window for displaying a digital orthophoto and a three-dimensional window for displaying point cloud data. When the cartographer adjusts the interface, the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window are linked and adjusted so that the current digital orthophoto and the current point cloud data correspond to each other. In this way, the cartographer can see the corresponding elevation information in real time through the current point cloud data in the three-dimensional window. When the cartographer performs an information extraction operation, linkage drawing is performed in the current digital orthophoto and the current point cloud data. In this way, the cartographer can quickly and accurately identify the objects that need to be vectorized. In this way, accurate object information can be obtained, and the accuracy of the produced map is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 An example diagram showing shooting information of aerial survey photographs provided in an embodiment of the present application is shown.

[0071] Figure 2 An example diagram of an aerial photograph provided by an embodiment of the present application is shown.

[0072] Figure 3 An example diagram of a digital orthophoto provided by an embodiment of the present application is shown.

[0073] Figure 4 An example of point cloud data provided by an embodiment of the present application is shown Figure 1 .

[0074] Figure 5 The following is a schematic diagram showing a process of an object extraction method provided in an embodiment of the present application. Figure 1 .

[0075] Figure 6 An example of a data linkage interface provided by an embodiment of the present application is shown Figure 1 .

[0076] Figure 7 An example diagram of a boundary drawing operation provided by an embodiment of the present application is shown.

[0077] Figure 8 An example diagram of the boundary of an object to be extracted provided by an embodiment of the present application is shown.

[0078] Fig. 9 An example of a data linkage interface provided by an embodiment of the present application is shown Figure 2 .

[0079] Fig.10 An example of a data linkage interface provided by an embodiment of the present application is shown Figure 3 .

[0080] Fig.11 An example of a data linkage interface provided by an embodiment of the present application is shown Figure 4 .

[0081] Fig.12 An example of a data linkage interface provided by an embodiment of the present application is shown Figure 5 .

[0082] Fig.13 A schematic diagram of the coordinate transformation relationship provided in an embodiment of the present application is shown.

[0083] Fig.14 A schematic diagram of a viewing cone provided in an embodiment of the present application is shown.

[0084] Fig.15 A schematic diagram of the geometric relationship provided in an embodiment of the present application is shown.

[0085] Fig.16 A schematic diagram of a two-dimensional image pyramid model provided in an embodiment of the present application is shown.

[0086] Fig.17 A schematic diagram showing the hierarchical correspondence provided in an embodiment of the present application is shown.

[0087] Fig.18 An example of point cloud data provided by an embodiment of the present application is shown Figure 2 .

[0088] Fig.19 An example of a data linkage interface provided by an embodiment of the present application is shown Figure 6 .

[0089] Fig. 20 A block diagram of an object extraction device provided in an embodiment of the present application is shown.

[0090] Fig.21 A block diagram of an electronic device provided in an embodiment of the present application is shown.

[0091] Icons: 100 - object extraction device; 101 - trigger response module; 102 - linkage adjustment module; 104 - linkage drawing module; 106 - vectorization module; 10 - electronic device; 11 - processor; 12 - memory; 13 - bus. DETAILED DESCRIPTION

[0092] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present application.

[0093] When making high-precision maps, the commonly used data production systems are mainly based on digital orthophotos for drawing. The data production system provides raster vectorization or manual vectorization tools. For example, ArcGIS Map, a data production system developed by ESRI, provides raster vectorization tools such as Raster to Point, Raster to Polygon, Raster to Polyline, and manual vectorization tools such as regon. Cartographers can use raster vectorization or manual vectorization tools to select objects found in digital orthophotos for vectorization operations to obtain corresponding object information. For example, cartographers use the mouse to select the boundaries of features in digital orthophotos to obtain the extracted features, and then give the feature type of the extracted features, such as windbreaks, shrubs, and telephone poles, so as to obtain object information.

[0094] However, the existing technology has the following problems: since digital orthophotos express two-dimensional scenes and lack elevation information, the lack of elevation information makes it impossible to recover the height information of objects above the ground, such as power lines, cable wires, windbreaks, etc., which in turn makes it impossible to obtain accurate object information, affecting the accuracy of the produced map.

[0095] In order to solve this problem, the embodiment of the present application configures a data linkage interface in the electronic device, and the data linkage interface includes a two-dimensional window for displaying digital orthophotos and a three-dimensional window for displaying point cloud data, and the two-dimensional window and the three-dimensional window are linked, that is, the cartographer operates in the two-dimensional window, and the three-dimensional window will be displayed synchronously, and the cartographer operates in the three-dimensional window, and the two-dimensional window will be displayed synchronously; in this way, the cartographer can see the corresponding elevation information in real time through the current point cloud data in the three-dimensional window, so that the objects that need to be vectorized can be quickly and accurately identified, and accurate object information can be obtained, thereby improving the accuracy of the produced map. The following is a detailed introduction.

[0096] The electronic device in the embodiment of the present application may be a personal computer, or a smart phone, a tablet computer, a server, etc. Users may select different devices according to actual application scenarios, which are not limited here. The following embodiments are described using a personal computer as an example.

[0097] In the embodiment of the present application, in the object extraction process, the data that may be used include aerial photographs, digital orthophotos and point cloud data. For ease of understanding, these three types of data are first introduced.

[0098] Aerial photographs are original aerial or space photographs. Usually, aerial photographs have shooting information, which can be EXIF ​​(Exchangeable image file format). EXIF ​​is specially set for photos of digital cameras and can record the attribute information and shooting data of digital photos. For example, Figure 1 As shown, the shooting information may include: attribute information of the shooting device when shooting the aerial survey photograph, such as contrast, saturation, clarity, etc.; and GPS information of the shooting device when shooting the aerial survey photograph, such as latitude, longitude, altitude, etc.

[0099] At the same time, aerial photographs also retain the original details of aerial or space photos, such as wires, poles, cable cables, etc. Figure 2 The aerial photograph shown includes power lines and poles. Therefore, aerial photographs can provide auxiliary verification of data accuracy.

[0100] Digital Orthophoto Map (DOM) is a set of digital orthophotos generated by digital differential correction and mosaicking of aerial or aerospace photographs and cropping them according to a certain map range. It is an image with both map geometric accuracy and image characteristics.

[0101] Since digital orthophotos are obtained by processing aerial or aerospace photos, the original details of the aerial or aerospace photos are missing, so digital orthophotos cannot accurately determine the object type of the extracted object. Figure 3 As shown in the figure, in the digital orthophoto, windbreaks and shrubs appear as green canopies and cannot be distinguished. Figure 3 As shown in the figure, in the digital orthophoto, the objects above the ground surface will produce shadows, thus interfering with the definition of the boundaries of the objects.

[0102] Point cloud data is a collection of massive points of target surface features. During its production process, the texture color is rendered using the color of the surrounding objects, resulting in color texture that does not match the actual situation. For example, Figure 4 As shown in the figure, the high-voltage wires in the field should have been gray-black, but the point cloud data was rendered in green, which made it impossible to accurately calibrate the corresponding ground objects through the point cloud data.

[0103] From the above introduction, it can be seen that in the object extraction process, if only one of the three types of data, aerial photographs, digital orthophotos and point cloud data, is used to extract objects, accurate object information cannot be obtained. Therefore, the embodiment of the present application uses a technical solution of linking different windows to combine the three types of data, aerial photographs, digital orthophotos and point cloud data, to make up for the defects of single data, ensure accurate object information, and thus improve the accuracy of the produced map.

[0104] Please refer to Figure 5 , Figure 5 A schematic diagram of a flow chart of an object extraction method provided in an embodiment of the present application is shown. The object extraction method is applied to an electronic device and may include the following steps:

[0105] S101, in response to the interface adjustment operation, the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window are linked and adjusted so that the map center of the current point cloud data is consistent with the map center of the current digital orthophoto and the display range of the current point cloud data is consistent with the map range of the current digital orthophoto.

[0106] The electronic device may be pre-configured with a data linkage interface, such as Figure 6 As shown, the data linkage interface may include a two-dimensional window and a three-dimensional window, the two-dimensional window is used to display digital orthophotos, and the three-dimensional window is used to display point cloud data.

[0107] Interface adjustment operations can be Figure 6 The adjustment operation of the digital orthophoto displayed in the two-dimensional window shown can also be Figure 6 The adjustment operation of the point cloud data displayed in the three-dimensional window shown in the figure. The interface adjustment operation can be, but is not limited to, translation operation, zoom operation, rotation operation, top view operation, etc.

[0108] When the cartographer adjusts the data linkage interface, the electronic device performs two-dimensional and three-dimensional linkage so that the current digital orthophoto displayed in the two-dimensional window corresponds to the current point cloud data displayed in the three-dimensional window, that is, the map center of the current point cloud data is consistent with the map center of the current digital orthophoto and the display range of the current point cloud data is consistent with the map range of the current digital orthophoto.

[0109] The current digital orthophoto refers to the digital orthophoto displayed in the 2D window at the current moment, and the current point cloud data refers to the point cloud data displayed in the 3D window at the current moment.

[0110] 2D-3D linkage refers to operating 2D or 3D scenes through input and output devices such as a mouse to achieve synchronous operation of 2D and 3D scenes. 2D scenes are digital orthophotos, and 3D scenes are point cloud data. That is, through the coordinate conversion mechanism, the geographic coordinates in the digital orthophotos correspond to the spatial positions in the point cloud data, and through the interactive event trigger mechanism, they are synchronized when their positions change, thereby achieving consistency of data at the visualization level.

[0111] S102, in response to the information extraction operation, performing linkage drawing in the current digital orthophoto and the current point cloud data to obtain drawing information of the object to be extracted.

[0112] In this embodiment, the information extraction operation can be an operation performed on a digital orthophoto displayed in a two-dimensional window, or an operation performed on point cloud data displayed in a three-dimensional window. The object to be extracted can be various objects that need to extract information in map drawing, such as ground objects (such as trees, houses, electric poles, etc.), obstacles, etc. The following embodiment is described by taking ground objects as an example.

[0113] In a possible implementation, the information extraction operation may be a boundary drawing operation, that is, drawing the boundary of the object to be extracted. Figure 6 The digital orthophoto displayed in the two-dimensional window shown in the figure draws the boundary of the object to be extracted; it can also be for Figure 6 The point cloud data displayed in the three-dimensional window shown in the figure is used to draw the boundary of the object to be extracted. For example, a point selection operation is performed on the boundary of the object to be extracted.

[0114] Linked drawing in the current digital orthophoto and the current point cloud data refers to the simultaneous real-time display of the drawing process corresponding to the boundary drawing operation in the current digital orthophoto and the current point cloud data. Figure 7 The digital orthophoto shown in the figure shows the basketball court, and the selection operations of A, B, and C are performed in sequence. Figure 7 The drawing process corresponding to the point selection operation is synchronously displayed in real time in the corresponding point cloud data.

[0115] After the boundary drawing operation is completed, the boundary of the object to be extracted can be obtained. The boundary of the object to be extracted can be a two-dimensional boundary of the object to be extracted in the current digital orthophoto, or a three-dimensional boundary of the object to be extracted in the current point cloud data. For example, Figure 8 As shown, for the object to be extracted, after the boundary drawing operation is completed, the two-dimensional boundary is displayed in the two-dimensional window, and the three-dimensional boundary is displayed in the three-dimensional window.

[0116] In another possible implementation, the information extraction operation may also be an object supplementation operation, that is, supplementing the outline of the object to be extracted. For example, if the object to be extracted in the digital orthophoto is blocked, the digital orthophoto and the point cloud data may be linked together to supplement the outline of the object to be extracted in the digital orthophoto according to the point cloud data to be extracted.

[0117] It should be noted that the information extraction operation may be some possible operations that cartographers may perform on the extracted objects during the mapping process. The above-mentioned boundary drawing operation and object supplementation operation are only examples. The embodiments of the present application do not impose any restrictions on this. The following embodiments are described using the boundary drawing operation as an example.

[0118] S103, performing vectorization based on the drawing information of the object to be extracted to obtain extracted object information.

[0119] In this embodiment, the object information may be the object type of the object to be extracted, for example, the type of ground feature, the type of obstacle, etc. Vectorization is performed based on the drawing information of the object to be extracted, that is, the object type of the object to be extracted is given.

[0120] When the information extraction operation is a boundary drawing operation, vectorization is performed based on the drawing information of the object to be extracted, that is, the boundary of the object to be extracted is vectorized. Vectorizing the boundary of the object to be extracted means giving the object type of the object to be extracted, for example, a house, a telephone pole, a windbreak, etc. The object type of the object to be extracted can be manually given by a cartographer, or it can be automatically selected from a plurality of object types pre-stored in an electronic device according to set rules, and the embodiments of the present application do not impose any restrictions on this. The object information after extraction may include: the boundary of the object to be extracted and the object type of the object to be extracted.

[0121] In one possible scenario, since digital orthophotos are processed from aerial photographs, the original details of the aerial photographs are missing; and the texture color of point cloud data is rendered using the color of the surrounding objects during the production process, there may be a situation where the color texture does not match the actual situation. Therefore, in the object extraction process, when combining digital orthophotos and point cloud data, there may still be a problem that the drawing information (for example, boundaries) of the extracted object cannot be accurately determined during the vectorization process.

[0122] To address this problem, the embodiment of the present application introduces aerial photographs based on digital orthophotos and point cloud data, and uses the three together to provide rich and effective data and spatial information to cartographers, helping them to quickly and accurately find the drawing information of the object to be extracted for vectorization operations, thereby obtaining accurate object information.

[0123] Therefore, please refer to Fig. 9 The data linkage interface may also include an aerial photograph window, which is used to display aerial photographs. At the same time, the electronic device pre-stores multiple aerial photographs, which have shooting location information. The shooting location information refers to the GPS information of the shooting device (e.g., camera, etc.) when shooting the aerial photograph. Figure 1 The GPS information in the shooting information is shown.

[0124] exist Figure 5 On the basis of, after step S101, the object extraction method provided in the embodiment of the present application may further include step S10B.

[0125] S10B, obtaining a current aerial photograph from multiple aerial photographs according to the map range and the map center, and displaying the current aerial photograph in the aerial photograph window; wherein the shooting location information of the current aerial photograph is within the map range and is closest to the map center.

[0126] When the cartographer adjusts the data linkage interface, the electronic device not only links the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window in two or three dimensions, but also links the digital orthophoto displayed in the two-dimensional window, the point cloud data displayed in the three-dimensional window and the aerial survey photograph displayed in the aerial photograph window, so as to display the current aerial survey photograph whose shooting location information is within the map range and closest to the center of the map in the aerial photograph window.

[0127] In this way, cartographers can quickly and accurately find the drawing information of the object to be extracted and perform vectorization operations by combining the current orthophoto, the photograph details retained in the current aerial survey photograph, and the elevation information in the current point cloud data, thereby obtaining accurate object information.

[0128] In one possible implementation, see Fig.10 The data linkage interface may also include a thumbnail window, which is used to display thumbnails of aerial photographs.

[0129] Therefore, in Figure 5 On the basis of, after step S101, the object extraction method provided in the embodiment of the present application may further include steps S10C to S10D.

[0130] S10C, according to the map range, all reference aerial survey photographs are determined from the multiple aerial survey photographs, and a thumbnail of each reference aerial survey photograph is arranged and displayed in a thumbnail window; wherein the shooting location information of each reference aerial survey photograph is within the map range.

[0131] S10D, determining the thumbnail of the current aerial survey photograph from all thumbnails displayed in the thumbnail window, and highlighting the thumbnail of the current aerial survey photograph.

[0132] When the cartographer adjusts the data linkage interface, the electronic device determines the reference aerial photographs whose shooting location information is within the map range from the pre-stored multiple aerial photographs, and arranges the thumbnails of each reference aerial photograph in the thumbnail window. At the same time, the current aerial photograph closest to the center of the map is found from the multiple reference aerial photographs, and is enlarged and displayed in the photograph window. At the same time, the thumbnail of the current aerial photograph is highlighted in the thumbnail window.

[0133] The following is an introduction to the triggering process of the data linkage interface.

[0134] exist Figure 5 On the basis of, before step S101, the object extraction method provided in the embodiment of the present application may further include step S10A.

[0135] S10A, in response to a trigger operation, displays a digital orthophoto in a two-dimensional window, displays at least one view of point cloud data in a three-dimensional window, and displays in an aerial photograph window an aerial photograph whose shooting location information is within the map range and is closest to the map coordinates corresponding to the position of the mouse in the two-dimensional window or the three-dimensional window.

[0136] The map center of the point cloud data is consistent with the map center of the digital orthophoto and the display range of the point cloud data is consistent with the map range of the digital orthophoto, and at least one view includes at least one of a main view, a left view, a top view and a front view.

[0137] In this embodiment, the initial interface of the data linkage interface is as follows: Fig.11 As shown, when the cartographer starts to extract the ground object, he clicks the "ground object extraction" button in the initial interface through an IO device such as a mouse to trigger the electronic device to extract the ground object. Therefore, the triggering operation can be the cartographer's clicking operation on the "ground object extraction" button in the initial interface.

[0138] After triggering the feature extraction, the data linkage interface can be switched to Fig.10 As shown, at this time, the 2D window displays the digital orthophoto, and the 3D window displays the point cloud data consistent with the current orthophoto. The cartographer uses the mouse to adjust the digital orthophoto displayed in the 2D window or the point cloud data displayed in the 3D window. At the same time, the aerial photograph window displays the aerial photograph, the shooting position information of which is within the map range and is closest to the map coordinates corresponding to the position of the mouse in the 2D window or the 3D window.

[0139] Since point cloud data is three-dimensional data, different viewing angles will have different display effects. Therefore, in order to better help cartographers obtain object information, after triggering the feature extraction, the data linkage interface can also be switched to Fig.12As shown, Fig.10 Compared with the data linkage interface shown, this data linkage interface can display the main view, left view, top view and front view of the point cloud data in a three-dimensional window, thereby helping cartographers to quickly and accurately identify the objects that need to be vectorized.

[0140] The following is a detailed description of step S101.

[0141] In one possible implementation, the interface adjustment operation may include a first adjustment operation on the point cloud data displayed in the three-dimensional window. The first adjustment operation may be at least one of a translation operation, a zoom operation, a rotation operation, and a top-down operation on the point cloud data displayed in the three-dimensional window.

[0142] Therefore, in Figure 5 On the basis of this, the process of responding to the interface adjustment operation in step S101 to link and adjust the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window may include S1011 to S1012.

[0143] S1011 , in response to a first adjustment operation, obtaining first canvas coordinates of the first adjustment operation in the three-dimensional window.

[0144] The first canvas coordinates refer to the coordinates of the mouse point position corresponding to the first adjustment operation in the three-dimensional window.

[0145] S1012, according to the first canvas coordinates and the viewing angle parameters of the current point cloud data, the digital orthophoto displayed in the two-dimensional window is adjusted in a linked manner to obtain a current digital orthophoto.

[0146] That is, when the cartographer makes adjustments to the point cloud data displayed in the three-dimensional window, the electronic device links the three-dimensional with the two-dimensional.

[0147] The main implementation of 3D linkage with 2D includes: taking the map center of the current point cloud data displayed in the 3D window as the map center of the current digital orthophoto to be displayed in the 2D window, and determining the map range of the current digital orthophoto to be displayed in the 2D window according to the display range of the current point cloud data, and then displaying the current digital orthophoto in the 2D window according to the map center and the map range, so that the map center of the current digital orthophoto is consistent with the map center of the current point cloud data and the map range of the current digital orthophoto is consistent with the display range of the current point cloud data.

[0148] In the embodiment of the present application, during the object extraction process, the coordinates that may be used include screen coordinates, canvas coordinates, scene coordinates, and world coordinates. For ease of understanding, these four types of coordinates are first introduced.

[0149] Screen coordinates refer to the coordinates of a point on the screen in the display, which are related to the display range of the display. For example, if the display range of the display is 1920×1080, if a screen coordinate system is established with the lower left corner of the display as the origin, the horizontal direction of the display as the horizontal coordinate, and the vertical direction of the display as the vertical coordinate, the horizontal coordinate range is (0,1920) and the vertical coordinate range is (0,1080). In this way, based on the established screen coordinate system, horizontal coordinate range, and vertical coordinate range, the screen coordinates of any point can be obtained.

[0150] Canvas coordinates refer to the coordinates of a point in a digital orthophoto in a 2D window, or the coordinates of a point in a point cloud in a 3D window. Canvas coordinates are related to the display range of the 2D window or 3D window, and to the proportion of the 2D window or 3D window on the display. For example, the data linkage interface displayed on the display is as follows: Figure 6 As shown, the two-dimensional window and the three-dimensional window each occupy For example, a point in a two-dimensional window has a y-coordinate equal to that of the screen coordinates, and a y-coordinate equal to that of the screen coordinates. Accordingly, if the display displays the two-dimensional window in full screen, for any point in the two-dimensional window, the canvas coordinates of the point are consistent with the screen coordinates.

[0151] World coordinates refer to the coordinates of any point in the real world, with the center of the world (longitude 0, latitude 0) as the origin. If the world coordinates of a point are expressed as (X, Y, Z), then X represents the longitude of the point, Y represents the latitude of the point, and Z represents the elevation of the point, that is, the vertical distance of the point above sea level.

[0152] Scene coordinates are converted from world coordinates. The difference between them is that world coordinates are determined by the world center (0,0) as the origin, while scene coordinates are determined by the user-defined position as the origin. For example, if you need to make a map of Beijing, you can change the origin from the world center (0,0) to the lower left corner of Beijing, and then convert the world coordinates of each point in Beijing according to the same conversion relationship to get the scene coordinates of each point in Beijing. Scene coordinates can be expressed as (x, y, z).

[0153] Obviously, the horizontal coordinate, vertical coordinate, and vertical coordinate of the world coordinate and the scene coordinate represent the longitude, latitude, and vertical distance above the sea level respectively. The only difference is that the origin is different.

[0154] Therefore, if Fig.13As shown, screen coordinates, canvas coordinates, scene coordinates and world coordinates can be converted, and the conversion logic includes: converting canvas coordinates and screen coordinates according to the size relationship between the canvas (i.e., two-dimensional window or three-dimensional window) and the display; converting world coordinates and scene coordinates according to the relationship between the two origins. At the same time, conversion can also be performed between canvas coordinates and scene coordinates, and between canvas coordinates and world coordinates. Since canvas coordinates are two-dimensional coordinates, the conversion is performed between the horizontal and vertical coordinates of canvas coordinates and scene coordinates, and between the horizontal and vertical coordinates of canvas coordinates and world coordinates. In addition, the conversion process involved is a prior art and will not be repeated here.

[0155] In this embodiment, when three-dimensional is linked with two-dimensional, the control of the two-dimensional scene needs to be completed through the scale pixel accuracy of the image. The field of view of the three-dimensional scene camera remains relatively unchanged. What changes are the coordinates and direction of the camera, as well as the farthest distance that can be seen, that is, the camera center and the visible distance.

[0156] like Fig.14 As shown in the figure, the far and near sections constructed in the three-dimensional scene are both rectangular viewing cones. The distance from the observation point to the far section is the visible distance, the range of the far section is the visible range, and the angle between the edge of the visible range and the line connecting the observation point is the field of view (FOV). The observation point here is the camera in the figure.

[0157] based on Fig.14 The frustum shown in the figure can be used to obtain the geometric relationship diagram of the three-dimensional scene calculation parameters. Fig.15 As shown. Among them, point O is the camera viewpoint of the three-dimensional scene, that is, the camera center. The plane constructed by ABCD is the field of view plane, called the ABCD plane. Point O' is the camera's visual point; OO' is the farthest distance seen, that is, the visible distance. Point O' is a point on the ABCD plane, and OO' constructs the normal vector straight line of the ABCD plane. The maximum range EF that can be seen based on point O is the visible range. L is the straight line constructed by EF, and L is on plane ABCD and perpendicular to OO'. Therefore, the viewing angle parameters of the three-dimensional scene may include, but are not limited to, the field of view angle, the camera center and the visible distance.

[0158] The following is based on Fig.13 The coordinate transformation relationship shown and Fig.15 The geometric relationship diagram shown introduces the detailed implementation of S1012. The process of adjusting the digital orthophoto displayed in the two-dimensional window according to the first canvas coordinates and the viewing angle parameters of the current point cloud data in S1012 to obtain the current digital orthophoto may include S10121 to S10124.

[0159] S10121, calculating the map center of the current digital orthophoto according to the viewing angle parameters of the current point cloud data.

[0160] In this embodiment, the viewing angle parameters of the current point cloud data may include the camera center and the visible distance. The process of calculating the map center of the current digital orthophoto according to the viewing angle parameters of the current point cloud data in S10121 may include:

[0161] S10121-1, obtain the scene coordinates of the camera center in the current point cloud data;

[0162] S10121-2, obtaining the world coordinates of the camera center according to the scene coordinates of the camera center and a preset conversion relationship between the scene coordinates and the world coordinates;

[0163] S10121-3, calculating the world coordinates of the camera's viewpoint according to the world coordinates of the camera center and the visible distance;

[0164] S10121-4, using the horizontal coordinate and vertical coordinate in the world coordinate of the camera's sight point as the horizontal coordinate and vertical coordinate of the map center respectively, to obtain the map center.

[0165] That is, first obtain the scene coordinates (x O ,y O ,z O ); Then, the scene coordinates (x O ,y O ,z O ) is converted to world coordinates (X O ,Y O ,Z O ); then project point O downward along the Z axis to the far section of the viewing cone to obtain the world coordinates (X O' ,Y O' ,Z O' ); Finally, the horizontal and vertical coordinates of point O' are used as the map center of the two-dimensional scene to obtain the map center of the current digital orthophoto (X O' ,Y O' ).

[0166] S10122, calculating the first scale pixel accuracy of the current digital orthophoto according to the viewing angle parameters of the current point cloud data and the map projection coordinate system corresponding to the current point cloud data.

[0167] In this embodiment, the viewing angle parameter of the current point cloud data may further include a field of view angle. The process of calculating the first scale pixel accuracy of the current digital orthophoto according to the viewing angle parameter of the current point cloud data and the map projection coordinate system corresponding to the current point cloud data in S10122 may include:

[0168] S10122-1, according to the field of view angle and the viewing distance, the viewing range is calculated according to the formula EF=2*OO'*tan(fov / 2), where EF represents the viewing range, OO' represents the viewing distance, and fov represents the field of view angle;

[0169] S10122-2, obtaining a unit value of a map projection coordinate system corresponding to the current point cloud data and a latitude band corresponding to the current point cloud data, wherein the unit value represents a geographical distance represented by each unit in the map projection coordinate system;

[0170] S10122-3, calculate the relative circumference of the latitude band according to the formula cicum=cos(latitude), where cicum represents the relative circumference, latitude represents the latitude band, and || represents taking the absolute value;

[0171] S10122-4, calculate the reference visible range according to the visible range, the unit value and the relative perimeter according to the formula EF'=EF / metersPerUnit / cicum, where EF' represents the reference visible range and metersPerUnit represents the unit value;

[0172] S10122-5, according to the length and width of the two-dimensional window, convert the reference visible range to the canvas coordinate system according to the formula R'=EF' / ((H+W) / 2) to obtain the first scale pixel accuracy, where R' represents the first scale pixel accuracy, H and W represent the length and width of the two-dimensional window respectively, and the first scale pixel accuracy represents the geographical distance represented by a pixel point in the two-dimensional window.

[0173] That is, first calculate the length of O'F according to the trigonometric sine theorem, and then calculate the length of EF, where EF is equal to twice O'F; then, obtain the projection parameter Project of the map projection coordinate system corresponding to the current point cloud data, and obtain the unit value therein, where the unit value is: meter / unit, which represents the geographical distance represented by a unit in the map projection coordinate system; next, since the earth is a sphere, it is necessary to consider the deformation difference under different latitude bands and calculate the relative circumference of the current latitude band, which is the latitude band where the map center of the current point cloud data is located; then calculate the reference visible range EF' under the map projection coordinate system based on EF, the unit value and the relative circumference of the current latitude band; finally, convert the pixel accuracy corresponding to the canvas size (i.e., the two-dimensional window) based on the reference visible range EF' to obtain the first scale pixel accuracy of the current digital orthophoto.

[0174] Since the length and width of the two-dimensional window are inconsistent, half of the sum of the length and width is taken as the canvas size to calculate the first scale pixel accuracy. The unit of the first scale pixel accuracy is: meter / pixel (m / pixel), which represents the geographical distance represented by a pixel point in the two-dimensional window.

[0175] S10123, determining the map range of the current digital orthophoto according to the first canvas coordinates and the first scale pixel accuracy.

[0176] In this embodiment, the process of determining the map range of the current digital orthophoto according to the first canvas coordinates and the first scale pixel accuracy in S10123 may include:

[0177] S10123-1, determining a first display level according to a first scale pixel precision and a preset level correspondence relationship, wherein the level correspondence relationship represents a one-to-one correspondence between each scale pixel precision and each display level.

[0178] The construction of the two-dimensional scene is based on the two-dimensional image pyramid model. Fig.16 As shown, it includes different display levels, namely levels in the figure. Each display level has a corresponding tile. With longitude and latitude [0,0] as the center and longitude and latitude [-180,90] as the upper left corner, the tiles of each display level in the two-dimensional scene are constructed in sequence from left to right and from top to bottom. Tiles are small squares in each display level. Each tile corresponds to 256 pixels. There is only one tile in the 0 display level, and the range of the tile is: longitude range [-180,180], latitude range [-90,90].

[0179] In a two-dimensional scene, each display level has a corresponding scale pixel precision. The hierarchical correspondence between the display level and the scale pixel precision is as follows: Fig.17 As shown, the image level in the first column is the display level, and the ground scale in the third column is the scale pixel accuracy.

[0180] Therefore, according to Fig.17 The hierarchical correspondence shown can determine the display level corresponding to the first scale pixel accuracy R' of the current digital orthophoto calculated in S10122, that is, the first display level.

[0181] It should be pointed out that in practice, it may not be possible to directly Fig.17 The display level corresponding to R' is found in the level correspondence relationship shown. Therefore, it is possible to first determine between which two display levels R' lies, and then use the display level with the smallest precision difference between the two display levels as the display level corresponding to R'.

[0182] S10123-2: Obtain first scene coordinates corresponding to the first adjustment operation according to the first canvas coordinates and a preset conversion relationship between the canvas coordinates and the scene coordinates.

[0183] Since the first adjustment operation is an adjustment operation on the current point cloud data displayed in the 3D window, the first canvas coordinates of the first adjustment operation can be obtained. Fig.13 The coordinate transformation relationship shown transforms the first canvas coordinates into the first scene coordinates.

[0184] S10123-3, according to the first scene coordinates, the preset tile size, the preset map cut origin and the first scale pixel accuracy, according to the formula Calculate the first row number and the first column number in the first display level;

[0185] Among them, x and y represent the horizontal and vertical coordinates of the first scene coordinates, col represents the first row number, row represents the first column number, x0 and y0 represent the horizontal and vertical coordinates of the map cut origin, tileSize represents the tile size, and R' represents the pixel accuracy of the first scale.

[0186] because Fig.16 The pixels corresponding to each tile are 256, so the tile size here is 256. The origin of the map cut is (0,0).

[0187] The first row number and the first column number in the first display level refer to the row number and the column number of the tile to be obtained in the display level obtained in S10123-1. Fig.16, assuming that the first display level is level 10, the first row number calculated according to the above process is 2 and the first column number is 1, then it can be determined that the tile to be obtained is the small black square in level 10.

[0188] S10123-4, according to the first row number and the first column number, according to the formula and The first corner point coordinates are calculated, wherein the first corner point coordinates include the first lower left corner point coordinates (x1, y1) and the first upper right corner point coordinates (x2, y2).

[0189] The first corner point coordinates refer to the lower left corner coordinates and upper right corner coordinates of the tile corresponding to the first row number and the first column number obtained in S10123-3. Fig.16 , assuming that the first row number is 2 and the first column number is 1, the lower left corner coordinates and upper right corner coordinates of the black square in level 10 can be calculated according to the above process.

[0190] S10123-5, determine the map range according to the first display level, the first row number, the first column number, and the first corner point coordinates based on a preset two-dimensional image pyramid model.

[0191] According to the above process, after calculating the first display level, the first row number, the first column number, and the first corner point coordinates, you can Fig.16 In the two-dimensional image pyramid model shown, the range of the corresponding tile is determined, and the range is the map range of the two-dimensional scene, that is, the map range of the current digital orthophoto that needs to be displayed in the two-dimensional window.

[0192] For example, combined with Fig.16 , assuming that the first display level is level10, the first row number is 2, the first column number is 1, and the coordinates of the lower left corner and the upper right corner are also known, the range of the small black square can be determined from the two-dimensional image pyramid model, which is the map range of the current digital orthophoto that needs to be displayed in the two-dimensional window.

[0193] S10124, obtaining the current digital orthophoto according to the map range, and displaying it in a two-dimensional window according to the center of the map.

[0194] After obtaining the map range of the current digital orthophoto to be displayed in the two-dimensional window, the current digital orthophoto can be acquired according to the map range, and the current digital orthophoto is displayed in the two-dimensional window according to the map center calculated in S10121.

[0195] For example, combined with Fig.16, obtain a small black square from the two-dimensional image pyramid model, the small black square is the current digital orthophoto, and then display the small black square in the two-dimensional window according to the map center calculated in S10121.

[0196] In another possible implementation, the interface adjustment operation may include a second adjustment operation on the digital orthophoto displayed in the two-dimensional window. The second adjustment operation may be at least one of a translation operation, a zoom operation, a rotation operation, and a bird's-eye view operation on the digital orthophoto displayed in the two-dimensional window.

[0197] Therefore, in Figure 5 On the basis of this, the process of responding to the interface adjustment operation in step S101 to link and adjust the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window may include S101A to S101B.

[0198] S101A, in response to a second adjustment operation, obtaining second canvas coordinates of the second adjustment operation in the two-dimensional window.

[0199] The second canvas coordinates refer to the coordinates of the mouse point position corresponding to the second adjustment operation in the two-dimensional window.

[0200] S101B, according to the second canvas coordinates and the map range and map center of the current digital orthophoto, the point cloud data displayed in the three-dimensional window are adjusted in a linked manner to obtain the current point cloud data.

[0201] That is, when the cartographer makes adjustments to the digital orthophoto displayed in the two-dimensional window, the electronic device links the two-dimensional with the three-dimensional.

[0202] The realization process of 2D linkage with 3D is the inverse process of 3D linkage with 2D, which mainly includes: determining the scale pixel accuracy of the current digital orthophoto according to the display level of the current digital orthophoto displayed in the 2D window; and then determining the visible range of the current point cloud data to be displayed in the 3D window according to the scale pixel accuracy and map center of the current digital orthophoto. At the same time, when 2D is linked with 3D, the field of view of the 3D scene is fixed and unchanged by default, so the field of view of the point cloud data displayed in the 3D window can be obtained, and the visible distance of the current point cloud data to be displayed in the 3D window can be determined according to the field of view. Afterwards, the point cloud data displayed in the 3D window is adjusted according to the field of view, the visible range and the visible distance, so that the map center of the current point cloud data is consistent with the map center of the current digital orthophoto and the display range of the current point cloud data is consistent with the map range of the current digital orthophoto.

[0203] The detailed implementation of S101B is introduced below. In S101B, the point cloud data displayed in the three-dimensional window is adjusted according to the second canvas coordinates and the map range and map center of the current digital orthophoto to obtain the process of current point cloud data, which may include S101B1 to S101B6.

[0204] S101B1, obtaining the second display level of the current digital orthophoto.

[0205] S101B2, determining a second scale pixel precision according to the second display level and a preset level correspondence relationship, wherein the level correspondence relationship represents a one-to-one correspondence between each scale pixel precision and each display level.

[0206] Since it is 2D linked to 3D, the display level of the 2D scene is known. Therefore, we can first obtain the display level of the current digital orthophoto in the 2D window, that is, the second display level; then Fig.17 The hierarchical correspondence shown can determine the scale pixel accuracy of the current digital orthophoto, that is, the second scale pixel accuracy.

[0207] S101B3, calculating the scene display radius of the current point cloud data according to the second scale pixel accuracy and the length and width of the two-dimensional window.

[0208] Combined with Fig.15 , the scene display radius is EO', that is, half of the maximum range EF that can be seen based on point O. The scene display radius can be calculated according to the second scale pixel accuracy and the length and width of the two-dimensional window according to the formula EO'=((H+W) / 2)*R / 2, where EO' represents the scene display radius, R represents the second scale pixel accuracy, H and W represent the length and width of the two-dimensional window respectively, and the second scale pixel accuracy represents the geographical distance represented by a pixel point in the two-dimensional window.

[0209] S101B4, calculating the visible range of the current point cloud data according to the scene display radius and the map center of the current digital orthophoto.

[0210] In this embodiment, the visible range of the current point cloud data can be calculated according to the scene display radius and the map center of the current digital orthophoto according to the formula n=n=max(x'+EO',y'+EO'),m=min(x'-EO',y'-EO'), where [m,n] represents the visible range, and x' and y' represent the horizontal and vertical coordinates of the map center, respectively.

[0211] S101B5, calculating the visible distance of the current point cloud data according to the scene display radius and the field of view of the point cloud data displayed in the three-dimensional window.

[0212] When 2D is linked to 3D, the default 3D scene field of view is fixed and does not change. Therefore, the field of view of the point cloud data displayed in the 3D window can be directly adjusted. Then, according to the scene display radius and the field of view of the point cloud data displayed in the 3D window, Fig.15 The geometric relationship of the three-dimensional scene calculation parameters shown is used to calculate the visible distance of the current point cloud data using the formula OO'=EO' / tan(fov / 2).

[0213] S101B6, adjusting the point cloud data displayed in the three-dimensional window according to the field of view, visible range and visible distance of the point cloud data displayed in the three-dimensional window to obtain current point cloud data.

[0214] Since the field of view of the default 3D scene is fixed and does not change when the 3D is linked to the 3D, after obtaining the visible range and visible distance of the current point cloud data that needs to be displayed in the 3D window, the point cloud data displayed in the 3D window can be adjusted according to the field of view, the visible range and the visible distance of the point cloud data displayed in the 3D window to obtain the current point cloud data.

[0215] In one possible scenario, if the second adjustment operation is a top-down operation on the digital orthophoto displayed in the 2D window, the current point cloud data displayed in the 3D window after adjustment is a 3D top view. However, it is impossible to distinguish objects above the ground surface from the 3D top view. For example, for the point cloud data of high-voltage power lines, Figure 4 is a three-dimensional tilt map, Fig.18 It is a three-dimensional top view. Obviously, Figure 4 It can be clearly seen that the high-voltage wires are above the ground, but Fig.18 This cannot be seen in the .

[0216] Based on this, when the second adjustment operation is a bird's-eye view of the digital orthophoto displayed in the two-dimensional window, in addition to displaying the three-dimensional bird's-eye view in the three-dimensional window, it is also necessary to display the side view corresponding to the three-dimensional bird's-eye view to supplement the elevation information of the objects, so as to quickly and accurately identify the objects above the ground in the three-dimensional scene, that is, the objects that need to be extracted, to help cartographers obtain accurate object information.

[0217] Therefore, after S101B, the step of responding to the interface adjustment operation in S101 to link and adjust the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window also includes S101C to S101D.

[0218] S101C, generating a side view corresponding to the current point cloud data according to the three-dimensional top view and the preset height, wherein the side view is used to indicate the elevation of the object;

[0219] S101D, display the 3D top view and side view in the 3D window.

[0220] In this embodiment, the process of generating a side view may be: first, according to the position M of the mouse point in the two-dimensional window, the scene coordinates corresponding to the mouse point are obtained; then, according to the scene coordinates, the point cloud data displayed in the three-dimensional window is converted into a three-dimensional top view; then, the ray method is used to find the vertical intersection point to obtain the ground point P; the three-dimensional top view is based on the ground point P, and starts to translate in real time at a preset height (for example, 3 meters); at the same time, the visible distance threshold of the three-dimensional top view can be set to 50 meters, and the viewing angle of the three-dimensional top view is horizontally extended along the Y-axis to obtain a side view.

[0221] For example, Fig.19 As shown, the digital orthophoto displayed in the two-dimensional window is operated using a mouse, and the corresponding three-dimensional top view and side view are synchronously displayed in the three-dimensional window.

[0222] The following is a detailed description of step S102. In step S102, in response to the information extraction operation, the process of performing linkage drawing in the current digital orthophoto and the current point cloud data to obtain drawing information of the object to be extracted may include steps S1021 to S1022.

[0223] S1021, in response to the boundary drawing operation, synchronously and real-timely displaying a drawing process corresponding to the boundary drawing operation in the current digital orthophoto and the current point cloud data.

[0224] S1022: When it is detected that the boundary drawing operation stops, the two-dimensional boundary of the object to be extracted is displayed in the current digital orthophoto, and the three-dimensional boundary of the object to be extracted is displayed in the current point cloud data.

[0225] The boundary drawing operation can be a point-select operation on the boundary of the feature in the digital orthophoto displayed in the two-dimensional window; it can also be a point-select operation on the boundary of the feature in the point cloud data displayed in the three-dimensional window. Accordingly, if the boundary drawing operation is performed on the digital orthophoto displayed in the two-dimensional window, the drawing process corresponding to the boundary drawing operation will be synchronously displayed in real time in the point cloud data displayed in the three-dimensional window; if the boundary drawing operation is performed on the point cloud data displayed in the three-dimensional window, the drawing process corresponding to the boundary drawing operation will be synchronously displayed in real time in the digital orthophoto displayed in the two-dimensional window.

[0226] After the boundary drawing operation is completed, the two-dimensional boundary of the object to be extracted is displayed in the current digital orthophoto, and at the same time, the three-dimensional boundary of the object to be extracted is displayed in the current point cloud data.

[0227] In an embodiment of the present application, when the two-dimensional scene and the three-dimensional scene are drawn in linkage, first, the two-dimensional scene needs to support rotation and pitch perspectives; then, the elevation rendering mode is used to display the point cloud data in the three-dimensional scene so as to highlight the elevation information of the point cloud data; at the same time, when looking down in the two-dimensional scene, the three-dimensional scene synchronizes the overlooking effect, and the three-dimensional scene displays the three-dimensional top view and side view, so that the objects above the ground surface in the three-dimensional scene, that is, the objects to be extracted, can be quickly and accurately identified; at the same time, when rotating in the two-dimensional scene, different angles can be used to confirm whether the boundaries of the objects are clear and definite; at the same time, the two-dimensional scene and the three-dimensional scene synchronously display the drawing process in real time. For example, when drawing the boundaries of the objects in the two-dimensional scene, the mouse is displayed in the two-dimensional scene and the three-dimensional scene in real time, and each time a point is clicked to draw in the two-dimensional scene, the drawing process is synchronously displayed in real time in the three-dimensional scene.

[0228] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0229] First, through the technical solution of linking different windows, the three types of data, aerial photographs, digital orthophotos and point cloud data, are combined and used. Cartographers can quickly and accurately find the drawing information of the object to be extracted and perform vectorization operations by combining the current orthophotos, the details of the aerial photographs retained in the current aerial photographs, and the elevation information in the current point cloud data, thereby obtaining accurate object information and improving the accuracy of the produced map.

[0230] Secondly, when looking down in a 2D scene, the 3D scene simultaneously displays the 3D top view and side view, so that objects above the ground in the 3D scene can be quickly and accurately identified, that is, the objects that need to be extracted;

[0231] Third, when performing information extraction operations in a two-dimensional scene or a three-dimensional scene, the drawing process is displayed in real time in the two-dimensional scene and the three-dimensional scene simultaneously, so that cartographers can pick out corresponding objects accurately and efficiently.

[0232] In order to execute the corresponding steps in the above method embodiment and each possible implementation mode, an implementation mode of the object extraction device is respectively given below.

[0233] Please refer to Fig. 20 , Fig. 20 The block diagram of the object extraction device 100 provided in the embodiment of the present application is shown. The object extraction device 100 is applied to an electronic device, and includes: a linkage adjustment module 102, a linkage drawing module 104 and a vectorization module 106.

[0234] The linkage adjustment module 102 is used to respond to the interface adjustment operation and linkage-adjust the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window so that the map center of the current point cloud data is consistent with the map center of the current digital orthophoto and the display range of the current point cloud data is consistent with the map range of the current digital orthophoto.

[0235] The linkage drawing module 104 is used to respond to the information extraction operation, perform linkage drawing in the current digital orthophoto and the current point cloud data, and obtain drawing information of the object to be extracted.

[0236] The vectorization module 106 is used to perform vectorization based on the drawing information of the object to be extracted to obtain the extracted object information.

[0237] Optionally, the interface adjustment operation may include a first adjustment operation on the point cloud data displayed in the three-dimensional window; the linkage adjustment module 102 is specifically used to: respond to the first adjustment operation, obtain the first canvas coordinates of the first adjustment operation in the three-dimensional window; according to the first canvas coordinates and the viewing angle parameters of the current point cloud data, linkage adjust the digital orthophoto displayed in the two-dimensional window to obtain the current digital orthophoto.

[0238] Optionally, the linkage adjustment module 102 executes linkage adjustment of the digital orthophoto displayed in the two-dimensional window according to the first canvas coordinates and the viewing angle parameter of the current point cloud data to obtain the current digital orthophoto, including:

[0239] Calculate the map center of the current digital orthophoto according to the viewing angle parameters of the current point cloud data;

[0240] Calculate the first scale pixel accuracy of the current digital orthophoto according to the viewing angle parameters of the current point cloud data and the map projection coordinate system corresponding to the current point cloud data;

[0241] Determine the map range of the current digital orthophoto according to the first canvas coordinates and the first scale pixel accuracy;

[0242] Get the current digital orthophoto according to the map range and display it in a two-dimensional window according to the center of the map.

[0243] Optionally, the viewing angle parameters include the camera center and the visible distance; the linkage adjustment module 102 performs a process of calculating the map center of the current digital orthophoto according to the viewing angle parameters of the current point cloud data, including:

[0244] Obtain the scene coordinates of the camera center in the current point cloud data;

[0245] The world coordinates of the camera center are obtained according to the scene coordinates of the camera center and the pre-set conversion relationship between the scene coordinates and the world coordinates;

[0246] Calculate the world coordinates of the camera's viewpoint based on the world coordinates of the camera center and the visible distance;

[0247] The horizontal coordinate and vertical coordinate in the world coordinate of the camera's viewpoint are used as the horizontal coordinate and vertical coordinate of the map center respectively to obtain the map center.

[0248] Optionally, the viewing angle parameter includes a field of view angle and a visible distance; the linkage adjustment module 102 executes a method of calculating the first scale pixel accuracy of the current digital orthophoto according to the viewing angle parameter of the current point cloud data and the map projection coordinate system corresponding to the current point cloud data, including:

[0249] According to the field of view angle and the viewing distance, the viewing range is calculated according to the formula EF=2*OO'*tan(fov / 2), where EF represents the viewing range, OO' represents the viewing distance, and fov represents the field of view angle;

[0250] Get the unit value of the map projection coordinate system corresponding to the current point cloud data, and the latitude band corresponding to the current point cloud data, where the unit value represents the geographical distance represented by each unit in the map projection coordinate system;

[0251] The relative circumference of the latitude band is calculated according to the formula cicum=cos(latitude), where cicum represents the relative circumference, latitude represents the latitude band, and || represents the absolute value;

[0252] According to the visible range, unit value and relative perimeter, the reference visible range is calculated according to the formula EF'=EF / metersPerUnit / cicum, where EF' represents the reference visible range and metersPerUnit represents the unit value;

[0253] According to the length and width of the two-dimensional window, the reference visible range is converted to the canvas coordinate system according to the formula R'=EF' / ((H+W) / 2) to obtain the first scale pixel accuracy, where R' represents the first scale pixel accuracy, H and W represent the length and width of the two-dimensional window respectively, and the first scale pixel accuracy represents the geographical distance represented by a pixel point in the two-dimensional window.

[0254] Optionally, the interface adjustment operation may include a second adjustment operation on the digital orthophoto displayed in the two-dimensional window; the linkage adjustment module 102 is specifically used to: respond to the second adjustment operation, obtain the second canvas coordinates of the second adjustment operation in the two-dimensional window; according to the second canvas coordinates and the map range and map center of the current digital orthophoto, linkage adjust the point cloud data displayed in the three-dimensional window to obtain the current point cloud data.

[0255] Optionally, the linkage adjustment module 102 executes linkage adjustment of the point cloud data displayed in the three-dimensional window according to the second canvas coordinates and the map range and map center of the current digital orthophoto to obtain the current point cloud data, including:

[0256] Get the second display level of the current digital orthophoto;

[0257] Determining a second scale pixel precision according to the second display level and a preset level correspondence relationship, wherein the level correspondence relationship represents a one-to-one correspondence between each scale pixel precision and each display level;

[0258] Calculate the scene display radius of the current point cloud data according to the pixel accuracy of the second scale and the length and width of the two-dimensional window;

[0259] Calculate the visible range of the current point cloud data according to the scene display radius and the map center of the current digital orthophoto;

[0260] Calculate the visible distance of the current point cloud data according to the scene display radius and the field of view of the point cloud data displayed in the 3D window;

[0261] According to the field of view, visible range and visible distance of the point cloud data displayed in the three-dimensional window, the point cloud data displayed in the three-dimensional window is adjusted to obtain the current point cloud data.

[0262] Optionally, the second adjustment operation is a bird's-eye view operation on the digital orthophoto displayed in the two-dimensional window, and the current point cloud data is a three-dimensional bird's-eye view; the linkage adjustment module 102 executes the response interface adjustment operation to link the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window, and the method also includes:

[0263] According to the 3D top view and the preset height, a side view corresponding to the current point cloud data is generated, wherein the side view is used to indicate the elevation of the object; and the 3D top view and the side view are displayed in the 3D window.

[0264] Optionally, the information extraction operation is a boundary drawing operation; the linkage drawing module 104 is specifically used to: respond to the boundary drawing operation, synchronously and in real time display the drawing process corresponding to the boundary drawing operation in the current digital orthophoto and the current point cloud data; when it is detected that the boundary drawing operation stops, the two-dimensional boundary of the object to be extracted is displayed in the current digital orthophoto, and the three-dimensional boundary of the object to be extracted is displayed in the current point cloud data.

[0265] Optionally, the electronic device pre-stores a plurality of aerial photographs, and the aerial photographs have shooting location information; the data linkage interface further includes an aerial photograph window, and the aerial photograph window is used to display the aerial photographs;

[0266] The linkage adjustment module 102 is also used to obtain the current aerial photograph from multiple aerial photographs according to the map range and the map center, and display the current aerial photograph in the aerial photograph window; wherein the shooting location information of the current aerial photograph is within the map range and closest to the map center.

[0267] Optionally, the data linkage interface further includes a thumbnail window, and the linkage adjustment module 102 is further used for:

[0268] According to the map range, all reference aerial photographs are determined from multiple aerial photographs, and thumbnails of each reference aerial photograph are arranged and displayed in a thumbnail window; wherein the shooting location information of each reference aerial photograph is within the map range;

[0269] The thumbnail of the current aerial survey film is determined from all thumbnails displayed in the thumbnail window, and the thumbnail of the current aerial survey film is highlighted.

[0270] Optionally, the object extraction device 100 further includes a trigger response module 101, and the trigger response module 101 is used to:

[0271] In response to the trigger operation, a digital orthophoto is displayed in a two-dimensional window, at least one view of the point cloud data is displayed in a three-dimensional window, and an aerial photograph having shooting location information within the map range and closest to the map coordinates corresponding to the position of the mouse in the two-dimensional window or in the three-dimensional window is displayed in the aerial photograph window;

[0272] The map center of the point cloud data is consistent with the map center of the digital orthophoto and the display range of the point cloud data is consistent with the map range of the digital orthophoto, and at least one view includes at least one of a main view, a left view, a top view and a front view.

[0273] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the object extraction device 100 described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0274] Please refer to Fig.21 , Fig.21 The block diagram of the electronic device 10 provided in the embodiment of the present application is shown. The electronic device 10 may be a personal computer, a smart phone, a tablet computer, a server, etc. The electronic device 10 includes a processor 11, a memory 12 and a bus 13, and the processor 11 is connected to the memory 12 via the bus 13.

[0275] The memory 12 is used to store programs, for example, Fig. 20 In the object extraction device 100 shown, after receiving the execution instruction, the processor 11 executes the program to implement the object extraction method disclosed in the above embodiment.

[0276] The memory 12 may include a high-speed random access memory (RAM) and may also include a non-volatile memory (NVM).

[0277] The processor 11 may be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 11 or an instruction in the form of software. The above processor 11 may be a general processor, including a central processing unit (CPU), a microcontroller unit (MCU), a complex programmable logic device (CPLD), a field programmable gate array (FPGA), an embedded ARM and other chips.

[0278] The embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by the processor 11, the object extraction method disclosed in the above embodiment is implemented.

[0279] In summary, the embodiments of the present application provide an object extraction method, device, electronic device and storage medium. By configuring a data linkage interface in the electronic device, the data linkage interface includes a two-dimensional window for displaying digital orthophotos and a three-dimensional window for displaying point cloud data, and the two-dimensional window and the three-dimensional window are linked, that is, the cartographer operates in the two-dimensional window and the three-dimensional window will be displayed synchronously, and the cartographer operates in the three-dimensional window and the two-dimensional window will be displayed synchronously; in this way, the cartographer can see the corresponding elevation information in real time through the current point cloud data in the three-dimensional window, so that the objects that need to be vectorized can be quickly and accurately identified, and accurate object information can be obtained, thereby improving the accuracy of the produced map.

[0280] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An object extraction method, characterized in that: Applied to an electronic device, the electronic device is pre-configured with a data linkage interface, the data linkage interface includes a two-dimensional window and a three-dimensional window, the two-dimensional window is used to display a digital orthophoto, and the three-dimensional window is used to display point cloud data; the electronic device pre-stores a plurality of aerial photographs, and the aerial photographs have shooting position information; The data linkage interface also includes an aerial photograph window, which is used to display aerial photographs; The method comprises: In response to the interface adjustment operation, the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window are adjusted in linkage, so that the map center of the current point cloud data is consistent with the map center of the current digital orthophoto and the display range of the current point cloud data is consistent with the map range of the current digital orthophoto; According to the map range and the map center, a current aerial photograph is obtained from the multiple aerial photographs, and the current aerial photograph is displayed in the aerial photograph window; wherein the shooting location information of the current aerial photograph is within the map range and is closest to the map center; In response to the information extraction operation, linkage drawing is performed on the current digital orthophoto and the current point cloud data to obtain drawing information of the object to be extracted; Vectorization is performed based on the drawing information of the object to be extracted to obtain extracted object information.

2. The method according to claim 1, characterized in that The interface adjustment operation includes a first adjustment operation on the point cloud data displayed in the three-dimensional window; The step of adjusting the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window in a linked manner in response to the interface adjustment operation includes: In response to the first adjustment operation, obtaining first canvas coordinates of the first adjustment operation in the three-dimensional window; The digital orthophoto displayed in the two-dimensional window is adjusted in a linked manner according to the first canvas coordinates and the viewing angle parameters of the current point cloud data to obtain the current digital orthophoto.

3. The method according to claim 2, characterized in that The step of adjusting the digital orthophoto displayed in the two-dimensional window in a linked manner according to the first canvas coordinates and the viewing angle parameters of the current point cloud data to obtain the current digital orthophoto comprises: Calculating the map center of the current digital orthophoto according to the viewing angle parameter of the current point cloud data; Calculating the first scale pixel accuracy of the current digital orthophoto according to the viewing angle parameter of the current point cloud data and the map projection coordinate system corresponding to the current point cloud data; Determining a map range of the current digital orthophoto according to the first canvas coordinates and the first scale pixel accuracy; The current digital orthophoto is acquired according to the map range and displayed in the two-dimensional window according to the center of the map.

4. The method according to claim 3, characterized in that The viewing angle parameters include camera center and viewing distance; The step of calculating the map center of the current digital orthophoto according to the viewing angle parameter of the current point cloud data comprises: Obtain the scene coordinates of the camera center in the current point cloud data; Obtaining the world coordinates of the camera center according to the scene coordinates of the camera center and a preset conversion relationship between the scene coordinates and the world coordinates; Calculate the world coordinates of the camera's sight point according to the world coordinates of the camera center and the visible distance; The map center is obtained by using the abscissa and ordinate in the world coordinates of the camera viewpoint as the abscissa and ordinate of the map center respectively.

5. The method according to claim 3, characterized in that The viewing angle parameters include viewing angle and viewing distance; The step of calculating the first scale pixel accuracy of the current digital orthophoto according to the viewing angle parameter of the current point cloud data and the map projection coordinate system corresponding to the current point cloud data comprises: According to the field of view angle and the visual distance, the visual range is calculated according to the formula EF=2*OO'*tan(fov / 2), wherein EF represents the visual range, OO' represents the visual distance, and fov represents the field of view angle; Obtaining a unit value of a map projection coordinate system corresponding to the current point cloud data and a latitude band corresponding to the current point cloud data, wherein the unit value represents a geographical distance represented by each unit in the map projection coordinate system; The relative circumference of the latitude band is calculated according to the formula cicum=cos(|latitude|), wherein cicum represents the relative circumference, latitude represents the latitude band, and || represents taking an absolute value; Calculate the reference visible range according to the visible range, the unit value and the relative circumference according to the formula EF'=EF / metersPerUnit / cicum, where EF' represents the reference visible range and metersPerUnit represents the unit value; According to the length and width of the two-dimensional window, the reference visible range is converted to the canvas coordinate system according to the formula R'=EF' / ((H+W) / 2) to obtain the first scale pixel accuracy, wherein R' represents the first scale pixel accuracy, H and W represent the length and width of the two-dimensional window respectively, and the first scale pixel accuracy represents the geographical distance represented by a pixel point in the two-dimensional window.

6. The method according to claim 1, characterized in that The interface adjustment operation includes a second adjustment operation on the digital orthophoto displayed in the two-dimensional window; The step of adjusting the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window in a linked manner in response to the interface adjustment operation includes: In response to the second adjustment operation, obtaining second canvas coordinates of the second adjustment operation in the two-dimensional window; The point cloud data displayed in the three-dimensional window are adjusted in a linked manner according to the second canvas coordinates and the map range and map center of the current digital orthophoto to obtain the current point cloud data.

7. The method according to claim 6, characterized in that The step of adjusting the point cloud data displayed in the three-dimensional window in a linked manner according to the second canvas coordinates and the map range and map center of the current digital orthophoto to obtain the current point cloud data comprises: Acquire a second display level of the current digital orthophoto; Determining a second scale pixel precision according to the second display level and a preset level correspondence relationship, wherein the level correspondence relationship represents a one-to-one correspondence between each scale pixel precision and each display level; Calculating a scene display radius of the current point cloud data according to the pixel accuracy of the second scale and the length and width of the two-dimensional window; Calculating the visible range of the current point cloud data according to the scene display radius and the map center of the current digital orthophoto; Calculating the visible distance of the current point cloud data according to the scene display radius and the field of view of the point cloud data displayed in the three-dimensional window; The point cloud data displayed in the three-dimensional window is adjusted according to the field of view angle, the visible range and the visible distance of the point cloud data displayed in the three-dimensional window to obtain current point cloud data.

8. The method according to claim 6, characterized in that The second adjustment operation is a bird's-eye view operation on the digital orthophoto displayed in the two-dimensional window, and the current point cloud data is a three-dimensional bird's-eye view; The step of adjusting the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window in a linked manner in response to the interface adjustment operation also includes: Generate a side view corresponding to the current point cloud data according to the three-dimensional top view and the preset height, wherein the side view is used to indicate the elevation of the object; The three-dimensional top view and the side view are displayed in the three-dimensional window.

9. The method according to claim 1, characterized in that The information extraction operation is a boundary drawing operation; The step of performing linkage drawing in the current digital orthophoto and the current point cloud data in response to the information extraction operation to obtain drawing information of the object to be extracted includes: In response to the boundary drawing operation, synchronously and real-timely displaying a drawing process corresponding to the boundary drawing operation in the current digital orthophoto and the current point cloud data; When it is detected that the boundary drawing operation stops, the two-dimensional boundary of the object to be extracted is displayed in the current digital orthophoto, and the three-dimensional boundary of the object to be extracted is displayed in the current point cloud data.

10. The method according to claim 1, characterized in that The data linkage interface also includes a thumbnail window; After the step of responding to the interface adjustment operation and linking the current digital orthophoto displayed in the two-dimensional window with the current point cloud data displayed in the three-dimensional window, the method further includes: According to the map range, all reference aerial photographs are determined from the plurality of aerial photographs, and thumbnails of each of the reference aerial photographs are arranged and displayed in the thumbnail window; wherein the shooting location information of each of the reference aerial photographs is within the map range; The thumbnail of the current aerial survey photograph is determined from all thumbnails displayed in the thumbnail window, and the thumbnail of the current aerial survey photograph is highlighted.

11. The method according to claim 1, characterized in that Before the step of adjusting the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window in a linked manner in response to the interface adjustment operation, the method further comprises: In response to the trigger operation, the digital orthophoto is displayed in the two-dimensional window, at least one view of the point cloud data is displayed in the three-dimensional window, and the aerial photograph whose shooting location information is within the map range and is closest to the map coordinates corresponding to the position of the mouse in the two-dimensional window or the three-dimensional window is displayed in the aerial photograph window; The map center of the point cloud data is consistent with the map center of the digital orthophoto and the display range of the point cloud data is consistent with the map range of the digital orthophoto, and the at least one view includes at least one of a main view, a left view, a top view and a front view.

12. An object extraction device, characterized in that: Applied to an electronic device, the electronic device is pre-configured with a data linkage interface, the data linkage interface includes a two-dimensional window and a three-dimensional window, the two-dimensional window is used to display a digital orthophoto, and the three-dimensional window is used to display point cloud data; the electronic device pre-stores a plurality of aerial photographs, and the aerial photographs have shooting position information; The data linkage interface also includes an aerial photograph window, which is used to display aerial photographs; The device comprises: A linkage adjustment module, for responding to the interface adjustment operation, linkage adjustment of the digital orthophoto displayed in the two-dimensional window and the point cloud data displayed in the three-dimensional window, so that the map center of the current point cloud data is consistent with the map center of the current digital orthophoto and the display range of the current point cloud data is consistent with the map range of the current digital orthophoto; The linkage adjustment module is further used to obtain a current aerial photograph from the multiple aerial photographs according to the map range and the map center, and display the current aerial photograph in the aerial photograph window; wherein the shooting location information of the current aerial photograph is within the map range and is closest to the map center; A linkage drawing module, used for responding to the information extraction operation, performing linkage drawing on the current digital orthophoto and the current point cloud data to obtain drawing information of the object to be extracted; The vectorization module is used to perform vectorization based on the drawing information of the object to be extracted to obtain the extracted object information.

13. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store a program, and the processor is used to implement the object extraction method according to any one of claims 1 to 11 when executing the program.

14. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the object extraction method according to any one of claims 1 to 11 is implemented.

Images