Building elevation estimation method based on contour vector registration

Abstract

The embodiment of the invention discloses a building elevation estimation method based on contour vector registration, and relates to the technical field of photogrammetry and remote sensing, and the method specifically comprises the steps: extracting a first building vector contour of a multi-view satellite image corresponding to the same target building; determining an elevation search range and an elevation step pitch; projecting the first building vector contours of other images except the reference image to the object space to obtain a second building vector contour, projecting the second building vector contour to the reference image to obtain a third building vector contour on the reference image, and calculating the overlapping area proportion of the third building vector contour and the reference building vector contour; and moving the elevation step pitch in the elevation search range to obtain a relation function between the overlapping area proportion and the elevation value, determining the elevation value of the target building through an interpolation method, and outputting the height of the target building. The method has the advantages of being high in calculation speed, high in precision and the like, a new thought can be provided for obtaining the elevation information of the building, and data support is provided for urban three-dimensional modeling.

Description

Technical Field

[0001] The present application relates to the field of photogrammetry and remote sensing technology, and in particular to a building elevation estimation method based on contour vector registration. Background Art

[0002] The height information of urban buildings, as basic data and important parameters, can reflect the vertical information of the city from the side. At present, the height of buildings is mainly measured by traditional surveying and mapping methods and measurement methods based on remote sensing technology.

[0003] Among them, traditional surveying and mapping methods include total station measurement, GPS measurement and laser scanning measurement. This method has mature technology and high measurement accuracy, but the measurement cost is high and time-consuming. It has certain requirements on personnel experience and equipment operation level, requires a lot of manpower, and is difficult to meet the needs of rapid measurement.

[0004] The measurement methods based on remote sensing technology mainly include shadow length detection method, same-name point image matching method and dense matching method. Compared with traditional surveying and mapping methods, these methods have the advantages of high efficiency, fast speed and wide coverage. Among them, the shadow length detection method can estimate the height of a building by using the shadow length of the building in a single satellite image combined with the image shooting time, orientation and other information. This method is simple to operate and has low implementation cost, but it is easily affected by environmental factors such as lighting conditions and terrain, and will produce large errors under the influence of environmental factors that are not conducive to detection; the same-name point image matching method can calculate the building height by matching the same-name image points of the same-name building in multi-view satellite images and performing forward intersection according to the image geometric positioning parameters. However, the success rate and reliability of the same-name point matching depend on the richness of the image texture, and in general, the roof of the building lacks texture, which seriously reduces the success rate and reliability of this method; the dense matching rule uses stereo images to reconstruct the three-dimensional surface information of the building through a dense matching algorithm. This method is also affected by the lack of texture in the building roof image.

[0005] Therefore, there is currently a lack of a method that is simple to operate and can quickly and easily obtain building elevation information. Summary of the invention

[0006] The embodiments of the present application provide a method, device, equipment and storage medium for estimating building elevation based on contour vector registration, which are used to solve the defects in the above-mentioned related technologies. The technical solution is as follows:

[0007] In a first aspect, an embodiment of the present application provides a method for estimating building elevation based on contour vector registration, comprising:

[0008] Acquire satellite images from at least two viewing angles, and extract the first building vector outline in each of the satellite images using a trained building outline extraction model;

[0009] Pairing all of the first building vector outlines to determine a first building vector outline corresponding to the same target building;

[0010] Determine the elevation search range of the target building, and project the first building vector outlines of the other images except the reference image to the object space based on each elevation value in the elevation search range, to obtain the second building vector outline corresponding to each of the first building vector outlines at different elevation values;

[0011] Projecting each of the second building vector outlines onto the reference image to obtain a third building vector outline on the reference image;

[0012] Calculating the overlapping area ratio between each of the third building vector outlines and the benchmark building vector outline of the benchmark image, and determining the building elevation value of the target building based on the changing relationship between the overlapping area ratio and the corresponding elevation value;

[0013] The height of the target building is output based on the building elevation value.

[0014] In an optional solution of the first aspect, pairing all the first building vector outlines to determine the first building vector outline corresponding to the same target building includes:

[0015] Calculate the outline similarity between every two first building vector outlines based on the geographic location, coverage area, number of vector nodes, and vector outline shape of each first building vector outline;

[0016] The first building vector outline whose outline similarity is greater than the outline similarity threshold is calculated as the first building vector outline corresponding to the same target building.

[0017] In an optional solution of the first aspect, determining the elevation search range of the target building includes:

[0018] According to the digital elevation model and the geographical range covered by the target building on the corresponding satellite image, the maximum elevation value and the minimum elevation value of all grid points within the geographical range are obtained, and the elevation search range is determined based on the maximum elevation value and the minimum elevation value.

[0019] In an optional solution of the first aspect, after determining the elevation search range of the target building, the method further includes:

[0020] Determine a first ground point on the object side corresponding to the preset reference point on the other image when the elevation takes the maximum elevation value, and a second ground point on the object side corresponding to the preset reference point on the other image when the elevation takes the minimum elevation value;

[0021] Projecting the first ground point and the second ground point onto the reference image to obtain corresponding projection points;

[0022] Determine the elevation step based on the ratio of the distance between the first ground point and the second ground point to the distance between the projection points;

[0023] Each elevation value in the elevation search range is determined based on the elevation step size and the elevation minimum value.

[0024] In an optional solution of the first aspect, projecting first building vector outlines of other images except the reference image to the object space based on each elevation value in the elevation search range to obtain second building vector outlines corresponding to each of the first building vector outlines at different elevation values ​​includes:

[0025] Projecting the first building vector outline to the object space based on the minimum elevation value to obtain the second building vector outline corresponding to the first building vector outline at the minimum elevation value;

[0026] The elevation value is updated by accumulating the elevation step based on the minimum elevation value, and the step of projecting the first building vector outline to the object space is performed based on the updated elevation value to obtain the second building vector outline corresponding to the current elevation value of the first building vector outline.

[0027] In an optional solution of the first aspect, the calculating the overlapping area ratio between each of the third building vector outlines and the reference building vector outline of the reference image includes:

[0028] Respectively obtain the overlapping area between each of the third building vector outlines and the reference building vector outline, and calculate the ratio of each overlapping area to the overlapping area of ​​the reference building vector outline;

[0029] Determine the changing relationship between the elevation values ​​corresponding to all the third building vector contours and the overlapping area ratio, obtain the elevation value corresponding to the maximum value of the overlapping area ratio, and determine the building elevation value of the target building based on the elevation value corresponding to the maximum value of the overlapping area ratio.

[0030] In an optional solution of the first aspect, outputting the height of the target building based on the building elevation value includes:

[0031] Obtaining the ground elevation value of the horizontal reference plane in the area where the target building is located;

[0032] The difference between the building elevation value and the ground elevation value is calculated, and the difference is output as the height of the target building.

[0033] In a second aspect, an embodiment of the present application further provides a building elevation estimation device based on contour vector registration, comprising:

[0034] A contour extraction module, used to obtain satellite images from at least two viewing angles, and extract the first building vector contour in each of the satellite images using a trained building contour extraction model;

[0035] A contour pairing module, used for pairing all the first building vector contours to determine the first building vector contour corresponding to the same target building;

[0036] A vector registration module is used to determine the elevation search range of the target building, and project the first building vector outlines of other images except the reference image to the object space based on each elevation value in the elevation search range, so as to obtain the second building vector outline corresponding to each of the first building vector outlines at different elevation values;

[0037] The vector registration module is also used to project each of the second building vector outlines onto the reference image to obtain a third building vector outline on the reference image;

[0038] A height calculation module, used for calculating the overlapping area ratio between each of the third building vector outlines and the reference building vector outline of the reference image, and determining the building elevation value of the target building based on the changing relationship between the overlapping area ratio and the corresponding elevation value;

[0039] The height calculation module is also used to output the height of the target building based on the building elevation value.

[0040] In a third aspect, an embodiment of the present application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method provided in the first aspect of the embodiment of the present application or any one of the implementation methods of the first aspect is implemented.

[0041] In a fourth aspect, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided by the first aspect of the embodiment of the present application or any one of the implementations of the first aspect.

[0042] The beneficial effects brought about by the technical solutions provided by some embodiments of the present application include at least:

[0043] The embodiment of the present application extracts and matches the building vector outlines in the multi-view satellite image by a deep learning method, estimates the value range of the building roof elevation, that is, the elevation search range, and calculates the search elevation step, assuming the roof elevation of the building within the elevation search range; further, the image-side building outlines of other images are projected to the object side using a rational function model, and then the object-side building outlines are projected to the reference image; subsequently, the matching degree of the projected outline polygon and the corresponding outline polygon of the original reference image is calculated (completed by calculating the overlapping area ratio), and the elevation value is changed by the elevation step to obtain the best matching elevation value as the roof elevation of the building; finally, the building height can be determined by subtracting the ground elevation from the building roof elevation, thereby providing key data for the three-dimensional reconstruction of the building. The embodiment of the present application has the advantages of simple operation, fast calculation speed, and high calculation accuracy, and can provide new ideas for obtaining building elevation information, and can provide accurate data support for urban three-dimensional modeling. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 It is a flowchart of a building elevation estimation method based on contour vector registration provided in an embodiment of the present application;

[0046] Figure 2 It is a schematic diagram of elevation step calculation of a building elevation estimation method based on contour vector registration provided in an embodiment of the present application;

[0047] Figure 3 It is a flowchart of a building elevation estimation method based on contour vector registration provided in an embodiment of the present application;

[0048] Figure 4 It is a vector registration schematic diagram of a building elevation estimation method based on contour vector registration provided in an embodiment of the present application;

[0049] Figure 5 It is a schematic diagram of the relationship between elevation value and overlapping area ratio in a building elevation estimation method based on contour vector registration provided in an embodiment of the present application;

[0050] Figure 6 It is a structural schematic diagram of a building elevation estimation method and device based on contour vector registration provided in an embodiment of the present application;

[0051] Figure 7 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0053] The terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or modules is not limited to the listed steps or modules, but may optionally include steps or modules that are not listed, or may optionally include other steps or modules that are inherent to these processes, methods, products or devices.

[0054] It should be noted that the terms "first\second" involved in the present application are only used to distinguish similar objects, and do not represent a specific order for the objects. It is understandable that "first\second" can be interchanged with a specific order or sequence where permitted. It should be understood that the objects distinguished by "first\second" can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those described or illustrated herein.

[0055] It should be noted that remote sensing images can be interpreted based on deep learning, and combined with the Segment Anything Model (SAM), the method of automatically identifying buildings and extracting contour vectors from satellite images can be gradually improved. The present application proposes a building elevation estimation method based on contour vector registration, which can first estimate the value range of the building roof elevation in combination with relevant technologies, and maximize the overlapping area of ​​the extracted and paired building vector contours in the multi-view images by traversing the elevation, thereby realizing contour vector registration and determining the height of the building.

[0056] The present application is described in detail below with reference to specific embodiments.

[0057] Next, combine Figure 1 , taking the terminal executing the building elevation estimation method based on contour vector registration as an example, the building elevation estimation method based on contour vector registration provided by the embodiment of the present application is introduced. For details, please refer to Figure 1 , Figure 1FIG. 1 is a flow chart of a method for estimating building elevation based on contour vector registration provided in an embodiment of the present application. Figure 1 As shown, the method comprises the following steps:

[0058] S101, obtaining satellite images from at least two viewing angles, and extracting a first building vector outline in each of the satellite images using a trained building outline extraction model.

[0059] S102, pairing all first building vector outlines to determine first building vector outlines corresponding to the same target building;

[0060] S103, determining the elevation search range of the target building, and projecting the first building vector outlines of the images other than the reference image to the object space based on each elevation value in the elevation search range, to obtain the second building vector outlines corresponding to each first building vector outline at different elevation values.

[0061] S104: Project each second building vector outline onto the reference image to obtain a third building vector outline on the reference image.

[0062] S105, calculating the overlapping area ratio between each third building vector outline and the benchmark building vector outline of the benchmark image, and determining the building elevation value of the target building based on the changing relationship between the overlapping area ratio and the corresponding elevation value.

[0063] S106: Output the height of the target building based on the building elevation value.

[0064] Specifically, in S101, high-resolution satellite images from multiple perspectives can be obtained, and the trained building extraction model can be used to extract the building vector outlines in each satellite image, that is, the first building vector outline corresponding to each satellite image is obtained. It can be understood that the first building vector outline is located in the image side of each satellite image.

[0065] Specifically, an image of one of the multi-view high-resolution satellite images can be used as a reference image, such as a main view image, and images of other views other than the reference image can be recorded as other images. For the reference image, the first building vector outline of the reference image is the reference building vector outline.

[0066] In some embodiments, vector contours may be paired in S102. Specifically, contour similarity between every two first building vector contours may be calculated based on the geographic location, coverage area, number of vector nodes, and vector contour shape of each first building vector contour. First building vector contours whose contour similarity is greater than a contour similarity threshold are calculated to be first building vector contours corresponding to the same target building.

[0067] In some embodiments, the elevation search range in S103 can obtain the maximum and minimum elevation values ​​of all grid points within the corresponding geographical range according to the digital elevation model and the geographical range covered by the target building on the corresponding satellite image, and determine the elevation search range based on the maximum and minimum elevation values.

[0068] It can be understood that the elevation value of each grid point within the coverage range of the image can be easily obtained through the existing digital elevation model and the geographical scope of the buildings in the satellite image obtained by capture, and the coverage range of the elevation value can be expanded based on the existing elevation value, that is, an elevation variable is added on the basis of the maximum elevation value obtained by determining the elevation value of the grid point, and / or an elevation variable is subtracted on the basis of the minimum elevation value obtained by determining the elevation value of the grid point, so as to obtain an expanded elevation search range to cover possible building heights.

[0069] Specifically, the obtained elevation search range can be expressed as [z min , z max ], where z min is the minimum elevation, z max is the maximum elevation value.

[0070] In some embodiments, in S103, Figure 2 The elevation step calculation shown can determine the elevation step of the elevation search range, including:

[0071] Select point P on other images as the preset reference point, for example, select the center point of the building vector outline, determine the preset reference point P on other images at the elevation to take the maximum elevation z max When the first ground point Q1 corresponding to the object space is at the same time, and the minimum elevation value z is taken at the elevation min The first ground point Q1 and the second ground point Q2 are respectively projected onto the reference image to obtain corresponding projection points, and corresponding image points P1 and P2 are respectively obtained on the reference image;

[0072] Determine the elevation step Δz based on the ratio of the distance Q1 Q2 between the first ground point Q1 and the second ground point Q2 and the distance P1 P2 between the projection points;

[0073] Based on the elevation step Δz and the minimum elevation z min Determines each elevation value based on the elevation search range.

[0074] For example, the preset reference point P has the maximum value z at the elevation maxWhen , the corresponding ground point is Q1 (X1, Y1, Z1), and the corresponding image point after being projected onto the reference image is P1 (x1, y1); and when point P obtains the minimum value z at the elevation min When , the corresponding ground point is Q2 (X2, Y2, Z2), and its corresponding image point after being projected onto the reference image is P2 (x2, y2). The calculation of the elevation step can be applied using the formula:

[0075]

[0076] Specifically, the rational function model can be used to convert the object coordinates of the ground point to the image point coordinates. The rational function model is a method used to describe the image coordinates of a point on a satellite image (l n ,s n ) and its corresponding ground point three-dimensional geographic coordinates (X n , Y n , Z n ) corresponds to a universal imaging model, the coefficients of which are rational polynomial coefficients (RPC), and the application formula is:

[0077]

[0078] Where n is any pixel; l n ,s n is the standardized image point coordinate; X n , Y n , Z n is the normalized ground point coordinate; according to the rational function mathematical model, P(X n , Y n , Z n ) is a cubic polynomial, and the rational polynomial coefficients (RPC parameters) are provided by the satellite image operators and refined through image block adjustment.

[0079] In some embodiments, Figure 3 As shown, S103 and S104 may specifically include the following steps:

[0080] S301, combining the first building vector outline and the rational polynomial coefficients of other images, projecting the first building vector outline to the object space based on the given elevation value through a rational function model, and obtaining the second building vector outline corresponding to the first building vector outline at the given elevation value; specifically selecting the minimum elevation value z min As the first given elevation value z0.

[0081] S302 , based on the rational polynomial coefficients of the reference image, back-project the second building vector outline of the object space onto the reference image through a rational function model to obtain a third building vector outline on the reference image.

[0082] S303, accumulating the elevation step distance based on the given elevation value z0, that is:

[0083] z i =z min +i·ΔZ, where i is an integer not less than 0;

[0084] If the updated elevation value z i Less than or equal to the maximum elevation z max , then based on the updated elevation value, execute the step of projecting the first building vector outline to the object side in S301 to obtain the second building vector outline corresponding to the current elevation value of the first building vector outline, and execute the step of back-projecting the second building vector outline of the object side to the reference image in S302 to obtain the third building vector outline on the reference image.

[0085] S304, if the updated elevation value z i Greater than the maximum elevation z max , outputs the third building vector outline corresponding to each elevation value in the elevation search range of other images.

[0086] For example, Figure 4 The schematic diagram of vector registration shown in FIG. 1 first projects the first building vector outline of other images to the object space through S301, and projects each elevation value separately to obtain the second building vector outline corresponding to each elevation value; further, the second building vector outline corresponding to each elevation value is back-projected from the object space to the reference image to obtain the third building vector outline on the reference image. Figure 4 The example takes the elevation value as z min , z max The corresponding third building vector outline, where z best is the building vector outline corresponding to the estimated optimal building elevation value, z best It is necessary to traverse each elevation value and compare each third building vector outline with the benchmark building vector outline of the benchmark image.

[0087] In some embodiments, in S105, the overlapping area between each third building vector outline and the reference building vector outline may be obtained respectively, and the ratio of each overlapping area to the overlapping area of ​​the reference building vector outline may be calculated;

[0088] Determine the changing relationship between the elevation values ​​corresponding to all third building vector contours and the overlapping area ratio, obtain the elevation value corresponding to the maximum overlapping area ratio, and determine the building elevation value of the target building based on the elevation value corresponding to the maximum overlapping area ratio.

[0089] Assuming that the graphic area of ​​the third building vector outline is S′, and the graphic area of ​​the reference building vector outline in the original reference image is S, the overlapping area ratio α is:

[0090]

[0091] Specifically, the overlapping area ratio α represents the intersection area ratio of two vector graphics, and can be used to reflect the correlation between the two.

[0092] Alternatively, each building vector outline can be considered as a polygon defined by multiple vertex coordinates, and the area calculation can apply the formula:

[0093]

[0094] In some embodiments, the elevation value corresponding to each third building vector outline can be used as a function, and the corresponding overlapping area ratio can be used as the function value to fit the changing relationship between the elevation values ​​and the overlapping area ratios corresponding to all third building vector outlines, and then determine the elevation value corresponding to the maximum overlapping area ratio.

[0095] For example, it can be drawn as follows Figure 5 The curve graph shown in the figure can easily determine the relationship between the elevation value and the overlapping area ratio, so as to determine the maximum value of the overlapping area ratio and the corresponding elevation value z best .

[0096] It should be noted that each elevation value obtained according to the elevation step cannot cover all elevation values. Parabola fitting can be performed on the domain value, and the elevation value z with the largest overlapping area ratio can be obtained by interpolation. best , thereby obtaining the building elevation value, that is, the optimal roof elevation of the building.

[0097] In some embodiments, in S106, the ground elevation value of the horizontal reference plane in the area where the target building is located can be obtained; the difference between the building elevation value and the ground elevation value is calculated, and the corresponding difference is output as the height of the target building.

[0098] Specifically, the ground elevation z of the building can be extracted from the digital elevation model ground , the height of the landmark building is the difference between the two, that is, z best -z ground .

[0099] In some embodiments, a measurement area may be selected, and the above steps S101 to S106 may be repeated for each building in the area, thereby obtaining the height of each building in the corresponding area.

[0100] The following are device embodiments of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0101] See next Figure 6 , is a schematic diagram of the structure of a building elevation estimation device based on contour vector registration provided by an exemplary embodiment of the present application. The device can be implemented as all or part of a terminal through software, hardware, or a combination of both, and can also be integrated on a server as an independent module. The building elevation estimation device based on contour vector registration in the embodiment of the present application can be applied to a terminal or a cloud. The device 60 includes a contour extraction module 601, a contour pairing module 602, a vector registration module 603, and a height calculation module 604, wherein:

[0102] The contour extraction module 601 is used to obtain satellite images of at least two viewing angles, and extract the first building vector contour in each of the satellite images by using a trained building contour extraction model;

[0103] The outline matching module 602 is used to match all the first building vector outlines to determine the first building vector outline corresponding to the same target building;

[0104] The vector registration module 603 is used to determine the elevation search range of the target building, and project the first building vector outlines of the other images except the reference image to the object space based on each elevation value in the elevation search range, so as to obtain the second building vector outline corresponding to each of the first building vector outlines at different elevation values;

[0105] The vector registration module 603 is further used to project each of the second building vector outlines onto the reference image to obtain a third building vector outline on the reference image;

[0106] The height calculation module 604 is used to calculate the overlapping area ratio between each of the third building vector outlines and the reference building vector outline of the reference image, and determine the building elevation value of the target building based on the changing relationship between the overlapping area ratio and the corresponding elevation value;

[0107] The height calculation module 604 is further configured to output the height of the target building based on the building elevation value.

[0108] It should be noted that, when the device 60 provided in the above embodiment executes the building elevation estimation method based on contour vector registration, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device provided in the above embodiment and the embodiment of the building elevation estimation method based on contour vector registration belong to the same concept, and its embodiment and implementation process are detailed in the method embodiment, which will not be repeated here.

[0109] An embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above-mentioned method embodiments when executing the program.

[0110] See also Figure 7 , which is a structural block diagram of an electronic device provided in an embodiment of the present application.

[0111] like Figure 7 As shown, the electronic device 700 includes: a processor 701 and a memory 702 .

[0112] In the embodiment of the present application, the processor 701 is the control center of the computer system, which can be a processor of a physical machine or a processor of a virtual machine. The processor 701 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 701 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array).

[0113] The processor 701 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also called a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state.

[0114] The memory 702 may include one or more computer-readable storage media, which may be non-transitory. The memory 702 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments of the present application, the non-transitory computer-readable storage medium in the memory 702 is used to store at least one instruction, which is used to be executed by the processor 701 to implement the method in the embodiment of the present application.

[0115] In some embodiments, the electronic device 700 further includes: a peripheral device interface 703 and at least one peripheral device 704. The processor 701, the memory 702 and the peripheral device interface 703 can be connected via a bus or a signal line. Each peripheral device 704 can be connected to the peripheral device interface 703 via a bus, a signal line or a circuit board. Specifically, the peripheral device 704 includes: a display screen, a camera and an audio circuit. The peripheral device interface 703 can be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 701 and the memory 702.

[0116] In some embodiments of the present application, the processor 701, the memory 702, and the peripheral device interface 703 are integrated on the same chip or circuit board; in some other embodiments of the present application, any one or two of the processor 701, the memory 702, and the peripheral device interface 703 can be implemented on a separate chip or circuit board. This embodiment of the present application does not specifically limit this.

[0117] The electronic device structure block diagram shown in the embodiment of the present application does not constitute a limitation on the electronic device 700. The electronic device 700 may include more or fewer components than shown in the figure, or combine certain components, or adopt a different component arrangement.

[0118] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the method of any of the above embodiments are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0119] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution can be essentially or in other words, the part that contributes to the relevant technology can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiment.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A building elevation estimation method based on contour vector registration, characterized in that: include: Acquire satellite images from at least two viewing angles, and extract the first building vector outline in each of the satellite images using a trained building outline extraction model; Pairing all of the first building vector outlines to determine a first building vector outline corresponding to the same target building; Determine the elevation search range of the target building, and project the first building vector outlines of the other images except the reference image to the object space based on each elevation value in the elevation search range, to obtain the second building vector outline corresponding to each of the first building vector outlines at different elevation values; Projecting each of the second building vector outlines onto the reference image to obtain a third building vector outline on the reference image; Calculating the overlapping area ratio between each of the third building vector outlines and the benchmark building vector outline of the benchmark image, and determining the building elevation value of the target building based on the changing relationship between the overlapping area ratio and the corresponding elevation value; The height of the target building is output based on the building elevation value.

2. A building elevation estimation method based on contour vector registration according to claim 1, characterized in that: The step of pairing all the first building vector outlines to determine the first building vector outline corresponding to the same target building includes: Calculate the outline similarity between every two first building vector outlines based on the geographic location, coverage area, number of vector nodes, and vector outline shape of each first building vector outline; The first building vector outline whose outline similarity is greater than the outline similarity threshold is calculated as the first building vector outline corresponding to the same target building.

3. A building elevation estimation method based on contour vector registration according to claim 1 or 2, characterized in that: Determining the elevation search range of the target building includes: According to the digital elevation model and the geographical range covered by the target building on the corresponding satellite image, the maximum elevation value and the minimum elevation value of all grid points within the geographical range are obtained, and the elevation search range is determined based on the maximum elevation value and the minimum elevation value.

4. A building elevation estimation method based on contour vector registration according to claim 3, characterized in that: After determining the elevation search range of the target building, the method further includes: Determine a first ground point on the object side corresponding to the preset reference point on the other image when the elevation takes the maximum elevation value, and a second ground point on the object side corresponding to the preset reference point on the other image when the elevation takes the minimum elevation value; Projecting the first ground point and the second ground point onto the reference image to obtain corresponding projection points; Determine the elevation step based on the ratio of the distance between the first ground point and the second ground point to the distance between the projection points; Each elevation value in the elevation search range is determined based on the elevation step size and the elevation minimum value.

5. A building elevation estimation method based on contour vector registration according to claim 4, characterized in that: The method of projecting the first building vector outlines of the other images except the reference image to the object space based on each elevation value in the elevation search range to obtain the second building vector outlines corresponding to each of the first building vector outlines at different elevation values ​​includes: Projecting the first building vector outline to the object space based on the minimum elevation value to obtain the second building vector outline corresponding to the first building vector outline at the minimum elevation value; The elevation value is updated by accumulating the elevation step based on the minimum elevation value, and the step of projecting the first building vector outline to the object space is performed based on the updated elevation value to obtain the second building vector outline corresponding to the current elevation value of the first building vector outline.

6. A building elevation estimation method based on contour vector registration according to claim 1 or 4, characterized in that: The calculating the overlapping area ratio between each of the third building vector outlines and the reference building vector outline of the reference image comprises: Respectively obtain the overlapping area between each of the third building vector outlines and the reference building vector outline, and calculate the ratio of each overlapping area to the overlapping area of ​​the reference building vector outline; Determine the changing relationship between the elevation values ​​corresponding to all the third building vector contours and the overlapping area ratio, obtain the elevation value corresponding to the maximum value of the overlapping area ratio, and determine the building elevation value of the target building based on the elevation value corresponding to the maximum value of the overlapping area ratio.

7. A building elevation estimation method based on contour vector registration according to claim 1, characterized in that: The step of outputting the height of the target building based on the building elevation value comprises: Obtaining the ground elevation value of the horizontal reference plane in the area where the target building is located; The difference between the building elevation value and the ground elevation value is calculated, and the difference is output as the height of the target building.

8. A building elevation estimation device based on contour vector registration, characterized in that: include: A contour extraction module, used to obtain satellite images from at least two viewing angles, and extract the first building vector contour in each of the satellite images using a trained building contour extraction model; A contour pairing module, used for pairing all the first building vector contours to determine the first building vector contour corresponding to the same target building; A vector registration module is used to determine the elevation search range of the target building, and project the first building vector outlines of other images except the reference image to the object space based on each elevation value in the elevation search range, so as to obtain the second building vector outline corresponding to each of the first building vector outlines at different elevation values; The vector registration module is also used to project each of the second building vector outlines onto the reference image to obtain a third building vector outline on the reference image; A height calculation module, used for calculating the overlapping area ratio between each of the third building vector outlines and the reference building vector outline of the reference image, and determining the building elevation value of the target building based on the changing relationship between the overlapping area ratio and the corresponding elevation value; The height calculation module is also used to output the height of the target building based on the building elevation value.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images