A method, device, electronic device and storage medium for measuring building height

Abstract

The present application provides a method, device, electronic device and storage medium for measuring building height. It includes: obtaining image data of the building to be measured, and obtaining building outline vector data based on the image data of the building to be measured; performing block processing on the building outline vector data to obtain multiple pairs of building spot matching data; performing spot height calculation on multiple pairs of the building spot matching data to obtain a spot height data set; merging the spot height data set to obtain the target building height. Based on this, the accuracy of building height measurement can be improved, automatic processing can be achieved, manual intervention can be reduced and costs can be reduced. Compared with traditional methods, such as laser radar (LiDAR) and on-site measurement, the present invention is more cost-effective and widely applicable. It is suitable for satellite images with sub-meter resolution and surface environments of different complexities, and significantly improves the efficiency and accuracy of building information extraction.

Description

Technical Field

[0001] The present application relates to the field of surveying and mapping technology, and in particular to a method, device, electronic device and storage medium for measuring the height of a building. Background Art

[0002] Accurate building outlines and height information are crucial in modern urban planning, disaster emergency response, and geographic information systems (GIS). Traditional methods such as field surveys and LiDAR are highly accurate but expensive and time-consuming. With the development of satellite remote sensing technology, extracting building information using left-right satellite images has become an efficient and economical method. The present invention uses AI technology to extract building outlines from left-right satellite images, and uses the RPC file of the image to match the outlines to obtain the building height. Compared with traditional point cloud methods, this method has the advantages of automated processing, high precision, and wide applicability, which significantly improves the efficiency and accuracy of building information extraction. Summary of the invention

[0003] In view of this, the embodiments of the present disclosure provide a building height measurement method, which at least partially solves the problems existing in the prior art, can improve the accuracy of building height measurement, realize automatic processing, reduce manual intervention and reduce costs. Compared with traditional methods such as laser radar (LiDAR) and on-site measurement, the present invention is more cost-effective and widely applicable, suitable for satellite images with sub-meter resolution and surface environments of different complexities, and significantly improves the efficiency and accuracy of building information extraction.

[0004] In one aspect, this embodiment discloses a method for measuring the height of a building, characterized by comprising:

[0005] Acquire image data of a building to be measured, and obtain building outline vector data based on the image data of the building to be measured;

[0006] Based on the geographical location clipping method, the building outline vector data is divided into blocks, and multiple pairs of building outline data are obtained after the block division;

[0007] Based on the to-be-paired spot data of one view of the building outline data, traverse and search for matching spots of another view to obtain paired spots, wherein the multiple pairs of building spot matching data include multiple pairs of the paired spots, and multiple pairs of building spot matching data are obtained;

[0008] Calculating the spot heights of the plurality of pairs of the building spot matching data to obtain a spot height data set;

[0009] The image patch height data sets are merged to obtain the target building height.

[0010] Specifically, obtaining the image data of the building to be measured includes: based on satellite remote sensing technology, obtaining the image data of the building at different viewing angles in the same area through left and right viewing satellite images.

[0011] Specifically, obtaining the building outline vector data based on the image data of the building to be tested includes: using deep learning or machine learning to process the image data of the building to be tested to obtain the building outline vector data.

[0012] Specifically, the block processing of the building outline vector data includes: based on the geographic location clipping method, the building outline vector data is processed in blocks, and multiple pairs of building outline data after the block processing is completed; based on the to-be-paired spot data of one view of the building outline data, traversing and searching for matching spots of another view to obtain paired spots, and the multiple pairs of building spot matching data include multiple pairs of the paired spots.

[0013] Specifically, traversing to find the matching spots of another view includes: converting the spot data to be matched into geographic coordinates, then converting into pixel coordinates of another view, and intersecting with the building outline data of another view to obtain an array of intersecting spots; obtaining the matching spots in the array of intersecting spots.

[0014] Specifically, obtaining the matching pattern spots in the intersection pattern array includes: obtaining a target intersection area based on a maximum intersection calculation method; and matching the matching pattern spots in the intersection pattern array by using the target intersection area.

[0015] Specifically, calculating the spot heights of the plurality of pairs of building spot matching data includes:

[0016] An intersection calculation is performed on each pair of building patch matching data according to a polygon algorithm.

[0017] On the other hand, the embodiment of the present disclosure provides a device for calculating the height of a building, including: a vector data acquisition module, used to acquire image data of a building to be measured, and obtain building outline vector data based on the image data of the building to be measured;

[0018] A pattern data acquisition module is used to process the building outline vector data in blocks to obtain multiple pairs of building pattern matching data;

[0019] A height data calculation module is used to calculate the spot heights of the plurality of pairs of the building spot matching data to obtain a spot height data set;

[0020] The height data merging module is used to merge the image spot height data sets to obtain the target building height.

[0021] In the third aspect, an embodiment of the present disclosure also provides an electronic device, characterized in that the electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the building height measurement method described in any one of the first aspects.

[0022] In the fourth aspect, the embodiment of the present disclosure also provides a non-transitory computer-readable storage medium, characterized in that the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the building height measurement method described in any one of the first aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A schematic diagram of a flow chart of a building height measurement method in an embodiment of the present application;

[0025] Figure 2 A schematic diagram of a building pattern of a building height measurement method in an embodiment of the present application;

[0026] Figure 3 A schematic diagram of the area of ​​intersection calculation in the building height measurement method in an embodiment of the present application;

[0027] Figure 4 A schematic structural diagram of a building height measuring device provided in a second embodiment of the present invention.

[0028] Figure 5 An exemplary structural diagram of a device capable of implementing the method according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0029] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0030] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0031] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0032] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The drawings only show components related to the present disclosure rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0033] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, one skilled in the art will appreciate that aspects may be practiced without these specific details.

[0034] The purpose of the present invention is to automatically extract the outline of a building through the left and right view data of a satellite image using existing AI technology, and to accurately match the image through the RPC file to obtain the building height. The purpose is to improve the accuracy of building height measurement, realize automated processing, reduce manual intervention and reduce costs. Compared with traditional methods such as LiDAR and on-site measurement, the present invention is more cost-effective and widely applicable. It is suitable for satellite images with sub-meter resolution and surface environments of varying complexity, and significantly improves the efficiency and accuracy of building information extraction.

[0035] First, on one hand, this embodiment discloses a method for measuring the height of a building, comprising:

[0036] S101, acquiring image data of a building to be measured, and obtaining building outline vector data based on the image data of the building to be measured;

[0037] The method of measuring the building height of the present invention is mainly carried out through the building image. Therefore, the image data of the building to be measured is first obtained. After the building image data is obtained, the vector data of the building outline is automatically extracted through the existing AI technology, and used for the subsequent building height calculation. Therefore, in this embodiment, the first step is to obtain the building image data, and then extract the corresponding building outline vector data. In this embodiment, the building image data can be an image RPC file, or other image data from which the building outline vector data can be extracted.

[0038] S102, based on the geographic location clipping method, the building outline vector data is divided into blocks, and multiple pairs of building outline data after the block division is completed are obtained; based on the to-be-paired spot data of one view of the building outline data, the matching spots of another view are traversed to obtain paired spots, and the multiple pairs of building spot matching data include multiple pairs of the paired spots, so as to obtain multiple pairs of building spot matching data;

[0039] In this embodiment, if Figure 2 As shown, Figure 2 This is a schematic diagram of a building pattern in the embodiment of the present application, in which the shaded portion is the building pattern portion. Due to the large number of buildings and the existence of building outline data from both left and right perspectives, it is necessary to perform block processing on the building outline vector data, and after block processing, multiple pairs of left and right view building pattern matching data can be obtained.

[0040] In this embodiment, since sub-meter single-view data is used, there are too many contours and block processing is required. Geographic location clipping is used here. In actual operation, the program language is as follows:

[0041]

[0042]

[0043] Among them, getExtend obtains the range of the data, shpExtend is the bounding rectangle of the data; rowStep and colStep are the step sizes.

[0044] After the block division is completed, the paired image patches corresponding to each piece of building outline vector data are searched in parallel through parallel computing.

[0045] S103, calculating the spot heights of the plurality of pairs of the building spot matching data to obtain a spot height data set;

[0046] In this embodiment, the method of calculating the spot height is similar to the fore-intersection algorithm, but it is different from the fore-intersection algorithm in that it uses feature point calculation method. The intersection calculation is performed based on the polygon, which reduces the error caused by feature point matching errors. The area calculated by the intersection of the polygon conforms to the normal distribution, so the step size approximation method is used to obtain the spot height. After calculating the spot height of multiple pairs of building spot matching data, a spot height data set can be obtained.

[0047] S104, merging the image spot height data sets to obtain the target building height.

[0048] It is easy to understand that after the patch height data sets are merged, the final result can be obtained, that is, the height of the target building in the target area.

[0049] Specifically, obtaining the image data of the building to be measured includes: based on satellite remote sensing technology, obtaining the image data of the building at different viewing angles in the same area through left and right viewing satellite images.

[0050] In this embodiment, satellite remote sensing technology is mainly used, and then left and right satellite images are used to extract building information. That is, building image data of different viewing angles in the same area are obtained through left and right satellite images. The building image data is an RPC file.

[0051] Specifically, obtaining the building outline vector data based on the image data of the building to be tested includes: using deep learning or machine learning to process the image data of the building to be tested to obtain the building outline vector data.

[0052] In this embodiment, left-right-view satellite image data acquired based on satellite remote sensing technology is extracted through deep learning or machine learning, and converted into left-right-view building outline vector data.

[0053] Specifically, traversing to find the matching spots of another view includes: converting the spot data to be matched into geographic coordinates, then converting into pixel coordinates of another view, and intersecting with the building outline data of another view to obtain an array of intersecting spots; obtaining the matching spots in the array of intersecting spots.

[0054] In this embodiment, a certain view is taken as the main one, and the left view is taken as an example. The left view spots are traversed to find the spots that match the right view. Here, it refers to the spots of the left and right views of the same building. Assuming that the i-th matching spot of the left view is found, the i-th left view picture is enlarged by n times, which can be 10 times in this embodiment. After converting it into geographic coordinates, it is converted into right view pixel coordinates. The spot is intersected with the right view building outline to obtain the possible spot that matches the i-th left view spot. Then, from the intersecting spot array, the best matching spot is found as the matching spot. In actual operation, the program language is as follows:

[0055]

[0056]

[0057]

[0058]

[0059] in, It is the left-view building patch data. is the i-th left view spot; Refers to the magnification (the default is 10); Function for zooming in; It is the left-view rpc file; is the elevation of the current position (input); Function used to convert pixel coordinates to geographic coordinates; It is the right view rpc file; Function used to convert geographic coordinates to pixel coordinates; It is the right-view building patch data; Used to obtain the intersecting patch array.

[0060] Specifically, obtaining the matching pattern spots in the intersection pattern array includes: obtaining a target intersection area based on a maximum intersection calculation method; and matching the matching pattern spots in the intersection pattern array by using the target intersection area.

[0061] In this embodiment, the most matching spot among possible spots is found by calculating the maximum intersection, and the two spots with the largest intersection area are used as matching spots. Figure 3 As shown, in Figure 3 In the example, P(x) is the intersection area. In actual operation, the program language is as follows:

[0062]

[0063]

[0064]

[0065]

[0066]

[0067]

[0068] in, Used to calculate the maximum rotated bounding rectangle for merging two spots; Used to calculate the intersection area; It refers to the intersection pattern obtained in step 4 of the jth step.

[0069] The intersection area of ​​the jth spot is Area comparison, if the area difference is The area is less than 0.1, and Area and If the area is similar, then and For paired spots.

[0070] Specifically, calculating the spot heights of the plurality of pairs of building spot matching data includes:

[0071] An intersection calculation is performed on each pair of building patch matching data according to a polygon algorithm.

[0072] In this embodiment, after obtaining the paired spots, based on the building spot matching data, the intersection calculation is performed according to the polygon in a manner similar to the forward intersection algorithm, which is different from the forward intersection algorithm in that it uses the characteristic point calculation method, thereby reducing the error caused by the characteristic point matching error. Here, the area of ​​the polygon used for intersection calculation conforms to the normal distribution, so the step length approximation method is used to obtain the height. In actual operation, the program language is as follows:

[0073]

[0074]

[0075]

[0076] Here step is a continuous value, area_i is compared with the previous value, if it is less than this maximum value, it is the previous value. The height is step.

[0077] On the other hand, an embodiment of the present disclosure provides a device for calculating building height, comprising:

[0078] The vector data acquisition module 210 is used to acquire image data of the building to be tested, and obtain building outline vector data based on the image data of the building to be tested;

[0079] The pattern data acquisition module 220 is used to process the building outline vector data into blocks to obtain multiple pairs of building pattern matching data;

[0080] A height data calculation module 230 is used to calculate the spot heights of the plurality of pairs of the building spot matching data to obtain a spot height data set;

[0081] The height data merging module 240 is used to merge the image spot height data sets to obtain the target building height.

[0082] The beneficial effects of the present invention are: the present invention is more cost-effective and widely applicable, suitable for satellite images with sub-meter resolution and surface environments of different complexities, and significantly improves the efficiency and accuracy of building information extraction.

[0083] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0084] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0086] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (English: Read-Only Memory, abbreviated: ROM), random access memory (English: Random Access Memory, abbreviated: RAM), disk or optical disk and other media that can store program codes.

[0087] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0088] The above are only preferred embodiments of the present application and are 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.

[0089] Therefore, the embodiments of the present disclosure provide the following technical solutions:

[0090] 1. A method for measuring building height, comprising:

[0091] Acquire image data of a building to be measured, and obtain building outline vector data based on the image data of the building to be measured;

[0092] The building outline vector data is processed into blocks to obtain a plurality of pairs of building patch matching data;

[0093] Calculating the spot heights of the plurality of pairs of the building spot matching data to obtain a spot height data set;

[0094] The image patch height data sets are merged to obtain the target building height.

[0095] 2. In the building height measurement method according to technical solution 1, obtaining the image data of the building to be measured comprises:

[0096] Based on satellite remote sensing technology, building image data from different perspectives in the same area are obtained through left and right satellite images.

[0097] 3. In the building height measurement method according to technical solution 1, the step of obtaining building outline vector data based on the image data of the building to be measured comprises:

[0098] The image data of the building to be tested is processed using deep learning or machine learning to obtain the building outline vector data.

[0099] 4. In the building height measurement method according to technical solution 1, the block processing of the building outline vector data comprises:

[0100] Based on the geographical location clipping method, the building outline vector data is divided into blocks, and multiple pairs of building outline data are obtained after the block division;

[0101] Based on the to-be-paired spot data of one view of the building outline data, matching spots of another view are traversed to obtain paired spots, and the multiple pairs of building spot matching data include multiple pairs of the paired spots.

[0102] 5. In the building height measurement method according to technical solution 4, the traversal to find a matching spot of another view comprises:

[0103] Convert the to-be-matched spot data into geographic coordinates, then convert them into pixel coordinates of another view, and intersect them with the building outline data of another view to obtain an intersecting spot array;

[0104] The matching spots in the intersection spot array are obtained.

[0105] 6. In the building height measurement method according to technical solution 5, the step of obtaining the matching pattern in the intersecting pattern array comprises:

[0106] Based on the maximum intersection calculation method, the target intersection area is obtained;

[0107] The target intersection area is used to match the matching pattern spots in the intersection pattern array.

[0108] 7. The building height measurement method according to technical solution 1 is characterized in that the step of calculating the spot heights of the plurality of pairs of building spot matching data comprises:

[0109] An intersection calculation is performed on each pair of building patch matching data according to a polygon algorithm.

[0110] 8. A device for calculating building height, comprising:

[0111] A vector data acquisition module, used to acquire image data of the building to be tested, and obtain building outline vector data based on the image data of the building to be tested;

[0112] A pattern data acquisition module is used to process the building outline vector data in blocks to obtain multiple pairs of building pattern matching data;

[0113] A height data calculation module is used to calculate the spot heights of the plurality of pairs of the building spot matching data to obtain a spot height data set;

[0114] The height data merging module is used to merge the image spot height data sets to obtain the target building height.

[0115] 9. An electronic device, comprising:

[0116] at least one processor; and,

[0117] a memory communicatively connected to the at least one processor; wherein,

[0118] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the building height measurement method of any one of Technical Solutions 1 to Technical Solutions 7.

[0119] 10. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the building height measurement method of any one of Technical Solutions 1 to Technical Solutions 7.

Claims

1. A method for measuring building height, characterized in that: include: Acquire image data of a building to be measured, and obtain building outline vector data based on the image data of the building to be measured; Based on the geographic location clipping method, the building outline vector data is divided into blocks, and multiple pairs of building outline data after the block division are obtained; based on the to-be-paired spot data of one view of the building outline data, the matching spots of another view are traversed to obtain paired spots, and the multiple pairs of building spot matching data include multiple pairs of the paired spots, so as to obtain multiple pairs of building spot matching data; Calculating the spot heights of the plurality of pairs of the building spot matching data to obtain a spot height data set; The image patch height data sets are merged to obtain the target building height.

2. The building height measurement method according to claim 1, characterized in that: The obtaining of image data of the building to be tested comprises: Based on satellite remote sensing technology, building image data from different perspectives in the same area are obtained through left and right satellite images.

3. The building height measurement method according to claim 1, characterized in that: The acquiring of building outline vector data based on the image data of the building to be measured comprises: The image data of the building to be tested is processed using deep learning or machine learning to obtain the building outline vector data.

4. The building height measurement method according to claim 3, characterized in that: The traversal to find a matching spot of another view includes: Convert the to-be-matched spot data into geographic coordinates, then convert them into pixel coordinates of another view, and intersect them with the building outline data of another view to obtain an intersecting spot array; The matching spots in the intersection spot array are obtained.

5. The building height measurement method according to claim 4, characterized in that: The obtaining of the matching spots in the intersecting spot array comprises: Based on the maximum intersection calculation method, the target intersection area is obtained; The target intersection area is used to match the matching pattern spots in the intersection pattern array.

6. The building height measurement method according to claim 1, characterized in that: The calculating of the spot heights of the plurality of pairs of the building spot matching data comprises: An intersection calculation is performed on each pair of building patch matching data according to a polygon algorithm.

7. A building height calculation device, characterized in that: include: A vector data acquisition module, used to acquire image data of the building to be tested, and obtain building outline vector data based on the image data of the building to be tested; A pattern data acquisition module is used to process the building outline vector data in blocks to obtain multiple pairs of building pattern matching data; A height data calculation module is used to calculate the spot heights of the plurality of pairs of the building spot matching data to obtain a spot height data set; The height data merging module is used to merge the image spot height data sets to obtain the target building height.

8. An electronic device, characterized in that: The electronic device includes: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the building height measurement method described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the building height measurement method described in any one of claims 1 to 6.

Images