Building completion data collection method and system, electronic device and storage medium

Abstract

The application provides a building completion data acquisition method and system, electronic equipment and storage medium, comprising: acquiring the unmanned aerial vehicle (UAV) pos data when the UAV flies around the building, solving the three-dimensional coordinates of the building feature points based on the pre-constructed collinear condition equation to obtain the overall structure sketch information of the building; intelligently grouping the feature point area through the K-Means clustering algorithm, dividing the building area into ordinary structure area and complex structure area according to the grouping result; dynamically adjusting the heading overlap rate and the lateral overlap rate according to the preset overlap rate and the actual overlap rate of the camera, and setting the heading overlap rate corresponding to the ordinary structure area and the complex structure area based on the lateral overlap rate to determine the best flight height and resolution of the UAV. The application optimizes the multi-dimensional parameters of the UAV, effectively improves the building completion data acquisition accuracy and efficiency.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of unmanned aerial vehicle data collection, and particularly relates to a building completion data collection method and system, an electronic device and a storage medium. BACKGROUND

[0002] With the continuous advancement of construction engineering and various infrastructure construction, the key of completion acceptance measurement work is increasingly prominent. As the core link of project acceptance process and later operation management, the accuracy and efficiency of its measurement results are getting more and more attention and attention.

[0003] Now, unmanned aerial vehicle photogrammetry plays an important role in building completion acceptance information collection. This technology uses wireless remote control device and ground station for flight control, has the characteristics of compact structure, light load, moderate cruising speed and large coverage area, etc. Because it has the advantages of rapid response, safe operation and controllable cost, it has become the focus of international academic and engineering circles, and continues to advance from the technical research and development stage to the industrialization application stage.

[0004] The traditional unmanned aerial vehicle surveying method mainly adopts a pre-set fixed flight route, and controls the lateral image overlap rate to ensure the continuity and integrity of the flight data, thereby providing basic data support for building completion surveying. However, the existing technology faces significant challenges in complex building scenes, for example: when dealing with buildings with large height difference, the actual overlap rate deviates from the preset value due to surface undulation, thereby causing image resolution difference in different elevation areas. This inconsistency in resolution will directly affect the later three-dimensional modeling effect, manifesting as unnatural color transition, texture connection fracture or geometric deformation, etc., ultimately reducing the mapping quality and the reliability of surveying data. SUMMARY

[0005] Therefore, the present application aims to provide a building completion data collection method, system, electronic device and storage medium to solve at least one of the above problems.

[0006] To achieve the above purpose, the technical scheme of the present application is as follows:

[0007] In a first aspect, the present application provides a building completion data collection method, comprising:

[0008] Obtaining the unmanned aerial vehicle pos data when the unmanned aerial vehicle flies around the building, solving the three-dimensional coordinates of the building feature points based on the pre-constructed collinear condition equation to obtain the overall structure information of the building, wherein the collinear condition equation is constructed based on the center projection of the unmanned aerial vehicle station and the building feature points;

[0009] The feature point region is intelligently grouped by a K-Means clustering algorithm, and the building region is divided into a normal structure region and a complex structure region according to the grouping result.

[0010] According to the preset overlap rate and the actual overlap rate of photographing, the heading overlap rate and the lateral overlap rate are dynamically adjusted, the heading overlap rate is set according to the normal structure region and the complex structure region, and the best flight height and resolution of the unmanned aerial vehicle are determined based on the lateral overlap rate.

[0011] In a second aspect, based on the same inventive concept, the application further provides a building completion data acquisition system, comprising:

[0012] The data acquisition module is configured to acquire the unmanned aerial vehicle pos data when the unmanned aerial vehicle flies around the building, and to solve the three-dimensional coordinates of the building feature points based on a pre-constructed collinear condition equation to obtain overall structure sketch information of the building, wherein the collinear condition equation is constructed based on the center projection of the unmanned aerial vehicle camera station and the building feature points.

[0013] The region division module is configured to intelligently group the feature point region by a K-Means clustering algorithm, and to divide the building region into a normal structure region and a complex structure region according to the grouping result.

[0014] The flight parameter adjustment module is configured to dynamically adjust the heading overlap rate and the lateral overlap rate according to the preset overlap rate and the actual overlap rate of photographing, to set the heading overlap rate according to the normal structure region and the complex structure region, and to determine the best flight height and resolution of the unmanned aerial vehicle based on the lateral overlap rate.

[0015] In a third aspect, based on the same inventive concept, the 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 the processor executes the program to implement the method of the first aspect.

[0016] In a fourth aspect, based on the same inventive concept, the application further provides a non-transitory computer readable storage medium, wherein the non-transitory computer readable storage medium stores computer instructions for causing the computer to execute the method of the first aspect.

[0017] Compared with the prior art, the building completion data acquisition method, system, electronic device and storage medium provided by the application have the following beneficial effects:

[0018] The building completion data acquisition method provided by the application optimizes the multi-dimensional parameters of the unmanned aerial vehicle, improves the data acquisition accuracy and the operation efficiency, and effectively guarantees the balance and consistency of the overall quality of the building completion three-dimensional model. The building completion data acquisition method provided by the application optimizes the multi-dimensional parameters of the unmanned aerial vehicle, improves the data acquisition accuracy and the operation efficiency, and effectively guarantees the balance and consistency of the overall quality of the building completion three-dimensional model. Attached Figure Description

[0019] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 This is a flowchart of a building completion data acquisition method according to an embodiment of this application;

[0021] Figure 2 This is a schematic diagram of the drone flying around a building according to an embodiment of this application;

[0022] Figure 3 This is a schematic diagram of the structure of a building completion data acquisition system according to an embodiment of this application;

[0023] Figure 4 This is a schematic diagram of the hardware structure of the electronic device described in an embodiment of this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0025] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0026] The embodiments of this application are described in detail below with reference to the accompanying drawings.

[0027] Please see Figure 1 As shown in the figure, this embodiment provides a method for collecting building completion data, which specifically includes the following steps:

[0028] Step S101: Obtain UAV POS data when the UAV flies around the building, and calculate the three-dimensional coordinates of the building feature points based on the pre-constructed collinearity condition equation to obtain the general information of the overall structure of the building. The collinearity condition equation is constructed based on the center projection of the UAV camera station and the building feature points.

[0029] Specifically, in this embodiment, the drone is first controlled to fly horizontally around the five sides of the building: east, south, west, north, and top, to obtain drone POS data information, which includes the three-dimensional coordinates and azimuth attitude angles of the camera station.

[0030] Then, the collinearity condition equations for the center projections of the image point and the object point are constructed, where the image point is the UAV camera station and the object point is the building feature point. (Setting...) Here are the coordinates of the drone photography center in the ground coordinate system. This represents the location of the building's feature points in the ground coordinate system. Let the image point be the projection point of the drone photography center on the projection plane. Based on the coordinate system of the image point and the object point, a system of equations is established:

[0031] (1)

[0032] In the formula, Indicates the camera's focal length. Indicates the scaling factor. The matrix representing the orthogonality between the image space coordinate system and the auxiliary image space coordinate system. , , ( =1, 2, 3) represents the direction cosines. Eliminate the scaling factor. The following formula can then be obtained:

[0033] (2)

[0034] (3)

[0035] The process of object point being projected from the projection center to the center of image point is described in equations (2) and (3), which establish the ground point. With image point The correspondence between them is expressed mathematically as follows:

[0036] (4)

[0037] From this, we can obtain equations (5) and (6) for the projection process from the image point to the corresponding object point via the projection center:

[0038] (5)

[0039] (6)

[0040] The condition equations of the same named image points in each image are established, and the three-dimensional space coordinates of the corresponding points are calculated by joint solving. The mathematical relationship can be expressed as follows:

[0041] (7)

[0042] The coordinates of the feature points of the building can be calculated by the collinear condition equation of formula (7) :

[0043] (8)

[0044] The above process is repeated to solve each feature point of the building, so as to obtain the overall structure coordinate of the building.

[0045] Step S102, intelligently grouping the feature point region by K-Means clustering algorithm, and dividing the building area into ordinary structure area and complex structure area according to the grouping result.

[0046] Specifically, in the embodiment, the K-means clustering algorithm updates the clustering center by iteration, unsupervised divides the building feature points inverted by the collinear condition equation, and realizes the spatial adaptive grouping.

[0047] Further, first, the building feature points are randomly divided into N groups, and n points are randomly specified as initial clustering centers;

[0048] Secondly, the distance of each feature point to all clustering centers is calculated, and it is classified into the cluster with the shortest path;

[0049] Then, after all feature points are classified, the n clustering centers are recalculated and updated according to the minimum total error sum of squares of the sample points to the belonging clustering center;

[0050] Finally, the n clustering centers obtained in the last round of calculation are compared, if the new clustering center is the same as the last round, the iteration is terminated, otherwise step 2 is returned to continue iteration, until the final grouping is output after convergence.

[0051] Since the number of feature points is related to the complexity of the building structure, according to the actual completion accuracy requirement, the k clustering center points of the first 25% of the feature points are divided into complex structure, and the rest are classified as ordinary structure.

[0052] Step S103, dynamically adjusting the heading overlap rate and the lateral overlap rate according to the preset overlap rate and the actual overlap rate of the camera, and setting the heading overlap rate based on the ordinary structure area and the complex structure area, and determining the best flight height and resolution of the unmanned aerial vehicle based on the lateral overlap rate.

[0053] Specifically, in the present embodiment, the preset overlap degree of the image and the actual overlap degree generally exist deviation, and the deviation will be significantly amplified in the scene where the building height difference is large. The present embodiment sets as the average height of all feature points in the measurement area, as the relative flight height of the UAV to the average height line of the measurement area, as the height of a certain feature point M, as the height of the feature point M relative to the average reference line, that is .

[0054] Suppose as the preset heading overlap rate on the average reference line of the measurement area, as the corresponding actual heading overlap rate of the image, then for any point, we have:

[0055] (9)

[0056] wherein, indicates the upward rounding processing of the result of formula (9).

[0057] Thus, the actual heading overlap rate corresponding to the preset heading overlap rate can be obtained, that is, the heading resolution of the building under different height conditions remains consistent; the actual lateral resolution is calculated by using the same process.

[0058] As shown in Figure 2 , when the UAV flies horizontally around the east, south, west, and north faces of the building, the camera parameter sensor width is , the focal length is , the pixel size is , and the lateral overlap rate is calculated by step 4. The initial flight height of the UAV is set to , and thus the optimal flight height of the UAV when flying around the east, south, west, and north faces of the building can be obtained, and the specific formula is as follows:

[0059] (10)

[0060] wherein, , ;

[0061] In the formula, indicates the actual lateral overlap rate, which is obtained from the heading overlap rate formula, indicates the initial flight height of the UAV, indicates the camera parameter sensor width, indicates the focal length, indicates the flight line interval of the UAV when flying horizontally around the building, indicates the flight circle number, indicates the initial flight height .

[0062] When the UAV flies at the top, the adjacent circle height difference is the route interval, and the top route interval formula is as follows:

[0063] (11)

[0064] In the formula, indicates the flight height when the UAV flies to the last circle, indicates the top route interval of the UAV.

[0065] Resolution when flying at the same height is unchanged and is set as:

[0066] (12)

[0067] In the formula, indicates the resolution, indicates the pixel size.

[0068] Further, after the route interval and the heading overlap rate of the UAV flight have been determined, the screened k cluster coordinates are classified into corresponding routes, and these routes are classified as complex structure areas, and the remaining routes are ordinary areas. For the two types of building structures, the heading overlap rate is set as follows:

[0069] The heading overlap rate of the ordinary structure is directly taken as the result calculated by formula (9) ;

[0070] The heading overlap rate of the complex structure is increased by 5% on the result calculated by formula (9), that is: .

[0071] Therefore, the resolution matching fine collection of the ordinary and complex structure areas is realized.

[0072] The method described in the application uses a clustering algorithm to intelligently classify building feature points, realizes spatial adaptive grouping, and then dynamically adjusts the heading and lateral overlap rates by real-time calculation of the actual overlap rate. Finally, the differential overlap rate is set according to the structure complexity. This method improves the data collection accuracy and work efficiency while effectively ensuring the balance and consistency of the overall quality of the building three-dimensional model in the later stage.

[0073] It is to be understood that the foregoing description is descriptive only. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order and still achieve desirable results. Additionally, the processes depicted in the attached figures do not necessarily require the particular order shown or sequential order to achieve desirable results. In certain implementations, multitasking and parallel processing can be advantageous.

[0074] Based on the same inventive concept, embodiments of the present application also provide a building completion data acquisition system corresponding to any of the above-mentioned embodiment methods.

[0075] As shown in Figure 3 The building completion data acquisition system comprises:

[0076] The data acquisition module 11 is configured to acquire the UAV pos data when the UAV flies around the building, and to calculate the three-dimensional coordinates of the building feature points based on a pre-constructed collinear condition equation to obtain the overall structure sketch information of the building, wherein the collinear condition equation is constructed based on the center projection of the UAV camera station and the building feature points.

[0077] The region division module 12 is configured to intelligently group the feature point regions through a K-Means clustering algorithm, and to divide the building region into an ordinary structure region and a complex structure region according to the grouping result.

[0078] The flight parameter adjustment module 13 is configured to dynamically adjust the heading overlap rate and the lateral overlap rate according to the preset overlap rate and the actual overlap rate of the photographing, to set the heading overlap rate corresponding to the ordinary structure region and the complex structure region, and to determine the best flight height and resolution of the UAV based on the lateral overlap rate.

[0079] For the convenience of description, the above system is described in various modules in terms of functions. Of course, the functions of the modules can be implemented in one or more software and / or hardware when implementing the embodiments of the present application.

[0080] The system of the above-mentioned embodiments is used to implement the corresponding method in any of the above-mentioned embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described here again.

[0081] Based on the same inventive concept, embodiments of the present application also provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of the above-mentioned embodiments when executing the program.

[0082] Figure 4A more specific electronic device hardware structure schematic diagram provided by the embodiment is shown, and the device can include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 for internal communication.

[0083] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, etc., for executing related programs to implement the technical solutions provided by the embodiments of the present specification.

[0084] The memory 1020 can be implemented by a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 can store an operating system and other application programs, and when the technical solutions provided by the embodiments of the present specification are implemented by software or firmware, the related program codes are stored in the memory 1020 and called and executed by the processor 1010.

[0085] The input / output interface 1030 is used to connect input / output modules to realize information input and output. The input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. The input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0086] The communication interface 1040 is used to connect a communication module (not shown in the figure) to realize the communication interaction between the device and other devices. The communication module can realize communication through a wired manner (such as USB, network cable, etc.) or through a wireless manner (such as mobile network, WIFI, Bluetooth, etc.).

[0087] The bus 1050 includes a channel for transmitting information between various components (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040) of the device.

[0088] It should be noted that although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device can also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device can also only contain the components necessary to implement the embodiments of the present application, and does not necessarily contain all the components shown in the figure.

[0089] The electronic device of the above embodiment is used to implement the corresponding method in any of the preceding embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described here.

[0090] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present application also provides a non-transitory computer readable storage medium, which stores computer instructions for causing the computer to execute the method of any of the above embodiments.

[0091] The computer readable medium of the present embodiment includes permanent and non-permanent, removable and non-removable media, which can be implemented by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage device, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0092] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the method of any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which are not described here.

[0093] Those skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope (including claims) of the present application is limited to these examples; under the idea of the present application, the above embodiments or technical features in different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes of different aspects of the embodiments of the present application as described above. In order to be brief, they are not provided in detail.

[0094] While the present application has been described in connection with certain embodiments thereof, many modifications, substitutions, changes, and of forms will be apparent to those of ordinary skill in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) can use the embodiments discussed.

[0095] Embodiments of the present application are intended to cover all such alterations, modifications, and variations as they can come within the scope of the appended claims. Accordingly, although specific embodiments have been furthered in connection with the present application, any omission, substitution, or change, in principle and in form, made to the present application should be included in the scope of the present application.

Claims

1. A method of collecting building completion data, characterized by, The method comprises the following steps: obtaining the pos data of the unmanned aerial vehicle when the unmanned aerial vehicle flies around the building, and solving the three-dimensional coordinates of the feature points of the building based on a pre-constructed collinear condition equation to obtain the overall structure information of the building, wherein the collinear condition equation is constructed based on the central projection of the camera station and the feature points of the building; intelligently grouping the feature point region through a K-Means clustering algorithm, and dividing the building region into a normal structure region and a complex structure region according to the grouping result, including: the K-Means clustering algorithm updates the clustering center through iteration, unsupervisedly divides the feature points of the building inverted by the collinear condition equation, classifies the screened clustering coordinates into the corresponding flight path, and classifies the flight path as a complex structure region, and the remaining flight paths are classified as normal structure regions; dynamically adjusting the forward overlap rate and the lateral overlap rate according to the preset overlap rate and the actual overlap rate of the imaging, and setting the forward overlap rate based on the normal structure region and the complex structure region, and determining the optimal flight height and resolution of the unmanned aerial vehicle based on the lateral overlap rate; wherein the formula of the forward overlap rate is as follows: ； In the formula, is the preset overlap ratio of the average baseline of the survey area, is the actual overlap ratio of the image corresponding to the actual heading, is the elevation of the feature point relative to the average baseline, is the relative altitude of the UAV to the average elevation line of the survey area, indicates that the heading overlap ratio result is rounded up; the actual lateral resolution The same process is used for calculation; the forward overlap rate of the normal structure region is the actual forward overlap rate, and the forward overlap rate of the complex structure region is the sum of the actual forward overlap rate and a preset threshold value; in response to the unmanned aerial vehicle flying horizontally around the building, the formula of the optimal flight height of the unmanned aerial vehicle is as follows: ； wherein , ; wherein, represents the actual side overlap ratio, which is derived from the heading overlap ratio formula, represents the camera parameter sensor width, represents the focal length, represents the flight line interval when the unmanned aerial vehicle horizontally circles the building, represents the number of flight circles, represents the initial flight height .

2. The method of claim 1, wherein: in response to the unmanned aerial vehicle flying on the top of the building, wherein the formula of the top flight path interval is as follows: ； In the formula, represents the flight height when the UAV flies to the last circle, represents the top route interval of the UAV.

3. The method of claim 1, wherein, the formula of the resolution is as follows: ； In the formulae, denotes the resolution, denotes the pixel size.

4. A building completion data collection system characterized by, The method comprises the following steps: a data acquisition module configured to obtain the pos data of the unmanned aerial vehicle when the unmanned aerial vehicle flies around the building, and solve the three-dimensional coordinates of the feature points of the building based on a pre-constructed collinear condition equation to obtain the overall structure information of the building, wherein the collinear condition equation is constructed based on the central projection of the camera station and the feature points of the building; a region division module configured to intelligently group the feature point region through a K-Means clustering algorithm, and divide the building region into a normal structure region and a complex structure region according to the grouping result, including: the K-Means clustering algorithm updates the clustering center through iteration, unsupervisedly divides the feature points of the building inverted by the collinear condition equation, classifies the screened clustering coordinates into the corresponding flight path, and classifies the flight path as a complex structure region, and the remaining flight paths are classified as normal structure regions; a flight parameter adjustment module configured to dynamically adjust the forward overlap rate and the lateral overlap rate according to the preset overlap rate and the actual overlap rate of the imaging, and set the forward overlap rate based on the normal structure region and the complex structure region, and determine the optimal flight height and resolution of the unmanned aerial vehicle based on the lateral overlap rate; wherein the formula of the forward overlap rate is as follows: ； In the formula, is the preset lateral overlap ratio of the average baseline of the survey area, is the actual lateral overlap ratio of the image, is the elevation of the feature point relative to the average baseline, is the relative altitude of the UAV to the average elevation line of the survey area, indicates that the lateral overlap ratio result is rounded up; the actual lateral resolution The same process is used for calculation; the forward overlap rate of the normal structure region is the actual forward overlap rate, and the forward overlap rate of the complex structure region is the sum of the actual forward overlap rate and a preset threshold value; In response to the UAV flying horizontally around the building, the optimal flight height of the UAV is as follows: ； wherein , ; wherein, represents the actual side overlap ratio, which is derived from the heading overlap ratio formula, represents the camera parameter sensor width, represents the focal length, represents the horizontal flight path spacing when the UAV circles the building, represents the number of flight circles, represents the initial flight height .

5. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the method of any of claims 1-3 when executing the program.

6. A non-transitory computer-readable storage medium, comprising: wherein, The non-transitory computer readable storage medium stores computer instructions for causing a computer to perform the method of any of claims 1-3.

Images