A method for measuring building height based on crowdsourced GNSS data

Abstract

This application discloses a method for measuring building height based on crowdsourced GNSS data, relating to the field of building measurement technology. The method includes: acquiring GNSS observation data from multiple receivers and extracting corresponding signal features; outputting the line-of-sight (LOS) signal probability using a trained signal classification neural network model; calculating the height estimate from the intersection point of the GNSS signal and the nearest facade of the prism facade (with the building boundary as its base) to the horizontal reference plane based on the positions of the GNSS satellites and receivers, and a two-dimensional map; and performing a fitting calculation based on the height estimate and the LOS signal probability, outputting the height estimate corresponding to the maximum LOS signal probability change rate as the corresponding building height measurement value. Using the method provided in this application, the height of buildings can be measured low-cost, efficiently, and in real-time using crowdsourced GNSS data, and a three-dimensional building map can be constructed by combining it with a two-dimensional map.

Description

Technical Field

[0001] This application relates to the field of building surveying technology, and in particular to a method for measuring building height based on crowdsourced GNSS data. Background Technology

[0002] With the rapid development of remote sensing technology, high-resolution remote sensing images can be used to visually display the geographical images of various cities. However, it is not possible to directly obtain the height information of various buildings in a city from two-dimensional images.

[0003] Related technologies typically acquire height information of buildings in cities through LiDAR and visual algorithms; however, both methods have at least the following drawbacks:

[0004] (1) High cost: It requires professional technicians to conduct on-site surveys using professional equipment, resulting in high labor costs; moreover, when dealing with a large number of building complexes, the labor and time costs are both high.

[0005] (2) Limited measurement conditions: Both of these measurement methods are easily affected by weather factors. The measurement accuracy will decrease under weather conditions such as rain and snow, resulting in the inability to provide high-precision measurement data in real time.

[0006] (3) Poor real-time performance: Since cities are constantly under construction, the height information of various buildings may change, and there may be situations where new buildings are added or buildings are removed in some areas. Therefore, it is necessary to update the height information of buildings in the city in real time. Both of the above methods require manual operation, which is inefficient and makes it difficult to ensure the real-time update of data.

[0007] Therefore, there is an urgent need for a method that can acquire building height information in real time at low cost and high efficiency. Summary of the Invention

[0008] This application provides a method for measuring building height based on crowdsourced GNSS data, which addresses the shortcomings of the aforementioned related technologies. The technical solution is as follows:

[0009] In a first aspect, embodiments of this application provide a method for measuring building height based on crowdsourced GNSS data, including:

[0010] Acquire GNSS observation data from multiple receivers within the area to be measured, and extract signal features corresponding to each GNSS signal based on the GNSS observation data;

[0011] The trained signal classification neural network model outputs the line-of-sight signal probability of the corresponding GNSS signal based on the signal features.

[0012] The projection of the line connecting the satellite and the receiver corresponding to each GNSS signal onto the two-dimensional map of the area to be measured is determined. The intersection point of the projection with the boundary of the building on the two-dimensional map is determined to be the boundary point closest to the projection point of the receiver. The straight-line distance between the projection point of the receiver and the intersection point of the boundary is calculated.

[0013] Based on the elevation angle characteristics of the GNSS signal, the straight-line distance, and the height of the receiver from the horizontal reference plane, the height estimate of the distance from the GNSS signal to the horizontal reference plane is calculated at the intersection point of the GNSS signal and the nearest face of the prism facade with the boundary of the building as its base. Based on the height estimate calculated for each GNSS signal and the corresponding line-of-sight signal probability, a fitting calculation is performed, and the height estimate corresponding to the maximum change rate of the line-of-sight signal probability is output as the height measurement value of the corresponding building.

[0014] In one alternative embodiment of the first aspect, the step of determining the projection of the line connecting the satellite and the receiver corresponding to each GNSS signal onto a two-dimensional map of the area to be measured, determining the intersection point of the projection with the boundary of a building on the two-dimensional map that is closest to the projection point of the receiver, and calculating the straight-line distance between the projection point of the receiver and the intersection point of the boundary, includes:

[0015] Based on the signal characteristics, determine the location information of the satellite corresponding to each GNSS signal and the location information of the corresponding receiver.

[0016] Based on the satellite's location information and the receiver's location information, a line connecting the receiver and the satellite is established in a standard coordinate system. The line is then projected onto the two-dimensional map, and the intersection point between the projection of the line and the boundary of the building on the two-dimensional map is determined to be the boundary point closest to the projection point of the receiver.

[0017] Based on the location information of the receiving end, the projection point of the receiving end on the two-dimensional map is determined, and the straight-line distance between the projection point and the intersection point of the boundary is determined.

[0018] In another alternative to the first aspect, the step of calculating the height estimate of the horizontal reference plane from the point where the GNSS signal intersects with the nearest face of the prism facade with the boundary of the building as its base, based on the elevation characteristics of the GNSS signal, the straight-line distance, and the height of the receiver from the horizontal reference plane, includes:

[0019] Based on the signal characteristics, the elevation angle characteristics corresponding to each GNSS signal are determined. The relative altitude is then calculated based on the elevation angle characteristics and the straight-line distance, using the following formula:

[0020] H0=γ·tanθ el ;

[0021] Obtain the height from the receiver corresponding to the GNSS signal to the horizontal reference plane. Calculate the estimated height based on the height from the receiver to the horizontal reference plane and the relative height, using the following formula:

[0022] IH = h u-terrain +γ·tanθ el ;

[0023] Where H0 is the relative height, θ el Let γ be the elevation angle, γ be the straight-line distance, IH be the estimated altitude, and h be the height. u-terrain The height of the receiving end from the horizontal reference plane.

[0024] In another alternative to the first aspect, before performing the fitting calculation based on the altitude estimate calculated for each GNSS signal and the corresponding line-of-sight signal probability, the method further includes:

[0025] Each height estimate and its corresponding line-of-sight signal probability are input into a sliding window filter. Sliding filtering is performed within a preset height range using a preset sliding window length. The filtered line-of-sight signal probability for each height estimate is then output, using the following formula:

[0026]

[0027] The fitting calculation based on the altitude estimate obtained from each GNSS signal and the corresponding line-of-sight signal probability includes:

[0028] The altitude estimate calculated for each GNSS signal is fitted and calculated using the probability of the filtered line-of-sight signal.

[0029] in, The filtered height range In-line GNSS signal probability; P LOS (IH) represents the probability of GNSS line-of-sight signals intersecting at height IH; M represents the altitude range. Number of internal GNSS signals; q is the window index; Δ h This represents the length of the sliding window.

[0030] In another alternative to the first aspect, the step of fitting the height estimate calculated based on each GNSS signal and the corresponding line-of-sight signal probability to output the height estimate corresponding to the maximum change rate of the line-of-sight signal probability as the measured height of the corresponding building includes:

[0031] Based on the logistic regression function, each height estimate and its corresponding line-of-sight signal probability are fitted and calculated, using the following formula:

[0032]

[0033] Based on the results of the fitting calculation, determine the height point corresponding to the maximum probability change rate of the line-of-sight signal, and output the height point corresponding to the maximum probability change rate as the height measurement value;

[0034] Where a is the slope at the inflection point of the logistic regression function, b is the height point corresponding to the maximum value of the probability change rate of the line-of-sight signal, and h is the input height estimate.

[0035] In another alternative to the first aspect, after the height estimate corresponding to the maximum value of the output line-of-sight signal probability change rate is the height measurement value of the corresponding building, it further includes:

[0036] Determine the height measurement value corresponding to each building on the two-dimensional map;

[0037] A three-dimensional building map of the area to be measured is constructed by combining the two-dimensional map and the height measurements of the buildings on the two-dimensional map.

[0038] In another alternative to the first aspect, the building height measurement method based on crowdsourced GNSS data provided in this application further includes:

[0039] GNSS observation data from multiple receivers within the test area are acquired at preset time intervals. Based on the GNSS observation data collected at each time, the height measurement value of buildings within the test area at the corresponding time is calculated. The height information of buildings within the test area is updated based on the height measurement value at the current time.

[0040] Secondly, embodiments of this application also provide a building height measurement device based on crowdsourced GNSS data, comprising:

[0041] The feature extraction module is used to acquire GNSS observation data from multiple receivers in the area to be measured, and extract the signal features corresponding to each GNSS signal based on the GNSS observation data.

[0042] The signal classification module is used to output the line-of-sight signal probability of the corresponding GNSS signal based on the signal features using a trained signal classification neural network model.

[0043] The intersection height calculation module is used to determine the projection of the line connecting the satellite and the receiver corresponding to each GNSS signal onto the two-dimensional map of the area to be measured, determine the boundary intersection point that is closest to the projection point of the receiver among the intersection points of the projection and the boundary of the building on the two-dimensional map, and calculate the straight-line distance between the projection point of the receiver and the intersection point of the boundary.

[0044] The intersection height calculation module is also used to calculate the estimated height of the intersection point between the GNSS signal and the nearest facade of the prism facade with the boundary of the building as the base, and the horizontal reference plane, based on the elevation angle characteristics of the GNSS signal, the straight-line distance, and the height of the receiver from the horizontal reference plane.

[0045] The building height measurement module is used to fit the height estimate obtained from each GNSS signal and the corresponding line-of-sight signal probability, and output the height estimate corresponding to the maximum line-of-sight signal probability change rate as the height measurement value of the corresponding building.

[0046] Thirdly, embodiments of this application also provide an electronic device, including 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 provided by the first aspect or any implementation thereof of the embodiments of this application.

[0047] Fourthly, this 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 embodiments of this application or any implementation thereof.

[0048] The beneficial effects of the technical solutions provided in some embodiments of this application include at least the following:

[0049] (1) Compared with the problem that related technologies can only measure height one by one through on-site surveys using professional equipment when facing a large number of building groups, resulting in low efficiency of height measurement, this application achieves coverage of a large area of ​​building groups by collecting GNSS observation data from multiple receivers, i.e. crowdsourced data. The collection of crowdsourced data does not require high-precision equipment and does not require the personnel using the equipment to have professional experience. It can provide a large amount of observation data at low cost and high efficiency, which is conducive to measuring the height information of a large area of ​​building groups.

[0050] (2) Compared with the shortcomings of related technologies, which are easily affected by weather conditions and have complicated measurement methods, resulting in the inability to update building height information in real time, this application combines existing two-dimensional maps for projection, which can quickly determine the height estimate of the horizontal reference plane from the intersection point of each GNSS signal and the prism facade with the building boundary as the base closest to the receiver. Based on the probability change rate of line-of-sight signals, it can determine the abrupt node of the line-of-sight signal turning into a non-line-of-sight signal, and then find the GNSS signal closest to the actual edge of the building, thereby obtaining the actual measurement value of the building height. It can not only output accurate height information, but is also not affected by weather factors. Based on crowdsourced data and the above calculation method, it can also realize the real-time acquisition and real-time updating of height information, which is conducive to the establishment of three-dimensional city maps. Attached Figure Description

[0051] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0052] Figure 1 This is a flowchart illustrating a method for measuring building height based on crowdsourced GNSS data, as provided in an embodiment of this application.

[0053] Figure 2 This is a two-dimensional map illustration of a method for measuring building height based on crowdsourced GNSS data provided in an embodiment of this application;

[0054] Figure 3 This is a schematic diagram showing the relative positions of boundary intersection points and facade intersection points in a building height measurement method based on crowdsourced GNSS data provided in an embodiment of this application.

[0055] Figure 4 This is a schematic diagram of a building height measurement device based on crowdsourced GNSS data provided in an embodiment of this application;

[0056] Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0058] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or modules is not limited to the steps or modules listed, but may optionally include steps or modules not listed, or may optionally include other steps or modules inherent to such process, method, product, or apparatus.

[0059] It should be noted that the terms "first" and "second" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects. It is understood that "first" and "second" can be interchanged in a specific order or sequence where permitted. It should be understood that the objects distinguished by "first" and "second" can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in an order other than those described or illustrated herein.

[0060] Understandably, the building height measurement method based on crowdsourced GNSS data provided in this application can be applied to fields such as urban surveying, map making, and urban planning. It can acquire GNSS observation data from each receiver in the area to be measured through one server or a server cluster composed of multiple servers. Software for implementing the building height measurement method based on crowdsourced GNSS data can be set up in the server or server cluster. This software is used to extract features from the acquired GNSS observation data and use the extracted signal features as input to a trained signal classification neural network model to obtain the line-of-sight signal probability of the corresponding GNSS signal, and further complete the calculation of the height measurement value.

[0061] Understandably, crowdsourced data, also known as crowdsourced data, refers to data acquired from multiple sources and devices. The GNSS observation data from multiple receivers within the test area acquired in this application is crowdsourced data. The test area can be any region of the city where altitude information needs to be measured, and one or more test areas can be defined based on an existing two-dimensional city map; this application does not limit this.

[0062] The receiving end can be a user-used terminal device, such as a mobile phone, tablet, vehicle-mounted device, or navigation device that can receive GNSS signals. The receiving end can also include base stations distributed in cities, drones used for surveying, and professional surveying equipment used for scientific research purposes. This application does not limit this aspect.

[0063] The present application will now be described in detail with reference to specific embodiments.

[0064] Next, combine Figure 1 This application introduces a building height measurement method based on crowdsourced GNSS data, as provided in its embodiments. Figure 1 The illustration shows a flowchart of a method for measuring building height based on crowdsourced GNSS data according to an embodiment of this application. The method includes the following steps:

[0065] S101: Acquire GNSS observation data from multiple receivers within the area to be measured, and extract the signal features corresponding to each GNSS signal based on the GNSS observation data.

[0066] Specifically, the GNSS data from multiple receivers includes, but is not limited to, the raw GNSS observation data from each receiver, as well as the corresponding broadcast ephemeris.

[0067] Specifically, the signal features corresponding to each GNSS signal extracted from GNSS data may include, but are not limited to, the carrier-to-noise ratio, elevation angle, azimuth angle, pseudorange residual, normalized pseudorange residual, and pseudorange residual percentage of the GNSS signal.

[0068] In some embodiments, the receiver clock bias can be estimated based on the weighted least squares principle, and the ionospheric delay and tropospheric delay can be corrected according to the classical Klobuchar model and the Saastamoinen model. The pseudorange residual is obtained by subtracting the satellite-receiver geometric distance, satellite clock bias, ionospheric delay, tropospheric delay and receiver clock bias from the original pseudorange. The normalized pseudorange residual and the percentage of pseudorange residual are calculated using a single-epoch normalization method.

[0069] S102, based on the signal characteristics, outputs the line-of-sight signal probability of the corresponding GNSS signal through a trained signal classification neural network model.

[0070] Specifically, the signal features corresponding to each GNSS signal can be used as input to a trained signal classification neural network model to further obtain the line-of-sight signal probability of the GNSS signal output by the signal classification neural network model as a line-of-sight signal.

[0071] Understandably, the signal classification neural network model can also directly output the classification result of whether the corresponding GNSS signal is a line-of-sight signal, or it can output the probability that the GNSS signal is a non-line-of-sight signal. This application does not limit this.

[0072] Understandably, after outputting the line-of-sight signal probability, the output classification result can be directly determined based on the set line-of-sight signal probability threshold.

[0073] In some embodiments, specifically, the signal classification neural network model is trained on a training dataset with line-of-sight / non-line-of-sight labels and GNSS signal features. The signal classification neural network model takes GNSS signal features such as carrier-to-noise ratio, satellite elevation angle, pseudorange residual, normalized pseudorange residual, and pseudorange residual percentage as input, and outputs the probability that the corresponding GNSS signal is a line-of-sight signal.

[0074] In some embodiments, a sky fisheye image of the data acquisition location can be acquired and the image azimuth angle recorded simultaneously with GNSS observation data acquisition. The sky fisheye image is then segmented using methods such as deep learning and manual segmentation to obtain a fisheye mask of the sky region at the data acquisition location. Based on the GNSS signal azimuth angle, elevation angle, and image azimuth angle from the GNSS signal features, the satellite is projected onto the fisheye mask. By determining whether the pixel coordinates of the projected satellite are within the sky region, if they are, the GNSS signal is identified as a line-of-sight (LAS) signal. This constructs a GNSS LAS / Non-LAS signal classification training dataset containing GNSS signal features and labels.

[0075] S103, determine the projection of the line connecting the satellite and the receiver corresponding to each GNSS signal onto the two-dimensional map of the area to be measured, determine the boundary intersection point that is closest to the projection point of the receiver among the intersection points of the projection and the boundary of the building on the two-dimensional map, and calculate the straight-line distance between the projection point of the receiver and the intersection point of the boundary.

[0076] In some embodiments, existing two-dimensional maps can be obtained directly from third parties or urban surveying departments. These maps can represent corresponding buildings using various graphic representations. Figure 2 The diagram shown is a schematic representation of a two-dimensional map.

[0077] For example, Figure 2The example illustrates the projections A, B, C, D, E, and F of buildings surrounding a street. The line PQ is the projection of the line connecting the satellite and the receiver onto a two-dimensional map. The line PQ intersects the boundary of building A at a point S closest to the projection point Q of the receiver. This allows us to determine the straight-line distance between the projection point Q of the receiver and the intersection point S on the boundary of building A. In some embodiments, the location of the receiver can be determined based on the GNSS data acquired in S101, thereby determining the location of the receiver's projection on the two-dimensional map.

[0078] Specifically, it can be based on the location of the receiver and the satellite azimuth angle θ. az Elevation angle θ el The WGS-84 coordinate system is selected as the standard coordinate system. The line equation connecting the receiver and the satellite in the standard coordinate system is established and projected onto a two-dimensional map. The intersection point of the projection with the boundary of the building on the two-dimensional map is determined to be the boundary point closest to the projection point of the receiver. The straight-line distance between the projection point of the receiver and the boundary intersection point is calculated.

[0079] S104, based on the elevation angle characteristics of the GNSS signal, the straight-line distance, and the height of the receiver from the horizontal reference plane, calculate the estimated height of the horizontal reference plane from the intersection point of the GNSS signal and the nearest facade of the prism facade with the boundary of the building as its base to the receiver.

[0080] Specifically, the elevation angle characteristic corresponding to each GNSS signal can be determined based on the signal characteristics, and the relative altitude can be calculated based on the elevation angle characteristic and the straight-line distance, using the following formula:

[0081] H0=γ·tanθ el ;

[0082] Obtain the height from the receiver corresponding to the GNSS signal to the horizontal reference plane. Calculate the estimated height based on the height from the receiver to the horizontal reference plane and the relative height, using the following formula:

[0083] IH = h u-terrain +γ·tanθ el ;

[0084] Where H0 is the relative height, θ el Let γ be the elevation angle, γ be the straight-line distance, IH be the estimated altitude, and h be the height. u-terrain The height of the receiving end from the horizontal reference plane.

[0085] Understandably, the vertical distance between the receiving end and the horizontal reference plane can generally be selected as 1.5m, or the actual distance between the receiving end and the horizontal reference plane can be collected during measurement.

[0086] Understandably, the horizontal reference plane can be any reference plane used to calculate the height of a building, such as a horizontal plane with an elevation of 0.

[0087] For example, such as Figure 3 As shown, assume that the GNSS signal intersects with the prism facade with the boundary of building R as its base. The projection of the line connecting the satellite and the receiver on the two-dimensional map intersects with the boundary of building R at the closest point to the projection J of the receiver J', i.e., point K. The intersection point of the straight line passing through the boundary intersection point K and perpendicular to the horizontal reference plane with the line connecting the satellite and the receiver is point K'. Point K' is also the intersection point of the GNSS signal and the prism facade with the boundary of building R as its base, which is closest to the receiver J'. The position of the receiver is point J', the projection of the receiver on the two-dimensional map is point J, the vertical distance between the relative height H0 between the facade intersection point K' and the receiver J' is K'L, and ∠K'J'L is the elevation angle λ. el The straight-line distance between K and J is γ, and the vertical distance between J' and J is the actual distance h between the receiving end and the horizontal reference plane. u-terrain That is, the height of the receiving end from the horizontal reference plane.

[0088] Understandably, according to Figure 3 The geometric relationship shown can be expressed by the elevation angle λ. el The relative height H0 is obtained by calculating the straight-line distance γ between K and KJ. Combined with the actual distance between the receiving end and the horizontal reference plane, the vertical distance between point K' and point K can be calculated, thus obtaining the above-mentioned height estimate.

[0089] S105, based on the height estimate calculated for each GNSS signal and the corresponding line-of-sight signal probability, performs fitting calculation and outputs the height estimate corresponding to the maximum line-of-sight signal probability change rate as the height measurement value of the corresponding building.

[0090] In some embodiments, before S105, the line-of-sight signal probability output by the signal classification neural network model in S102 can be filtered to adjust the line-of-sight signal probability corresponding to each GNSS signal.

[0091] Specifically, each height estimate and its corresponding line-of-sight signal probability can be input into a sliding window filter. Sliding filtering is performed within a preset height range using a preset sliding window length. The filtered line-of-sight signal probability for each height estimate is then output, using the following formula:

[0092]

[0093] in, The filtered height range In-line GNSS signal probability; P LOS (IH) represents the probability of GNSS line-of-sight signals intersecting at height IH; M represents the altitude range. Number of internal GNSS signals; q is the window index; Δ h This represents the length of the sliding window.

[0094] Understandably, sliding window filtering can eliminate the possibility of incorrect probability values ​​output by the signal classification neural network model, thereby improving the accuracy of signal classification and thus improving the accuracy of building height measurement.

[0095] It should be noted that the step of outputting the line-of-sight signal probability in S102 is performed before the fitting calculation in S105. This application embodiment does not limit the execution order of S102 and S103-S104. S102 can be executed first after extracting signal features in S101, or S103 and S104 can be executed first after extracting signal features in S101 to calculate the height estimate, or S102 and S103-S104 can be executed simultaneously. This application embodiment does not limit this.

[0096] In some embodiments, a logistic regression function is used to fit and calculate the probability of each height estimate and the corresponding line-of-sight signal, applying the following formula:

[0097]

[0098] Based on the results of the fitting calculation, determine the height point corresponding to the maximum probability change rate of the line-of-sight signal, and output the height point corresponding to the maximum probability change rate as the height measurement value;

[0099] Where a is the slope at the inflection point of the logistic regression function, b is the height point corresponding to the maximum value of the probability change rate of the line-of-sight signal, and h is the input height estimate.

[0100] Understandably, the height range of the transition from line-of-sight (LOS) signal to non-LOS signal can be determined by the above-mentioned logistic regression function. In the graph of the logistic regression function, the horizontal axis represents the height measurement value of the intersection point of the building and the GNSS signal, and the vertical axis represents the LOS signal probability. Based on the image, it is easy to extract the height point corresponding to the maximum change rate of the LOS signal probability, i.e., point b. The height estimate value of the mapping point corresponding to point b is output, and thus the height measurement value of the building can be obtained.

[0101] In some embodiments, after S105, the height measurement value corresponding to each building on the two-dimensional map can be determined, and a three-dimensional building map of the area to be measured can be constructed by combining the two-dimensional map and the height measurement value of the building projection on the two-dimensional map.

[0102] In some embodiments, steps S101-S105 can be executed periodically to achieve real-time updates of building height information, so that the building height information is synchronized with the urban construction and development process, and the constructed three-dimensional building map can display the building height information in real time.

[0103] Specifically, GNSS observation data from multiple receivers within the area to be measured can be acquired at preset time intervals. Based on the GNSS observation data collected at each time, the height measurement value of the buildings within the area to be measured at the corresponding time can be calculated, and then the height information of the buildings within the area to be measured can be updated based on the height measurement value at the current time.

[0104] The following are apparatus embodiments of this application, which can be used to execute the method embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the method embodiments of this application.

[0105] Please see below. Figure 4 This is a schematic diagram of a building height measurement device based on crowdsourced GNSS data, provided as an exemplary embodiment of this application. This device can be implemented as all or part of a terminal through software, hardware, or a combination of both, or it can be integrated as an independent module on a server. The building height measurement device 40 based on crowdsourced GNSS data in this embodiment includes a feature extraction module 410, a signal classification module 420, an intersection height calculation module 430, and a building height measurement module 440, wherein:

[0106] The feature extraction module 410 is used to acquire GNSS observation data from multiple receivers in the area to be measured, and extract the signal features corresponding to each GNSS signal based on the GNSS observation data;

[0107] The signal classification module 420 is used to output the line-of-sight signal probability of the corresponding GNSS signal based on the signal features using a trained signal classification neural network model;

[0108] The intersection height calculation module 430 is used to determine the projection of the line connecting the satellite and the receiver corresponding to each GNSS signal onto the two-dimensional map of the area to be measured, determine the boundary intersection point that is closest to the projection point of the receiver among the intersection points of the projection and the boundary of the building on the two-dimensional map, and calculate the straight-line distance between the projection point of the receiver and the intersection point of the boundary.

[0109] The intersection height calculation module 430 is also used to calculate the estimated height of the intersection point between the GNSS signal and the nearest facade of the prism facade with the boundary of the building as the base, and the horizontal reference plane, based on the elevation angle characteristics of the GNSS signal, the straight distance, and the height of the receiver from the horizontal reference plane.

[0110] The building height measurement module 440 is used to fit the height estimate value calculated based on each GNSS signal and the corresponding line-of-sight signal probability, and output the height estimate value corresponding to the maximum line-of-sight signal probability change rate as the height measurement value of the corresponding building.

[0111] It should be noted that the above-described embodiment of the apparatus 40, when executing the building height measurement method based on crowdsourced GNSS data, is only illustrative of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the apparatus provided in the above embodiment and the embodiment of the building height measurement method based on crowdsourced GNSS data belong to the same concept, and their implementation process is detailed in the method embodiment, which will not be repeated here.

[0112] This 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 executes the program to implement the steps of any of the methods described above.

[0113] Please see Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of this application, such as... Figure 5 As shown, the electronic device 500 includes a processor 501 and a memory 502. In this embodiment, the processor 501 is the control center of the computer system, and can be a processor of a physical machine or a processor of a virtual machine. The processor 501 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 501 can be implemented using at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array).

[0114] Processor 501 may also include a main processor and a coprocessor. The main processor is a processor used to process data in the wake-up state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor used to process data in the standby state.

[0115] Memory 502 may include one or more computer-readable storage media, which may be non-transitory. Memory 502 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments of this application, the non-transitory computer-readable storage media in memory 502 is used to store at least one instruction, which is executed by processor 501 to implement the method in the embodiments of this application.

[0116] In some embodiments, the electronic device 500 further includes a peripheral device interface 503 and at least one peripheral device 504. The processor 501, memory 502, and peripheral device interface 503 can be connected via a bus or signal line. Each peripheral device 504 can be connected to the peripheral device interface 503 via a bus, signal line, or circuit board. Specifically, the peripheral device 504 includes: a display screen, a camera, and audio circuitry. The peripheral device interface 503 can be used to connect at least one I / O (Input / Output) related peripheral device to the processor 501 and memory 502.

[0117] In some embodiments of this application, the processor 501, memory 502, and peripheral device interface 503 are integrated on the same chip or circuit board; in other embodiments of this application, any one or two of the processor 501, memory 502, and peripheral device interface 503 can be implemented on separate chips or circuit boards. This application does not specifically limit the implementation in this regard.

[0118] The block diagram of the electronic device shown in the embodiments of this application does not constitute a limitation on the electronic device 500. The electronic device 500 may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0119] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the methods in any of the foregoing embodiments. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0120] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of software products. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for measuring building height based on crowdsourced GNSS data, characterized in that, include: Acquire GNSS observation data from multiple receivers within the area to be measured, and extract signal features corresponding to each GNSS signal based on the GNSS observation data; The trained signal classification neural network model outputs the line-of-sight signal probability of the corresponding GNSS signal based on the signal features. The projection of the line connecting the satellite and the receiver corresponding to each GNSS signal onto the two-dimensional map of the area to be measured is determined. The intersection point of the projection with the boundary of the building on the two-dimensional map is determined to be the boundary point closest to the projection point of the receiver. The straight-line distance between the projection point of the receiver and the intersection point of the boundary is calculated. Based on the elevation angle characteristics of the GNSS signal, the straight-line distance, and the height of the receiver from the horizontal reference plane, calculate the estimated height of the horizontal reference plane from the intersection point of the GNSS signal and the nearest face of the prism facade with the boundary of the building as its base. The height estimate calculated based on each GNSS signal and the corresponding line-of-sight signal probability are fitted together, and the height estimate corresponding to the maximum change rate of the line-of-sight signal probability is output as the height measurement value of the corresponding building.

2. The building height measurement method based on crowdsourced GNSS data according to claim 1, characterized in that, The process of determining the projection of the line connecting the satellite and the receiver corresponding to each GNSS signal onto a two-dimensional map of the area to be measured, determining the intersection point of the projection with the boundary of a building on the two-dimensional map that is closest to the projection point of the receiver, and calculating the straight-line distance between the projection point of the receiver and the intersection point of the boundary includes: Based on the signal characteristics, determine the location information of the satellite corresponding to each GNSS signal and the location information of the corresponding receiver. Based on the satellite's location information and the receiver's location information, a line connecting the receiver and the satellite is established in a standard coordinate system. The line is then projected onto the two-dimensional map, and the intersection point between the projection of the line and the boundary of the building on the two-dimensional map is determined to be the boundary point closest to the projection point of the receiver. Based on the location information of the receiving end, the projection point of the receiving end on the two-dimensional map is determined, and the straight-line distance between the projection point and the intersection point of the boundary is determined.

3. The method for measuring building height based on crowdsourced GNSS data according to claim 1 or 2, characterized in that, The calculation of the height estimate from the horizontal reference plane to the intersection point of the GNSS signal and the nearest facade of the prism facade with the building boundary as its base, based on the elevation angle characteristics of the GNSS signal, the straight-line distance, and the height of the receiver from the horizontal reference plane, includes: Based on the signal characteristics, the elevation angle characteristics corresponding to each GNSS signal are determined. The relative altitude is calculated based on the elevation angle characteristics and the straight-line distance, using the following formula: H0=γ·tanθ el ; Obtain the height from the receiver corresponding to the GNSS signal to the horizontal reference plane. Calculate the estimated height based on the height from the receiver to the horizontal reference plane and the relative height, using the following formula: IH=h u-terrain +γ·tanθ el 4 Where H0 is the relative height, θ el Let γ be the elevation angle, γ be the straight-line distance, IH be the estimated height, and h be the elevation angle. u-terrain The height of the receiving end from the horizontal reference plane.

4. The method for measuring building height based on crowdsourced GNSS data according to claim 1, characterized in that, Before fitting the height estimate calculated based on each GNSS signal and the corresponding line-of-sight signal probability, the method further includes: Each height estimate and its corresponding line-of-sight signal probability are input into a sliding window filter. Sliding filtering is performed within a preset height range using a preset sliding window length. The filtered line-of-sight signal probability for each height estimate is then output, using the following formula: The fitting calculation based on the altitude estimate obtained from each GNSS signal and the corresponding line-of-sight signal probability includes: The altitude estimate calculated for each GNSS signal is fitted and calculated using the probability of the filtered line-of-sight signal. in, The filtered height range In-line GNSS signal probability, P LOS (IH) represents the probability of GNSS line-of-sight signals intersecting at height IH, and M represents the altitude interval. Number of internal GNSS signals, q is the window index, Δ h This represents the length of the sliding window.

5. The method for measuring building height based on crowdsourced GNSS data according to claim 1 or 4, characterized in that, The height estimate calculated based on each GNSS signal is fitted with the corresponding line-of-sight signal probability, and the height estimate corresponding to the maximum change rate of the line-of-sight signal probability is output as the measured height of the corresponding building, including: Based on the logistic regression function, each height estimate and its corresponding line-of-sight signal probability are fitted and calculated, using the following formula: Based on the results of the fitting calculation, determine the height point corresponding to the maximum probability change rate of the line-of-sight signal, and output the height point corresponding to the maximum probability change rate as the height measurement value; Where a is the slope at the inflection point of the logistic regression function, b is the height point corresponding to the maximum value of the probability change rate of the line-of-sight signal, and h is the input height estimate.

6. The method for measuring building height based on crowdsourced GNSS data according to claim 1, characterized in that, After the height estimate corresponding to the maximum value of the output line-of-sight signal probability change rate is the height measurement value of the corresponding building, it also includes: Determine the height measurement value corresponding to each building on the two-dimensional map; A three-dimensional building map of the area to be measured is constructed by combining the two-dimensional map and the height measurements of the buildings on the two-dimensional map.

7. The method for measuring building height based on crowdsourced GNSS data according to claim 1, characterized in that, The method further includes: GNSS observation data from multiple receivers within the test area are acquired at preset time intervals. Based on the GNSS observation data collected at each time, the height measurement value of buildings within the test area at the corresponding time is calculated. The height information of buildings within the test area is updated based on the height measurement value at the current time.

8. A building height measurement device based on crowdsourced GNSS data, characterized in that, include: The feature extraction module is used to acquire GNSS observation data from multiple receivers in the area to be measured, and extract the signal features corresponding to each GNSS signal based on the GNSS observation data. The signal classification module is used to output the line-of-sight signal probability of the corresponding GNSS signal based on the signal features using a trained signal classification neural network model. The intersection height calculation module is used to determine the projection of the line connecting the satellite and the receiver corresponding to each GNSS signal onto the two-dimensional map of the area to be measured, determine the boundary intersection point that is closest to the projection point of the receiver among the intersection points of the projection and the boundary of the building on the two-dimensional map, and calculate the straight-line distance between the projection point of the receiver and the intersection point of the boundary. The intersection height calculation module is also used to calculate the estimated height of the intersection point between the GNSS signal and the nearest facade of the prism facade with the boundary of the building as the base, and the horizontal reference plane, based on the elevation angle characteristics of the GNSS signal, the straight-line distance, and the height of the receiver from the horizontal reference plane. The building height measurement module is used to fit the height estimate obtained from each GNSS signal and the corresponding line-of-sight signal probability, and output the height estimate corresponding to the maximum line-of-sight signal probability change rate as the height measurement value of the corresponding building.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method as described in any one of claims 1 to 7.

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, it implements the steps of the method as described in any one of claims 1 to 7.

Images