GNSS (Global Navigation Satellite System) observation environment complexity measurement method, device, equipment and medium

Abstract

The invention relates to the technical field of GNSS observation environment evaluation, in particular to a GNSS observation environment complexity measurement method, device and equipment and a medium, and the method comprises the steps: obtaining a sky image of a target area through a fisheye camera, and carrying out the recognition of the sky image through an image processing algorithm, and obtaining a sky recognition result; calculating trajectories of all satellites based on almanac information, and obtaining an openness index of the target region in combination with a sky recognition result; gNSS observation data are obtained, and a quality index is calculated according to the GNSS observation data; and combining the openness index with the quality index through a gradient lifting regression algorithm, predicting the calculation precision, and converting the predicted calculation precision into environment complexity. According to the GNSS observation environment evaluation method, the machine learning algorithm is combined with the sky view and the data quality index, the evaluation accuracy of the GNSS observation environment under the complex environment is improved, and the GNSS observation environment evaluation method is suitable for GNSS observation environment evaluation under various complex terrain conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of GNSS observation environment evaluation, and in particular to a GNSS observation environment complexity measurement method, device, equipment and medium. Background Art

[0002] As a core technology widely used in navigation, positioning and monitoring, the performance of the Global Navigation Satellite System (GNSS) is largely limited by the observation conditions of the receiver's environment. Complex observation environments, such as urban canyons, densely forested areas, and mountainous areas, often cause GNSS signals to be blocked, multipath effects, and other interference, which in turn affects the accuracy and reliability of positioning. Traditional environmental assessment methods usually rely on empirical analysis or the calculation of a single indicator (such as DOP value, multipath error, etc.), which are difficult to fully reflect the overall complexity of the receiver's observation environment.

[0003] In recent years, the combination of sky view analysis and data quality indicators has provided a new idea for evaluating the complexity of the observation environment. The sky view captures the visible range above the receiver through a fisheye camera, which can intuitively analyze the obstructed area above the receiver; while quality indicators such as multipath effect, data integrity rate, and carrier-to-noise ratio quantitatively reflect data reliability. Integrating the information of the two can fully characterize the complexity of the receiver environment.

[0004] Currently, there is a lack of effective methods to combine sky views with quality indicators for systematic complexity assessment. Existing technologies either ignore the spatial characteristics of the environment on the observation conditions or fail to quantify the contribution of different quality indicators to the overall environmental complexity, resulting in insufficient accuracy and applicability of the assessment results.

[0005] In summary, there is an urgent need for a GNSS observation environment complexity measurement method, device, equipment and medium to solve the problems in the prior art. Summary of the invention

[0006] The present invention aims to provide a method, device, equipment and medium for measuring the complexity of a GNSS observation environment. The specific technical solution is as follows: A method for measuring the complexity of a GNSS observation environment comprises the following steps: S1: Obtain a sky image of the target area, apply an image processing algorithm to identify the sky image, and obtain a sky recognition result; S2: Calculate the trajectories of all satellites based on the almanac information and combine it with the sky recognition results to obtain the openness index of the target area; S3: Obtain GNSS observation data and calculate quality indicators based on the GNSS observation data; S4: The openness index is combined with the quality index through the gradient boosting regression algorithm to predict the solution accuracy and convert the predicted solution accuracy into environmental complexity.

[0007] Optionally, in S1, a 180-degree view image of the sky above the target area is obtained, specifically: a GNSS receiver is set in the target area, and a 180-degree view image of the sky above the position of the GNSS receiver is obtained by using a fisheye camera to obtain a sky image.

[0008] Optionally, in S1, an image processing algorithm is applied to identify the sky image, and the process is as follows: Use the Canny operator to perform edge detection, generate an edge mask for the image, and perform dilation on the image; The image is clustered using K-Means clustering to obtain a clustering result, wherein the clustering result includes a sky area, a building occlusion area, and a tree occlusion area; By performing connected domain analysis on the clustering results, candidate seed points in the sky area are screened out; According to the grayscale reference value, the deviation of each candidate seed point is calculated, and the sky seed points are screened out according to the brightness threshold; The selected sky seed points are expanded using the edge mask until the edge stops, thereby obtaining a sky recognition result, which includes a sky visible area and a sky blocked area.

[0009] Optionally, in S2, the trajectories of all satellites are calculated based on the almanac information, and combined with the sky identification result, the openness index of the receiver position is obtained, and the process is as follows: Calculate the satellite's azimuth based on the satellite's almanac information and altitude angle ; According to the orthographic projection model and focal length of the fisheye camera used , calculate the trajectory of the satellite, specifically: first calculate the satellite projection position to the center of the sky image Distance , and then calculate the position of the satellite projection on the sky image , the calculation expression is as follows: ; ; The openness is the ratio of the visible sky area to the total sky area at the receiver location. The tree-blocked area that the signal can penetrate is weighted and included in the visible sky area. The weighting factor is the data integrity rate of the tree-blocked area. The calculation expression of the openness is as follows: ; in, It represents the openness index. They are the visible sky area, the tree-blocked area, and the total sky area. It is the weighting factor of the tree-blocked area, that is, the satellite signal's ability to penetrate trees.

[0010] Optionally, in S3, the quality indicators include data integrity rate, pseudorange multipath, cycle slip ratio and position geometry precision factor, wherein: The data integrity rate is used to reflect the integrity of the observation value. The calculation expression is as follows: ; in, Indicates the theoretical number of observations. The theoretical number of observations is the number of complete observation values ​​that can be received, calculated based on the set satellite cutoff elevation angle and the obtained satellite ephemeris. represents the actual number of observations, which is the number of complete observations actually received by the GNSS receiver; the complete observations are satellites for which pseudorange, carrier phase, Doppler and signal strength are present; Satellite signals are affected by the external observation environment during propagation. The interference delay caused by the interference between the signal and the receiver antenna through the reflector is called the multipath effect. The multipath value is related to the spatial position of the satellite relative to the receiver antenna, the observation environment, and the satellite altitude angle. After calculating the multipath value of each epoch, the sliding average method is used to calculate the multipath average value of the sliding window. At this time, the multipath error of a certain epoch is the instantaneous multipath value of the current epoch minus the average value of the window. The cycle slip ratio is used to measure the number of cycle slips at a station. The cycle slip ratio is the total number of observations divided by the number of cycle slips or the total number of epochs divided by the number of epochs where cycle slips occur. The TurboEdit algorithm is used for cycle slip detection. The TurboEdit algorithm consists of two cycle slip detection algorithms: the MW combination and the GF combination. The observed value expressions of MW combination and GF combination are as follows: ; ; in, represents the observed value of the MW combination, represents the observed value of GF combination, Respectively represent the first frequency and the second frequency The pseudorange observation value of Respectively represent the first frequency and the second frequency The phase observation value of Respectively represent the first frequency and the second frequency The unknown number of whole cycles on the carrier, is the ionospheric residual, Represents the comprehensive error of multipath residual and combined observation noise; After calculating the observation values ​​of the MW combination and the GF combination respectively, the epoch difference is performed, and the difference value is compared with the threshold. If it exceeds the threshold, it is considered a cycle slip; The position geometric precision factor is used to describe the impact of the geometric distribution of observed satellites on positioning accuracy. The smaller the position geometric precision factor, the more favorable the geometric distribution of satellites is and the higher the solution accuracy is. The calculation formula is as follows: ; in, represents the position geometric precision factor, Represent the variance of the x, y, and z coordinates of the site, respectively. is the unit weight variance.

[0011] Optionally, in S4, the openness index and the quality index are combined using the GBR algorithm to perform model training and calculate the environmental complexity. The process is as follows: Normalization is used to preprocess the openness and data quality indicators, and the expression is as follows: ; In the formula, After the indicator is dimensionless The mth index value of the index, is the amount of translation of the logarithmic value, The indicator is trending. The mth index value of the index, It is The minimum value of the indicator, It is The maximum value of the index; The preprocessed openness index and quality index are used as features, and the known solution accuracy is used as a label, and input into the GBR model for training; The data of different observation environments are divided into training sets and validation sets, where the training set is used for training the GBR model; During the training process, the hyperparameters of GBR were adjusted by cross-validation method; Use the random forest algorithm to calculate the importance of features to labels, filter out unimportant features, avoid feature redundancy, and avoid overfitting of the model; Input the validation set data into the trained model, calculate common evaluation indicators, and evaluate the prediction performance of the model on unseen data; The prediction accuracy of the GBR model output is mapped to the environmental complexity through linear transformation, and the expression is as follows: ; in, is the maximum allowable error of RTK dynamic solution, Predict the solution accuracy for the model.

[0012] In addition, the present invention also includes a GNSS observation environment complexity measurement device, which is used to implement the GNSS observation environment complexity measurement method as described above, and the device includes: Fisheye camera module: The fisheye camera module is installed directly above the GNSS receiver antenna. The inertial navigation device is installed on the fisheye camera module. The sensor axis of the inertial navigation device is kept consistent with the optical axis of the camera. The camera heading angle is recorded in real time to ensure that the lens of the fisheye camera is horizontal and the top of the image corresponds to the north. The fisheye camera module is used to obtain a panoramic image within a 180-degree range above the antenna position. Image processing module: receives image data provided by the fisheye camera module, accurately divides the visible area and the blocked area of ​​the sky through the image recognition algorithm, and outputs the sky recognition result; The data calculation module uses the sky recognition results and the GNSS observation data collected by the GNSS receiver to calculate the openness index and quality index, and uses the GBR algorithm to combine the openness index and the quality index to perform model training and calculate the environmental complexity; Data storage and display module: used to store all generated data, including original images, recognition results, index calculation values ​​and complexity scores. The data storage and display module is also used to provide an intuitive graphical interface to display the evaluation process and results through recognition images, openness index calculation results and complexity score curves.

[0013] In addition, the present invention also includes a computer device, including a memory and a processor; The memory is used to store a computer program executable on the processor; The processor is used to implement the steps of the above-mentioned GNSS observation environment complexity measurement method when executing the computer program.

[0014] In addition, the present invention also includes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the GNSS observation environment complexity measurement method as described above are implemented.

[0015] The application of the technical solution of the present invention has the following beneficial effects: The present invention proposes a method and device for measuring the complexity of GNSS observation environment. The method of the present invention comprehensively evaluates the complexity of GNSS observation environment. In the evaluation process, the sky view and GNSS data quality indicators are combined, the visible area of ​​the sky is accurately extracted through image recognition, and the openness index is calculated in combination with the satellite trajectory. At the same time, the quality indicators are calculated based on GNSS observation data, including data integrity rate, multipath effect, cycle slip ratio and carrier-to-noise ratio. The quality indicators and openness indicators are integrated through the GBR algorithm, and finally a quantitative evaluation of complex environment is achieved.

[0016] In addition to the above-described objects, features and advantages, the present invention has other objects, features and advantages. The present invention will be further described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 is a flowchart of the steps of the method for measuring the complexity of the GNSS observation environment in a preferred embodiment of the present invention; Figure 2 It is a structural schematic diagram of a GNSS observation environment complexity measurement device in a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the scheme of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0020] like Figure 1 As shown, this embodiment provides a GNSS observation environment complexity measurement method, including the following steps: S1: Obtain a sky image of the target area, apply an image processing algorithm to identify the sky image, and obtain a sky recognition result; S2: Calculate the trajectories of all satellites based on the almanac information and combine it with the sky recognition results to obtain the openness index of the target area; S3: Obtain GNSS observation data and calculate quality indicators based on the GNSS observation data; S4: The openness index is combined with the quality index through the gradient boosting regression algorithm to predict the solution accuracy and convert the predicted solution accuracy into environmental complexity.

[0021] Specifically, in S1, a 180-degree view image of the sky above the target area is obtained, specifically: a GNSS receiver is set in the target area, and a 180-degree view image of the sky above the position of the GNSS receiver is obtained by using a fisheye camera to obtain a sky image.

[0022] Specifically, in S1, the image processing algorithm is applied to identify the sky image, and the process is as follows: Use the Canny operator to detect edges, generate an edge mask for the image, and dilate the image to enhance the boundaries of trees or buildings. Dilation of the image helps ensure that the boundaries of the sky area are not covered by other objects (such as buildings or trees).

[0023] The image is clustered using K-Means clustering (K=3 is set in this embodiment) to obtain a clustering result, wherein the clustering result includes a sky area, a building occlusion area, and a tree occlusion area; By performing connected domain analysis on the clustering results, candidate seed points in the sky area are screened out; According to the grayscale reference value, the deviation of each candidate seed point is calculated, and the sky seed points are screened out according to the brightness threshold; The selected sky seed points are expanded using the edge mask until the edge stops, thereby obtaining a sky recognition result, which includes a sky visible area and a sky blocked area.

[0024] Optionally, in S2, the trajectories of all satellites are calculated based on the almanac information, and combined with the sky identification result, the openness index of the receiver position is obtained, and the process is as follows: Calculate the satellite's azimuth based on the satellite's almanac information and altitude angle ; According to the orthographic projection model and focal length of the fisheye camera used , calculate the trajectory of the satellite, specifically: first calculate the satellite projection position to the center of the sky image Distance , and then calculate the position of the satellite projection on the sky image , the calculation expression is as follows: ; ; The openness is the ratio of the visible sky area to the total sky area at the receiver location. The tree-blocked area that the signal can penetrate is weighted and included in the visible sky area. The weighting factor is the data integrity rate of the tree-blocked area. The calculation expression of the openness is as follows: ; in, It represents the openness index. They are the visible sky area, the tree-blocked area, and the total sky area. It is the weighting factor of the tree-blocked area, that is, the satellite signal's ability to penetrate trees.

[0025] Optionally, in S3, the quality indicators include data integrity rate, pseudorange multipath, cycle slip ratio, position geometry precision factor and carrier-to-noise ratio, wherein: The data integrity rate is used to reflect the integrity of the observation value. The calculation expression is as follows: ; in, Indicates the theoretical number of observations. The theoretical number of observations is the number of complete observation values ​​that can be received, calculated based on the set satellite cutoff elevation angle and the obtained satellite ephemeris. represents the actual number of observations, which is the number of complete observations actually received by the GNSS receiver; the complete observations are satellites for which pseudorange, carrier phase, Doppler and signal strength are present; ; Satellite signals are affected by the external observation environment during propagation. The interference delay caused by the interference between the signal and the receiver antenna through the reflector is called the multipath effect. The multipath value is related to the spatial position of the satellite relative to the receiver antenna, the observation environment, and the satellite altitude angle. After calculating the multipath value of each epoch, the sliding average method is used to calculate the multipath average value of the sliding window. The window size is generally 30 epochs, and no cycle jump occurs within the window. At this time, the multipath error of a certain epoch is the instantaneous multipath value of the current epoch minus the average value of the window. The cycle slip ratio is used to measure the number of cycle slips at a station. The cycle slip ratio is the total number of observations divided by the number of cycle slips or the total number of epochs divided by the number of epochs where cycle slips occur. The TurboEdit algorithm is used for cycle slip detection. The TurboEdit algorithm consists of two cycle slip detection algorithms: the MW combination and the GF combination. The observed value expressions of MW combination and GF combination are as follows: ; ; in, represents the observed value of the MW combination, represents the observed value of GF combination, Respectively represent the first frequency and the second frequency The pseudorange observation value of Respectively represent the first frequency and the second frequency The phase observation value of Respectively represent the first frequency and the second frequency The unknown number of whole cycles on the carrier, is the ionospheric residual, Represents the comprehensive error of multipath residual and combined observation noise; After calculating the observation values ​​of the MW combination and the GF combination respectively, the epoch difference is performed, and the difference value is compared with the threshold. If it exceeds the threshold, it is considered a cycle slip; The position geometric precision factor is used to describe the impact of the geometric distribution of observed satellites on positioning accuracy. The smaller the position geometric precision factor, the more favorable the geometric distribution of satellites is and the higher the solution accuracy is. The calculation formula is as follows: ; in, represents the position geometric precision factor, Represent the variance of the x, y, and z coordinates of the site, respectively. is the unit weight variance.

[0026] The carrier-to-noise ratio is the ratio of the carrier signal strength to the noise strength. It is mainly affected by the antenna gain parameters, the receiver correlator state and the pseudo-range multipath effect, and can be directly obtained from the observation file of each station.

[0027] Optionally, in S4, the openness index and the quality index are combined using the GBR algorithm to perform model training and calculate the environmental complexity. The process is as follows: Normalization is used to preprocess the openness and data quality indicators, and the expression is as follows: ; In the formula, After the indicator is dimensionless The mth index value of the index, is the amount of translation of the logarithmic value, The indicator is trending. The mth index value of the index, It is The minimum value of the indicator, It is The maximum value of the index; The preprocessed openness index and quality index are used as features, and the known solution accuracy is used as a label, and input into the GBR model for training; The data of different observation environments are divided into training sets and validation sets, where the training set is used for training the GBR model; During the training process, the hyperparameters of GBR were adjusted by cross-validation method; Use the random forest algorithm to calculate the importance of features to labels, filter out unimportant features, avoid feature redundancy, and avoid overfitting of the model; Input the validation set data into the trained model, calculate common evaluation indicators, and evaluate the prediction performance of the model on unseen data; The prediction accuracy of the GBR model output is mapped to the environmental complexity through linear transformation, and the expression is as follows: ; in, is the maximum allowable error of RTK dynamic solution, Predict the solution accuracy for the model.

[0028] It should be noted that the model training in this embodiment also uses the following indicators: Mean Squared Error (MSE): A commonly used evaluation metric in regression models that measures the difference between the predicted value and the actual value. MSE is calculated by squaring the error of each sample and then taking the average of the squared errors of all samples.

[0029] First indicator : A commonly used indicator to measure the fitting effect of a regression model, indicating the strength of the correlation between the independent variable (input) and the dependent variable (output).

[0030] Second indicator : Adjusted Yes The correction, The number of independent variables in the model is taken into account (especially when the number of independent variables is large), so that Compare More effective.

[0031] The expression of the above indicator is as follows: ; ; ; in, is the sample size, is the number of independent variables (number of features), is the actual solution accuracy, is the prediction solution accuracy, is the mean prediction accuracy.

[0032] The embodiment of the present invention introduces a sky view and a machine learning algorithm (gradient boosting regression) to evaluate the complexity of the GNSS observation environment, which can effectively address the problem that the environmental complexity cannot be quantified or is quantified inaccurately. By using gradient boosting regression to integrate the sky view obtained by the fisheye camera and the quality indicators in the GNSS observation data, a method for evaluating environmental complexity suitable for complex environments is constructed, which avoids the problem of inaccurate evaluation results caused by over-reliance on a single indicator in traditional methods. Specifically, the present invention first uses a fisheye camera to obtain a 180-degree sky view image above the receiver antenna position, applies an image processing algorithm to divide the sky area and the occluded area, and calculates the openness index of the receiver position; then, combined with the quality indicators in the GNSS observation data, the environmental complexity is calculated by the gradient boosting regression algorithm.

[0033] To verify the effectiveness of the algorithm, this embodiment divides the data collected under different simulated observation environments into training sets and validation sets. The training set is used to train the GBR model and establish a prediction model by learning the relationship between features and environmental complexity; the validation set does not participate in model training and is dedicated to testing the prediction performance of the model. Through this division, the generalization ability of the model can be effectively evaluated to ensure that it can adapt to changes in various complex environments.

[0034] The simulation experiment was conducted on the rooftop of a certain place. Data were collected in three different environments: open, blocked by buildings, and blocked by buildings and trees. The data was divided into two hours to obtain 43 groups of data. The quality index and openness index of each group of data were calculated as the features of gradient boosting regression model training. The open source software Net_Diff was used to perform RTK dynamic solution on the collected data, and the solution accuracy of each group was counted as the label of gradient model training. The features (quality index and openness index) and labels (solution accuracy) of each group of data are shown in Table 1. 80% of the data were used for model training and 20% of the data were used for model verification. In the training set and the verification set, the data proportions of the three environments were basically the same.

[0035] Table 1 Data features and labels

[0036] After completing the GBR model training, the data of the validation set is input into the model to obtain the prediction accuracy of the validation set, which is then linearly converted into environmental complexity to achieve quantitative evaluation of environmental complexity.

[0037] Calculate the mean square error and the model and As shown in Table 2, the mean square error of the model's prediction accuracy is 0.282 cm, indicating that the model has a high prediction accuracy and the prediction accuracy is very close to the actual accuracy; the value of the model is 0.90, indicating that the model can explain 90% of the data variability and the fitting effect is very good. A higher value usually means that the model can capture the rules in the data more accurately and has a strong predictive ability. At the same time, the value is 0.80, indicating that even considering the influence of the number of features, the fitting effect of the model remains at a high level. This means that the model can effectively select important features and avoid the overfitting problem caused by too many features, showing a good balance between feature selection and data fitting.

[0038] Table 2 Model prediction accuracy and environment complexity In addition, if Figure 2 As shown, the present invention also includes a GNSS observation environment complexity measurement device, which is used to implement the GNSS observation environment complexity measurement method as described above, and the device includes: GNSS data receiving module: used to receive GNSS observation data. The GNSS data receiving module in this embodiment includes a GNSS receiver.

[0039] Fisheye camera module: The fisheye camera module is installed directly above the GNSS receiver antenna. The inertial navigation device is installed on the fisheye camera module. The sensor axis of the inertial navigation device is kept consistent with the optical axis of the camera. The camera heading angle is recorded in real time to ensure that the lens of the fisheye camera is horizontal and the top of the image corresponds to the north. The fisheye camera module is used to obtain a panoramic image within a 180-degree range above the antenna position. Image processing module: receives image data provided by the fisheye camera module, accurately divides the visible area and the blocked area of ​​the sky through the image recognition algorithm, and outputs the sky recognition result; The data calculation module uses the sky recognition results and the GNSS observation data collected by the GNSS receiver to calculate the openness index and quality index, and uses the GBR algorithm to combine the openness index and the quality index to perform model training and calculate the environmental complexity; Data storage and display module: used to store all generated data, including original images, recognition results, index calculation values ​​and complexity scores. The data storage and display module is also used to provide an intuitive graphical interface to display the evaluation process and results through recognition images, openness index calculation results and complexity score curves.

[0040] In addition, this embodiment also provides a computer device, including a memory and a processor; The memory is used to store a computer program executable on the processor; The processor is used to implement the steps of the above-mentioned GNSS observation environment complexity measurement method when executing the computer program.

[0041] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the computer device.

[0042] The computer device may be a computing device such as a mobile phone, a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may include, but is not limited to, a processor and a memory. For example, the computer device may also include an input / output device, a network access device, a bus, etc.

[0043] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

[0044] The memory can be used to store the computer program and / or module, and the processor implements the computer program by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0045] Wherein, if the module / unit integrated in the computer device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0046] In addition, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned GNSS observation environment complexity measurement method are implemented.

[0047] This embodiment provides a method, device, equipment and medium for measuring the complexity of a GNSS observation environment. The method of the embodiment of the present invention comprehensively evaluates the complexity of the GNSS observation environment. In the evaluation process, the sky view and the GNSS data quality index are combined, the visible area of ​​the sky is accurately extracted through image recognition, and the openness index is calculated in combination with the satellite trajectory. At the same time, the quality index is calculated based on the GNSS observation data, including the data integrity rate, multipath effect, cycle slip ratio and carrier-to-noise ratio, and the quality index and the openness index are integrated through the GBR algorithm, and finally a quantitative evaluation of the complex environment is achieved.

[0048] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0049] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for measuring the complexity of a GNSS observation environment, characterized in that: The following steps are involved: S1: Obtain a sky image of the target area, apply an image processing algorithm to identify the sky image, and obtain a sky recognition result; S2: Calculate the trajectories of all satellites based on the almanac information and combine it with the sky recognition results to obtain the openness index of the target area; S3: Obtain GNSS observation data and calculate quality indicators based on the GNSS observation data; S4: The openness index is combined with the quality index through the gradient boosting regression algorithm to predict the solution accuracy and convert the predicted solution accuracy into environmental complexity.

2. The GNSS observation environment complexity measurement method according to claim 1, characterized in that: In S1, a 180-degree view image of the sky above the target area is obtained. Specifically, a GNSS receiver is set in the target area, and a 180-degree view image of the sky above the position of the GNSS receiver is obtained by using a fisheye camera to obtain a sky image.

3. The method for measuring the complexity of the GNSS observation environment according to claim 2, characterized in that: In S1, the image processing algorithm is applied to identify the sky image, and the process is as follows: Use the Canny operator to perform edge detection, generate an edge mask for the image, and perform dilation on the image; The image is clustered using K-Means clustering to obtain a clustering result, wherein the clustering result includes a sky area, a building occlusion area, and a tree occlusion area; By performing connected domain analysis on the clustering results, candidate seed points in the sky area are screened out; According to the grayscale reference value, the deviation of each candidate seed point is calculated, and the sky seed points are screened out according to the brightness threshold; The selected sky seed points are expanded using the edge mask until the edge stops, thereby obtaining a sky recognition result, which includes a sky visible area and a sky blocked area.

4. The method for measuring the complexity of the GNSS observation environment according to claim 3, characterized in that: In S2, the trajectories of all satellites are calculated based on the almanac information, and combined with the sky identification results, the openness index of the receiver position is obtained. The process is as follows: Calculate the satellite's azimuth based on the satellite's almanac information and altitude angle ; According to the orthographic projection model and focal length of the fisheye camera used , calculate the trajectory of the satellite, specifically: first calculate the satellite projection position to the center of the sky image Distance , and then calculate the position of the satellite projection on the sky image , the calculation expression is as follows: ； ； The openness is the ratio of the visible sky area to the total sky area at the receiver location. The tree-blocked area that the signal can penetrate is weighted and included in the visible sky area. The weighting factor is the data integrity rate of the tree-blocked area. The calculation expression of the openness is as follows: ； in, It represents the openness index. They are the visible sky area, the tree-blocked area, and the total sky area. It is the weighting factor of the tree-blocked area, that is, the satellite signal's ability to penetrate trees.

5. The method for measuring the complexity of the GNSS observation environment according to claim 4, characterized in that: In S3, the quality indicators include data integrity rate, pseudorange multipath, cycle slip ratio and position geometry precision factor, where: The data integrity rate is used to reflect the integrity of the observation value. The calculation expression is as follows: ； in, Indicates the theoretical number of observations. The theoretical number of observations is the number of complete observation values ​​that can be received, calculated based on the set satellite cutoff elevation angle and the obtained satellite ephemeris. represents the actual number of observations, which is the number of complete observations actually received by the GNSS receiver; the complete observations are satellites for which pseudorange, carrier phase, Doppler and signal strength are present; Satellite signals are affected by the external observation environment during propagation. The interference delay caused by the interference between the signal and the receiver antenna through the reflector is called the multipath effect. The multipath value is related to the spatial position of the satellite relative to the receiver antenna, the observation environment, and the satellite altitude angle. After calculating the multipath value of each epoch, the sliding average method is used to calculate the multipath average value of the sliding window. At this time, the multipath error of a certain epoch is the instantaneous multipath value of the current epoch minus the average value of the window. The cycle slip ratio is used to measure the number of cycle slips at a station. The cycle slip ratio is the total number of observations divided by the number of cycle slips or the total number of epochs divided by the number of epochs where cycle slips occur. The TurboEdit algorithm is used for cycle slip detection. The TurboEdit algorithm consists of two cycle slip detection algorithms: the MW combination and the GF combination. The observed value expressions of MW combination and GF combination are as follows: ； ； in, represents the observed value of the MW combination, represents the observed value of GF combination, Represents the first frequency and the second frequency The pseudorange observation value of Represents the first frequency and the second frequency The phase observation value of Represents the first frequency and the second frequency The unknown number of whole cycles on the carrier, is the ionospheric residual, Represents the comprehensive error of multipath residual and combined observation noise; After calculating the observation values ​​of the MW combination and the GF combination respectively, the epoch difference is performed, and the difference value is compared with the threshold. If it exceeds the threshold, it is considered a cycle slip; The position geometric precision factor is used to describe the impact of the geometric distribution of observed satellites on positioning accuracy. The smaller the position geometric precision factor, the more favorable the geometric distribution of satellites is and the higher the solution accuracy is. The calculation formula is as follows: ； in, represents the position geometric precision factor, Represent the variance of the x, y, and z coordinates of the site, respectively. is the unit weight variance.

6. The method for measuring the complexity of the GNSS observation environment according to claim 5, characterized in that: In S4, the GBR algorithm is used to combine the openness index with the quality index to train the model and calculate the environmental complexity. The process is as follows: Normalization is used to preprocess the openness and data quality indicators, and the expression is as follows: ； In the formula, After the indicator is dimensionless The mth index value of the index, is the amount of translation of the logarithmic value, The indicator is trending. The mth index value of the index, It is The minimum value of the indicator, It is The maximum value of the index; The preprocessed openness index and quality index are used as features, and the known solution accuracy is used as a label, and input into the GBR model for training; The data of different observation environments are divided into training sets and validation sets, where the training set is used for training the GBR model; During the training process, the hyperparameters of GBR were adjusted by cross-validation method; Use the random forest algorithm to calculate the importance of features to labels, filter out unimportant features, avoid feature redundancy, and avoid overfitting of the model; Input the validation set data into the trained model, calculate common evaluation indicators, and evaluate the prediction performance of the model on unseen data; The prediction accuracy of the GBR model output is mapped to the environmental complexity through linear transformation, and the expression is as follows: ； in, is the maximum allowable error of RTK dynamic solution, Predict the solution accuracy for the model.

7. A GNSS observation environment complexity measurement device, characterized in that: Used to implement the GNSS observation environment complexity measurement method according to any one of claims 1 to 6, the device comprises: Fisheye camera module: The fisheye camera module is installed directly above the GNSS receiver antenna. The inertial navigation device is installed on the fisheye camera module. The sensor axis of the inertial navigation device is kept consistent with the optical axis of the camera. The camera heading angle is recorded in real time to ensure that the lens of the fisheye camera is horizontal and the top of the image corresponds to the north. The fisheye camera module is used to obtain a panoramic image within a 180-degree range above the antenna position. Image processing module: receives image data provided by the fisheye camera module, accurately divides the visible area and the blocked area of ​​the sky through the image recognition algorithm, and outputs the sky recognition result; The data calculation module uses the sky recognition results and the GNSS observation data collected by the GNSS receiver to calculate the openness index and quality index, and uses the GBR algorithm to combine the openness index and the quality index to perform model training and calculate the environmental complexity; Data storage and display module: used to store all generated data, including original images, recognition results, index calculation values ​​and complexity scores. The data storage and display module is also used to provide an intuitive graphical interface to display the evaluation process and results through recognition images, openness index calculation results and complexity score curves.

8. A computer device, characterized in that: including memory and processor; The memory is used to store a computer program executable on the processor; The processor is configured to implement the steps of the GNSS observation environment complexity measurement method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the GNSS observation environment complexity measurement method according to any one of claims 1 to 6 are implemented.

Images