A GNSS Observation Environment Complexity Measurement Method, Device, Equipment and Medium

Abstract

The present invention relates to the technical field of GNSS observation environment evaluation, and specifically relates to a method, device, equipment and medium for measuring the complexity of a GNSS observation environment. The method includes: obtaining a sky image of a target area by using a fisheye camera, applying an image processing algorithm to identify the sky image to obtain a sky recognition result; calculating the trajectories of all satellites based on almanac information, and combining with the sky recognition result to obtain an openness index of the target area; obtaining GNSS observation data, and calculating a quality index according to the GNSS observation data; combining the openness index and the quality index through a gradient boosting regression algorithm to predict the solution accuracy, and converting the predicted solution accuracy into environmental complexity. The present invention combines the sky view and data quality index through a machine learning algorithm, improves the evaluation accuracy of the GNSS observation environment under complex environments, and is applicable to the evaluation of GNSS observation environments under various complex terrain conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of GNSS observation environment evaluation, and particularly relates to a method, device, equipment and medium for measuring the complexity of a GNSS observation environment. 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 environment where the receiver is located. A complex observation environment, such as an urban canyon, a densely forested area, and a mountainous area, often causes GNSS signals to be blocked, affected by multipath effects, etc., thereby affecting the accuracy and reliability of positioning. Traditional environmental assessment methods usually rely on empirical analysis or the calculation of a single index (such as DOP value, multipath error, etc.), and these methods are difficult to comprehensively reflect the overall complexity of the receiver observation environment.

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

[0004] Currently, there is still a lack of an effective method to combine the sky view with quality indicators for systematic complexity evaluation. Existing technologies either ignore the spatial characteristics of the environment on the observation conditions, or cannot quantify the contribution of different quality indicators to the overall environmental complexity, resulting in insufficient accuracy and applicability of the evaluation results.

[0005] In summary, there is an urgent need for a method, device, equipment and medium for measuring the complexity of a GNSS observation environment to solve the problems in the existing technology. Summary of the Invention

[0006] The purpose of the present invention is to provide a method, device, equipment and medium for measuring the complexity of a GNSS observation environment, and the specific technical solutions are as follows:

[0007] A method for measuring the complexity of a GNSS observation environment includes the following steps:

[0008] S1: Obtain the sky image of the target area, apply an image processing algorithm to identify the sky image, and obtain the sky recognition result;

[0009] S2: Calculate the trajectories of all satellites based on the almanac information, and combine the sky recognition result to obtain the openness index of the target area;

[0010] S3: Obtain GNSS observation data, and calculate quality indicators according to the GNSS observation data;

[0011] S4: Combine the openness index and the quality index through the gradient boosting regression algorithm to predict the solution accuracy, and convert the predicted solution accuracy into environmental complexity.

[0012] Optionally, in S1, obtain a 180-degree view image of the sky over the target area. Specifically: Set a GNSS receiver in the target area, and use a fisheye camera to obtain a 180-degree view image of the sky above the position of the GNSS receiver to obtain a sky image.

[0013] Optionally, in S1, apply an image processing algorithm to identify the sky image. The process is as follows:

[0014] Use the Canny operator for edge detection to generate an edge mask of the image, and perform a dilation operation on the image;

[0015] Use K-Means clustering to cluster the image to obtain a clustering result, where the clustering result includes a sky area, a building occlusion area, and a tree occlusion area;

[0016] Through connected component analysis of the clustering result, filter out candidate seed points in the sky area;

[0017] Calculate the deviation of each candidate seed point according to the gray reference value, and filter out sky seed points according to the brightness threshold;

[0018] Use the edge mask to expand the selected sky seed points until the edge stops, thereby obtaining a sky recognition result, where the sky recognition result includes a sky visible area and a sky occlusion area.

[0019] Optionally, in S2, calculate the trajectories of all satellites based on the almanac information, and combine the sky recognition result to obtain the openness index of the receiver position. The process is as follows:

[0020] Based on the almanac information of the satellite, calculate the azimuth angle of the satellite and the elevation angle ;

[0021] According to the orthographic projection model and focal length of the used fisheye camera , calculate the trajectory of the satellite. Specifically: First calculate the distance from the satellite projection position to the center of the sky image ; Then calculate the position of the satellite projection in the sky image . The calculation expressions are as follows:

[0022] ;

[0023] ;

[0024] The openness is the ratio of the visible sky area at the receiver position to the total sky area, and the tree occlusion area through which the signal can penetrate is weighted and incorporated into the visible sky area. The weighting factor is the data integrity rate of the tree occlusion area. The calculation expression of the openness is as follows:

[0025] ;

[0026] Among them, represents the openness index, are the visible sky area, the tree occlusion area, and the total sky area respectively, is the weighting factor of the tree occlusion area, that is, the penetration ability of the satellite signal through the trees.

[0027] Optionally, in S3, the quality indicators include data integrity rate, pseudorange multipath, cycle slip ratio, and position dilution of precision. Among them:

[0028] The data integrity rate is used to reflect the integrity of the observations. The calculation expression of the data integrity rate is as follows:

[0029] ;

[0030] Among them, represents the theoretical number of observations. The theoretical number of observations is the number of complete observable values that can be received calculated according to the set satellite elevation cut-off angle and the obtained satellite ephemeris; represents the actual number of observations. The actual number of observations is the number of complete observable values actually received by the GNSS receiver; the complete observable value is a satellite with pseudorange, carrier phase, Doppler, and signal strength all present;

[0031] During the propagation of the satellite signal, it is affected by the external observation environment. The interference delay caused by the signal interfering with the receiver antenna after being reflected by the reflector is called the multipath effect. The multipath value is related to the spatial position relationship between the satellite and the receiver antenna, the observation environment, and the satellite elevation angle; after calculating the multipath value for each epoch, the sliding average method is used to calculate the average multipath 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 where it is located;

[0032] The cycle slip ratio is used to measure the number of cycle slips at the station. The cycle slip ratio is the ratio of the total number of observations to the number of cycle slips or the ratio of the total number of epochs to the number of epochs with cycle slips; 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;

[0033] The observation value expressions of the MW combination and the GF combination are as follows:

[0034] ;

[0035] ;

[0036] Among them, represents the observed value of the MW combination, represents the observed value of the GF combination, respectively represent the first frequency and the second frequency pseudorange observed values; respectively represent the first frequency and the second frequency phase observed values; respectively represent the first frequency and the second frequency integer ambiguity on the carrier, is the ionospheric residual, represents the comprehensive error such as multipath residual and combined observation noise;

[0037] After calculating the observed values of the MW combination and the GF combination respectively, epoch difference is performed, and the difference value is compared with the threshold. If it exceeds the threshold, it is determined as a cycle slip;

[0038] The position dilution of precision is used to describe the influence of the geometric distribution of observed satellites on the positioning accuracy. The smaller the position dilution of precision, the more favorable the geometric distribution of satellites, and the higher the solution accuracy. The calculation formula is as follows:

[0039] ;

[0040] Among them, represents the position dilution of precision, respectively represent the variances of the site x, y, z coordinates, is the variance of unit weight.

[0041] Optionally, in S4, the GBR algorithm is used to combine the openness index and the quality index for model training and calculation of the environmental complexity. The process is as follows:

[0042] Normalization is adopted to preprocess the openness and the quality index of the data. The expression is as follows:

[0043] ;

[0044] In the formula, is the m-th index value of the n-th index after dimensionless processing of the index, is the translation amount for shifting the logarithm value, is the m-th index value of the n-th index after co-trending of the index, is the n-th is the The minimum value of the is the maximum value of the

[0045] Taking the pre - processed openness index and quality index as features, and the known solution accuracy as the label, input them into the GBR model for training;

[0046] For data in different observation environments, divide them into a training set and a validation set, where the training set is used for training the GBR model;

[0047] During the training process, adjust the hyperparameters of GBR through the cross - validation method;

[0048] Use the random forest algorithm to calculate the importance of features for the label, filter out unimportant features, and avoid feature redundancy causing model overfitting;

[0049] Input the validation set data into the trained model, calculate common evaluation metrics, and evaluate the prediction performance of the model on unseen data;

[0050] The predicted solution accuracy output by the GBR model is linearly transformed and mapped to the environmental complexity, and the expression is as follows:

[0051] ;

[0052] Among them, is the maximum allowable error of RTK dynamic solution, is the predicted solution accuracy of the model.

[0053] In addition, the present invention also includes a GNSS observation environment complexity measurement device for implementing the GNSS observation environment complexity measurement method as described above. The device includes:

[0054] Fisheye camera module: The fisheye camera module is installed directly above the GNSS receiver antenna. At the same time, the inertial navigation device is installed on the fisheye camera module, keeping the sensor axis of the inertial navigation consistent with the optical axis direction of the camera, and recording the heading angle of the camera in real - time to ensure that the fisheye camera lens is horizontal and the upper part 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;

[0055] Image processing module; Receiving the image data provided by the fisheye camera module, accurately dividing the sky visible area and the occlusion area through an image recognition algorithm, and outputting the sky recognition result;

[0056] The data calculation module uses the sky recognition result and the GNSS observation data collected by the GNSS receiver to calculate the openness index and the quality index, and uses the GBR algorithm to combine the openness index and the quality index for model training and calculate the environmental complexity;

[0057] The data storage and display module is used to store all the generated data, including the original image, the recognition result, the index calculation value and the complexity score. The data storage and display module is also used to provide an intuitive graphical interface to display the evaluation process and results through the recognition image, the openness index calculation result and the complexity score curve.

[0058] In addition, the present invention further includes a computer device, including a memory and a processor;

[0059] The memory is used to store a computer program that can run on the processor;

[0060] The processor is used to implement the steps of the GNSS observation environment complexity measurement method as described above when executing the computer program.

[0061] In addition, the present invention further includes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, the steps of the GNSS observation environment complexity measurement method as described above are implemented.

[0062] Applying the technical solution of the present invention has the following beneficial effects:

[0063] The present invention proposes a method and device for measuring the complexity of the GNSS observation environment. The method of the present invention comprehensively evaluates the complexity of the GNSS observation environment. During the evaluation process, the sky view and the GNSS data quality index are combined. The sky visible area 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, the multipath effect, the cycle slip ratio and the carrier-to-noise ratio. The quality index and the openness index are integrated through the GBR algorithm, and finally the quantitative evaluation of the complex environment is realized.

[0064] In addition to the purposes, features and advantages described above, the present invention has other purposes, features and advantages. The present invention will be further described in detail below with reference to the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] To more clearly illustrate the technical solutions of the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0066] Figure 1 is the flowchart of the steps of the GNSS observation environment complexity measurement method in the preferred embodiment of the present invention;

[0067] Figure 2 is the structural schematic diagram of the GNSS observation environment complexity measurement device in the preferred embodiment of the present invention. Detailed implementation manners

[0068] In order to enable those skilled in the art to better understand the solution of the present invention, the following further details the present invention in conjunction with the drawings and specific implementation manners. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0069] As Figure 1 shown, this embodiment provides a GNSS observation environment complexity measurement method, including the following steps:

[0070] S1: Obtain the sky image of the target area, apply an image processing algorithm to identify the sky image, and obtain the sky recognition result;

[0071] S2: Calculate the trajectories of all satellites based on the almanac information, and combine with the sky recognition result to obtain the openness index of the target area;

[0072] S3: Obtain GNSS observation data, and calculate the quality index according to the GNSS observation data;

[0073] S4: Combine the openness index and the quality index through the gradient boosting regression algorithm to predict the solution accuracy, and convert the predicted solution accuracy into the environment complexity.

[0074] Specifically, in S1, obtain the 180-degree view image above the target area. Specifically: Set a GNSS receiver in the target area, and use a fish-eye camera to obtain the 180-degree view image above the position of the GNSS receiver to obtain the sky image.

[0075] Specifically, in S1, apply an image processing algorithm to identify the sky image. The process is as follows:

[0076] Edge detection is performed using the Canny operator to generate an edge mask of the image, and the image is dilated to enhance the boundaries of trees or buildings. Dilating the image helps ensure that the boundaries of the sky region are not covered by other objects (such as buildings or trees).

[0077] The image is clustered using K-Means clustering (with K = 3 set in this embodiment) to obtain a clustering result, which includes a sky region, a building occlusion region, and a tree occlusion region;

[0078] Candidate seed points for the sky region are selected by performing connected component analysis on the clustering result;

[0079] The deviation of each candidate seed point is calculated based on a gray reference value, and sky seed points are selected according to a brightness threshold;

[0080] The selected sky seed points are expanded using the edge mask until the edge stops, thereby obtaining a sky recognition result, which includes a visible sky region and a sky occlusion region.

[0081] Optionally, in S2, the trajectories of all satellites are calculated based on almanac information, and combined with the sky recognition result, an openness index of the receiver position is obtained, and the process is as follows:

[0082] Based on the almanac information of the satellite, the azimuth angle of the satellite is calculated and the elevation angle ;

[0083] According to the orthographic projection model and focal length of the used fisheye camera , the trajectory of the satellite is calculated. Specifically, first calculate the distance from the satellite projection position to the center of the sky image , and then calculate the position of the satellite projection on the sky image , and the calculation expressions are as follows: ;

[0084] ;

[0085] ;

[0086] The openness is the ratio of the visible sky area at the receiver position to the total sky area, and the tree occlusion region through which the signal can penetrate is weighted and incorporated into the visible sky region, and the weighting factor is the data integrity rate of the tree occlusion region. The calculation expression of the openness is as follows:

[0087] ;

[0088] Among them, represents the openness index, They are the visible sky area, the tree occlusion area, and the total sky area respectively. is the weighting factor of the tree occlusion area, that is, the penetration ability of satellite signals through trees.

[0089] Optionally, in S3, the quality indicators include data integrity rate, pseudorange multipath, cycle slip ratio, position dilution of precision, and carrier-to-noise ratio, where:

[0090] The data integrity rate is used to reflect the integrity of the observed values. The data integrity rate is calculated as follows:

[0091] ;

[0092] where represents the theoretical number of observations. The theoretical number of observations is the number of complete observable values that can be received, calculated based on the set satellite elevation cut-off angle and the obtained satellite ephemeris; represents the actual number of observations. The actual number of observations is the number of complete observable values actually received by the GNSS receiver; the complete observable values are satellites with pseudorange, carrier phase, Doppler, and signal strength all present;

[0093] During the propagation of satellite signals, affected by the external observation environment, the interference delay caused by the signal interfering with the receiver antenna after reflection from a reflector is called the multipath effect. The multipath value is related to the spatial position relationship between the satellite and the receiver antenna, the observation environment, and the satellite elevation angle; after calculating the multipath value for each epoch, the sliding average method is used to calculate the average multipath value of the sliding window. Generally, the window size is 30 epochs and there are no cycle slips within the window. At this time, the multipath error for a certain epoch is the instantaneous multipath value of the current epoch minus the average value of the window where it is located;

[0094] The cycle slip ratio is used to measure the number of cycle slips at the station. The cycle slip ratio is the ratio of the total number of observations to the number of cycle slips or the ratio of the total number of epochs to the number of epochs with cycle slips; 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;

[0095] The observed value expressions of the MW combination and the GF combination are as follows:

[0096] ;

[0097] ;

[0098] where represents the observed value of the MW combination, represents the observed value of the GF combination, respectively represent the first frequency and the second frequency Pseudorange observation value; respectively represent the phase observation values of the first frequency and the second frequency; respectively represent the first frequency and the integer ambiguity on the carrier of the second frequency, is the ionospheric residual, represents the combined error such as multipath residual and combined observation noise;

[0099] After calculating the observation values of the MW combination and the GF combination respectively, epoch difference is performed, and the difference value is compared with the threshold. If it exceeds the threshold, it is determined as a cycle slip;

[0100] The position dilution of precision is used to describe the influence of the geometric distribution of observed satellites on the positioning accuracy. The smaller the position dilution of precision, the more favorable the geometric distribution of satellites, and the higher the solution accuracy. The calculation formula is as follows:

[0101] ;

[0102] Among them, represents the position dilution of precision, respectively represent the variances of the site x, y, z coordinates, is the variance of unit weight.

[0103] The carrier-to-noise ratio is the ratio of the carrier signal strength to the noise strength, which is mainly affected by antenna gain parameters, receiver correlator status and pseudorange multipath effect, and can be directly obtained from the observation files of each station.

[0104] Optionally, in S4, the GBR algorithm is used to combine the openness index and the quality index, and model training is performed and the environmental complexity is calculated. The process is as follows:

[0105] Normalization is adopted to preprocess the openness and the quality index of the data. The expression is as follows:

[0106] ;

[0107] In the formula, is the m-th index value of the th index after dimensionless processing of the index, is the translation amount for translating the logarithm value, is the m-th index value of the th index after co-trending processing of the index, is the minimum value of the th index, is the maximum value of the th index;

[0108] Using the preprocessed openness index and quality index as features, and the known solution accuracy as labels, input them into the GBR model for training;

[0109] For data in different observation environments, divide it into a training set and a validation set, where the training set is used for training the GBR model;

[0110] During the training process, adjust the hyperparameters of GBR through the cross-validation method;

[0111] Use the random forest algorithm to calculate the importance of features for labels, filter out unimportant features, and avoid feature redundancy causing model overfitting;

[0112] Input the validation set data into the trained model, calculate common evaluation metrics, and evaluate the prediction performance of the model on unseen data;

[0113] The predicted solution accuracy output by the GBR model is linearly transformed and mapped to the environmental complexity, and the expression is as follows:

[0114] ;

[0115] where, is the maximum allowable error of RTK dynamic solution, is the predicted solution accuracy of the model.

[0116] It should be noted that the following metrics are also used in the model training of this embodiment:

[0117] Mean Squared Error (MSE): A commonly used evaluation metric in regression models, which measures the difference between the predicted value and the actual value. The calculation method of MSE is to square the error of each sample and then take the average of the squared errors of all samples.

[0118] The first metric : A commonly used metric to measure the fitting effect of a regression model, indicating the correlation strength between the independent variable (input) and the dependent variable (output).

[0119] The second metric : Adjusted is a correction of , considering the number of independent variables in the model (especially when the number of independent variables is large), making more effective than .

[0120] The expressions of the above metrics are as follows:

[0121] ;

[0122] ;

[0123] ;

[0124] wherein, is the number of samples, is the number of independent variables (number of features), is the actual solution accuracy, is the predicted solution accuracy, is the mean of the predicted solution accuracy.

[0125] 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 problems of inability to quantify and inaccurate quantification of environmental complexity. By using gradient boosting regression to comprehensively combine the sky view obtained by the fisheye camera and the quality indicators in the GNSS observation data, an environmental complexity evaluation method suitable for complex environments is constructed, avoiding 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 occlusion area, and calculates the openness index of the receiver position; then, in combination with the quality indicators in the GNSS observation data, the environmental complexity is calculated through the gradient boosting regression algorithm.

[0126] To verify the effectiveness of the algorithm, the data collected in different simulated observation environments in this embodiment is divided into a training set and a validation set. The training set is used to train the GBR model, and a prediction model is established by learning the relationship between features and environmental complexity; the validation set does not participate in model training and is specifically used to test 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.

[0127] The simulation experiment was carried out on the roof of a certain place. Data in three different environments of open, building occlusion, and building plus tree occlusion were collected, and the data was segmented every two hours to obtain 43 groups of data. The quality indicators and openness indicators of each group of data were calculated as the features for training the gradient boosting regression model, and 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 statistically counted as the label for training the ladder model. The features (quality indicators and openness indicators) and labels (solution accuracy) of each group of data are shown in Table 1. 80% of the data was used for model training, and 20% of the data was used for model verification. In the training set and the validation set, the data proportions of the three environments were basically the same.

[0128] Table 1 Data Features and Labels

[0129]

[0130] After completing the training of the GBR model, the data of the validation set is input into the model to obtain the prediction and solution accuracy of the validation set, and then it is linearly transformed into the environmental complexity, realizing the quantitative evaluation of the environmental complexity.

[0131] Calculate the mean square error and the of the model , as shown in Table 2, the mean square error of the prediction and solution accuracy of the model is 0.282 cm, indicating that the model has a high accuracy in prediction and the prediction and solution 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 prediction 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 still 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, demonstrating a good balance of the model in feature selection and data fitting.

[0132] Table 2 Model prediction accuracy and environmental complexity

[0133]

[0134] In addition, as Figure 2 shown, the present invention also includes a GNSS observation environment complexity measurement device for implementing the GNSS observation environment complexity measurement method as described above. The device includes:

[0135] GNSS data receiving module: used to receive GNSS observation data. The GNSS data receiving module in this embodiment includes a GNSS receiver.

[0136] Fisheye camera module: The fisheye camera module is installed directly above the GNSS receiver antenna. At the same time, the inertial navigation device is installed on the fisheye camera module to keep the sensor axis of the inertial navigation consistent with the optical axis direction of the camera, and the heading angle of the camera is recorded in real time to ensure that the lens of the fisheye camera is horizontal and the image above corresponds to the north; the fisheye camera module is used to obtain a panoramic image within 180 degrees above the antenna position.

[0137] Image processing module; receives the image data provided by the fisheye camera module, accurately divides the visible area and occlusion area of the sky through an image recognition algorithm, and outputs the sky recognition result.

[0138] The data calculation module uses the sky recognition result and the GNSS observation data collected by the GNSS receiver to calculate the openness index and the quality index, and uses the GBR algorithm to combine the openness index and the quality index for model training and calculate the environmental complexity;

[0139] The data storage and display module is used to store all the generated data, including the original image, the recognition result, the index calculation value, and the complexity score. The data storage and display module is also used to provide an intuitive graphical interface to display the evaluation process and results through the recognition image, the openness index calculation result, and the complexity score curve.

[0140] In addition, this embodiment also provides a computer device, including a memory and a processor;

[0141] The memory is used to store a computer program that can run on the processor;

[0142] The processor is used to implement the steps of the above GNSS observation environment complexity measurement method when executing the computer program.

[0143] Exemplarily, the computer program can be divided into one or more modules / units. The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the computer device.

[0144] The computer device can be a mobile phone, a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The computer device may include, but is not limited to, a processor and a memory. For example, the computer device may further include input / output devices, network access devices, a bus, etc.

[0145] The so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor, etc. The processor is the control center of the computer device, and connects various parts of the entire computer device through various interfaces and lines.

[0146] The memory can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory, and invoking the data stored in the memory, the processor implements the computer programs. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0147] Among them, if the modules / units integrated in the computer device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0148] In addition, an embodiment of the present invention also 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.

[0149] This embodiment provides a method, apparatus, device, 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. During the evaluation process, it combines the sky view and GNSS data quality indicators, accurately extracts the sky visible area through image recognition, and calculates the openness index in combination with the satellite trajectory. At the same time, it calculates the quality indicators based on the GNSS observation data, including data integrity rate, multipath effect, cycle slip ratio, and carrier-to-noise ratio. The quality indicators and the openness index are integrated through the GBR algorithm, and finally, a quantitative evaluation of the complex environment is achieved.

[0150] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0151] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within 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 the predicted solution accuracy is converted into environmental complexity; The process of S4 is as follows: Normalization is used to preprocess the openness and data quality indicators, and the expression is as follows: In the formula, is the mth index value of the lth index after the index is dimensionless, c is the translation amount of the logarithmic value, is the mth indicator value of the lth indicator after the indicator is trended, Min l is the minimum value of the lth indicator, Max l is the maximum value of the lth indicator; 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: Among them, E max is the maximum allowable error of RTK dynamic solution, E pred Predict the solution accuracy for the model.

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: Based on the satellite's almanac information, calculate the satellite's azimuth ε sat and the altitude angle α sat ; According to the orthographic projection model and focal length f of the fisheye camera used c , calculate the trajectory of the satellite, specifically: first calculate the satellite projection position to the center of the sky image (x c ,y c ) pix , and then calculate the position of the satellite projection on the sky image (x sat ,y sat ), 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: Among them, O represents the openness index, A(open), A(tree), and A(all) are the visible sky area, the tree-blocked area, and the total sky area, respectively, and k1 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 of the data integrity rate ratio is as follows: Among them, O exp Represents the theoretical number of observations, which 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; have 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: Among them, N MW represents the observed value of the MW combination, represents the observation value of the GF combination, ρ1 and ρ2 represent the pseudorange observation values ​​of the first frequency f1 and the second frequency f2 respectively; Represent the phase observation values ​​of the first frequency f1 and the second frequency f2 respectively; N1 and N2 represent the integer unknowns on the carriers of the first frequency f1 and the second frequency f2 respectively, ion is the ionospheric residual, ε 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: Among them, PDOP represents the position geometry precision factor, Represent the variance of the x, y, and z coordinates of the site, respectively. is the unit weight variance.

6. 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 5, 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.

7. 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 5 when executing the computer program.

8. 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 5 are implemented.

Images