CN114494315A - Tunnel cross section feature extraction method, device, equipment and storage medium - Google Patents
Tunnel cross section feature extraction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114494315A CN114494315A CN202111675567.5A CN202111675567A CN114494315A CN 114494315 A CN114494315 A CN 114494315A CN 202111675567 A CN202111675567 A CN 202111675567A CN 114494315 A CN114494315 A CN 114494315A
- Authority
- CN
- China
- Prior art keywords
- cross
- section
- data
- tunnel
- contour line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/143—Segmentation; Edge detection involving probabilistic approaches, e.g. Markov random field [MRF] modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Aerodynamic Tests, Hydrodynamic Tests, Wind Tunnels, And Water Tanks (AREA)
- Image Processing (AREA)
Abstract
The application relates to a method and a device for extracting tunnel cross section features, computer equipment, a storage medium and a computer program product, which are applied to the technical field of tunnel three-dimensional point cloud data feature extraction and used for improving the accuracy of tunnel cross section feature extraction. The method comprises the following steps: sampling cross section data of the cross section of the target tunnel to obtain sampling data; inputting the sampling data into a parameter estimation model corresponding to the cross section of the target tunnel, and estimating parameters in a contour line fitting model corresponding to the cross section of the target tunnel through the parameter estimation model based on the sampling data to obtain an estimation value of the parameters in the contour line fitting model; and inputting the estimated value into the contour line fitting model to obtain a contour line of the cross section of the target tunnel, wherein the contour line is used as a first target characteristic of the cross section of the target tunnel.
Description
Technical Field
The application relates to the technical field of tunnel three-dimensional point cloud data feature extraction, in particular to a tunnel cross section feature extraction method, a tunnel cross section feature extraction device, computer equipment, a storage medium and a computer program product.
Background
After the tunnel construction is completed, the tunnel which is excavated needs to be measured to obtain the actual size of the tunnel, so that the error between the actual size and the design size of the tunnel is determined, and further, the construction of subsequent rails and contact networks is reasonably adjusted. The deviation between the actual dimension and the design dimension of the tunnel obtained through detection is also used for determining parameters such as tunnel vault settlement, overexcavation underexcavation, axis deviation and the like so as to detect whether the tunnel after excavation meets the target task requirement or not. The three-dimensional laser scanning technology has the characteristics of high speed, accurate precision, convenient operation and the like, and is gradually applied to tunnel measurement.
However, three-dimensional point cloud data obtained through a three-dimensional laser scanning technology is very huge, in the traditional technology, a least square method is often used for fitting a cross section, and a line type of a tunnel is obtained from the center position of the cross section in the direction of the extension degree. If abnormal data are removed by using a mode of setting a threshold value, data imbalance is easily caused when parameters are improperly selected, and deviation exists between the average value of the residual data and the actual average value. Therefore, how to process the point cloud data and accurately extract the characteristics and line types of the cross section of the tunnel is always a difficult problem in engineering application.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device, a computer readable storage medium, and a computer program product for extracting a cross-sectional tunnel feature, which can improve the accuracy of extracting the cross-sectional tunnel feature.
In a first aspect, the application provides a method for extracting cross-sectional features of a tunnel. The method comprises the following steps:
sampling cross section data of the cross section of the target tunnel to obtain sampling data;
inputting the sampling data into a parameter estimation model corresponding to the cross section of the target tunnel, and estimating parameters in a contour line fitting model corresponding to the cross section of the target tunnel through the parameter estimation model based on the sampling data to obtain an estimation value of the parameters in the contour line fitting model;
and inputting the estimated value into the contour line fitting model to obtain a contour line of the cross section of the target tunnel as a first target characteristic of the cross section of the target tunnel.
In one embodiment, estimating, by the parameter estimation model, parameters in a contour line fitting model corresponding to the cross section of the target tunnel based on the sampling data to obtain estimated values of the parameters in the contour line fitting model includes:
carrying out probability statistical processing on the sampled data through the parameter estimation model to obtain posterior distribution information of parameters in the contour line model;
and performing likelihood estimation on the parameters according to the posterior distribution information to obtain estimated values of the parameters.
In one embodiment, before performing probability calculation on the sample through the parameter estimation model to obtain the posterior distribution of the parameter, the method further includes:
according to the parameter estimation model, carrying out probability distribution processing on the sampled data to obtain a probability distribution curve of the sampled data;
according to the tail characteristics of the probability distribution curve, standard deviation fluctuation processing is carried out on the sampled data to obtain processed sampled data;
the probability statistics processing is carried out on the sampling data through the parameter estimation model to obtain posterior distribution information of parameters in the contour line fitting model, and the probability statistics processing comprises the following steps:
and carrying out probability statistical processing on the sampled data through the parameter estimation model to obtain posterior distribution information of parameters in the contour line fitting model.
In one embodiment, before inputting the sampled data into the parameter estimation model corresponding to the target tunnel cross section, the method further includes:
generating an initial parameter estimation model according to a preset standard deviation and a preset degree of freedom;
inputting the cross section data into a mean value statistical model associated with the initial parameter estimation model to obtain a mean value parameter value in the initial parameter estimation model;
and updating the mean parameter in the initial parameter estimation model by using the mean parameter value to obtain the parameter estimation model.
In one embodiment, before sampling the cross-sectional data of the target tunnel cross section to obtain the sampled data, the method further includes:
performing data extraction processing on three-dimensional point cloud data corresponding to a scene where the cross section of the target tunnel is located to obtain initial cross section data of the cross section of the target tunnel;
and extracting plane coordinate data in the initial cross section data to obtain the cross section data.
In one embodiment, the method further comprises:
inputting the estimated value into a central point model of the cross section of the tunnel to obtain a central point coordinate of the cross section of the target tunnel;
and determining the central point coordinate as a second target feature of the target tunnel cross section.
In a second aspect, the application further provides a tunnel cross section feature extraction device. The device comprises:
the sampling module is used for sampling the cross section data of the cross section of the target tunnel to obtain sampling data;
the estimation module is used for inputting the sampling data into a parameter estimation model corresponding to the cross section of the target tunnel, and estimating parameters in a contour line fitting model corresponding to the cross section of the target tunnel through the parameter estimation model based on the sampling data to obtain estimated values of the parameters in the contour line fitting model;
and the characteristic module is used for inputting the estimated value into the contour line fitting model to obtain a contour line of the cross section of the target tunnel, and the contour line is used as a first target characteristic of the cross section of the target tunnel.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:
sampling cross section data of the cross section of the target tunnel to obtain sampling data;
inputting the sampling data into a parameter estimation model corresponding to the cross section of the target tunnel, and estimating parameters in a contour line fitting model corresponding to the cross section of the target tunnel through the parameter estimation model based on the sampling data to obtain an estimation value of the parameters in the contour line fitting model;
and inputting the estimated value into the contour line fitting model to obtain a contour line of the cross section of the target tunnel, wherein the contour line is used as a first target characteristic of the cross section of the target tunnel.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
sampling cross section data of the cross section of the target tunnel to obtain sampling data;
inputting the sampling data into a parameter estimation model corresponding to the cross section of the target tunnel, and estimating parameters in a contour line fitting model corresponding to the cross section of the target tunnel through the parameter estimation model based on the sampling data to obtain an estimation value of the parameters in the contour line fitting model;
and inputting the estimated value into the contour line fitting model to obtain a contour line of the cross section of the target tunnel, wherein the contour line is used as a first target characteristic of the cross section of the target tunnel.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:
sampling cross section data of the cross section of the target tunnel to obtain sampling data;
inputting the sampling data into a parameter estimation model corresponding to the cross section of the target tunnel, and estimating parameters in a contour line fitting model corresponding to the cross section of the target tunnel through the parameter estimation model based on the sampling data to obtain an estimation value of the parameters in the contour line fitting model;
and inputting the estimated value into the contour line fitting model to obtain a contour line of the cross section of the target tunnel, wherein the contour line is used as a first target characteristic of the cross section of the target tunnel.
The method, the device, the computer equipment, the storage medium and the computer program product for extracting the cross section features of the tunnel are characterized in that the cross section data of the cross section of the target tunnel is sampled to obtain sampled data, then the sampled data are input into a parameter estimation model corresponding to the cross section of the target tunnel, parameters in a contour line fitting model corresponding to the cross section of the target tunnel are estimated through the parameter estimation model based on the sampled data to obtain estimated values of the parameters in the contour line fitting model, and then the estimated values are input into the contour line fitting model to obtain the contour line of the cross section of the target tunnel as the first target feature of the cross section of the target tunnel. By adopting the method, the whole cross section data does not need to be processed, the characteristic extraction step is executed aiming at the sampling data obtained by sampling processing, the characteristic extraction speed of the cross section of the tunnel is improved, the abnormal value processing of the sampling data does not need to be carried out in advance, and the influence of the abnormal data in the sampling data is reduced based on the probability distribution characteristic of the parameter estimation model, so that the accuracy of the characteristic extraction of the cross section of the tunnel is improved.
Drawings
FIG. 1 is a schematic flow chart of a method for extracting cross-sectional features of a tunnel according to an embodiment;
FIG. 2 is a graph of results of a contour line based on a least squares fit method in one embodiment;
FIG. 3 is a diagram illustrating the results of contour lines obtained by a method for extracting cross-sectional features of a tunnel according to an embodiment;
FIG. 4 is a distribution diagram of three-dimensional point cloud data of a subway tunnel cross section in one embodiment;
FIG. 5 is a schematic flow chart of a tunnel cross-sectional feature extraction method in another embodiment;
FIG. 6 is a schematic flow chart of a tunnel cross-sectional feature extraction method in yet another embodiment;
fig. 7 is a block diagram showing the structure of a tunnel cross-sectional feature extraction device according to an embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In an embodiment, as shown in fig. 1, a method for extracting a cross-sectional feature of a tunnel is provided, and this embodiment is illustrated by applying the method to a server, it is to be understood that the method may also be applied to a terminal, and may also be applied to a system including the terminal and the server, and is implemented by interaction between the terminal and the server. In this embodiment, the method includes the steps of:
and step S101, sampling cross section data of the cross section of the target tunnel to obtain sampling data.
The target tunnel cross section is a tunnel cross section which needs to be subjected to tunnel characteristic parameter extraction.
Specifically, cross section data of the cross section of the target tunnel is obtained, and sampling processing is performed on the cross section of the target tunnel according to a data set sampler to obtain sampling data.
In practice, the data set sampler comprises a NUTS sampler.
And S102, inputting the sampling data into a parameter estimation model corresponding to the cross section of the target tunnel, and estimating parameters in a contour line fitting model corresponding to the cross section of the target tunnel through the parameter estimation model based on the sampling data to obtain an estimation value of the parameters in the contour line fitting model.
In practical application, due to the influence of various objective factors, abnormal data may exist in actual cross section data of a target tunnel cross section, and in the technical field of tunnel three-dimensional point cloud data feature extraction, the abnormal data has a large influence on the accuracy of a tunnel cross section feature extraction result, so that the obtained parameters are prone to have deviation, and the parameter deviation can directly influence the design and construction of a subsequent tunnel.
The parameter estimation model is a parameter estimation model carrying target probability distribution, and abnormal data in the sampled data are eliminated through the target probability distribution; the parameter estimation model is used for estimating parameters in the contour line fitting model; the parameter estimation model comprises a student t distribution Bayesian model, and the student t distribution Bayesian model is used for reducing the influence of abnormal data in the sampling data on the extraction of the cross-sectional features of the tunnel based on the student t distribution.
The abnormal data comprise noise points, lining inner grooves, bulges and other data, and abnormal data.
Specifically, a parameter estimation model corresponding to the cross section of the target tunnel is obtained, sampling data are input into the parameter estimation model, standard deviation fluctuation caused by abnormal data in the sampling data is eliminated based on the probability distribution characteristics of the parameter estimation model, processed sampling data are obtained, and each parameter in a contour line fitting model corresponding to the cross section of the target tunnel is estimated through the parameter estimation model based on the processed sampling data, so that the estimation value of each parameter in the contour line fitting model is obtained.
And step S103, inputting the estimated value into a contour line fitting model to obtain a contour line of the target tunnel cross section as a first target feature of the target tunnel cross section.
Wherein the target features required for the cross section of the target tunnel comprise a first target feature and a second target feature.
And the contour line fitting model is used for fitting the contour line of the cross section of the target tunnel.
Specifically, the estimated values of the parameters are substituted into corresponding parameters in the contour line fitting model to obtain a target contour line fitting model, contour line fitting is carried out on the sampled data based on the target contour line fitting model to obtain a contour line of the cross section of the target tunnel, and the contour line is used as a first target feature of the cross section of the target tunnel.
In practical application, the general formula of the ellipse equation shown below can be used to fit the contour line of the cross section of the target tunnel:
AY2+BYZ+CZ2+DY+EZ+1＝0
where A, B, C, D and E respectively denote parameters in the contour fitting model, and Y and Z respectively denote Y-axis coordinates and Z-axis coordinates of the sampled data on the plane coordinate system YZ of the cross sectional data.
According to the method for extracting the cross section characteristics of the tunnel, the cross section data of the target tunnel cross section is sampled to obtain sampled data, then the sampled data are input into a parameter estimation model corresponding to the target tunnel cross section, parameters in a contour line fitting model corresponding to the target tunnel cross section are estimated through the parameter estimation model based on the sampled data to obtain estimated values of the parameters in the contour line fitting model, and then the estimated values are input into the contour line fitting model to obtain a contour line of the target tunnel cross section as a first target characteristic of the target tunnel cross section. By adopting the method, the whole cross section data does not need to be processed, the feature extraction step is executed aiming at the sampling data obtained by sampling processing, the feature extraction speed of the cross section of the tunnel is improved, the abnormal value processing of the sampling data does not need to be carried out in advance, and the influence of the abnormal data in the sampling data is reduced based on the probability distribution characteristic of the parameter estimation model, so that the accuracy of the feature extraction of the cross section of the tunnel is improved.
In an embodiment, in step S102, the sampling data is input into a parameter estimation model corresponding to the cross section of the target tunnel, and parameters in a contour line fitting model corresponding to the cross section of the target tunnel are estimated by the parameter estimation model based on the sampling data, so as to obtain estimated values of the parameters in the contour line fitting model, which specifically includes the following contents:
carrying out probability statistical processing on the sampled data through a parameter estimation model to obtain posterior distribution information of parameters in the contour line model; and performing likelihood estimation on the parameters according to the posterior distribution information to obtain estimated values of the parameters.
Specifically, since the value of the parameter in the parameter estimation model is not determined temporarily, prior distribution is set for each parameter in advance, probability statistics is performed on the sampled data and the prior distribution set for each parameter in advance through the parameter estimation model to obtain posterior distribution of each parameter, the posterior distribution is input into the parameter estimation model to perform likelihood estimation processing, and mean value estimation is obtained to be used as an estimated value of the parameter.
In practice, the prior distribution of the parameters can be set to a normal distribution N (0,100) with a mean value of 0 and a standard deviation of 100.
In the embodiment, the estimated value of the parameter of the contour line fitting model is obtained by performing likelihood estimation on the parameter estimation model based on the sampling data and the prior distribution of the parameter, the abnormal data in the sampling data does not need to be processed in advance, the influence of the abnormal data in the sampling data on the contour line fitting model can be effectively reduced, and the accuracy of extracting the cross section feature of the tunnel is improved.
In one embodiment, before performing probability calculation on the sampled samples through the parameter estimation model to obtain the posterior distribution of the parameters, the method further includes:
according to the parameter estimation model, carrying out probability distribution processing on the sampled data to obtain a probability distribution curve of the sampled data; according to the tail characteristics of the probability distribution curve, standard deviation fluctuation processing is carried out on the sampled data to obtain processed sampled data;
carrying out probability statistical processing on the sampled data through a parameter estimation model to obtain posterior distribution information of parameters in a contour line fitting model, and the method comprises the following steps: and performing probability statistical processing on the processed sampling data through a parameter estimation model to obtain posterior distribution information of parameters in the contour line fitting model.
Specifically, according to the target probability distribution of the parameter estimation model, carrying out probability distribution processing on the sampled data to obtain a probability distribution curve of the sampled data; and when the tail characteristic of the probability distribution curve is a thick tail characteristic, detecting abnormal data from the sampled data according to the thick tail characteristic of the probability distribution curve, and performing standard deviation fluctuation elimination processing on the abnormal data to obtain processed sampled data, wherein the data volume of the processed sampled data is smaller than that of the sampled data. Therefore, after the processed sample data is obtained, the subsequent tunnel cross-sectional feature extraction step is carried out by taking the processed sample data as a processing basis.
The target probability distribution is used to eliminate standard deviation fluctuation caused by abnormal data, and may be t distribution.
In practical application, due to objective factors in a measurement process, abnormal data may exist in cross-sectional data, and further abnormal data may also exist in sampling data obtained by sampling based on the cross-sectional data, and the abnormal data may cause a large fitting deviation influence on a linear fitting result of a contour line.
Further, in order to further reflect the influence of the abnormal data on the linear fitting result of the profile, based on the same sampled data carrying the abnormal data, a least square fitting method and the tunnel cross section feature extraction method in this embodiment are respectively adopted to obtain the profile of the tunnel cross section, and the obtained results are shown in fig. 2 and 3, where an abscissa and an ordinate in fig. 2 and 3 respectively represent a y-axis coordinate value and a z-axis coordinate value of the sampled data on a plane coordinate system YZ. Fig. 2 shows a diagram of the result of the contour line obtained based on the least square fitting method, and it can be seen from fig. 2 that the contour line obtained by the least square fitting is deviated from the data points, a part of the contour line is located above the data, i.e. along the upper edge of the data, and a part of the contour line is deviated from the data centerline, and thus it can be seen that, when the abnormal value processing is not performed on the sampled data, the least square fitting method is affected by the abnormal data, so that the generated contour line is deviated from the data centerline. Fig. 3 is a result diagram of contour lines obtained based on the tunnel cross-sectional feature extraction method in this embodiment, and it can be seen from fig. 3 that the contour lines obtained in this embodiment are all along a data center line, and thus, the contour lines obtained in this embodiment are not affected by abnormal data, so that the generated contour lines are fitted to the data center line.
In the embodiment, standard deviation fluctuation caused by abnormal data in the sampled data is eliminated through target probability distribution set in the parameter estimation model, so that the influence of the abnormal data on the contour line fitting model is reduced, abnormal value processing does not need to be performed on the sampled data in advance, the influence of the abnormal data in the sampled data can be reduced directly on the basis of the probability distribution characteristic of the parameter estimation model, and the accuracy of tunnel cross section feature extraction is improved.
In one embodiment, before inputting the sampled data into the parameter estimation model corresponding to the cross section of the target tunnel, the method further comprises the following steps:
generating an initial parameter estimation model according to a preset standard deviation and a preset degree of freedom; inputting the cross section data into a mean value statistical model associated with the initial parameter estimation model to obtain a mean value parameter value in the initial parameter estimation model; and updating the mean parameter in the initial parameter estimation model by using the mean parameter value to obtain a parameter estimation model.
Specifically, a preset standard deviation and a preset degree of freedom are obtained, and a data parameter estimation model is generated according to the preset standard deviation, the preset degree of freedom and a target probability distribution; inputting the cross section data into a mean value statistical model associated with the initial parameter estimation model to obtain a mean value parameter value in the initial parameter estimation model; the mean statistical model can be represented by the following formula:
μ＝AY2+BYZ+CZ2+DY+EZ+1
where μ denotes a mean parameter, and the parameters Y and Z denote a Y-axis coordinate and a Z-axis coordinate of the sample data on a plane coordinate system YZ of the cross-sectional data, respectively.
And updating the mean parameter in the initial parameter estimation model by using the mean parameter value to obtain a parameter estimation model.
Furthermore, the observation data input when the parameter estimation model performs calculation is a one-dimensional 0 vector, and the length of the observation data is the same as the number of the three-dimensional point cloud data.
Wherein the observation data is not a real observation data in a physical sense, but a hypothetical one-dimensional zero vector. Since μ is theoretically 0, μ is made 0 by the parameters A, B, C, D and E.
In practical applications, the prior distribution of the preset standard deviation may be set as a semi-normal distribution with the standard deviation of 100, and the prior distribution of the preset degrees of freedom may be set as an exponential distribution with θ being 29, where θ represents a model parameter.
In the embodiment, standard deviation fluctuation caused by abnormal data in the sampled data is eliminated through target probability distribution set in the parameter estimation model, so that the influence of the abnormal data on the contour line fitting model is reduced, abnormal value processing does not need to be performed on the sampled data in advance, the influence of the abnormal data in the sampled data can be reduced directly on the basis of the probability distribution characteristic of the parameter estimation model, and the accuracy of tunnel cross section feature extraction is improved.
In one embodiment, before sampling the cross-sectional data of the target tunnel cross section to obtain the sampled data, the method further includes:
performing data extraction processing on three-dimensional point cloud data corresponding to a scene where the cross section of the target tunnel is located to obtain initial cross section data of the cross section of the target tunnel; and extracting plane coordinate data in the initial cross section data to obtain the cross section data.
Wherein, the target tunnel can be obtained by shield construction.
Specifically, after the target tunnel is constructed, three-dimensional laser scanning is performed on the scene of the target tunnel to obtain three-dimensional point cloud data, for example, the three-dimensional point cloud data of the cross section of the subway tunnel is shown in fig. 4; performing data extraction processing on the three-dimensional point cloud data according to the target cross section to obtain initial cross section data of the target cross section, and if the initial cross section data at different positions along the length direction needs to be obtained, intercepting the three-dimensional point cloud data segment by segment from the starting point of the three-dimensional point cloud data; and (3) taking the plane coordinate system of the initial cross section data as XYZ, and extracting YZ plane coordinate data in the initial cross section to obtain cross section data.
In the embodiment, the whole three-dimensional point cloud data does not need to be processed, the extracted cross section data is processed, the data needing to be processed is greatly reduced, the feature extraction speed of the cross section of the tunnel is improved, the feature extraction step is executed according to the sampling data obtained by sampling processing, the number of the data needing to be processed is further reduced, and the feature extraction speed of the cross section of the tunnel is greatly improved.
In one embodiment, the method for extracting the cross section features of the tunnel further includes acquiring coordinates of a center point of the cross section of the target tunnel, and specifically includes the following steps:
inputting the estimated value into a central point model of the cross section of the tunnel to obtain a central point coordinate of the cross section of the target tunnel; and determining the coordinates of the central point as a second target characteristic of the cross section of the target tunnel.
The tunnel cross section central point model is used for acquiring central point coordinates of the target tunnel cross section.
Specifically, the estimation value output by the parameter estimation model is input into a central point model of the cross section of the tunnel, the central point coordinate of the cross section of the target tunnel is obtained through calculation and is used as a second target feature of the cross section of the target tunnel, and the central point coordinate is used for calculating subsequent line type calculation of the cross section of the target tunnel.
In practical application, the coordinate (Y) of the center point of the cross section of the target tunnelc，Zc) Can be calculated by the following formula:
wherein, muA、μB、μC、μDAnd muEMean estimates of parameters A, B, C, D and E in the contour fitting model, respectively, representing the parameter estimation model outputs.
In the embodiment, the estimated value output by the parameter estimation model is input into the central point model of the cross section of the tunnel to obtain the central point coordinate of the cross section of the target tunnel, the central point coordinate is used as the second target feature of the cross section of the target tunnel, other line types of the cross section of the target tunnel can be calculated through the second target feature, and meanwhile, the influence of abnormal data on the estimated value is eliminated based on the target probability distribution in the parameter estimation model, so that the calculation accuracy of the central point coordinate is improved, namely the accuracy of extracting the features of the cross section of the tunnel is improved.
In one embodiment, as shown in fig. 5, another tunnel cross-sectional feature extraction method is provided, which is described by taking the method as an example for being applied to a server, and includes the following steps:
step S501, data extraction processing is carried out on three-dimensional point cloud data corresponding to a scene where the cross section of the target tunnel is located, and initial cross section data of the cross section of the target tunnel is obtained.
Step S502, extracting plane coordinate data in the initial cross section data to obtain cross section data; and sampling the cross section data of the cross section of the target tunnel to obtain sampled data.
And S503, generating an initial parameter estimation model according to the preset standard deviation and the preset degree of freedom.
Step S504, inputting the cross section data into a mean value statistical model associated with the initial parameter estimation model to obtain a mean value parameter value in the initial parameter estimation model; and updating the mean parameter in the initial parameter estimation model by using the mean parameter value to obtain a parameter estimation model.
Step S505, according to the parameter estimation model, carrying out probability distribution processing on the sampled data to obtain a probability distribution curve of the sampled data; and carrying out standard deviation fluctuation processing on the sampled data according to the tail characteristics of the probability distribution curve to obtain the processed sampled data.
Step S506, carrying out probability statistical processing on the processed sampling data through a parameter estimation model to obtain posterior distribution information of parameters in a contour line fitting model; and performing likelihood estimation on the parameters according to the posterior distribution information to obtain estimated values of the parameters.
And step S507, inputting the estimated value into a contour line fitting model to obtain a contour line of the cross section of the target tunnel, wherein the contour line is used as a first target characteristic of the cross section of the target tunnel.
The method for extracting the cross section features of the tunnel can provide the following beneficial effects:
(1) the method has the advantages that the whole three-dimensional point cloud data is not required to be processed, extracted cross section data is processed, the data needing to be processed are greatly reduced, the feature extraction speed of the cross section of the tunnel is improved, the feature extraction step is executed according to the sampled data obtained through sampling processing, the number of the data needing to be processed is further reduced, and the feature extraction speed of the cross section of the tunnel is greatly improved.
(2) The standard deviation fluctuation caused by abnormal data in the sampled data is eliminated through the target probability distribution set in the parameter estimation model, so that the influence of the abnormal data on the contour line fitting model is reduced, the abnormal value processing of the sampled data is not needed in advance, the influence of the abnormal data in the sampled data can be reduced directly on the basis of the probability distribution characteristic of the parameter estimation model, and the accuracy of the extraction of the cross section characteristics of the tunnel is improved.
(3) According to the estimated value, the central point coordinate of the cross section of the target tunnel can be obtained, so that other line types of the cross section of the calculated target tunnel can be obtained through calculation, meanwhile, the influence of abnormal data on the estimated value is eliminated based on the target probability distribution in the parameter estimation model, the calculation accuracy of the central point coordinate is further improved, and the accuracy of the feature extraction of the cross section of the tunnel is improved.
In order to clarify the method for extracting the cross-sectional feature of the tunnel provided by the embodiment of the present disclosure more clearly, the method for extracting the cross-sectional feature of the tunnel is specifically described below with a specific embodiment. In an embodiment, as shown in fig. 6, the present disclosure further provides a method for extracting a cross-sectional feature of a tunnel, which specifically includes the following steps:
step S601, reading three-dimensional point cloud data;
step S602, intercepting cross section data from the three-dimensional point cloud data, and recording a plane coordinate system YZ of the cross section;
step S603, establishing a student t distribution Bayes model, wherein the prior distribution of standard deviation of the student t distribution Bayes model is a heminormal distribution with standard deviation of 100, and the prior distribution of the degree of freedom parameter of the student t distribution Bayes model is an exponential distribution with the degree of freedom parameter theta of 29;
step S604, fitting the shield tunnel cross section by adopting a general formula of an elliptic equation, wherein the formula of the elliptic equation is as follows:
AY2+BYZ+CZ2+DY+EZ+1＝0
in the student t-distribution Bayes model, the prior distribution of parameters A, B, C, D and E is normal distribution N (0,100) with the mean value of 0 and the standard deviation of 100;
step S605, a formula shown as the following is used as a mean value of the student t distribution Bayes model, and observation data is a one-dimensional 0 vector when the student t distribution Bayes model is calculated;
μ＝AY2+BYZ+CZ2+DY+EZ+1
step S606, the student t distribution Bayes model is calculated, the sampling data of each parameter in the student t distribution Bayes model is obtained in a sampling mode, the posterior distribution of each parameter is calculated, and the mu is estimated according to the mean value of the posterior distribution calculation parameters A, B, C, D and EA、μB、μC、μDAnd muE。
Step S607, estimating the mean value muA、μB、μC、μDAnd muESubstituting into the ellipse equation in the step S603 to obtain the contour line of the cross section of the target tunnel, and estimating the mean value muA、μB、μC、μDAnd muESubstituting into the central point coordinate calculation formula of the target tunnel cross section to obtain the central point coordinate (Y) of the target tunnel cross sectionc，Zc) The central point coordinate calculation formula is as follows:
in the embodiment, the whole cross section data does not need to be processed, the feature extraction step is executed according to the sampling data obtained by sampling processing, the feature extraction speed of the tunnel cross section is improved, abnormal value processing does not need to be performed on the sampling data in advance, and the influence of abnormal data in the sampling data is reduced based on the probability distribution characteristic of the parameter estimation model, so that the accuracy of the feature extraction of the tunnel cross section is improved.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides a tunnel cross section feature extraction device for implementing the above-mentioned tunnel cross section feature extraction method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so that specific limitations in one or more embodiments of the tunnel cross-section feature extraction device provided below can be referred to the limitations on the tunnel cross-section feature extraction method in the foregoing, and details are not repeated herein.
In one embodiment, as shown in fig. 7, there is provided a tunnel cross-sectional feature extraction apparatus 700, including: a sampling module 701, an estimation module 702, and a characterization module 703, wherein:
the sampling module 701 is used for sampling cross section data of the cross section of the target tunnel to obtain sampling data;
the estimation module 702 is configured to input the sampled data into a parameter estimation model corresponding to the cross section of the target tunnel, and estimate parameters in a contour line fitting model corresponding to the cross section of the target tunnel through the parameter estimation model based on the sampled data to obtain an estimated value of the parameters in the contour line fitting model;
and the characteristic module 703 is configured to input the estimated value into the contour line fitting model to obtain a contour line of the target tunnel cross section, which is used as a first target characteristic of the target tunnel cross section.
In one embodiment, the estimating module 702 is further configured to perform probability statistics on the sampled data through a parameter estimation model to obtain posterior distribution information of parameters in the contour model; and performing likelihood estimation on the parameters according to the posterior distribution information to obtain estimated values of the parameters.
In one embodiment, the device for extracting the cross-sectional features of the tunnel further comprises an anomaly detection module, which is used for performing probability distribution processing on the sampled data according to the parameter estimation model to obtain a probability distribution curve of the sampled data; according to the tail characteristics of the probability distribution curve, standard deviation fluctuation processing is carried out on the sampled data to obtain processed sampled data; and the estimation module is also used for carrying out probability statistical processing on the processed sampling data through the parameter estimation model to obtain posterior distribution information of parameters in the contour line fitting model.
In one embodiment, the device for extracting the cross section features of the tunnel further comprises a model construction module, configured to generate an initial parameter estimation model according to a preset standard deviation and a preset degree of freedom; inputting the cross section data into a mean value statistical model associated with the initial parameter estimation model to obtain a mean value parameter value in the initial parameter estimation model; and updating the mean parameter in the initial parameter estimation model by using the mean parameter value to obtain a parameter estimation model.
In one embodiment, the device for extracting the cross section features of the tunnel further comprises a data processing module, configured to perform data extraction processing on three-dimensional point cloud data corresponding to a scene where the cross section of the target tunnel is located, so as to obtain initial cross section data of the cross section of the target tunnel; and extracting plane coordinate data in the initial cross section data to obtain the cross section data.
In one embodiment, the device for extracting the characteristic of the cross section of the tunnel further comprises a coordinate characteristic module, which is used for inputting the estimation value into a central point model of the cross section of the tunnel to obtain a central point coordinate of the cross section of the target tunnel; and determining the coordinates of the central point as a second target characteristic of the cross section of the target tunnel.
The modules in the tunnel cross-section feature extraction device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing cross section data, sampling data and other relevant data of the target cross section. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of tunnel cross-sectional feature extraction.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases involved in the embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A method for extracting features of a cross section of a tunnel is characterized by comprising the following steps:
sampling cross section data of the cross section of the target tunnel to obtain sampling data;
inputting the sampling data into a parameter estimation model corresponding to the cross section of the target tunnel, and estimating parameters in a contour line fitting model corresponding to the cross section of the target tunnel through the parameter estimation model based on the sampling data to obtain an estimation value of the parameters in the contour line fitting model;
and inputting the estimated value into the contour line fitting model to obtain a contour line of the cross section of the target tunnel, wherein the contour line is used as a first target characteristic of the cross section of the target tunnel.
2. The method according to claim 1, wherein the estimating parameters in the contour line fitting model corresponding to the target tunnel cross section based on the sampled data by the parameter estimation model to obtain the estimated values of the parameters in the contour line fitting model comprises:
carrying out probability statistical processing on the sampled data through the parameter estimation model to obtain posterior distribution information of parameters in the contour line model;
and performing likelihood estimation on the parameters according to the posterior distribution information to obtain estimated values of the parameters.
3. The method of claim 2, further comprising, before performing a probability calculation on the sample samples through the parameter estimation model to obtain a posterior distribution of the parameter:
according to the parameter estimation model, carrying out probability distribution processing on the sampled data to obtain a probability distribution curve of the sampled data;
according to the tail characteristics of the probability distribution curve, standard deviation fluctuation processing is carried out on the sampled data to obtain processed sampled data;
the probability statistical processing is carried out on the sampling data through the parameter estimation model to obtain posterior distribution information of parameters in the contour line fitting model, and the probability statistical processing comprises the following steps:
and carrying out probability statistical processing on the processed sampling data through the parameter estimation model to obtain posterior distribution information of parameters in the contour line fitting model.
4. The method of claim 1, further comprising, before inputting the sampled data into the parameter estimation model corresponding to the target tunnel cross section:
generating an initial parameter estimation model according to a preset standard deviation and a preset degree of freedom;
inputting the cross section data into a mean value statistical model associated with the initial parameter estimation model to obtain a mean value parameter value in the initial parameter estimation model;
and updating the mean parameter in the initial parameter estimation model by using the mean parameter value to obtain the parameter estimation model.
5. The method of claim 1, wherein before sampling the cross-sectional data of the target tunnel cross-section to obtain the sampled data, the method further comprises:
performing data extraction processing on three-dimensional point cloud data corresponding to a scene where the cross section of the target tunnel is located to obtain initial cross section data of the cross section of the target tunnel;
and extracting plane coordinate data in the initial cross section data to obtain the cross section data.
6. The method according to any one of claims 1 to 5, further comprising:
inputting the estimated value into a central point model of the cross section of the tunnel to obtain a central point coordinate of the cross section of the target tunnel;
and determining the central point coordinate as a second target feature of the target tunnel cross section.
7. A tunnel cross section feature extraction device, characterized in that the device comprises:
the sampling module is used for sampling the cross section data of the cross section of the target tunnel to obtain sampling data;
the estimation module is used for inputting the sampling data into a parameter estimation model corresponding to the cross section of the target tunnel, and estimating parameters in a contour line fitting model corresponding to the cross section of the target tunnel through the parameter estimation model based on the sampling data to obtain estimated values of the parameters in the contour line fitting model;
and the characteristic module is used for inputting the estimated value into the contour line fitting model to obtain a contour line of the cross section of the target tunnel, and the contour line is used as a first target characteristic of the cross section of the target tunnel.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111675567.5A CN114494315B (en) | 2021-12-31 | 2021-12-31 | Tunnel cross section feature extraction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111675567.5A CN114494315B (en) | 2021-12-31 | 2021-12-31 | Tunnel cross section feature extraction method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114494315A true CN114494315A (en) | 2022-05-13 |
| CN114494315B CN114494315B (en) | 2022-11-08 |
Family
ID=81497334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111675567.5A Active CN114494315B (en) | 2021-12-31 | 2021-12-31 | Tunnel cross section feature extraction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114494315B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298737A (en) * | 2014-10-08 | 2015-01-21 | 同济大学 | Discrete point cloud fitting method based on maximum sampling nuclear density steady model |
| GB201609906D0 (en) * | 2016-01-20 | 2016-07-20 | Soliton Holdings Corp Delaware Corp | Method for computational fluid dynamics and apparatuses for jet-effect use |
| CN106570206A (en) * | 2016-09-30 | 2017-04-19 | 南京航空航天大学 | Designed compaction number-of-times determining method of emulsified asphalt cold recycled mixture |
| CN106600617A (en) * | 2016-12-29 | 2017-04-26 | 中科宇图科技股份有限公司 | Method of extracting building contour line from Lidar point cloud data based on curvature |
| CN108305184A (en) * | 2017-12-22 | 2018-07-20 | 安徽海螺集团有限责任公司 | A kind of number mining softwares platform |
| CN110977982A (en) * | 2019-12-19 | 2020-04-10 | 南京理工大学 | Depth vision-based double-mechanical-arm control method |
| CN111336991A (en) * | 2020-03-27 | 2020-06-26 | 南京航空航天大学 | Tunnel ellipticity analysis method, device and system based on laser point cloud |
| CN111767853A (en) * | 2020-06-30 | 2020-10-13 | 北京百度网讯科技有限公司 | Lane line detection method and device |
| CN111859572A (en) * | 2020-07-21 | 2020-10-30 | 上海扩博智能技术有限公司 | Method, system, equipment and storage medium for fitting surface contour line of fan blade |
| CN112990533A (en) * | 2021-01-19 | 2021-06-18 | 中国农业大学 | Wind power cluster power prediction method based on sparse constraint and dynamic weight distribution |
-
2021
- 2021-12-31 CN CN202111675567.5A patent/CN114494315B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298737A (en) * | 2014-10-08 | 2015-01-21 | 同济大学 | Discrete point cloud fitting method based on maximum sampling nuclear density steady model |
| GB201609906D0 (en) * | 2016-01-20 | 2016-07-20 | Soliton Holdings Corp Delaware Corp | Method for computational fluid dynamics and apparatuses for jet-effect use |
| CN106570206A (en) * | 2016-09-30 | 2017-04-19 | 南京航空航天大学 | Designed compaction number-of-times determining method of emulsified asphalt cold recycled mixture |
| CN106600617A (en) * | 2016-12-29 | 2017-04-26 | 中科宇图科技股份有限公司 | Method of extracting building contour line from Lidar point cloud data based on curvature |
| CN108305184A (en) * | 2017-12-22 | 2018-07-20 | 安徽海螺集团有限责任公司 | A kind of number mining softwares platform |
| CN110977982A (en) * | 2019-12-19 | 2020-04-10 | 南京理工大学 | Depth vision-based double-mechanical-arm control method |
| CN111336991A (en) * | 2020-03-27 | 2020-06-26 | 南京航空航天大学 | Tunnel ellipticity analysis method, device and system based on laser point cloud |
| CN111767853A (en) * | 2020-06-30 | 2020-10-13 | 北京百度网讯科技有限公司 | Lane line detection method and device |
| CN111859572A (en) * | 2020-07-21 | 2020-10-30 | 上海扩博智能技术有限公司 | Method, system, equipment and storage medium for fitting surface contour line of fan blade |
| CN112990533A (en) * | 2021-01-19 | 2021-06-18 | 中国农业大学 | Wind power cluster power prediction method based on sparse constraint and dynamic weight distribution |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114494315B (en) | 2022-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Amat et al. | Advances in iterative methods for nonlinear equations | |
| US20180329402A1 (en) | Estimation of abnormal sensors | |
| CN115841046A (en) | Accelerated degradation test data processing method and device based on wiener process | |
| CN115795928A (en) | Accelerated degradation test data processing method and device based on gamma process | |
| CN113487019A (en) | Circuit fault diagnosis method and device, computer equipment and storage medium | |
| US10467538B2 (en) | Link de-noising in a network | |
| US20170199904A1 (en) | Low memory sampling-based estimation of distinct elements and deduplication | |
| CN114494315B (en) | Tunnel cross section feature extraction method, device, equipment and storage medium | |
| US11762730B2 (en) | Selection of outlier-detection programs specific to dataset meta-features | |
| JP2020098455A (en) | Object identification system, object identification method, and image identification program | |
| CN112861239A (en) | Method, system, device and storage medium for initially balancing ground stress of numerical model | |
| CN115760812A (en) | Chip packaging defect detection and positioning method and device | |
| Zabolotnii et al. | Semi-parametric estimation of the change-point of parameters of non-Gaussian sequences by polynomial maximization method | |
| CN115409070A (en) | Method, device and equipment for determining critical point of discrete data sequence | |
| CN112632894A (en) | Josephson junction array voltage output method, apparatus, device and storage medium | |
| CN113313049A (en) | Method, device, equipment, storage medium and computer program product for determining hyper-parameters | |
| CN109146840B (en) | Method and device for evaluating data geometric positioning precision based on Gaussian probability statistics | |
| CN112488528A (en) | Data set processing method, device, equipment and storage medium | |
| CN113379056B (en) | Quantum state data processing method and device, electronic equipment and storage medium | |
| WO2024016893A1 (en) | Height data determination method and apparatus, computer device, and storage medium | |
| CN116127785B (en) | Reliability evaluation method, device and equipment based on multiple performance degradation | |
| White | Gate set tomography is not just hyperaccurate, it’sa different way of thinking | |
| CN115001997B (en) | Extreme value theory-based smart city network equipment performance abnormal threshold evaluation method | |
| CN114492564B (en) | Sequential design method, device and equipment based on local Gaussian process fitting | |
| Acha Chigozie et al. | Towards Efficiency in the Residual and Parametric Bootstrap Techniques |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |