Laser rangefinder detection method, device, electronic equipment and storage medium

Abstract

The present disclosure provides a detection method, device, electronic device and storage medium for a laser rangefinder. The detection method for the laser rangefinder includes: obtaining target performance data of the laser rangefinder to be detected; classifying the target performance data by a preset classification model to obtain a classification result; and obtaining a detection result of the laser rangefinder to be detected according to the classification result. By obtaining the target performance data of the laser rangefinder to be detected, classifying the target performance data by using a preset classification model, and obtaining a detection result of the laser rangefinder to be detected according to the classification result, the target performance data and the classification model are used to classify the laser rangefinder to be detected, which does not require a large amount of manpower, material resources and time, thereby improving the detection efficiency of the laser rangefinder.

Description

Technical Field

[0001] The present invention relates to the technical field of laser rangefinder detection, and in particular to a laser rangefinder detection method, device, electronic equipment and storage medium. Background Art

[0002] Laser rangefinder is an instrument used to measure the distance between the target and the current position. Laser rangefinders are generally tested before leaving the factory to ensure the quality of the products. The existing detection method is mainly to measure the distance between the target and the rangefinder with a tape measure, and compare it with the distance between the target and the laser rangefinder detected by the laser rangefinder to determine the accuracy and error of the rangefinder. This test method cannot eliminate the errors caused by terrain, weather environment and human misoperation. Moreover, a qualified laser rangefinder often involves many judgment criteria. It is necessary to comprehensively determine whether the laser rangefinder is qualified from a large number of performance indicators, which will require a lot of manpower, material resources and time. It has the disadvantages of large errors, high costs, low efficiency, and complex operation, which makes the detection efficiency of existing laser rangefinders low. Summary of the invention

[0003] The embodiments of the present invention provide a detection method, device, electronic device and storage medium for a laser rangefinder, aiming to solve the problem of low detection efficiency of existing laser rangefinders. By acquiring target performance data of a laser rangefinder to be detected, the target performance data is classified using a preset classification model, and a detection result of the laser rangefinder to be detected is obtained according to the classification result. The laser rangefinder to be detected is classified by using the target performance data and the classification model, which does not require a large amount of manpower, material resources and time, thereby improving the detection efficiency of the laser rangefinder.

[0004] In a first aspect, an embodiment of the present invention provides a detection method of a laser rangefinder, the method comprising:

[0005] Obtain target performance data of the laser rangefinder to be tested;

[0006] Classifying the target performance data using a preset classification model to obtain a classification result;

[0007] The detection result of the laser rangefinder to be detected is obtained according to the classification result.

[0008] Optionally, before the step of classifying the target performance data by using the predicted classification model to obtain a classification result, the method further includes:

[0009] Acquire experimental performance data of the laser rangefinder, and perform dimensionality reduction processing on the experimental performance data to obtain sample data;

[0010] A classification model is trained based on the sample data.

[0011] Optionally, before the step of classifying the target performance data by using the predicted classification model to obtain a classification result, the method further includes:

[0012] The comprehensive performance data of the laser rangefinder to be detected is obtained, and the dimensionality reduction process is performed on the comprehensive performance data to obtain target performance data, wherein the target performance data has the same dimension as the sample data.

[0013] Optionally, the step of obtaining experimental performance data of the laser rangefinder and performing dimensionality reduction processing on the experimental performance data to obtain sample data includes:

[0014] Performing a performance experiment on N laser rangefinders to obtain experimental performance data corresponding to the N laser rangefinders, wherein the experimental performance data includes M performance index data;

[0015] The experimental performance data is reduced in dimension by a principal component analysis method to obtain sample data, wherein the sample data includes K performance index data, wherein K is less than M.

[0016] Optionally, the N laser rangefinders include n1 qualified laser rangefinders and n2 unqualified laser rangefinders, and the step of reducing the dimension of the experimental performance data by the principal component analysis method to obtain sample data includes:

[0017] Performing dimensionality reduction on the experimental performance data corresponding to n1 qualified laser rangefinders by a principal component analysis method to obtain first sample data, wherein the first sample data includes k1 performance indicator data;

[0018] Performing dimensionality reduction on the experimental performance data corresponding to n2 unqualified laser rangefinders by a principal component analysis method to obtain second sample data, wherein the second sample data includes k2 performance indicator data;

[0019] Based on the first sample data and the second sample data, sample data is obtained, wherein the sum of k1 and k2 is greater than or equal to K.

[0020] Optionally, the step of obtaining sample data having a third dimension based on the first sample data and the second sample data includes:

[0021] If the first sample data and the second sample data do not have the same performance indicator data, concatenating the first sample data and the second sample data to obtain sample data;

[0022] If the same performance indicator data exists in the first sample data and the second sample data, the contribution values ​​of the same performance indicator data in the first sample data and the second sample data are calculated respectively, and the same performance indicator data with a smaller contribution value is deleted from the first sample data or the second sample data, and the first sample data and the second sample data without the same performance indicator data are spliced ​​to obtain sample data.

[0023] Optionally, the step of training a classification model according to the sample data includes:

[0024] Modeling is performed based on convolutional neural networks to obtain an initial classification model;

[0025] Performing a first training on the initial classification model using experimental performance data of the laser rangefinder to obtain an intermediate classification model;

[0026] The intermediate classification model is trained using the sample data to obtain a trained classification model.

[0027] In a second aspect, a detection device for a laser rangefinder is provided, the device comprising:

[0028] A first acquisition module is used to acquire target performance data of the laser rangefinder to be detected;

[0029] A classification module, used to classify the target performance data through a preset classification model to obtain a classification result;

[0030] A detection module is used to obtain a detection result of the laser rangefinder to be detected according to the classification result.

[0031] In a third aspect, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps in the detection method of a laser rangefinder as described in any one of the embodiments of the present invention are implemented.

[0032] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps in the detection method of a laser rangefinder as described in any one of the embodiments of the present invention are implemented.

[0033] In an embodiment of the present invention, target performance data of a laser rangefinder to be detected is obtained; the target performance data is classified by a preset classification model to obtain a classification result; and the detection result of the laser rangefinder to be detected is obtained according to the classification result. By obtaining the target performance data of the laser rangefinder to be detected, the target performance data is classified by using a preset classification model, and the detection result of the laser rangefinder to be detected is obtained according to the classification result, the target performance data and the classification model are used to classify the laser rangefinder to be detected, which does not require a large amount of manpower, material resources and time, thereby improving the detection efficiency of the laser rangefinder. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0035] Figure 1 The present invention is a flow chart of a detection method of a laser rangefinder.

[0036] Figure 2 The present invention is a structural schematic diagram of a detection device of a laser rangefinder. DETAILED DESCRIPTION

[0037] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, but are not to be construed as limiting the present invention. All other embodiments obtained by ordinary technicians in the field without creative work based on the embodiments of the present invention are within the scope of protection of the present invention.

[0038] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “circumferential”, “radial”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0039] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0040] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0041] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0042] See also Figure 1 , Figure 1 A detection method for a laser rangefinder provided in this application comprises:

[0043] 101. Obtain target performance data of the laser rangefinder to be tested.

[0044] In an embodiment of the present invention, the target performance data may include performance index data of the laser rangefinder, and the performance index data may be obtained by measuring and testing the corresponding performance index. The performance index in the target performance data may be a performance index that can represent whether the laser rangefinder is qualified or unqualified.

[0045] The above performance indicators may include accuracy and anti-interference ability at different temperatures, accuracy and anti-interference ability at different visibility levels, accuracy and anti-interference ability at different humidity levels, and so on.

[0046] 102. Classify the target performance data using a preset classification model to obtain a classification result.

[0047] In an embodiment of the present invention, the above-mentioned preset classification model may be a classification model based on a convolutional neural network, or a classification model based on a random forest or a support vector machine.

[0048] Preferably, the above-mentioned preset classification model can be a classification model based on a convolutional neural network, which uses the convolutional neural network to extract the implicit relationship between the target performance data and the classification results to form corresponding model parameters, so that the model parameters have the ability to determine which type of classification the target performance data belongs to.

[0049] Furthermore, the above classification model can be a binary classification model based on a convolutional neural network. The binary classification model can divide the target performance data into two, one classification result is qualified, and the other classification result is unqualified.

[0050] It is only necessary to input the target performance data into the classification model, and the classification model will automatically output the classification results of the target performance data.

[0051] 103. Obtain the detection result of the laser rangefinder to be detected according to the classification result.

[0052] In the embodiment of the present invention, the above classification result represents the qualified type of the laser rangefinder to be detected, and the qualified type may include qualified and unqualified types.

[0053] In an embodiment of the present invention, target performance data of a laser rangefinder to be detected is obtained; the target performance data is classified by a preset classification model to obtain a classification result; and the detection result of the laser rangefinder to be detected is obtained according to the classification result. By obtaining the target performance data of the laser rangefinder to be detected, the target performance data is classified by using a preset classification model, and the detection result of the laser rangefinder to be detected is obtained according to the classification result, the target performance data and the classification model are used to classify the laser rangefinder to be detected, which does not require a large amount of manpower, material resources and time, thereby improving the detection efficiency of the laser rangefinder.

[0054] Optionally, before classifying the target performance data through the predicted classification model to obtain the classification result, the experimental performance data of the laser rangefinder can be obtained, and the dimensionality reduction processing of the experimental performance data can be performed to obtain sample data; and the classification model can be trained based on the sample data.

[0055] In the embodiment of the present invention, the above-mentioned laser rangefinder may also be referred to as a sample laser rangefinder, and the above-mentioned laser rangefinder and the laser rangefinder to be detected are laser rangefinders of the same model.

[0056] The above experimental performance data includes all performance index data, and each performance index data can be obtained by measuring and testing the corresponding performance index. The above performance indexes may include accuracy and anti-interference ability at different temperatures, accuracy and anti-interference ability at different visibility, accuracy and anti-interference ability at different humidity, etc.

[0057] The above-mentioned dimensionality reduction process can be understood as selecting a few representative performance indicators from all performance indicators. For example, selecting one or more accuracies at different temperatures from the accuracies at different temperatures to represent whether the accuracy of the laser rangefinder at different temperatures is qualified.

[0058] The dimension of the above sample data is smaller than the dimension of the experimental performance data. The above classification model can be a classification model based on a convolutional neural network. The classification model can be trained according to the sample data to obtain a trained classification model. The target performance data is input into the trained classification model for processing, and the corresponding classification results are output through the trained classification model.

[0059] In the embodiment of the present invention, the experimental performance data of the laser rangefinder is subjected to dimensionality reduction processing to obtain sample data for training a classification model, which can make the classification accuracy of the classification model higher.

[0060] Optionally, before classifying the target performance data through the predicted classification model to obtain the classification result, the comprehensive performance data of the laser rangefinder to be detected can be obtained, and the comprehensive performance data can be reduced in dimension to obtain the target performance data, and the target performance data has the same dimension as the sample data.

[0061] In an embodiment of the present invention, after obtaining the comprehensive performance data of the laser rangefinder to be detected, dimensionality reduction processing may be performed on the comprehensive performance data to obtain target performance data having the same dimensionality as the sample data.

[0062] In a possible embodiment, the target performance data can also be obtained by measuring and testing the corresponding performance indicators according to the performance indicators in the sample data, so that the performance indicators of the target performance data are the same as the performance indicators in the sample data, and the dimensions are also the same.

[0063] By performing dimensionality reduction processing on the target performance data, the target performance data and the sample data can have the same dimension, so that the target performance data can be used as input data for the classification model.

[0064] Optionally, in the step of obtaining experimental performance data of a laser rangefinder, performing dimensionality reduction processing on the experimental performance data, and obtaining sample data, performance experiments can be conducted on N laser rangefinders to obtain experimental performance data corresponding to the N laser rangefinders, wherein the experimental performance data include M performance index data; and the experimental performance data are reduced in dimensionality by a principal component analysis method to obtain sample data, wherein the sample data include K performance index data, wherein K is less than M.

[0065] In an embodiment of the present invention, performance experiments can be conducted on N laser rangefinders to obtain experimental performance data corresponding to the N laser rangefinders. M performance index data corresponding to the N laser rangefinders can be constructed into a first matrix through a principal component analysis method, and the first matrix includes the N laser rangefinders and the M performance index data; the covariance matrix of the first matrix is ​​calculated, and dimensionality reduction processing is performed according to the covariance matrix to obtain a second matrix; based on the first matrix and the second matrix, sample data is obtained.

[0066] Specifically, the M performance indicator data corresponding to the N laser rangefinders can be constructed into an N×M first matrix H, in which each column corresponds to performance indicator data of a performance indicator, and each row corresponds to performance indicator data of a laser rangefinder.

[0067] For the first matrix H, the average value of each column of performance indicator data is calculated, and the average value is subtracted from each column of performance indicator data to obtain the standard deviation corresponding to each performance indicator data. The covariance corresponding to each performance indicator data is obtained by the square of the standard deviation, and the N×M covariance matrix C is obtained based on the covariance.

[0068] By extracting the variation information of the performance index data from the covariance matrix, and then reducing the dimension of the covariance matrix through the variation information, sample data with a high degree of variation can be extracted to ensure the high influence of the sample data on the qualification test.

[0069] Furthermore, after obtaining the covariance matrix C of the first matrix H, the eigenvalues ​​and corresponding eigenvectors of the covariance matrix C are calculated; the eigenvectors are sorted according to the size of the eigenvalues; the eigenvectors with the largest eigenvalues ​​are retained to obtain the M×K second matrix D. The degree of variation of the performance indicator data is determined by the eigenvalues, so that sample data with a high degree of variation can be selected to ensure the high influence of the sample data on the qualification test.

[0070] Furthermore, the third matrix G = HD is the matrix multiplication of the first matrix N × M and the second matrix M × K, and the third matrix G of N × K is obtained. Then the first matrix is ​​reduced from M dimension to K dimension, and the performance index data with little influence on the result is removed. Through matrix multiplication, the dimensionality reduction processing is performed to obtain sample data with a high degree of variation, ensuring the high influence of sample data on qualification detection.

[0071] Optionally, the N laser rangefinders include n1 qualified laser rangefinders and n2 unqualified laser rangefinders. In the step of reducing the dimension of the experimental performance data by using the principal component analysis method to obtain sample data, the experimental performance data corresponding to the n1 qualified laser rangefinders can be reduced in dimension by using the principal component analysis method to obtain first sample data, wherein the first sample data includes k1 performance index data; the experimental performance data corresponding to the n2 unqualified laser rangefinders can be reduced in dimension by using the principal component analysis method to obtain second sample data, wherein the second sample data includes k2 performance index data; sample data is obtained based on the first sample data and the second sample data, wherein the sum of k1 and k2 is greater than or equal to K.

[0072] In an embodiment of the present invention, the first sample data and the second sample data can be acquired according to the principal component analysis method of the sample data, and the laser rangefinder is divided into qualified and unqualified, so that the sample data may include qualified sample data and unqualified sample data, the qualified sample data includes high-influence performance indicators that affect the qualification detection, and the unqualified sample data includes high-influence performance indicators that affect the unqualified detection.

[0073] By training the classification model with sample data including qualified sample data and unqualified sample data, the classification model can be enabled to classify qualified laser rangefinders and unqualified laser rangefinders, thereby increasing the classification accuracy of the classification model.

[0074] Optionally, in the step of obtaining sample data having a third dimension based on the first sample data and the second sample data, if the first sample data and the second sample data do not have the same performance indicator data, the first sample data and the second sample data may be spliced ​​to obtain sample data; if the first sample data and the second sample data have the same performance indicator data, the contribution values ​​of the same performance indicator data in the first sample data and the second sample data are calculated respectively, and the same performance indicator data with a smaller contribution value is deleted from the first sample data or the second sample data, and the first sample data and the second sample data with the same performance indicator data deleted are spliced ​​to obtain sample data.

[0075] In the embodiment of the present invention, when the sum of k1 and k2 is equal to K, the first sample data and the second sample data can be directly concatenated, and the first sample data and the second sample data may include the same performance indicator or may not include the same performance indicator.

[0076] When the sum of k1 and k2 is less than K, the first sample data and the second sample data may contain the same performance indicator data. For example, the first sample data and the second sample data may contain accuracy data of 30 degrees. At this time, one performance indicator affects both the qualification test and the non-qualification test. At this time, the same performance indicator data in the first sample data and the second sample data can be deleted, so that the first sample data and the second sample data do not have the same performance indicator.

[0077] Specifically, the above contribution value can be the position ranking of the same performance indicator data in the first sample data and the second sample data. This is because, after obtaining the covariance matrix C of the first matrix H, the eigenvalues ​​and corresponding eigenvectors of the covariance matrix C are calculated; the eigenvectors are sorted according to the size of the eigenvalues; the eigenvectors with the largest first K eigenvalues ​​are retained to obtain the M×K second matrix D. In the step, the larger the eigenvalue, the higher the ranking, indicating that its influence is greater, and thus the corresponding contribution is greater. Conversely, the later the ranking, the smaller its influence is, and thus the smaller the contribution is.

[0078] In an embodiment of the present invention, by splicing the first sample data and the second sample data, the sample data is made to contain both qualified sample data and unqualified sample data to train the classification model, so that the classification model can classify qualified laser rangefinders and unqualified laser rangefinders, thereby increasing the classification accuracy of the classification model.

[0079] Optionally, in the step of training a classification model based on sample data, modeling can be performed based on a convolutional neural network to obtain an initial classification model; the initial classification model can be first trained using experimental performance data of the laser rangefinder to obtain an intermediate classification model; and the intermediate classification model can be trained using sample data to obtain a trained classification model.

[0080] In an embodiment of the present invention, the experimental performance data of the laser rangefinder can be used as the first data set, and the sample data can be used as the second data set. The initial classification model is first trained using the first data set to obtain an intermediate classification model, and the intermediate classification model is trained using the second data set to obtain a trained classification model.

[0081] The experimental performance data includes all performance indicator data, and the sample data includes the performance indicator data retained after dimensionality reduction.

[0082] The initial classification model is first trained through the experimental performance data of the laser rangefinder, and the intermediate classification model is trained through the sample data to obtain a trained classification model, which can further improve the classification accuracy of the classification model.

[0083] In an embodiment of the present invention, target performance data of a laser rangefinder to be detected is obtained, a preset classification model is used to classify the target performance data, and a detection result of the laser rangefinder to be detected is obtained according to the classification result. The target performance data and the classification model are used to classify the laser rangefinder to be detected, which does not require a large amount of manpower, material resources and time, thereby improving the detection efficiency of the laser rangefinder.

[0084] See also Figure 2 , Figure 2 A detection device for a laser rangefinder provided in the present application comprises:

[0085] The first acquisition module 201 is used to acquire target performance data of the laser rangefinder to be detected;

[0086] The classification module 202 is used to classify the target performance data using a preset classification model to obtain a classification result;

[0087] The detection module 203 is used to obtain the detection result of the laser rangefinder to be detected according to the classification result.

[0088] Optionally, the device further comprises:

[0089] A second acquisition module is used to acquire experimental performance data of the laser rangefinder, and perform dimensionality reduction processing on the experimental performance data to obtain sample data;

[0090] The training module is used to train a classification model based on the sample data.

[0091] Optionally, the device further comprises:

[0092] The third acquisition module is used to acquire the comprehensive performance data of the laser rangefinder to be detected, perform dimensionality reduction processing on the comprehensive performance data, and obtain target performance data, wherein the target performance data has the same dimension as the sample data.

[0093] Optionally, the second acquisition module is also used to conduct performance experiments on N laser rangefinders to obtain experimental performance data corresponding to the N laser rangefinders, and the experimental performance data includes M performance index data; the experimental performance data is reduced in dimension by a principal component analysis method to obtain sample data, and the sample data includes K performance index data, where K is less than M.

[0094] Optionally, the second acquisition module is further used to reduce the dimension of experimental performance data corresponding to n1 qualified laser rangefinders by a principal component analysis method to obtain first sample data, wherein the first sample data includes k1 performance index data; reduce the dimension of experimental performance data corresponding to n2 unqualified laser rangefinders by a principal component analysis method to obtain second sample data, wherein the second sample data includes k2 performance index data; and obtain sample data based on the first sample data and the second sample data, wherein the sum of k1 and k2 is greater than or equal to K.

[0095] Optionally, the second acquisition module is also used to, if the first sample data and the second sample data do not have the same performance indicator data, splice the first sample data and the second sample data to obtain sample data; if the first sample data and the second sample data have the same performance indicator data, calculate the contribution values ​​of the same performance indicator data in the first sample data and the second sample data respectively, and delete the same performance indicator data with a smaller contribution value from the first sample data or the second sample data, and splice the first sample data and the second sample data without the same performance indicator data to obtain sample data.

[0096] Optionally, the training module is also used to perform modeling based on a convolutional neural network to obtain an initial classification model; perform a first training on the initial classification model using experimental performance data of the laser rangefinder to obtain an intermediate classification model; and train the intermediate classification model using the sample data to obtain a trained classification model.

[0097] In an embodiment of the present invention, target performance data of a laser rangefinder to be detected is obtained, a preset classification model is used to classify the target performance data, and a detection result of the laser rangefinder to be detected is obtained according to the classification result. The target performance data and the classification model are used to classify the laser rangefinder to be detected, which does not require a large amount of manpower, material resources and time, thereby improving the detection efficiency of the laser rangefinder.

[0098] An embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any laser rangefinder detection method recorded in the above method embodiments.

[0099] An embodiment of the present invention further provides an electronic device, comprising a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to execute part or all of the steps of any one of the laser rangefinder detection methods described in the above method embodiments.

[0100] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0101] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0102] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0103] 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 on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0104] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software program modules.

[0105] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0106] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0107] The embodiments of the present invention are described in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A detection method for a laser rangefinder, characterized in that: The method comprises: Obtain target performance data of the laser rangefinder to be tested; Performing a performance experiment on N laser rangefinders to obtain experimental performance data corresponding to the N laser rangefinders, wherein the experimental performance data includes M performance index data; the N laser rangefinders include n1 qualified laser rangefinders and n2 unqualified laser rangefinders; Performing dimensionality reduction on the experimental performance data corresponding to n1 qualified laser rangefinders by a principal component analysis method to obtain first sample data, wherein the first sample data includes k1 performance indicator data; Performing dimensionality reduction on the experimental performance data corresponding to n2 unqualified laser rangefinders by a principal component analysis method to obtain second sample data, wherein the second sample data includes k2 performance indicator data; Based on the first sample data and the second sample data, sample data is obtained, where the sample data includes K performance indicator data, wherein the sum of k1 and k2 is greater than or equal to K, and K is less than M; If the first sample data and the second sample data do not have the same performance indicator data, concatenating the first sample data and the second sample data to obtain sample data; If the first sample data and the second sample data have the same performance indicator data, then the contribution values ​​of the same performance indicator data in the first sample data and the second sample data are calculated respectively, and the same performance indicator data with a smaller contribution value is deleted from the first sample data or the second sample data, and the first sample data and the second sample data without the same performance indicator data are concatenated to obtain sample data; the contribution value is the position sorting of the same performance indicator data in the first sample data and the second sample data; According to the sample data, a classification model is obtained by training; Classifying the target performance data using a preset classification model to obtain a classification result; The detection result of the laser rangefinder to be detected is obtained according to the classification result.

2. The method according to claim 1, characterized in that Before the step of classifying the target performance data by using a preset classification model to obtain a classification result, the method further includes: The comprehensive performance data of the laser rangefinder to be detected is obtained, and the dimensionality reduction process is performed on the comprehensive performance data to obtain target performance data, wherein the target performance data has the same dimension as the sample data.

3. The method according to claim 1, characterized in that The step of training a classification model according to the sample data comprises: Modeling is performed based on convolutional neural networks to obtain an initial classification model; Performing a first training on the initial classification model using experimental performance data of the laser rangefinder to obtain an intermediate classification model; The intermediate classification model is trained using the sample data to obtain a trained classification model.

4. A detection device for a laser rangefinder, characterized in that: The device comprises: A first acquisition module is used to acquire target performance data of the laser rangefinder to be detected; The second acquisition module is used to perform performance experiments on N laser rangefinders to obtain experimental performance data corresponding to the N laser rangefinders, and the experimental performance data includes M performance index data; the N laser rangefinders include n1 qualified laser rangefinders and n2 unqualified laser rangefinders; the experimental performance data corresponding to the n1 qualified laser rangefinders are reduced in dimension by a principal component analysis method to obtain first sample data, and the first sample data includes k1 performance index data; the experimental performance data corresponding to the n2 unqualified laser rangefinders are reduced in dimension by a principal component analysis method to obtain second sample data, and the second sample data includes k2 performance index data; based on the first sample data and the second sample data, sample data is obtained, and the sample data includes K performance index data, wherein, The sum of k1 and k2 is greater than or equal to K, and K is less than M; if the first sample data and the second sample data do not have the same performance indicator data, the first sample data and the second sample data are spliced ​​to obtain sample data; if the first sample data and the second sample data have the same performance indicator data, the contribution values ​​of the same performance indicator data in the first sample data and the second sample data are calculated respectively, and the same performance indicator data with a smaller contribution value is deleted from the first sample data or the second sample data, and the first sample data and the second sample data with the same performance indicator data deleted are spliced ​​to obtain sample data; the contribution value is the position sorting of the same performance indicator data in the first sample data and the second sample data; A training module, used for training a classification model based on the sample data; A classification module, used to classify the target performance data through a preset classification model to obtain a classification result; A detection module is used to obtain a detection result of the laser rangefinder to be detected according to the classification result.

5. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the detection method of the laser rangefinder according to any one of claims 1 to 3 when executing the computer program.

6. 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 in the detection method of the laser rangefinder according to any one of claims 1 to 3 are implemented.

Images