Intelligent shaft type identification method, device, electronic equipment and storage medium

Abstract

The present invention discloses an intelligent axle type recognition method, device, electronic device and storage medium. The method includes: obtaining multiple vehicle images and first sound data of a target vehicle passing through a metering guide section through a camera and a first sound sensor, determining a first axle type recognition result from each vehicle image of the multiple vehicle images, determining at least one reference sound data set based on the sound data of at least one axle type, obtaining a metering value and second sound data of the target vehicle passing through a metering section through a metering monitoring device and a second sound sensor, determining the axle type of the target vehicle based on the first sound data, the second sound data and at least one reference sound data set, obtaining a target axle type, determining a metering threshold corresponding to the target axle type, and determining that the target vehicle is overweight if the metering value is greater than the metering threshold. The implementation of the present application improves the accuracy of vehicle overweight detection.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle overweight detection, and in particular to an intelligent axle type recognition method, device, electronic equipment and storage medium. Background Art

[0002] If a vehicle is overloaded while driving, it will most likely lead to a series of serious consequences, which can easily cause great danger.

[0003] At the entrance of the highway, vehicles are generally checked for overweight to prevent them from being overweight. However, if the axle type of the vehicle is misidentified, the vehicle weight limit will not be determined accurately, resulting in inaccurate overweight detection. Therefore, how to perform accurate axle type identification to improve the accuracy of vehicle overweight detection needs to be solved urgently. Summary of the invention

[0004] The embodiments of the present application provide an intelligent axle type recognition method, device, electronic device and storage medium, which accurately identify the axle type of a target vehicle and determine the corresponding measurement threshold of the target vehicle. When the measurement value of the target vehicle is greater than the measurement threshold, the target vehicle is determined to be overweight, thereby improving the accuracy of vehicle overweight detection.

[0005] In a first aspect, an embodiment of the present application provides an intelligent axle type recognition method, which is applied to a metering system, wherein the metering system includes a metering monitoring device, a first sound sensor, a second sound sensor, and a camera, wherein the first sound sensor and the camera are located in a metering guidance section, and the second sound sensor and the metering monitoring device are located in a metering section. The method includes:

[0006] Acquire multiple vehicle images of the target vehicle passing through the metering guidance section through a camera, and acquire first sound data of the target vehicle passing through the metering guidance section through a first sound sensor;

[0007] Extracting image features from each vehicle image of the plurality of vehicle images to obtain an image feature set;

[0008] Determine a first axis type recognition result based on the image feature set; the first axis type recognition result includes at least one axis type;

[0009] Acquire sound data of at least one axis type to obtain at least one reference sound data set; each axis type corresponds to a reference sound data set;

[0010] Obtaining a metering value when the target vehicle passes through a metering section through a metering monitoring device, and obtaining second sound data when the target vehicle passes through a metering section through a second sound sensor;

[0011] Determine the axle type of the target vehicle according to the first sound data, the second sound data, and at least one reference sound data set to obtain a target axle type;

[0012] Determine the measurement threshold corresponding to the target axis type;

[0013] If the measurement value is greater than the measurement threshold, it is determined that the target vehicle is overweight.

[0014] In a second aspect, an embodiment of the present application provides an intelligent axle type recognition device, which is applied to a metering system. The metering system includes a metering monitoring device, a first sound sensor, a second sound sensor, and a camera. The first sound sensor and the camera are located in a metering guide section, and the second sound sensor and the metering monitoring device are located in a metering section. The device includes: an acquisition unit and a processing unit;

[0015] an acquisition unit, used to acquire multiple vehicle images when the target vehicle passes through the metering guidance section through a camera, and to acquire first sound data when the target vehicle passes through the metering guidance section through a first sound sensor;

[0016] A processing unit, configured to extract image features from each of the plurality of vehicle images to obtain an image feature set;

[0017] Determine a first axis type recognition result based on the image feature set; the first axis type recognition result includes at least one axis type;

[0018] An acquisition unit, used to acquire sound data of at least one axis type to obtain at least one reference sound data set; each axis type corresponds to a reference sound data set;

[0019] A processing unit, used to obtain a metering value when the target vehicle passes through the metering section through a metering monitoring device, and to obtain second sound data when the target vehicle passes through the metering section through a second sound sensor;

[0020] Determine the axle type of the target vehicle according to the first sound data, the second sound data, and at least one reference sound data set to obtain a target axle type;

[0021] Determine the measurement threshold corresponding to the target axis type;

[0022] If the measurement value is greater than the measurement threshold, it is determined that the target vehicle is overweight.

[0023] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor so that the electronic device executes the method of the first aspect.

[0024] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.

[0025] In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, so that a computer executes the method of the first aspect.

[0026] The implementation of the present invention has the following beneficial effects:

[0027] It can be seen that the intelligent axle type recognition method described in the embodiment of the present invention is applied to a metering system, wherein the metering system includes a metering monitoring device, a first sound sensor, a second sound sensor, and a camera. The first sound sensor and the camera are located in a metering guide section, and the second sound sensor and the metering monitoring device are located in a metering section. The camera is used to obtain multiple vehicle images of a target vehicle passing through a metering guide section, and the first sound data of the target vehicle passing through a metering guide section is obtained through the first sound sensor. The metering value of the target vehicle passing through the metering section is obtained through the metering monitoring device, and the second sound data of the target vehicle passing through the metering section is obtained through the second sound sensor. At least one reference sound data set can be determined based on the multiple vehicle images, and then the axle type of the target vehicle can be determined based on the first sound data, the second sound data, and at least one reference sound data set to obtain the target axle type, obtain the metering threshold corresponding to the target axle type, and when the metering value of the target vehicle is greater than the metering threshold, it is determined that the target vehicle is overweight, thereby improving the accuracy of vehicle overweight detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the implementation methods of the present application or the background technology, the drawings required for use in the implementation methods of the present application or the background technology will be described below.

[0029] Figure 1 It is a structural schematic diagram of a metering system provided in an embodiment of the present application;

[0030] Figure 2 is a flow chart of an intelligent shaft type recognition method provided by an embodiment of the present application;

[0031] Figure 3 is a flow chart of determining a matching value corresponding to a first axis type provided by an embodiment of the present application;

[0032] Figure 4 It is a structural schematic diagram of an intelligent shaft type identification device provided in an embodiment of the present application;

[0033] Figure 5It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the implementation mode of the present application will be clearly and completely described below in conjunction with the drawings in the implementation mode of the present application. Obviously, the described implementation mode is only a part of the implementation mode of the present application, not all the implementation modes. Based on the implementation mode in the present application, all other implementation modes obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0035] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0036] Reference to "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0037] See also Figure 1 , Figure 1 It is a structural schematic diagram of a metering system provided in an embodiment of the present application. The metering system 10 includes a metering monitoring device 101, a first sound sensor 102, a second sound sensor 103, and a camera 104.

[0038] In this embodiment, the first sound sensor and the camera are located in the metering guide section, and the second sound sensor and the metering monitoring device are located in the metering section. First, multiple vehicle images of the target vehicle passing through the metering guide section are obtained through the camera, and the first sound data of the target vehicle passing through the metering guide section is obtained through the first sound sensor. Then, image features are extracted from each vehicle image of the multiple vehicle images to obtain an image feature set, and a first axle type recognition result is determined based on the image feature set, wherein the first axle type recognition result includes at least one axle type. Then, the sound data of at least one axle type is obtained to obtain at least one reference sound data set, wherein each axle type corresponds to a reference sound data set, and then the metering value of the target vehicle passing through the metering section is obtained through the metering monitoring device, and the second sound data of the target vehicle passing through the metering section is obtained through the second sound sensor. The axle type of the target vehicle is determined according to the first sound data, the second sound data and at least one reference sound data set to obtain the target axle type, and finally the metering threshold corresponding to the target axle type is determined. If the metering value is greater than the metering threshold, it is determined that the target vehicle is overweight, thereby improving the accuracy of vehicle overweight detection.

[0039] It needs to be explained that the metering guidance section mainly plays the role of guiding vehicles into the metering state, preliminarily collecting relevant data and preparing for formal metering. The vehicle information obtained in the metering guidance section, such as axle type, speed, acceleration, etc., can provide reference and supplement for the metering work of the metering section, which is helpful for more accurate metering. The metering guidance section is the prelude to the metering section. The metering guidance section and the metering section are continuous in space. Vehicles can transition naturally during driving to ensure a smooth metering process.

[0040] See also Figure 2 , Figure 2 This is a flow chart of an intelligent shaft type recognition method provided by an embodiment of the present application, including but not limited to the following steps:

[0041] S201: Acquire multiple vehicle images when a target vehicle passes through a metering guidance section through a camera, and acquire first sound data when the target vehicle passes through a metering guidance section through a first sound sensor.

[0042] In this embodiment, the camera is rotatable and the rotation angle can be 360 ​​degrees, ensuring that the camera can clearly capture the full view of the vehicle and the driving process of the vehicle on the road section, covering key parts such as the front, side and rear of the vehicle, and the axle. The first sound sensor can be set on the road surface of the metering guide section, or on a crossbar or column on the road surface to ensure that the first sound sensor can accurately obtain the sound data of the target vehicle. When the target vehicle enters the metering guidance section, the camera and the first sound sensor should start working at the same time. The camera continuously captures images of the vehicle passing by and stores these images in a certain format and frequency. The sound sensor collects the sound generated during the vehicle's driving in real time and converts the sound signal into digital data for recording, thereby obtaining multiple vehicle images when the target vehicle passes through the metering guidance section and the third sound data when the target vehicle passes through the metering guidance section. Then, the curvature and flatness of the metering guidance section are obtained through the camera. Specifically, image processing technology is used to extract features such as road edges and markings in the image captured by the camera to obtain multiple feature points. Then, curve fitting is performed on the extracted feature points. Polynomial curves or spline curves can be used to approximate the shape of the road. Through mathematical analysis of the fitting curve, the curvature of the curve at different positions is calculated to obtain the curvature of the metering guidance section. The texture characteristics of the road surface are analyzed. The uneven road surface texture will show irregular and large changes. The flatness is evaluated based on the extracted texture characteristics to obtain the flatness of the metering guidance section. Exemplarily, a first adjustment parameter corresponding to the curvature and a second adjustment parameter corresponding to the flatness are determined. Specifically, a first mapping relationship between the curvature and the adjustment parameter and a second mapping relationship between the flatness and the adjustment parameter are pre-stored, and the first adjustment parameter corresponding to the curvature is determined based on the first mapping relationship, and the second adjustment parameter corresponding to the flatness is determined based on the second mapping relationship. Exemplarily, the third sound data is adjusted according to the first adjustment parameter and the second adjustment parameter to obtain the first sound data. Specifically, the ratio between the first adjustment parameter and the second adjustment parameter is first determined, and the sum of the ratios of the first adjustment parameter and the second adjustment parameter is 1, and then the third sound data is adjusted specifically according to the following formula:

[0043]

[0044] in, is the first sound data, is the third sound data, is the proportion of the first adjustment parameter, is the proportion of the second adjustment parameter, is the first adjustment parameter, is the second adjustment parameter.

[0045] It should be explained that since the road surface of the metering section is relatively flat and the vehicle's driving speed on the metering section is relatively stable, the flatness and curvature of the road surface have relatively little impact on the vehicle at this time, so this implementation does not consider the impact of the flatness and curvature of the metering section on the sound data.

[0046] It can be seen that the rotatable 360-degree camera and the reasonably set sound sensors can comprehensively and accurately obtain the image and sound data of the vehicle. The image processing technology is used to obtain the curvature and flatness of the metering guide section, and the corresponding adjustment parameters are determined, so that the metering system can adapt to different road conditions, improving the versatility and flexibility of the metering system in various environments. Since the road surface of the metering section is relatively flat and the vehicle travels at a steady speed, the influence of flatness and curvature on the sound data is not considered, which can reduce the amount of calculation and the complexity of analysis, and improve the efficiency of data processing.

[0047] S202: Extracting image features from each of the multiple vehicle images to obtain an image feature set.

[0048] In this embodiment, image processing technology, such as edge detection algorithm, is first used to extract the axle features of the vehicle from multiple vehicle images, and then a feature extraction algorithm, such as scale-invariant feature transformation algorithm, is used to detect multiple key points in the image. Then, each vehicle image is sorted and combined according to the extracted axle features and multiple key points to form an image feature set.

[0049] S203: Determine a first axis type recognition result based on the image feature set.

[0050] In this embodiment, the first axis type recognition result includes at least one axis type. First, an axis type feature database is established, which contains typical image features of various axis types. These features are obtained by analyzing and extracting a large number of images of known axis types. Then, a machine learning or deep learning algorithm is used to perform axis type recognition. The extracted image feature set is input into the trained model. The model will output the axis type recognition result according to the degree of matching between the input features and the axis type features in the database. For example, if a convolutional neural network is used, it is usually necessary to properly organize and preprocess the image feature set to meet the input requirements of the network. The network will automatically learn the complex relationship between the features and the axis type, and give a predicted axis type. After obtaining the preliminary recognition result, the final axis type can be determined by setting a threshold or probability, and the axis type with a predicted probability exceeding the threshold is included in the first axis type recognition result.

[0051] S204: Acquire at least one axial sound data set to obtain at least one reference sound data set.

[0052] In this embodiment, each axle type corresponds to a reference sound data set, and the reference sound data set is obtained in advance by collecting, analyzing and sorting the sounds of a large number of coaxial vehicles in various driving conditions. After obtaining at least one axle type that the target vehicle may correspond to, determine the reference sound data set corresponding to each axle type in at least one axle type, and obtain at least one reference sound data set. For example, if the first axle type recognition result includes axle type 1, axle type 2 and axle type 3, then there will be three groups of sound data corresponding to axle type 1, axle type 2 and axle type 3 respectively. The sound data of axle type 1 constitutes one reference sound data set, the sound data of axle type 2 constitutes another reference sound data set, and the sound data of axle type 3 constitutes another reference sound data set.

[0053] It should be explained that the sound data in this embodiment may include engine sound, exhaust sound, tire and road friction sound, transmission system sound, vehicle internal mechanical operation sound, as well as the frequency, amplitude, timbre and other characteristics of these sounds.

[0054] It can be seen that by establishing a rich reference sound data set corresponding to each axle type in advance, more reliable basis and comparison samples can be provided for accurate judgment of the axle type, reducing the possibility of misjudgment. Classifying the sound data into different data sets according to the axle type is conducive to orderly management of the data, and when the data needs to be updated or supplemented, operations can be performed more targetedly, and the diverse sound characteristics of different axle types can be coped with, making the entire measurement system applicable to a wider range of vehicles, rather than just limited to a few common vehicles.

[0055] S205: Obtaining the metering value of the target vehicle when it passes through the metering section through the metering monitoring device, and obtaining the second sound data of the target vehicle when it passes through the metering section through the second sound sensor.

[0056] In this embodiment, when the target vehicle enters the metering section, the metering monitoring device automatically starts and begins monitoring. The metering monitoring device may use technologies such as pressure sensors and strain gauges. When the vehicle passes, the metering monitoring device senses the pressure applied by the vehicle and converts the pressure into a corresponding metering value. It should be explained that the metering monitoring device can be installed on a specially constructed platform or weighing area, and the vehicle directly drives over the platform or weighing area for metering monitoring. The metering monitoring device can also be embedded in the ground so that the vehicle can be measured and monitored when passing on the ground.

[0057] The second sound sensor is started synchronously with the metering monitoring equipment. When the target vehicle enters the metering section, the sound sensor starts to collect sound signals, and then digitizes the sound signals through analog-to-digital conversion to obtain second sound data.

[0058] S206: Determine the axle type of the target vehicle according to the first sound data, the second sound data, and at least one reference sound data set to obtain a target axle type.

[0059] In this embodiment, each reference sound data set in at least one reference sound data set includes multiple reference sound data, and each reference sound data corresponds to an attribute information. First, the first attribute information of the metering guide section and the second attribute information of the guide section are obtained, wherein the first attribute information includes the road condition and the road surface material of the metering guide section, and the second attribute information includes the road condition and the road surface material of the guide section.

[0060] After obtaining the first attribute information of the metering guide section and the second attribute information of the guide section, the matching value corresponding to each axis type in at least one axis type can be determined according to the first attribute information and the second attribute information to obtain multiple target matching values. First, taking the first axis type as an example, the matching value corresponding to the first axis type is determined, wherein the first axis type is any axis type in at least one axis type. Figure 3 , Figure 3 A flowchart of determining a matching value corresponding to a first axis type provided by an embodiment of the present application includes but is not limited to the following steps:

[0061] S301: Determine first reference sound data corresponding to first attribute information in a first reference sound data set.

[0062] In this embodiment, the first reference sound data set is any reference sound data set in at least one reference sound data set, the first reference sound data set corresponds to a first axis type, and the first axis type is any axis type in the at least one axis type.

[0063] It should be explained that in this embodiment, the axle type may include the number of axles, the arrangement of the axles, the form of the axle group, and the position of the axles in the vehicle, etc., which are not limited here. In this embodiment, different vehicle models have different axle types. After the axle type is determined, the vehicle model can also be clarified. The vehicle model may include the vehicle brand and model, vehicle type, vehicle level, body structure, drive mode, fuel type, etc.

[0064] First, it is necessary to establish a database or index table containing the correspondence between various attribute information and corresponding sound data. This database or index table is pre-established and can be continuously updated and improved. When the first attribute information is obtained, the database or index table is matched according to the first attribute information to find the sound data that matches the first attribute information currently obtained, and it is determined as the first reference sound data.

[0065] It can be seen that comprehensive consideration of various attribute information of the metering guidance section can more comprehensively and meticulously evaluate the degree of fit between the axis type and the section characteristics, thereby obtaining a more accurate axis type judgment result.

[0066] S302: Determine second reference sound data corresponding to second attribute information in the first reference sound data set.

[0067] In this embodiment, the method of determining the first reference sound data is the same as that of obtaining the second attribute information. When the second attribute information is obtained, a match is performed in the database or index table based on the second attribute information to find the sound data that matches the second attribute information currently obtained and determine it as the second reference sound data.

[0068] It can be seen that obtaining the sound data of the metering section and the metering guidance section can provide a more comprehensive understanding of the sound characteristics of the vehicle in the entire metering-related area, reduce the limitations and errors that may exist in the data of a single section, and thus improve the accuracy of the judgment of the vehicle status and characteristics.

[0069] S303: Match the first sound data with the first reference sound data to obtain a first matching value.

[0070] In this embodiment, firstly, a first reference amplitude and a first reference frequency corresponding to the first reference sound data are obtained, and a first amplitude and a first frequency corresponding to the first sound data are obtained.

[0071] Exemplarily, an amplitude difference is determined based on the first amplitude and the first reference amplitude, and an amplitude difference ratio is determined based on the amplitude difference and the first reference amplitude. Specifically, a subtraction operation is first performed based on the first amplitude and the first reference amplitude to determine the amplitude difference, and then the amplitude difference is divided by the first reference amplitude to obtain the amplitude difference ratio.

[0072] Exemplarily, a frequency difference is determined based on the first frequency and the first reference frequency, and a frequency difference ratio is determined based on the frequency difference and the first reference frequency. Specifically, a subtraction operation is first performed based on the first frequency and the first reference frequency to determine the frequency difference, and then the frequency difference is divided by the first reference frequency to obtain the frequency difference ratio.

[0073] Exemplarily, a first target weight corresponding to the amplitude difference ratio and a second target weight corresponding to the frequency difference ratio are determined. Specifically, a first reference weight corresponding to the amplitude difference ratio and a second reference weight corresponding to the frequency difference ratio are first obtained. A mapping relationship between a preset amplitude difference ratio and a reference weight and a mapping relationship between a preset frequency difference ratio and a reference weight may be pre-stored. Based on the mapping relationship, a first reference weight corresponding to the amplitude difference ratio and a second reference weight corresponding to the frequency difference ratio are determined.

[0074] Exemplarily, the target distance between the target vehicle and the first sound sensor when passing the metering guidance section is obtained. Specifically, a distance measurement technology such as laser ranging, radar ranging, or a ranging method based on image analysis can be used to obtain the target distance between the target vehicle and the first sound sensor when passing the metering guidance section.

[0075] Exemplarily, determining the first optimization factor corresponding to the target distance may specifically be to pre-store a mapping relationship between a preset distance and the optimization factor, and determining the first optimization factor corresponding to the target distance based on the mapping relationship.

[0076] Exemplarily, the first reference weight is optimized according to the first optimization factor to obtain the first target weight. Specifically, the first reference weight can be optimized according to the first optimization factor. The specific calculation formula is as follows:

[0077] The first target weight = the first reference weight × (1 + the first optimization factor); the first target weight can be obtained according to the above formula.

[0078] Exemplarily, the target ambient temperature is obtained. Specifically, a temperature sensor can be installed in the metering guide section to measure and transmit ambient temperature data in real time. The speed at which sound propagates in a medium is related to the temperature of the medium. When the temperature rises, the thermal motion of air molecules intensifies and the molecular distance increases, causing the density of the air to decrease. At the same time, the elasticity of the air will also change. Since the speed of sound propagation is related to the elasticity and density of the medium, an increase in temperature will increase the speed of sound propagation, so it is necessary to consider the effect of temperature on the difference in sound frequency.

[0079] Exemplarily, the second optimization factor corresponding to the target ambient temperature is determined. Specifically, a mapping relationship between a preset ambient temperature and the optimization factor may be pre-stored, and the second optimization factor corresponding to the target ambient temperature is determined based on the mapping relationship.

[0080] Exemplarily, the second reference weight is optimized according to the second optimization factor to obtain the second target weight. Specifically, the second reference weight can be optimized according to the second optimization factor. The specific calculation formula is as follows:

[0081] The second target weight = the second reference weight × (1 + the second optimization factor); the second target weight can be obtained according to the above formula.

[0082] It can be seen that by obtaining the distance between the target vehicle and the sound sensor and the ambient temperature and determining the optimization factor accordingly to optimize the weight, the influence of the actual situation on the sound data can be more accurately reflected.

[0083] Exemplarily, a target deviation value corresponding to the first reference sound data and the first sound data is determined based on the amplitude difference ratio, the frequency difference ratio, the first target weight, and the second target weight. Specifically, a target deviation value is obtained by calculation based on the amplitude difference ratio, the frequency difference ratio, the first target weight, and the second target weight. The target deviation value is calculated specifically according to the following formula:

[0084]

[0085] in, is the target deviation value, is the amplitude difference ratio, is the frequency difference ratio, is the first target weight, is the second target weight.

[0086] Exemplarily, a first matching value between the first reference sound data and the first sound data is determined based on a target deviation value. Specifically, a reference matching value corresponding to the target deviation value is first determined. The mapping relationship between a preset deviation value and a matching value may be pre-stored, and the reference matching value corresponding to the target deviation value is determined based on the mapping relationship.

[0087] Exemplarily, historical matching values ​​between reference sound data and actual sound data within a preset time period are obtained to obtain k historical matching values, where k is a positive integer and each matching value corresponds to a matching value determination moment. Specifically, the historical matching value is matching value data recorded during similar experiments or monitoring processes within a historical time period.

[0088] Exemplarily, fitting is performed based on k historical matching values ​​and the corresponding matching value determination moments to obtain a fitting straight line, wherein the horizontal axis of the fitting straight line is time and the vertical axis is the matching value. Specifically, the k historical matching values ​​and the corresponding matching value determination moments are used as data points for fitting. Fitting can be performed using a linear regression method or a polynomial fitting method. The purpose of fitting is to find a straight line that can better describe the trend of historical matching values ​​changing over time. The horizontal axis of the obtained fitting straight line is time, and the vertical axis is the historical matching value.

[0089] Exemplarily, the target slope of the fitting line is obtained. Specifically, by arbitrarily selecting two points on the fitting line, the slope corresponding to the fitting line can be calculated to obtain the target slope.

[0090] Exemplarily, the target fine-tuning parameter corresponding to the target slope is determined. Specifically, a mapping relationship between a preset slope and an optimization parameter may be pre-stored, and the target fine-tuning parameter corresponding to the target slope is determined based on the mapping relationship.

[0091] The reference matching value is fine-tuned according to the target fine-tuning parameter to obtain a first matching value between the first reference sound data and the first sound data. Specifically, the reference matching value can be optimized according to the target fine-tuning parameter. The specific calculation formula is as follows:

[0092] The first matching value = reference matching value × (1 + target fine-tuning parameter); the first matching value can be obtained according to the above formula.

[0093] It can be seen that by combining the amplitude difference ratio, the frequency difference ratio and different weights to determine the target deviation value, multiple key features of the sound data can be comprehensively considered to make the deviation assessment more comprehensive and accurate. The reference matching value is determined by using a pre-set mapping relationship and fine-tuned in combination with the trend of the historical matching value. This can more accurately reflect the degree of matching between the current sound data and improve the accuracy of the matching. Taking into account the influence of the time factor on the matching value, the slope of the fitting line is obtained and the fine-tuning parameters are determined accordingly, so that the determination of the matching value can adapt to the changes that may occur in the sound data over time.

[0094] S304: Match the second sound data with the second reference sound data to obtain a second matching value.

[0095] In this embodiment, the method for determining the second matching value is the same as the method for determining the first matching value. The first sound data is matched with the first reference sound data to obtain the first matching value, and the second sound data can be matched with the second reference sound data to obtain the second matching value, which will not be repeated here.

[0096] S305: Determine a target matching value corresponding to the first axis type according to the first matching value and the second matching value.

[0097] In this embodiment, illustratively, the third reference weight corresponding to the first matching value and the fourth reference weight corresponding to the second matching value are determined. Specifically, a mapping relationship between preset matching values ​​and reference weights may be pre-stored, and the third reference weight corresponding to the first matching value and the fourth reference weight corresponding to the second matching value are determined based on the mapping relationship. It should be explained that the sum of the third reference weight and the fourth reference weight is 1.

[0098] Exemplarily, to obtain the first acceleration of the target vehicle in the metering guidance section, the speed of the target vehicle in the metering guidance section can be determined by a camera of the metering guidance section, and then the first acceleration of the target vehicle in the metering guidance section can be determined based on the speed of the target vehicle in the metering guidance section.

[0099] Exemplarily, the first adjustment parameter corresponding to the first acceleration is determined. Specifically, a mapping relationship between a preset acceleration and an adjustment parameter may be pre-stored, and the first adjustment parameter corresponding to the first acceleration is determined based on the mapping relationship.

[0100] Exemplarily, the third reference weight is adjusted according to the first adjustment parameter to obtain the third target weight. Specifically, the third reference weight can be optimized according to the first adjustment parameter. The specific calculation formula is as follows:

[0101] The third target weight = the third reference weight × (1 + the first adjustment parameter); the third target weight can be obtained according to the above formula.

[0102] Exemplarily, the second acceleration of the target vehicle in the metering section is obtained. A camera can also be set in the metering section. The speed of the target vehicle in the metering section can be determined by the camera of the metering section, and then the second acceleration of the target vehicle in the metering section is determined according to the speed of the target vehicle in the metering section.

[0103] Exemplarily, the second adjustment parameter corresponding to the second acceleration is determined. Specifically, a mapping relationship between a preset acceleration and an adjustment parameter may be pre-stored, and the second adjustment parameter corresponding to the second acceleration is determined based on the mapping relationship.

[0104] Exemplarily, the fourth reference weight is adjusted according to the second adjustment parameter to obtain the fourth target weight. Specifically, the fourth reference weight can be optimized according to the second adjustment parameter. The specific calculation formula is as follows:

[0105] The fourth target weight=the fourth reference weight×(1+the second adjustment parameter); the fourth target weight can be obtained according to the above formula.

[0106] Exemplarily, the target matching value is obtained by calculating based on the first matching value, the second matching value, the third target weight, and the fourth target weight. Specifically, the target matching value is obtained by calculating based on the first matching value, the second matching value, the third target weight, and the fourth target weight. Specifically, the target deviation value is calculated according to the following formula:

[0107]

[0108] in, is the target matching value, is the first matching value, is the second matching value, is the third objective weight, is the fourth target weight.

[0109] It can be seen that comprehensively considering the acceleration and matching values ​​of different road sections to determine the final target matching value makes the matching result more accurate and reliable. Adjusting the weight according to the acceleration of the target vehicle in different road sections can reflect the changes in the vehicle's driving status in real time, making the matching process more in line with the actual situation.

[0110] S207: Determine a measurement threshold corresponding to the target axis type.

[0111] In this embodiment, after the target axle type is determined, the metering threshold corresponding to the target axle type can be determined according to the standards and specifications of vehicle metering. It should be noted that in this embodiment, not only the metering threshold corresponding to the target axle type can be determined, but also the axle load excess value, vehicle size excess value, tire load excess value, and cargo volume excess value corresponding to the target axle type can be determined.

[0112] S208: If the measurement value is greater than the measurement threshold, it is determined that the target vehicle is overweight.

[0113] In this embodiment, if the metering value of the target vehicle obtained by the metering monitoring device when passing through the metering section is greater than the metering threshold, it means that the actual condition of the target vehicle exceeds the prescribed safety standard, and the target vehicle is determined to be overweight. An obvious warning light, warning slogan or display screen is set on the metering monitoring device to directly display the vehicle overweight information. A voice warning can also be issued through a speaker to inform the driver that the vehicle is overweight. If the unit to which the vehicle belongs or the driver has pre-registered the relevant information, the overweight reminder can be pushed through text messages, emails, etc. If the vehicle is equipped with an intelligent vehicle-mounted terminal, the overweight information can be sent directly to the vehicle-mounted terminal device for display and reminder.

[0114] It can be seen that clear overweight reminders can help regulate the transportation behavior of drivers and their units, reduce the occurrence of overweight, and timely reminders of overweight vehicles can help avoid potential risks such as traffic accidents and road damage that may be caused by overweight vehicles.

[0115] In summary, the implementation of the present invention has the following beneficial effects:

[0116] It can be seen that the intelligent axle type recognition method described in the embodiment of the present invention is applied to a metering system, wherein the metering system includes a metering monitoring device, a first sound sensor, a second sound sensor, and a camera. The first sound sensor and the camera are located in a metering guide section, and the second sound sensor and the metering monitoring device are located in a metering section. The camera is used to obtain multiple vehicle images of a target vehicle passing through a metering guide section, and the first sound data of the target vehicle passing through a metering guide section is obtained through the first sound sensor. The metering value of the target vehicle passing through the metering section is obtained through the metering monitoring device, and the second sound data of the target vehicle passing through the metering section is obtained through the second sound sensor. At least one reference sound data set can be determined based on the multiple vehicle images, and then the axle type of the target vehicle can be determined based on the first sound data, the second sound data, and at least one reference sound data set to obtain the target axle type, obtain the metering threshold corresponding to the target axle type, and when the metering value of the target vehicle is greater than the metering threshold, it is determined that the target vehicle is overweight, thereby improving the accuracy of vehicle overweight detection.

[0117] See also Figure 4 , Figure 4 It is a structural schematic diagram of an intelligent axle type recognition device provided by an embodiment of the present application, which is applied to a metering system, wherein the metering system includes a metering monitoring device, a first sound sensor, a second sound sensor, and a camera, wherein the first sound sensor and the camera are located in a metering guide section, and the second sound sensor and the metering monitoring device are located in a metering section; the intelligent axle type recognition device 400 includes: an acquisition unit 401 and a processing unit 402;

[0118] An acquisition unit 401 is used to acquire multiple vehicle images when a target vehicle passes through a metering guidance section through a camera, and acquire first sound data when the target vehicle passes through a metering guidance section through a first sound sensor;

[0119] A processing unit 402 is used to extract image features from each of the plurality of vehicle images to obtain an image feature set;

[0120] Determine a first axis type recognition result based on the image feature set; the first axis type recognition result includes at least one axis type;

[0121] An acquisition unit 401 is used to acquire sound data of at least one axis type to obtain at least one reference sound data set; each axis type corresponds to a reference sound data set;

[0122] The processing unit 402 is used to obtain the metering value of the target vehicle when it passes through the metering section through the metering monitoring device, and obtain the second sound data of the target vehicle when it passes through the metering section through the second sound sensor;

[0123] Determine the axle type of the target vehicle according to the first sound data, the second sound data, and at least one reference sound data set to obtain a target axle type;

[0124] Determine the measurement threshold corresponding to the target axis type;

[0125] If the measurement value is greater than the measurement threshold, it is determined that the target vehicle is overweight.

[0126] In some possible implementations, in determining the axle type of the target vehicle according to the first sound data, the second sound data, and at least one reference sound data set to obtain the target axle type, the processing unit 402 is specifically configured to:

[0127] Acquire first attribute information of the metering guidance section;

[0128] Acquire second attribute information of the guidance section;

[0129] According to the following steps A1-A5, a matching value corresponding to each axis type in at least one axis type is determined according to the first attribute information and the second attribute information to obtain multiple target matching values, which are specifically the following steps:

[0130] A1. Determine first reference sound data corresponding to the first attribute information in the first reference sound data set; the first reference sound data set is any reference sound data set in at least one reference sound data set, the first reference sound data set corresponds to a first axis type, and the first axis type is any axis type in at least one axis type;

[0131] A2. determining second reference sound data corresponding to the second attribute information in the first reference sound data set;

[0132] A3. Matching the first sound data with the first reference sound data to obtain a first matching value;

[0133] A4. Match the second sound data with the second reference sound data to obtain a second matching value;

[0134] A5. Determine a target matching value corresponding to the first axis type according to the first matching value and the second matching value;

[0135] The maximum value among multiple target matching values ​​is selected, and the axis type corresponding to the maximum value is used as the target axis type.

[0136] In some possible implementations, in matching the first sound data with the first reference sound data to obtain the first matching value, the processing unit 402 is specifically configured to:

[0137] Acquire a first reference amplitude and a first reference frequency corresponding to the first reference sound data;

[0138] Acquire a first amplitude and a first frequency corresponding to the first sound data;

[0139] Determine an amplitude difference based on the first amplitude and the first reference amplitude, and determine an amplitude difference ratio based on the amplitude difference and the first reference amplitude;

[0140] Determine a frequency difference based on the first frequency and the first reference frequency, and determine a frequency difference ratio based on the frequency difference and the first reference frequency;

[0141] Determine a first target weight corresponding to the amplitude difference ratio value and a second target weight corresponding to the frequency difference ratio value;

[0142] Determine a target deviation value corresponding to the first reference sound data and the first sound data based on the amplitude difference ratio value, the frequency difference ratio value, the first target weight value, and the second target weight value;

[0143] A first matching value between the first reference sound data and the first sound data is determined based on the target deviation value.

[0144] In some possible implementations, in determining the first target weight corresponding to the amplitude difference ratio value and the second target weight corresponding to the frequency difference ratio value, the processing unit 402 is specifically configured to:

[0145] Obtain a first reference weight corresponding to the amplitude difference ratio value and a second reference weight corresponding to the frequency difference ratio value;

[0146] Acquiring a target distance between the target vehicle and the first sound sensor when the target vehicle passes through the metering guidance section;

[0147] determining a first optimization factor corresponding to the target distance;

[0148] Optimizing the first reference weight according to the first optimization factor to obtain a first target weight;

[0149] Get the target ambient temperature;

[0150] determining a second optimization factor corresponding to the target ambient temperature;

[0151] The second reference weight is optimized according to the second optimization factor to obtain a second target weight.

[0152] In some possible implementations, in determining the first matching value between the first reference sound data and the first sound data based on the target deviation value, the processing unit 402 is specifically configured to:

[0153] Determine a reference matching value corresponding to the target deviation value;

[0154] Obtaining historical matching values ​​between reference sound data and actual sound data within a preset time period, and obtaining k historical matching values; k is a positive integer, and each matching value corresponds to a matching value determination time;

[0155] According to k historical matching values ​​and the corresponding matching value determination time, fitting is performed to obtain a fitting straight line; the horizontal axis of the fitting straight line is time and the vertical axis is the matching value;

[0156] Get the target slope of the fitted straight line;

[0157] determining a target fine-tuning parameter corresponding to the target slope;

[0158] The reference matching value is fine-tuned according to the target fine-tuning parameter to obtain a first matching value between the first reference sound data and the first sound data.

[0159] In some possible implementations, in determining the target matching value corresponding to the first axis type according to the first matching value and the second matching value, the processing unit 402 is specifically configured to:

[0160] Determine a third reference weight corresponding to the first matching value and a fourth reference weight corresponding to the second matching value;

[0161] Acquiring a first acceleration of the target vehicle in the metering guidance section;

[0162] determining a first adjustment parameter corresponding to the first acceleration;

[0163] Adjust the third reference weight according to the first adjustment parameter to obtain a third target weight;

[0164] Obtaining a second acceleration of the target vehicle in the metering section;

[0165] determining a second adjustment parameter corresponding to the second acceleration;

[0166] Adjust the fourth reference weight according to the second adjustment parameter to obtain a fourth target weight;

[0167] A target matching value is obtained by performing calculations based on the first matching value, the second matching value, the third target weight, and the fourth target weight.

[0168] In some possible implementations, in acquiring the first sound data when the target vehicle passes through the metering guidance section through the first sound sensor, the processing unit 402 is specifically configured to:

[0169] Acquiring third sound data when the target vehicle passes through the metering guidance section through the first sound sensor;

[0170] The curvature and flatness of the measurement guidance section are obtained through the camera;

[0171] Determining a first adjustment parameter corresponding to the curvature and a second adjustment parameter corresponding to the flatness;

[0172] The third sound data is adjusted according to the first adjustment parameter and the second adjustment parameter to obtain the first sound data.

[0173] See also Figure 5 , Figure 5 Schematic diagram of the structure of an electronic device provided by the embodiment of the present application. Figure 5 As shown, the electronic device 500 includes a transceiver 501, a processor 502 and a memory 503. They are connected via a bus 504. The memory 503 is used to store computer programs and data, and the transceiver 501 is used to transmit the data stored in the memory 503 to the processor 502. The electronic device 500 includes a controller of a metering system, and the metering system includes a metering monitoring device, a first sound sensor, a second sound sensor, and a camera. The first sound sensor and the camera are located in the metering guidance section, and the second sound sensor and the metering monitoring device are located in the metering section. The above program includes instructions for executing the following steps:

[0174] Acquire multiple vehicle images of the target vehicle passing through the metering guidance section through a camera, and acquire first sound data of the target vehicle passing through the metering guidance section through a first sound sensor;

[0175] Extracting image features from each vehicle image of the plurality of vehicle images to obtain an image feature set;

[0176] Determine a first axis type recognition result based on the image feature set; the first axis type recognition result includes at least one axis type;

[0177] Acquire sound data of at least one axis type to obtain at least one reference sound data set; each axis type corresponds to a reference sound data set;

[0178] Obtaining a metering value when the target vehicle passes through a metering section through a metering monitoring device, and obtaining second sound data when the target vehicle passes through a metering section through a second sound sensor;

[0179] Determine the axle type of the target vehicle according to the first sound data, the second sound data, and at least one reference sound data set to obtain a target axle type;

[0180] Determine the measurement threshold corresponding to the target axis type;

[0181] If the measurement value is greater than the measurement threshold, it is determined that the target vehicle is overweight.

[0182] In some possible implementations, in terms of determining the axle type of the target vehicle according to the first sound data, the second sound data, and at least one reference sound data set to obtain the target axle type, the program includes instructions for performing the following steps:

[0183] Acquire first attribute information of the metering guidance section;

[0184] Acquire second attribute information of the guidance section;

[0185] According to the following steps A1-A5, a matching value corresponding to each axis type in at least one axis type is determined according to the first attribute information and the second attribute information to obtain multiple target matching values, which are specifically the following steps:

[0186] A1. Determine first reference sound data corresponding to the first attribute information in the first reference sound data set; the first reference sound data set is any reference sound data set in at least one reference sound data set, the first reference sound data set corresponds to a first axis type, and the first axis type is any axis type in at least one axis type;

[0187] A2. determining second reference sound data corresponding to the second attribute information in the first reference sound data set;

[0188] A3. Matching the first sound data with the first reference sound data to obtain a first matching value;

[0189] A4. Match the second sound data with the second reference sound data to obtain a second matching value;

[0190] A5. Determine a target matching value corresponding to the first axis type according to the first matching value and the second matching value;

[0191] The maximum value among multiple target matching values ​​is selected, and the axis type corresponding to the maximum value is used as the target axis type.

[0192] In some possible implementations, in terms of matching the first sound data with the first reference sound data to obtain a first matching value, the program includes instructions for performing the following steps:

[0193] Acquire a first reference amplitude and a first reference frequency corresponding to the first reference sound data;

[0194] Acquire a first amplitude and a first frequency corresponding to the first sound data;

[0195] Determine an amplitude difference based on the first amplitude and the first reference amplitude, and determine an amplitude difference ratio based on the amplitude difference and the first reference amplitude;

[0196] Determine a frequency difference based on the first frequency and the first reference frequency, and determine a frequency difference ratio based on the frequency difference and the first reference frequency;

[0197] Determine a first target weight corresponding to the amplitude difference ratio value and a second target weight corresponding to the frequency difference ratio value;

[0198] Determine a target deviation value corresponding to the first reference sound data and the first sound data based on the amplitude difference ratio value, the frequency difference ratio value, the first target weight value, and the second target weight value;

[0199] A first matching value between the first reference sound data and the first sound data is determined based on the target deviation value.

[0200] In some possible implementations, in determining a first target weight corresponding to the amplitude difference ratio value and a second target weight corresponding to the frequency difference ratio value, the program includes instructions for performing the following steps:

[0201] Obtain a first reference weight corresponding to the amplitude difference ratio value and a second reference weight corresponding to the frequency difference ratio value;

[0202] Acquiring a target distance between the target vehicle and the first sound sensor when the target vehicle passes through the metering guidance section;

[0203] determining a first optimization factor corresponding to the target distance;

[0204] Optimizing the first reference weight according to the first optimization factor to obtain a first target weight;

[0205] Get the target ambient temperature;

[0206] determining a second optimization factor corresponding to the target ambient temperature;

[0207] The second reference weight is optimized according to the second optimization factor to obtain a second target weight.

[0208] In some possible implementations, in determining a first matching value between the first reference sound data and the first sound data based on the target deviation value, the program includes instructions for performing the following steps:

[0209] Determine a reference matching value corresponding to the target deviation value;

[0210] Obtaining historical matching values ​​between reference sound data and actual sound data within a preset time period, and obtaining k historical matching values; k is a positive integer, and each matching value corresponds to a matching value determination time;

[0211] According to k historical matching values ​​and the corresponding matching value determination time, fitting is performed to obtain a fitting straight line; the horizontal axis of the fitting straight line is time and the vertical axis is the matching value;

[0212] Get the target slope of the fitted straight line;

[0213] determining a target fine-tuning parameter corresponding to the target slope;

[0214] The reference matching value is fine-tuned according to the target fine-tuning parameter to obtain a first matching value between the first reference sound data and the first sound data.

[0215] In some possible implementations, in determining the target matching value corresponding to the first axis type according to the first matching value and the second matching value, the program includes instructions for executing the following steps:

[0216] Determine a third reference weight corresponding to the first matching value and a fourth reference weight corresponding to the second matching value;

[0217] Acquiring a first acceleration of the target vehicle in the metering guidance section;

[0218] determining a first adjustment parameter corresponding to the first acceleration;

[0219] Adjust the third reference weight according to the first adjustment parameter to obtain a third target weight;

[0220] Obtaining a second acceleration of the target vehicle in the metering section;

[0221] determining a second adjustment parameter corresponding to the second acceleration;

[0222] Adjust the fourth reference weight according to the second adjustment parameter to obtain a fourth target weight;

[0223] A target matching value is obtained by performing calculations based on the first matching value, the second matching value, the third target weight, and the fourth target weight.

[0224] In some possible implementations, in terms of acquiring the first sound data of the target vehicle passing through the metering guidance section through the first sound sensor, the above program includes instructions for executing the following steps:

[0225] Acquiring third sound data when the target vehicle passes through the metering guidance section through the first sound sensor;

[0226] The curvature and flatness of the measurement guidance section are obtained through the camera;

[0227] Determining a first adjustment parameter corresponding to the curvature and a second adjustment parameter corresponding to the flatness;

[0228] The third sound data is adjusted according to the first adjustment parameter and the second adjustment parameter to obtain the first sound data.

[0229] It should be understood that the electronic devices in this application may include smart phones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, laptops, mobile Internet devices MID (Mobile Internet Devices, referred to as: MID) or wearable devices or servers, edge computing nodes, etc. The above electronic devices are only examples, not exhaustive, and include but are not limited to the above electronic devices.

[0230] The present application also provides a computer-readable storage medium storing a computer program, which is executed by a processor to implement part or all of the steps of any one of the intelligent shaft type recognition methods described in the above method implementation.

[0231] The embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program can be operated to enable a computer to execute part or all of the steps of any one of the intelligent shaft type identification methods recorded in the above method embodiments.

[0232] It should be noted that, for the above-mentioned various method implementations, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the implementations described in the specification are all optional implementations, and the actions and modules involved are not necessarily required by this application.

[0233] In the above-mentioned 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.

[0234] In the several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device implementation described above is only schematic, such as the division of 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 devices or units can be electrical or other forms.

[0235] 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 present embodiment.

[0236] In addition, each functional unit in each embodiment of the present application 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 integrated unit may be implemented in the form of hardware or in the form of a software program module.

[0237] 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 application, 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. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of each implementation method of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0238] A person skilled in the art may understand that all or part of the steps in the various methods of the above-mentioned embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable memory, and the memory may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0239] The above is a detailed introduction to the implementation methods of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above implementation methods is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An intelligent shaft type recognition method, characterized in that: Applied to a metering system, the metering system includes a metering monitoring device, a first sound sensor, a second sound sensor, and a camera, the first sound sensor and the camera are located in a metering guidance section, the second sound sensor and the metering monitoring device are located in a metering section, and the method includes: Acquire multiple vehicle images of the target vehicle passing through the metering guidance section by the camera, and acquire first sound data of the target vehicle passing through the metering guidance section by the first sound sensor; Extracting image features from each of the plurality of vehicle images to obtain an image feature set; Determine a first axis type recognition result based on the image feature set; the first axis type recognition result includes at least one axis type; Acquire the sound data corresponding to the at least one axis type to obtain at least one reference sound data set; each axis type corresponds to a reference sound data set; Acquire the metering value of the target vehicle when it passes through the metering section by the metering monitoring device, and acquire the second sound data of the target vehicle when it passes through the metering section by the second sound sensor; Determine the axle type of the target vehicle according to the first sound data, the second sound data and the at least one reference sound data set to obtain a target axle type; Determining a measurement threshold corresponding to the target axis type; If the measurement value is greater than the measurement threshold, it is determined that the target vehicle is overweight.

2. The method according to claim 1, characterized in that Each of the at least one reference sound data set includes a plurality of reference sound data, and each reference sound data corresponds to a property information; determining the axle type of the target vehicle according to the first sound data, the second sound data, and the at least one reference sound data set to obtain the target axle type includes: Acquire first attribute information of the metering guidance section; Acquiring second attribute information of the guide section; According to the following steps A1-A5, the matching value corresponding to each axis type in the at least one axis type is determined according to the first attribute information and the second attribute information to obtain multiple target matching values, which are specifically the following steps: A1. Determine first reference sound data corresponding to the first attribute information in a first reference sound data set; the first reference sound data set is any reference sound data set in the at least one reference sound data set, the first reference sound data set corresponds to a first axis type, and the first axis type is any axis type in the at least one axis type; A2. determining second reference sound data corresponding to the second attribute information in the first reference sound data set; A3. Matching the first sound data with the first reference sound data to obtain a first matching value; A4. Matching the second sound data with the second reference sound data to obtain a second matching value; A5. Determine a target matching value corresponding to the first axis type according to the first matching value and the second matching value; The maximum value among the multiple target matching values ​​is selected, and the axis type corresponding to the maximum value is used as the target axis type.

3. The method according to claim 2, characterized in that The matching the first sound data with the first reference sound data to obtain a first matching value includes: Acquire a first reference amplitude and a first reference frequency corresponding to the first reference sound data; Acquire a first amplitude and a first frequency corresponding to the first sound data; determining an amplitude difference based on the first amplitude and the first reference amplitude, and determining an amplitude difference ratio based on the amplitude difference and the first reference amplitude; Determine a frequency difference based on the first frequency and the first reference frequency, and determine a frequency difference ratio based on the frequency difference and the first reference frequency; Determine a first target weight corresponding to the amplitude difference ratio value and a second target weight corresponding to the frequency difference ratio value; Determine a target deviation value corresponding to the first reference sound data and the first sound data based on the amplitude difference ratio value, the frequency difference ratio value, the first target weight value, and the second target weight value; A first matching value between the first reference sound data and the first sound data is determined based on the target deviation value.

4. The method according to claim 3, characterized in that The determining of the first target weight corresponding to the amplitude difference ratio value and the second target weight corresponding to the frequency difference ratio value includes: Obtaining a first reference weight corresponding to the amplitude difference ratio value and a second reference weight corresponding to the frequency difference ratio value; Acquiring a target distance between the target vehicle and the first sound sensor when the target vehicle passes through the metering guidance section; determining a first optimization factor corresponding to the target distance; Optimize the first reference weight according to the first optimization factor to obtain the first target weight; Get the target ambient temperature; determining a second optimization factor corresponding to the target ambient temperature; The second reference weight is optimized according to the second optimization factor to obtain the second target weight.

5. The method according to claim 3, characterized in that The determining a first matching value between the first reference sound data and the first sound data based on the target deviation value includes: Determine a reference matching value corresponding to the target deviation value; Obtaining historical matching values ​​between reference sound data and actual sound data within a preset time period, and obtaining k historical matching values; k is a positive integer, and each matching value corresponds to a matching value determination time; According to the k historical matching values ​​and the corresponding matching value determination time, fitting is performed to obtain a fitting straight line; the horizontal axis of the fitting straight line is time and the vertical axis is the matching value; Obtaining a target slope of the fitted straight line; determining a target fine-tuning parameter corresponding to the target slope; The reference matching value is fine-tuned according to the target fine-tuning parameter to obtain the first matching value between the first reference sound data and the first sound data.

6. The method according to any one of claims 2 to 5, characterized in that: The determining a target matching value corresponding to the first axis type according to the first matching value and the second matching value includes: Determine a third reference weight corresponding to the first matching value and a fourth reference weight corresponding to the second matching value; Acquiring a first acceleration of the target vehicle in the metering guidance section; determining a first adjustment parameter corresponding to the first acceleration; Adjust the third reference weight according to the first adjustment parameter to obtain a third target weight; Acquiring a second acceleration of the target vehicle in the metering section; determining a second adjustment parameter corresponding to the second acceleration; Adjust the fourth reference weight according to the second adjustment parameter to obtain a fourth target weight; The target matching value is obtained by performing calculation according to the first matching value, the second matching value, the third target weight, and the fourth target weight.

7. The method according to claim 1, characterized in that The step of obtaining the first sound data of the target vehicle passing through the metering guidance section by the first sound sensor includes: Acquiring, by means of the first sound sensor, third sound data when the target vehicle passes through the metering guidance section; Acquiring the curvature and flatness of the metering guide section through the camera; Determining a first adjustment parameter corresponding to the curvature and a second adjustment parameter corresponding to the flatness; The third sound data is adjusted according to the first adjustment parameter and the second adjustment parameter to obtain the first sound data.

8. An intelligent shaft type identification device, characterized in that: Applied to a metering system, the metering system comprises a metering monitoring device, a first sound sensor, a second sound sensor, and a camera, the first sound sensor and the camera are located in a metering guidance section, the second sound sensor and the metering monitoring device are located in a metering section, and the device comprises: an acquisition unit and a processing unit; The acquisition unit is used to acquire multiple vehicle images when the target vehicle passes through the metering guidance section through the camera, and acquire first sound data when the target vehicle passes through the metering guidance section through the first sound sensor; The processing unit is used to extract image features from each of the plurality of vehicle images to obtain an image feature set; Determine a first axis type recognition result based on the image feature set; the first axis type recognition result includes at least one axis type; The acquisition unit is used to acquire the sound data corresponding to the at least one axis type to obtain at least one reference sound data set; each axis type corresponds to a reference sound data set; The processing unit is used to obtain the metering value of the target vehicle when it passes through the metering section through the metering monitoring device, and to obtain the second sound data of the target vehicle when it passes through the metering section through the second sound sensor; Determine the axle type of the target vehicle according to the first sound data, the second sound data and the at least one reference sound data set to obtain a target axle type; Determining a measurement threshold corresponding to the target axis type; If the measurement value is greater than the measurement threshold, it is determined that the target vehicle is overweight.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store one or more programs and is configured to be executed by the processor, wherein the program includes instructions for executing the steps in the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 7.

Images