A method and system for monitoring the weight of a road vehicle

Abstract

The present invention provides a method and system for monitoring the weight of a vehicle traveling on a highway, wherein the method comprises: installing a vibration sensing module on the side of a target road in advance, and setting an audio and video acquisition module at a preset distance of the vibration sensing module; using the vibration sensing module to collect ground vibration signals generated when the vehicle passes the target road; using the audio and video acquisition module to collect audio and video data generated when the vehicle passes the target road; the audio and video data includes audio data and video image data; based on the ground vibration signal and the audio and video data, calculating the weight data of the vehicle. Therefore, the vehicle weight monitoring technology based on ground vibration and audio and video signals of the present invention has the advantages of non-contact, low cost, easy implementation and durability, realizes efficient and real-time monitoring of vehicle weight, greatly improves measurement accuracy and reduces costs.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic monitoring, and in particular to a method and system for monitoring the weight of a road vehicle. Background Art

[0002] With the rapid development of the transportation industry, the types and number of vehicles on the road are increasing. Real-time monitoring of the weight of vehicles, especially trucks, is of great significance for road maintenance, traffic management and overload control. Traditional vehicle weighing methods such as dynamic weighbridges and axle load meters, although with certain accuracy, are complex to install, have high maintenance costs, and are easily affected by the environment. Summary of the invention

[0003] To this end, the present invention provides a method and system for monitoring the weight of road vehicles, aiming to solve the technical problems of vehicle weighing methods in the prior art, such as complex installation, high maintenance cost, and susceptibility to environmental influences.

[0004] To achieve the above objectives, the present invention adopts the following technical solutions:

[0005] According to a first aspect of the present invention, the present invention provides a method for monitoring the weight of a road vehicle, the method comprising:

[0006] Pre-install a vibration sensor module on the side of the target road, and set an audio and video acquisition module at a preset distance from the vibration sensor module;

[0007] Using the vibration sensor module to collect ground vibration signals generated when the vehicle passes through the target road;

[0008] The audio and video acquisition module is used to collect audio and video data generated when the vehicle passes through the target road; the audio and video data includes audio data and video image data;

[0009] The weight data of the vehicle is calculated based on the ground vibration signal and the audio and video data.

[0010] Optionally, before calculating the weight data of the vehicle based on the ground vibration signal and the audio and video data, the method further includes:

[0011] Preprocessing the ground vibration signal and the audio and video data respectively to obtain a valid vibration signal and valid audio and video data; the valid audio and video data includes valid audio data and valid video image data;

[0012] Wherein, the data preprocessing includes at least one of denoising, filtering and normalization.

[0013] Optionally, the calculating the weight data of the vehicle based on the ground vibration signal and the audio and video data includes:

[0014] Extracting features from the effective vibration signal and the effective audio and video data respectively to obtain vehicle feature data;

[0015] The vehicle characteristic data is predicted using a target vehicle estimation model to obtain weight data of the vehicle.

[0016] Optionally, the extracting features of the effective vibration signal and the effective audio and video data respectively to obtain vehicle feature data includes:

[0017] Extracting peak amplitude characteristics and duration characteristics of the vehicle passing through the target road corresponding to the effective vibration signal and the effective audio data using a time domain analysis method; and,

[0018] Extracting the frequency component characteristics of the effective vibration signal corresponding to the vehicle passing through the target road by using a frequency domain analysis method; and,

[0019] Extracting audio signal features in the valid audio data based on MFCC Mel-frequency cepstral coefficient analysis; the audio signal features include tone, pitch, and Mel coefficient; and,

[0020] The speed, lane, and vehicle type characteristics of the vehicle when passing through the target road corresponding to the effective video image data are extracted in real time using a Kalman filter or a machine learning model.

[0021] Optionally, before predicting the vehicle characteristic data using the target vehicle estimation model to obtain the weight data of the vehicle, the method further includes:

[0022] Constructing a vehicle estimation model based on machine learning; the vehicle estimation model includes a linear regression module, an SVM support vector machine and / or a neural network module;

[0023] The historical ground vibration signals, historical audio and video data and corresponding weight data generated by historical vehicles are collected as training samples, and the vehicle estimation model is trained to obtain a trained target vehicle estimation model.

[0024] Optionally, the method further comprises:

[0025] The target vehicle estimation model is calibrated according to known real weight data.

[0026] Optionally, the method further comprises:

[0027] The ground vibration signal, the audio and video data, and the weight data of the vehicle are stored in a database as historical data to support subsequent optimization of the target vehicle estimation model.

[0028] Optionally, the method further comprises:

[0029] The ground vibration signal, the audio and video data, the vehicle weight data and / or the vehicle characteristic data are displayed on a page, stored and / or downloaded using a human-computer interaction interface.

[0030] Optionally, the preset distance is 1 to 5 meters.

[0031] According to a second aspect of the present invention, the present invention provides a weight monitoring system for a road vehicle, the system comprising a vibration sensing module, an audio and video acquisition module, and a central processing module; the vibration sensing module is installed on the side of a target road, the audio and video acquisition module is arranged at a preset distance from the vibration sensing module; the vibration sensing module and the audio and video acquisition module are respectively connected to the central processing module for communication;

[0032] The vibration sensor module is used to collect ground vibration signals generated when the vehicle passes through the target road;

[0033] The audio and video acquisition module is used to collect audio and video data generated when the vehicle passes through the target road; the audio and video data includes audio data and video image data;

[0034] The central processing module is used to calculate the weight data of the vehicle based on the ground vibration signal and the audio and video data.

[0035] The present invention adopts the above technical solution and has at least the following beneficial effects:

[0036] Through the scheme of the present invention, a vibration sensing module is pre-installed on the side of the target road, and an audio and video acquisition module is set at a preset distance from the vibration sensing module; the vibration sensing module is used to collect the ground vibration signal generated when the vehicle passes the target road; the audio and video acquisition module is used to collect the audio and video data generated when the vehicle passes the target road; the audio and video data includes audio data and video image data; based on the ground vibration signal and the audio and video data, the weight data of the vehicle is calculated. Therefore, the vehicle weight monitoring technology based on ground vibration and audio and video signals of the present invention has the advantages of non-contact, low cost, easy implementation and durability, realizes efficient and real-time monitoring of vehicle weight, greatly improves measurement accuracy and reduces costs.

[0037] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 A schematic diagram showing a flow chart of a method for monitoring the weight of a road vehicle provided by an embodiment of the present invention;

[0040] Figure 2 A schematic diagram showing the installation positions of a vibration sensor module and an audio and video acquisition module provided in an embodiment of the present invention is shown;

[0041] Figure 3 A schematic structural diagram of a weight monitoring system for a road vehicle provided by an embodiment of the present invention is shown;

[0042] Figure 4 A schematic structural diagram of a weight monitoring system for a road vehicle provided by another embodiment of the present invention is shown. DETAILED DESCRIPTION

[0043] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0044] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0045] The embodiment of the present invention provides a method for monitoring the weight of a road vehicle. Figure 1As shown, at least the following steps S101 to S103 may be included:

[0046] Step S101, pre-install a vibration sensor module on the side of the target road, and set an audio and video acquisition module at a preset distance from the vibration sensor module.

[0047] The vibration sensing module in the embodiment of the present invention may be a vibration sensor using a high-sensitivity accelerometer currently available on the market, and may be used to collect ground vibration signals when a vehicle passes by. Figure 2 The figure shows the installation position diagram of the vibration sensing module and the audio and video acquisition module. In the embodiment of the present invention, the vibration sensor is installed at a key position on the side of the road, such as a bridge deck or a flat road surface. Generally, an embedded installation method is adopted to ensure that the vibration sensor can accurately capture the ground vibration caused by the vehicle. In addition, it is necessary to arrange the audio and video acquisition module 1 to 5 meters near the vibration sensor to record the audio and video data of the vehicle driving on the road. It should be noted that in actual applications, the vibration sensing module and the audio and video acquisition module should be reasonably distributed according to the road width and the vehicle driving path, and are usually arranged at the edge of one side outside the emergency lane of the road.

[0048] Step S102, using a vibration sensor module to collect ground vibration signals generated when the vehicle passes through the target road; and using an audio and video acquisition module to collect audio and video data generated when the vehicle passes through the target road.

[0049] In the embodiment of the present invention, when a vehicle whose weight needs to be detected passes through the target road, the vibration sensor module can be used to collect the ground vibration signal and audio and video data generated when the vehicle passes by. The audio and video data includes audio data and video image data.

[0050] In addition, the ground vibration signal and audio and video data can be converted into digital signals that can be read and recognized by the central processing unit and sent to the central processing unit for subsequent data processing.

[0051] Step S103, calculating the weight data of the vehicle based on the ground vibration signal and the audio and video data.

[0052] It should be noted that before calculating the weight of the vehicle based on the ground vibration signal and audio and video data, it is necessary to pre-process the ground vibration signal and audio and video data, including denoising, filtering, normalization and other operations, to obtain the effective vibration signal and effective audio and video data generated when the vehicle passes through the target road. Among them, the effective audio and video data includes effective audio data and effective video image data.

[0053] Furthermore, features can be extracted from effective vibration signals and effective audio and video data to obtain vehicle feature data for model training and model prediction; the vehicle feature data can be predicted using a target vehicle estimation model to obtain vehicle weight data.

[0054] The vehicle feature data required in the embodiment of the present invention include peak amplitude features, frequency component features, duration features, tone, pitch, Mel coefficient, vehicle speed, vehicle type, lane, etc. Specifically, the peak amplitude features and duration features of the corresponding vehicle when passing the target road in the effective vibration signal and effective audio data can be extracted by using the time domain analysis method; the frequency component features of the corresponding vehicle when passing the target road in the effective vibration signal can be extracted by using the frequency domain analysis method (such as Fourier transform), and it is particularly necessary to pay attention to the signal changes in the low frequency band that are closely related to the vehicle weight; the audio signal features in the effective audio data are extracted based on MFCC Mel frequency cepstrum coefficient analysis; the audio signal features include tone, pitch, Mel coefficient; the speed, lane, and vehicle type features of the corresponding vehicle when passing the target road in the effective video image data can be detected and extracted in real time by using Kalman filtering or machine learning models.

[0055] It is understandable that before using the target vehicle estimation model to predict the vehicle feature data, it is necessary to construct the target vehicle estimation model and conduct necessary model training. Specifically, the embodiment of the present invention constructs a vehicle estimation model based on machine learning, and the vehicle estimation model may include a linear regression module, an SVM support vector machine, and a neural network module. Before training the vehicle estimation model, a large amount of historical ground vibration signals, historical audio and video data, and corresponding weight data generated by historical vehicles may be collected as training samples to train the vehicle estimation model. During the training, the influence of factors such as vehicle speed and vehicle type on the vibration signal is focused on to obtain a trained target vehicle estimation model.

[0056] Thus, the vehicle characteristic data of the vehicle passing through the target road is used as a model input of the target vehicle estimation model, and the estimated vehicle weight data can be input.

[0057] Furthermore, the embodiment of the present invention can also calibrate the parameters of the target vehicle estimation model according to the known real weight data. That is, by comparing the estimated vehicle weight data with the known real weight data through a standard vehicle with a known weight (such as a standard truck), the error is calculated, and the parameters of the target vehicle estimation model are adjusted to improve the accuracy.

[0058] Furthermore, the embodiment of the present invention may also store ground vibration signals, audio and video data, and vehicle weight data in a database as historical data to support subsequent optimization of the target vehicle estimation model.

[0059] Furthermore, the embodiment of the present invention can also utilize the human-computer interaction interface to display, store and download the ground vibration signal, audio and video data, vehicle weight data and / or vehicle characteristic data.

[0060] The embodiment of the present invention provides a method for monitoring the weight of a vehicle traveling on a highway, comprising installing a vibration sensing module on the side of a target road in advance, and setting an audio and video acquisition module at a preset distance from the vibration sensing module; using the vibration sensing module to collect ground vibration signals generated when the vehicle passes the target road; using the audio and video acquisition module to collect audio and video data generated when the vehicle passes the target road; the audio and video data includes audio data and video image data; based on the ground vibration signal and the audio and video data, the weight data of the vehicle is calculated. Therefore, the vehicle weight monitoring technology based on ground vibration and audio and video signals of the present invention can monitor the vehicle weight in real time without installing complex equipment such as a weighbridge or axle weight meter, thereby reducing installation and maintenance costs; combining multiple feature parameters and machine learning models to improve the accuracy of vehicle weight estimation; the present invention can also be expanded to more roads or lanes as needed to achieve large-scale application.

[0061] Further, as Figure 1 In a specific implementation, an embodiment of the present invention provides a weight monitoring system for a road vehicle, such as Figure 3 As shown, the device may include: a vibration sensing module 310, an audio and video acquisition module 320 and a central processing module 330; the vibration sensing module 310 is installed on the side of the target road, and the audio and video acquisition module 320 is set at a preset distance from the vibration sensing module; the vibration sensing module 310 and the audio and video acquisition module 320 are respectively connected to the central processing module 330 through a wired or wireless network.

[0062] The vibration sensor module 310 can be used to collect ground vibration signals generated when the vehicle passes through the target road;

[0063] The audio and video acquisition module 320 can be used to collect audio and video data generated when the vehicle passes through the target road; the audio and video data includes audio data and video image data;

[0064] The central processing module 330 may be used to calculate the weight data of the vehicle based on the ground vibration signal and the audio and video data.

[0065] Optionally, the central processing module 330 can also be used to perform data preprocessing on the ground vibration signal and the audio and video data respectively to obtain a valid vibration signal and valid audio and video data; the valid audio and video data includes valid audio data and valid video image data;

[0066] The data preprocessing includes at least one of denoising, filtering and normalization.

[0067] Optionally, the central processing module 330 may also be used to extract features from the effective vibration signal and the effective audio and video data to obtain vehicle feature data;

[0068] The target vehicle estimation model is used to predict the vehicle characteristic data to obtain the vehicle weight data.

[0069] Optionally, the central processing module 330 may also be used to extract peak amplitude characteristics and duration characteristics of the vehicle passing through the target road corresponding to the effective vibration signal and the effective audio data by using a time domain analysis method; and

[0070] Using frequency domain analysis method to extract the frequency component characteristics of the effective vibration signal corresponding to the vehicle passing through the target road; and,

[0071] Extracting audio signal features from valid audio data based on MFCC Mel-frequency cepstral coefficient analysis; audio signal features include tone, pitch, and Mel coefficient; and,

[0072] Kalman filtering or machine learning models are used to extract the speed, lane, and vehicle type characteristics of the corresponding vehicles passing through the target road in real time from the effective video image data.

[0073] Optionally, the central processing module 330 may also be used to construct a vehicle estimation model based on machine learning; the vehicle estimation model includes a linear regression module, a SVM support vector machine and / or a neural network module;

[0074] The historical ground vibration signals, historical audio and video data and corresponding weight data generated by historical vehicles are collected as training samples, and the vehicle estimation model is trained to obtain a trained target vehicle estimation model.

[0075] Optionally, the central processing module 330 may also be used to calibrate parameters of the target vehicle estimation model according to known real weight data.

[0076] Alternatively, if Figure 4 As shown, another embodiment of the present invention provides a weight monitoring system for road vehicles, which further includes: a database 340 and a human-computer interaction interface 350 .

[0077] The database 340 can be used to store ground vibration signals, audio and video data, and vehicle weight data as historical data to support subsequent optimization of the target vehicle estimation model.

[0078] The human-machine interaction interface 350 can be used to display, store and / or download ground vibration signals, audio and video data, vehicle weight data and / or vehicle characteristic data.

[0079] It should be noted that for other corresponding descriptions of the functional modules involved in the weight monitoring system for highway vehicles provided in the embodiment of the present invention, reference can be made to Figure 1 The corresponding description of the method shown will not be repeated here.

[0080] Those skilled in the art can clearly understand that the specific working processes of the systems, devices, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and for the sake of brevity, they are not further described here.

[0081] In addition, the functional units in various embodiments of the present invention may be physically independent of each other, or two or more functional units may be integrated together, or all functional units may be integrated into one processing unit. The above integrated functional units may be implemented in the form of hardware, or in the form of software or firmware.

[0082] A person skilled in the art can understand that if the integrated functional unit is implemented in the form of software and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially 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 storage medium, which includes several instructions to enable a computing device (such as a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention when running the instructions. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0083] Alternatively, all or part of the steps of implementing the aforementioned method embodiments may be accomplished by hardware associated with program instructions (such as a computing device such as a personal computer, a server, or a network device), and the program instructions may be stored in a computer-readable storage medium. When the program instructions are executed by a processor of the computing device, the computing device executes all or part of the steps of the method described in the various embodiments of the present invention.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that within the spirit and principles of the present invention, the technical solutions described in the aforementioned embodiments can still be modified, or some or all of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate from the protection scope of the present invention.

Claims

1. A method for monitoring the weight of a road vehicle, characterized in that: The method comprises: Pre-install a vibration sensor module on the side of the target road, and set an audio and video acquisition module at a preset distance from the vibration sensor module; Using the vibration sensor module to collect ground vibration signals generated when the vehicle passes through the target road; The audio and video acquisition module is used to collect audio and video data generated when the vehicle passes through the target road; the audio and video data includes audio data and video image data; the ground vibration signal and the audio and video data are respectively preprocessed to obtain a valid vibration signal and valid audio and video data; the valid audio and video data includes valid audio data and valid video image data; Calculating the weight data of the vehicle based on the ground vibration signal and the audio and video data, include: Feature extraction is performed on the effective vibration signal and the effective audio and video data respectively to obtain vehicle feature data, including: Extracting peak amplitude characteristics and duration characteristics of the vehicle passing through the target road corresponding to the effective vibration signal and the effective audio data using a time domain analysis method; and, Extracting the frequency component characteristics of the effective vibration signal corresponding to the vehicle passing through the target road by using a frequency domain analysis method; and, Extracting audio signal features in the valid audio data based on MFCC Mel-frequency cepstral coefficient analysis; the audio signal features include tone, pitch, and Mel coefficient; and, The speed, lane and vehicle type characteristics of the vehicle passing through the target road corresponding to the effective video image data are extracted in real time by using a Kalman filter or a machine learning model; the vehicle characteristic data includes at least one of peak amplitude characteristics, frequency component characteristics, duration characteristics, tone, pitch, Mel coefficient, vehicle speed, vehicle type and lane; a vehicle estimation model based on machine learning is constructed; the vehicle estimation model includes a linear regression module, an SVM support vector machine and / or a neural network module; Collect historical ground vibration signals, historical audio and video data, and corresponding weight data generated by historical vehicles as training samples, train the vehicle estimation model, and obtain a trained target vehicle estimation model; The vehicle characteristic data is predicted using a target vehicle estimation model to obtain weight data of the vehicle.

2. The method for monitoring the weight of a road vehicle according to claim 1, characterized in that: The data preprocessing includes at least one of denoising, filtering, and normalization.

3. The method for monitoring the weight of a road vehicle according to claim 1, characterized in that: The method for monitoring the weight of a road vehicle further comprises: The target vehicle estimation model is calibrated according to known real weight data.

4. The method for monitoring the weight of a road vehicle according to claim 1, characterized in that: The method for monitoring the weight of a road vehicle further comprises: The ground vibration signal, the audio and video data, and the weight data of the vehicle are stored in a database as historical data to support subsequent optimization of the target vehicle estimation model.

5. The method for monitoring the weight of a road vehicle according to any one of claims 1 to 4, characterized in that: The method for monitoring the weight of a road vehicle further comprises: The ground vibration signal, the audio and video data, the vehicle weight data and / or the vehicle characteristic data are displayed on a page, stored and / or downloaded using a human-computer interaction interface.

6. The method for monitoring the weight of a road vehicle according to claim 1, characterized in that: The preset distance is 1 to 5 meters.

7. A weight monitoring system for a road vehicle, characterized in that: The system comprises a vibration sensing module, an audio and video acquisition module, and a central processing module; the vibration sensing module is installed on the side of the target road, and the audio and video acquisition module is arranged at a preset distance from the vibration sensing module; the vibration sensing module and the audio and video acquisition module are respectively connected to the central processing module for communication; The vibration sensor module is used to collect ground vibration signals generated when the vehicle passes through the target road; The audio and video acquisition module is used to collect audio and video data generated when the vehicle passes through the target road; the audio and video data includes audio data and video image data; The central processing module is used to calculate the weight data of the vehicle based on the ground vibration signal and the audio and video data; The central processing module is also used to perform data preprocessing on the ground vibration signal and the audio and video data respectively to obtain a valid vibration signal and valid audio and video data; the valid audio and video data includes valid audio data and valid video image data; Extracting features from the effective vibration signal and the effective audio and video data respectively to obtain vehicle feature data; the vehicle feature data includes at least one of peak amplitude feature, frequency component feature, duration feature, tone, pitch, Mel coefficient, vehicle speed, vehicle type and lane; The central processing module is also used to construct a vehicle estimation model based on machine learning; the vehicle estimation model includes a linear regression module, an SVM support vector machine and / or a neural network module; Collect historical ground vibration signals, historical audio and video data, and corresponding weight data generated by historical vehicles as training samples, train the vehicle estimation model, and obtain a trained target vehicle estimation model; Predicting the vehicle characteristic data using a target vehicle estimation model to obtain weight data of the vehicle; Extracting peak amplitude characteristics and duration characteristics of the vehicle passing through the target road corresponding to the effective vibration signal and the effective audio data using a time domain analysis method; and, Extracting the frequency component characteristics of the effective vibration signal corresponding to the vehicle passing through the target road by using a frequency domain analysis method; and, Extracting audio signal features from the valid audio data based on MFCC Mel-frequency cepstral coefficient analysis; the audio signal features include tone, pitch, and Mel coefficient; as well as, The speed, lane, and vehicle type characteristics of the vehicle when passing through the target road corresponding to the effective video image data are extracted in real time using a Kalman filter or a machine learning model.

Images