Vehicle overload detection method and device based on IMU (Inertial Measurement Unit)

Abstract

The invention provides an IMU-based vehicle overload detection method and device, and the method comprises the steps: obtaining the motion data of a vehicle, and enabling the motion data to be determined by the vehicle IMU data collected by an IMU installed on the vehicle; state analysis is carried out based on the motion data, and the motion state of the vehicle is obtained; overload detection is carried out based on the motion state to obtain an overload detection result, the overload detection comprises multi-person riding detection or multi-person riding detection and load detection, the defects that in a traditional scheme, vehicle overload detection is not comprehensive and accurate enough, tedious and inconvenient to apply are overcome, accurate recognition of multi-person riding and load overweight is achieved, and the detection efficiency is improved. According to the technical scheme, the structure of the vehicle does not need to be upgraded and transformed, overload detection can be achieved based on a general structure, the comprehensiveness and accuracy of overload detection are effectively improved, disordered phases caused by multi-person riding can be avoided, and therefore the safety performance and management efficiency of the two-wheeled vehicle are optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle management, and in particular to an IMU-based vehicle overload detection method and device. Background Art

[0003] At present, the solution for vehicle overload detection mainly revolves around pressure sensors, that is, using pressure sensors to measure the vehicle load and compare it with the preset safe load threshold. Although this method can achieve overload detection, it has certain limitations, such as the need to upgrade and modify the vehicle structure, and the inability to clearly identify the cause of overload. Therefore, detection based on this method cannot effectively avoid the above problems, and the comprehensiveness and accuracy of the detection are worrying. Summary of the invention

[0004] The present invention provides an IMU-based vehicle overload detection method and device, which are used to solve the problem that vehicle overload detection in the prior art is not comprehensive and accurate enough.

[0005] The present invention provides a vehicle overload detection method based on IMU, comprising: Acquiring motion data of the vehicle, wherein the motion data is determined by vehicle IMU data collected by an inertial sensor IMU installed on the vehicle; Performing state analysis based on the motion data to obtain the motion state of the vehicle; An overload detection is performed based on the motion state to obtain an overload detection result, wherein the overload detection includes multi-person riding detection, or includes multi-person riding detection and load detection.

[0006] According to a vehicle overload detection method based on an IMU provided by the present invention, the overload detection is performed based on the motion state to obtain an overload detection result, including: Perform multi-person riding detection based on the motion state to obtain a riding detection result; If the riding detection result indicates that there are multiple people riding, determining an overload detection result based on the riding detection result; Otherwise, a load detection is performed based on the motion state to obtain a load detection result, and the overload detection result is determined based on the riding detection result and the load detection result.

[0007] According to a vehicle overload detection method based on an IMU provided by the present invention, the multi-person riding detection is performed based on the motion state to obtain a riding detection result, including: Inputting the motion state into a riding detection model to obtain a riding detection result of the vehicle output by the riding detection model; The riding detection model is trained based on sample motion data of multi-person riding and sample motion data of single-person riding.

[0008] According to a vehicle overload detection method based on an IMU provided by the present invention, the state analysis is performed based on the motion data to obtain the motion state of the vehicle, including: Based on the motion data, performing a state analysis on the vehicle, the state analysis comprising at least one of a vibration analysis, an acceleration analysis, an angular velocity analysis, and a tilt angle analysis; The motion state of the vehicle is determined based on at least one of the vehicle vibration condition, vehicle acceleration, vehicle angular velocity and vehicle tilt angle obtained through state analysis.

[0009] According to a vehicle overload detection method based on an IMU provided by the present invention, the overload detection is performed based on the motion state to obtain an overload detection result, and then further includes: Uploading the overload detection result to the cloud to request the cloud to generate a vehicle operation strategy based on the overload detection result; Receive the vehicle operation strategy returned by the cloud, and control the vehicle operation based on the vehicle operation strategy.

[0010] According to an IMU-based vehicle overload detection method provided by the present invention, the vehicle operation strategy includes any one of normal riding, restricted riding and prohibited riding; The receiving of the vehicle operation strategy returned by the cloud further includes: The overload detection result and the vehicle operation strategy are displayed on the instrument panel, voice broadcast display, sound and light alarm display or at least one of the above.

[0011] The present invention also provides a vehicle overload detection device based on IMU, comprising: An acquisition unit, used for acquiring motion data of the vehicle, wherein the motion data is determined by vehicle IMU data collected by an inertial sensor IMU installed on the vehicle; An analysis unit, configured to perform state analysis based on the motion data to obtain a motion state of the vehicle; The detection unit is used to perform overload detection based on the motion state to obtain an overload detection result, wherein the overload detection includes multi-person riding detection, or includes multi-person riding detection and load detection.

[0012] The present invention also provides a vehicle, comprising an inertial sensor IMU, a processor and a display, wherein the display comprises at least one of a dashboard, a voice announcer and an audible and visual alarm; The processor is used to obtain the motion data of the vehicle, and perform state analysis based on the motion data to obtain the motion state of the vehicle; perform overload detection based on the motion state to obtain the overload detection result, and control the display to display the overload detection result on the instrument panel, voice broadcast display, and sound and light alarm display; The motion data is determined by vehicle IMU data collected by the inertial sensor IMU, and the overload detection includes multi-person riding detection, or includes multi-person riding detection and load detection.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the IMU-based vehicle overload detection method as described above is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the vehicle overload detection method based on the IMU as described above is implemented.

[0015] The IMU-based vehicle overload detection method and device provided by the present invention perform state analysis according to motion data obtained by real-time monitoring, and perform multi-person riding detection, or multi-person riding detection and load detection, through the motion state of the vehicle obtained by analysis. This overcomes the defects of vehicle overload detection in traditional solutions that are not comprehensive and accurate, as well as cumbersome and inconvenient to use, and achieves accurate identification of multi-person riding and overload. Overload detection can be achieved based on a general structure without upgrading and modifying the structure of the vehicle, effectively improving the comprehensiveness and accuracy of overload detection, helping to avoid the chaos of multi-person riding, and optimizing the safety performance and management efficiency of two-wheeled vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 It is a flow chart of the vehicle overload detection method based on IMU provided by the present invention; Figure 2 It is a structural schematic diagram of an IMU-based vehicle overload detection device provided by the present invention; Figure 3 is a structural schematic diagram of a vehicle provided by the present invention; Figure 4It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] With the popularity of shared two-wheeled vehicles (shared bicycles and shared electric vehicles), as a low-carbon, environmentally friendly and convenient way of travel, it has greatly alleviated the pressure of urban traffic. However, with the increase in the number of vehicles put into use, the number of shared two-wheeled vehicles in cities has reached saturation, which has brought about a series of management and safety issues, among which the problem of overloading of two-wheeled vehicles is particularly prominent.

[0020] At present, the detection of overload of two-wheeled vehicles is mostly limited to load detection, that is, to detect the load of the vehicle. However, in actual travel, the overload of two-wheeled vehicles not only has the problem of overload, but more importantly, the problem of multiple people riding. However, most of the current solutions cannot take this into account. They only measure the vehicle load during riding based on pressure sensors, and compare the detected load with the preset safety load threshold to achieve load detection. However, this method has certain limitations. When overweight is detected, it is impossible to distinguish whether the overweight is due to the excessive weight of a single user or multiple users riding together. In addition, this method also involves the upgrade and modification of the vehicle structure, which is very cumbersome. In short, the current vehicle overload detection method is not comprehensive and accurate, and is cumbersome and inconvenient to use.

[0021] In this regard, the present invention provides a vehicle overload detection method based on IMU, which aims to perform state analysis according to the vehicle motion data obtained by real-time monitoring, and perform overload detection by analyzing the vehicle's motion state, so as to achieve accurate identification of multiple people riding and overload, without upgrading and modifying the vehicle structure, and can effectively improve the comprehensiveness, accuracy and detection efficiency of overload detection, avoid the chaos of multiple people riding, and optimize the safety performance and management efficiency of two-wheeled vehicles. Figure 1 FIG. 1 is a flow chart of a vehicle overload detection method based on IMU provided by the present invention, such as Figure 1 As shown, the method can be applied to a vehicle. The method comprises: Step 110, obtaining motion data of the vehicle, where the motion data is determined by vehicle IMU data collected by an inertial sensor IMU installed on the vehicle; Step 120, performing state analysis based on the motion data to obtain the motion state of the vehicle; Step 130, performing overload detection based on the motion state to obtain an overload detection result, wherein the overload detection includes multi-person riding detection, or includes multi-person riding detection and load detection.

[0022] Specifically, considering that the current overload detection of two-wheeled vehicles is limited to pressure sensors, resulting in poor comprehensiveness, accuracy and convenience of detection, in an embodiment of the present invention, it is proposed that the vehicle can be monitored in real time by an inertial sensor IMU (Inertial Measurement Unit) to obtain the vehicle's motion data, and analyze and detect based on this motion data to obtain the vehicle's overload detection result. By analyzing the data collected by the IMU, accurate detection of multiple people riding and overload during the vehicle's movement can be achieved, avoiding the problem of current detection being not comprehensive and accurate, and there is no need to make large-scale changes to the vehicle structure. Overload detection can be achieved based on a general structure, which is more accurate, convenient and practical.

[0023] It is understandable that in actual application, before conducting an overload detection on a two-wheeled vehicle, it is necessary to first obtain the data required for the detection. Specifically, the motion data of the two-wheeled vehicle (vehicle) is obtained. The motion data can be obtained based on the analysis of the vehicle IMU data collected by the IMU. The IMU can be directly installed on the vehicle, such as at the center of gravity of the vehicle, without being buried in the seat cushion like a pressure sensor. The installation of the IMU is simple and convenient, and there is no need to modify the vehicle structure.

[0024] The IMU installed on the vehicle can monitor the movement of the vehicle in real time, and obtain data during the movement of the vehicle, which is referred to as vehicle IMU data, and may include acceleration, angular velocity, body posture, etc. during the movement of the vehicle. In order to ensure the accuracy of subsequent detection, in the embodiment of the present invention, after obtaining the vehicle IMU data, it can also be pre-processed, and invalid data can be eliminated and normalized through pre-processing operations, so as to obtain the vehicle's movement data.

[0025] After that, the state analysis can be performed based on the motion data to obtain the motion state of the vehicle. That is, the motion state of the vehicle can be analyzed based on the motion data, specifically, the vehicle body posture can be analyzed to determine its tilt, the acceleration and angular velocity of the vehicle can be analyzed to determine its motion state, and the vibration of the vehicle body can be analyzed to determine the number and frequency of vibrations, so as to obtain the motion state of the vehicle.

[0026] It should be noted that the motion state here can be a conclusion based on whether the state is abnormal or not based on the motion data analysis, such as the vehicle's motion state is normal, the vehicle's motion state is abnormal, the vehicle's motion state cannot be determined, etc. It can also be a vehicle condition determined based on motion data analysis, such as the vehicle's tilt angle, number of vibrations, etc. It can also include both of the above, and the embodiments of the present invention do not specifically limit this.

[0027] After obtaining the motion state of the vehicle, in the embodiment of the present invention, an overload detection can be performed based on the motion state to detect whether the vehicle is overloaded, thereby obtaining the overload detection result of the vehicle. However, in the actual application of two-wheeled vehicles, especially shared two-wheeled vehicles, the phenomenon of multiple people riding is more common and difficult to control, and the adverse consequences it brings are worse than overweight. Therefore, in the embodiment of the present invention, when performing overload detection on the vehicle, the first thing to consider is the problem of multiple people riding, that is, performing multiple people riding detection on the vehicle, or performing load detection and multiple people riding detection on the vehicle, so as to detect whether the vehicle has multiple people riding and overweight through the motion state or the motion state and motion data, thereby obtaining the overload detection result.

[0028] After that, the overload detection result can be processed to control the operation of the vehicle. For example, when the overload detection result indicates that there are multiple people riding in the current vehicle and / or the load is overweight, control measures can be proposed to control the operation of the vehicle to prohibit riding, avoid riding accidents, and improve safety. For another example, when the overload detection result indicates that the current vehicle is not overloaded, but is at the overload critical value, a control strategy can be proposed to control the movement speed of the vehicle. For another example, when the overload detection result indicates that the current vehicle does not have the above problems, it can be temporarily not regulated to allow it to operate normally.

[0029] The IMU-based vehicle overload detection method provided by the present invention performs state analysis according to the vehicle's motion data obtained by real-time monitoring, and performs multi-person riding detection, or multi-person riding detection and load detection, through the analyzed vehicle's motion state, thereby overcoming the defects of vehicle overload detection in traditional solutions that are not comprehensive and accurate, as well as cumbersome and inconvenient to use, and realizes accurate identification of multi-person riding and overload, and overload detection can be realized based on a general structure without upgrading and modifying the vehicle's structure, effectively improving the comprehensiveness and accuracy of overload detection, helping to avoid the chaos of multi-person riding, thereby optimizing the safety performance and management efficiency of two-wheeled vehicles.

[0030] Based on the above embodiment, step 130 includes: Perform multi-person riding detection based on the motion state and obtain riding detection results; If the riding detection result indicates that there are multiple people riding, then determining an overload detection result based on the riding detection result; Otherwise, a load detection is performed based on the motion state to obtain a load detection result, and an overload detection result is determined based on the riding detection result and the load detection result.

[0031] Specifically, the process of performing overload detection according to the motion state in step 130 to obtain the overload detection result may specifically include: Taking into account the uncertainty of user behavior and the economy of travel in the management of two-wheeled vehicles, especially in the management of shared electric motorcycles, multi-person riding is more common and more difficult to control. Therefore, in order to improve detection efficiency, save computing resources, and obtain overload detection results faster, in an embodiment of the present invention, a priority strategy can be formulated according to actual conditions, so that detection can be performed in sequence according to the priority strategy, which can not only ensure the orderliness of detection, but also further optimize detection efficiency and improve practicality.

[0032] Specifically, in the embodiments of the present invention, when performing overload detection on a vehicle, a multi-person riding detection may be performed first to detect whether there are multiple people riding on the vehicle, thereby obtaining a riding detection result. That is, it is possible to determine whether there are multiple people riding on the vehicle through the data of the vehicle body posture, tilt, vibration, acceleration, angular velocity, etc. presented in the motion state, and the conclusion of the vehicle motion state obtained by analysis, thereby obtaining a detection result of multiple people riding on the vehicle, that is, a riding detection result.

[0033] Furthermore, when the riding detection result indicates that there are multiple riders riding the vehicle and there is a problem of multiple riders riding, there is no need to perform load detection at this time. The reason is that when it is confirmed that there is a problem of multiple riders riding the vehicle, the vehicle needs to be regulated regardless of whether its current load is overweight. In this case, load detection is of little significance. In order to obtain results faster and perform riding control in a timely manner, in an embodiment of the present invention, the overload detection result can be determined directly based on the riding detection result at this time, so that based on this overload detection result, the movement of the vehicle can be regulated, for example, power off, locking the vehicle, etc., to prohibit riding, thereby ensuring travel safety.

[0034] Correspondingly, when the riding detection result reflects that there is no problem of multiple people riding the vehicle at present, that is, it is a single person riding, then the vehicle can be loaded and tested, that is, the current load of the vehicle can be detected based on the vehicle's motion state, or the motion state and motion data to determine whether it is overloaded, thereby obtaining the load detection result. Furthermore, based on this load detection result and the riding detection result, the final overload detection result of the vehicle can be determined. That is, the results of the multi-person riding detection and the results of the load detection can be combined to analyze and determine the final overload detection result.

[0035] It should be noted that, in addition to the detection scheme based on the vehicle's motion data provided in the embodiment of the present invention, vehicle load detection can also be achieved through various currently mature load detection technologies, which are not exhaustively listed in the embodiment of the present invention.

[0036] Based on the above embodiment, multi-person riding detection is performed based on the motion state to obtain a riding detection result, including: The motion state is input into the riding detection model to obtain a riding detection result of the vehicle output by the riding detection model; The riding detection model is trained based on sample motion data of multi-person riding and sample motion data of single-person riding.

[0037] Specifically, the process of performing multi-person riding detection according to the motion state and obtaining the riding detection result can be implemented by a riding detection model. That is, the motion state of the vehicle can be input into the riding detection model, and the riding detection model can perform multi-person riding detection according to the input information to detect whether there is a problem of multi-person riding in the vehicle at present, and output the detection result, thereby obtaining the riding detection result of multi-person riding.

[0038] It should be noted that, in order to ensure the accuracy of detection, before the motion state is input into the riding detection model, in the embodiment of the present invention, sample data can also be used for pre-training to obtain a riding detection model for multi-person riding detection.

[0039] In detail, in order to enable the model to accurately detect the situation of multi-person riding and to achieve accurate distinction between multi-person riding and single-person riding, in an embodiment of the present invention, during the model training process, two different types of data can be used, namely, sample motion data in the case of multi-person riding and sample motion data in the case of single-person riding, for targeted training. This allows the model to learn the mapping relationship between the input sample motion data and the riding condition, and at the same time, can accurately capture the difference in motion data between multi-person riding and single-person riding through sample comparison, so that the multi-person riding situation can be accurately identified in the application link to ensure the accuracy of detection.

[0040] Based on the above embodiment, step 120 includes: Based on the motion data, a state analysis is performed on the vehicle, where the state analysis includes at least one of a vibration analysis, an acceleration analysis, an angular velocity analysis, and a tilt angle analysis; The motion state of the vehicle is determined based on at least one of the vehicle vibration condition, vehicle acceleration, vehicle angular velocity and vehicle tilt angle obtained through state analysis.

[0041] Specifically, the process of performing state analysis based on the motion data to obtain the motion state of the vehicle may include: First, the vehicle state analysis can be performed based on the vehicle motion data, and the state analysis here can include any one or more of vibration analysis, acceleration analysis, angular velocity analysis, and tilt angle analysis. That is, the vehicle motion state can be analyzed based on the motion data, and specifically, at least one of the vehicle tilt, vehicle acceleration, angular velocity, and vehicle body vibration can be analyzed to obtain the vehicle analysis results at the above levels.

[0042] Then, the vehicle's motion state can be determined based on the vehicle vibration conditions obtained by the state analysis, such as the number, frequency, severity of the vibration of the vehicle body, and any one or more of the vehicle acceleration, vehicle angular velocity, and vehicle tilt angle. Here, the vehicle's motion state can be determined by combining the analysis results of one or more levels. The motion state can be directly represented by the analysis results, or can be represented by a conclusion further synthesized from the analysis results. The embodiment of the present invention does not specifically limit this.

[0043] Based on the above embodiment, in step 120, overload detection is performed based on the motion state to obtain an overload detection result, and then the following steps are further included: Upload the overload detection results to the cloud to request the cloud to generate a vehicle operation strategy based on the overload detection results; Receive the vehicle operation strategy returned by the cloud, and control the vehicle operation based on the vehicle operation strategy.

[0044] Specifically, after performing overload detection according to the motion state and obtaining the overload detection result of the vehicle, in order to facilitate management and control and achieve targeted vehicle management, in the embodiment of the present invention, the overload detection result obtained by local detection can be uploaded to the cloud, so that the cloud can return management measures in a targeted manner according to the received overload detection result. That is, after receiving the overload detection result, the cloud can generate corresponding management measures, referred to as vehicle operation strategies, based on the overload situation of the vehicle reflected by the overload detection result, such as whether there are multiple people riding, whether the load is overweight, etc., and can return this strategy to the local.

[0045] After that, after receiving the vehicle operation policy returned from the cloud, the local vehicle can control the vehicle operation according to this vehicle operation policy. For example, when the vehicle operation policy is to prohibit riding, the vehicle can lock the vehicle and cut off the power by controlling the vehicle lock, electric door, etc., so as to achieve the purpose of prohibiting riding. For another example, when the vehicle operation policy is to restrict riding, the vehicle can limit the speed by controlling the electric door, brake valve, etc., so as to achieve the purpose of limiting the riding speed and ensuring riding safety. For another example, when the vehicle operation policy is normal riding, the vehicle can control the vehicle lock to open, the electric door to operate normally, etc., so as to achieve normal riding of the vehicle.

[0046] Based on the above embodiment, the vehicle operation strategy includes any one of normal riding, restricted riding and prohibited riding; Receive the vehicle operation strategy returned by the cloud, and then include: The overload detection result and the vehicle operation strategy are displayed on the instrument panel, by voice broadcast, or by sound and light alarm.

[0047] Specifically, after the overload detection result of the vehicle is detected, in order to improve the safety of travel, in the embodiment of the present invention, the overload detection result can also be displayed so that the user can know the detection result in time and take measures in time under abnormal circumstances to ensure safety. In the embodiment of the present invention, the overload detection result can be specifically displayed on the instrument panel, voice broadcast display, sound and light alarm display, that is, the overload detection result can be displayed on the instrument panel, the overload detection result can be voice broadcast, or the detection result can be displayed by sound and light information. The overload detection result can also be displayed in combination with the above two or three ways, and the embodiment of the present invention does not specifically limit this.

[0048] Correspondingly, after receiving the vehicle operation strategy returned from the cloud, it can also be displayed. Specifically, the vehicle operation strategy can be displayed on the dashboard, or the vehicle operation strategy can be announced by voice, for example, voice announcement "The current vehicle is prohibited from riding", or the vehicle operation strategy can be displayed through sound and light information, such as displaying different operation strategies through different sounds and lights of different colors and brightness. The vehicle operation strategy can also be displayed in combination with the above two or three methods, and the embodiments of the present invention do not make specific limitations on this.

[0049] It should be noted that the voice broadcast display can be realized by a voice broadcaster, and the sound and light alarm display can be realized by light emitting diodes, buzzers, sound and light alarms, etc.

[0050] The IMU-based vehicle overload detection device provided by the present invention is described below. The IMU-based vehicle overload detection device described below and the IMU-based vehicle overload detection method described above can refer to each other.

[0051] Figure 2 FIG. 1 is a schematic diagram of the structure of the vehicle overload detection device based on IMU provided by the present invention, such as Figure 2 As shown, the device comprises: An acquisition unit 210 is used to acquire motion data of the vehicle, wherein the motion data is determined by vehicle IMU data collected by an inertial sensor IMU installed on the vehicle; An analysis unit 220, configured to perform state analysis based on the motion data to obtain a motion state of the vehicle; The detection unit 230 is used to perform overload detection based on the motion state to obtain an overload detection result. The overload detection includes multi-person riding detection, or multi-person riding detection and load detection.

[0052] The IMU-based vehicle overload detection device provided by the present invention performs state analysis according to the vehicle's motion data obtained by real-time monitoring, and performs multi-person riding detection, or multi-person riding detection and load detection, through the analyzed vehicle's motion state, thereby overcoming the defects of vehicle overload detection in traditional solutions that are not comprehensive and accurate, as well as cumbersome and inconvenient to use, and realizes accurate identification of multi-person riding and overload, and can realize overload detection based on a general structure without upgrading and modifying the vehicle's structure, effectively improving the comprehensiveness and accuracy of overload detection, helping to avoid the chaos of multi-person riding, thereby optimizing the safety performance and management efficiency of two-wheeled vehicles.

[0053] Based on the above embodiment, the detection unit 230 is used for: Perform multi-person riding detection based on the motion state to obtain a riding detection result; If the riding detection result indicates that there are multiple people riding, determining an overload detection result based on the riding detection result; Otherwise, a load detection is performed based on the motion state to obtain a load detection result, and the overload detection result is determined based on the riding detection result and the load detection result.

[0054] Based on the above embodiment, the detection unit 230 is used for: Inputting the motion state into a riding detection model to obtain a riding detection result of the vehicle output by the riding detection model; The riding detection model is trained based on sample motion data of multi-person riding and sample motion data of single-person riding.

[0055] Based on the above embodiment, the analysis unit 220 is used for: Based on the motion data, performing a state analysis on the vehicle, the state analysis comprising at least one of a vibration analysis, an acceleration analysis, an angular velocity analysis, and a tilt angle analysis; The motion state of the vehicle is determined based on at least one of the vehicle vibration condition, vehicle acceleration, vehicle angular velocity and vehicle tilt angle obtained through state analysis.

[0056] Based on the above embodiment, the device further includes a management and control unit, which is used to: Uploading the overload detection result to the cloud to request the cloud to generate a vehicle operation strategy based on the overload detection result; Receive the vehicle operation strategy returned by the cloud, and control the vehicle operation based on the vehicle operation strategy.

[0057] Based on the above embodiment, the vehicle operation strategy includes any one of normal riding, restricted riding and prohibited riding; The device also includes a display unit for: The overload detection result and the vehicle operation strategy are displayed on the instrument panel, voice broadcast display, sound and light alarm display or at least one of the above.

[0058] Figure 3 : is a schematic diagram of the structure of the vehicle provided by the present invention, such as Figure 3 As shown, the vehicle includes an inertial sensor IMU 310, a processor 320 and a display 330, wherein the display 330 includes at least one of a dashboard, a voice announcer and an audible and visual alarm; The processor 320 is used to obtain the motion data of the vehicle, and perform state analysis based on the motion data to obtain the motion state of the vehicle; perform overload detection based on the motion state to obtain the overload detection result, and control the display 330 to display the overload detection result on the instrument panel, voice broadcast display, and sound and light alarm display; The motion data is determined by vehicle IMU data collected by the inertial sensor IMU310, and the overload detection includes multi-person riding detection, or includes multi-person riding detection and load detection.

[0059] The vehicle provided by the present invention performs state analysis based on the vehicle's motion data obtained by real-time monitoring, and performs multi-person riding detection, or multi-person riding detection and load detection, through the analyzed vehicle's motion state, thereby overcoming the defects of vehicle overload detection in traditional solutions that are not comprehensive and accurate, as well as cumbersome and inconvenient to use, and realizes accurate identification of multi-person riding and overload, without the need to upgrade and transform the vehicle's structure, and overload detection can be achieved based on a general structure, effectively improving the comprehensiveness and accuracy of overload detection, helping to avoid the chaos of multi-person riding, thereby optimizing the safety performance and management efficiency of two-wheeled vehicles.

[0060] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the vehicle overload detection method based on the IMU, the method comprising: obtaining the motion data of the vehicle, the motion data being determined by the vehicle IMU data collected by the inertial sensor IMU installed on the vehicle; performing state analysis based on the motion data to obtain the motion state of the vehicle; performing overload detection based on the motion state to obtain the overload detection result, the overload detection including multi-person riding detection, or including multi-person riding detection and load detection.

[0061] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0062] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the IMU-based vehicle overload detection method provided by the above-mentioned methods, and the method includes: obtaining vehicle motion data, wherein the motion data is determined by vehicle IMU data collected by an inertial sensor IMU installed on the vehicle; performing state analysis based on the motion data to obtain the motion state of the vehicle; performing overload detection based on the motion state to obtain an overload detection result, wherein the overload detection includes multi-person riding detection, or includes multi-person riding detection and load detection.

[0063] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the IMU-based vehicle overload detection method provided by the above-mentioned methods, the method comprising: acquiring motion data of the vehicle, the motion data being determined by vehicle IMU data collected by an inertial sensor IMU installed on the vehicle; performing state analysis based on the motion data to obtain the motion state of the vehicle; performing overload detection based on the motion state to obtain an overload detection result, the overload detection including multi-person riding detection, or including multi-person riding detection and load detection.

[0064] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0065] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0066] 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 they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle overload detection method based on IMU, characterized in that: include: Acquiring motion data of the vehicle, wherein the motion data is determined by vehicle IMU data collected by an inertial sensor IMU installed on the vehicle; Performing state analysis based on the motion data to obtain the motion state of the vehicle; An overload detection is performed based on the motion state to obtain an overload detection result, wherein the overload detection includes multi-person riding detection, or includes multi-person riding detection and load detection.

2. The vehicle overload detection method based on IMU according to claim 1, characterized in that: The performing overload detection based on the motion state to obtain an overload detection result includes: Perform multi-person riding detection based on the motion state to obtain a riding detection result; If the riding detection result indicates that there are multiple people riding, determining an overload detection result based on the riding detection result; Otherwise, a load detection is performed based on the motion state to obtain a load detection result, and the overload detection result is determined based on the riding detection result and the load detection result.

3. The vehicle overload detection method based on IMU according to claim 2, characterized in that: The performing multi-person riding detection based on the motion state to obtain a riding detection result includes: Inputting the motion state into a riding detection model to obtain a riding detection result of the vehicle output by the riding detection model; The riding detection model is trained based on sample motion data of multi-person riding and sample motion data of single-person riding.

4. The vehicle overload detection method based on IMU according to any one of claims 1 to 3, characterized in that: The performing state analysis based on the motion data to obtain the motion state of the vehicle includes: Based on the motion data, performing a state analysis on the vehicle, the state analysis comprising at least one of a vibration analysis, an acceleration analysis, an angular velocity analysis, and a tilt angle analysis; The motion state of the vehicle is determined based on at least one of the vehicle vibration condition, vehicle acceleration, vehicle angular velocity and vehicle tilt angle obtained through state analysis.

5. The vehicle overload detection method based on IMU according to any one of claims 1 to 3, characterized in that: The overload detection is performed based on the motion state to obtain an overload detection result, and then the method further includes: Uploading the overload detection result to the cloud to request the cloud to generate a vehicle operation strategy based on the overload detection result; Receive the vehicle operation strategy returned by the cloud, and control the vehicle operation based on the vehicle operation strategy.

6. The vehicle overload detection method based on IMU according to claim 5, characterized in that: The vehicle operation strategy includes any one of normal riding, restricted riding and prohibited riding; The receiving of the vehicle operation strategy returned by the cloud further includes: The overload detection result and the vehicle operation strategy are displayed on the instrument panel, voice broadcast display, sound and light alarm display or at least one of the above.

7. A vehicle overload detection device based on IMU, characterized in that: include: An acquisition unit, used for acquiring motion data of the vehicle, wherein the motion data is determined by vehicle IMU data collected by an inertial sensor IMU installed on the vehicle; An analysis unit, configured to perform state analysis based on the motion data to obtain a motion state of the vehicle; The detection unit is used to perform overload detection based on the motion state to obtain an overload detection result, wherein the overload detection includes multi-person riding detection, or includes multi-person riding detection and load detection.

8. A vehicle, characterized in that: It includes an inertial sensor IMU, a processor and a display, wherein the display includes at least one of a dashboard, a voice announcer and an audible and visual alarm; The processor is used to obtain motion data of the vehicle, and perform state analysis based on the motion data to obtain the motion state of the vehicle; Performing overload detection based on the motion state to obtain an overload detection result, and controlling the display to display the overload detection result on a dashboard, voice broadcast display, or sound and light alarm display; The motion data is determined by vehicle IMU data collected by the inertial sensor IMU, and the overload detection includes multi-person riding detection, or includes multi-person riding detection and load detection.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the IMU-based vehicle overload detection method as described in any one of claims 1 to 6 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the IMU-based vehicle overload detection method according to any one of claims 1 to 6 is implemented.

Images