Deceleration strip detection method, device, equipment, medium and program product
The method enhances speed bump detection accuracy and safety by using IMU data and a logistic regression model to generate timely alerts and power adjustments, addressing the limitations of existing methods.
Patent Information
- Application Number
- CN202411216780.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-02
- Publication Date
- 2024-12-24
AI Technical Summary
Existing speed bump detection methods in intelligent driving technology suffer from low accuracy due to reliance on simple sensor data processing or traditional machine learning algorithms.
A method involving real-time data acquisition, similarity feature extraction using IMU data, and a pre-trained logistic regression model to generate driving warning signals, including sound, visual, and vibration alerts, and power assistance adjustments based on vehicle state.
Improves the computational efficiency and accuracy of speed bump detection, enhancing driving safety by promptly alerting drivers to adjust speed and behavior.
Smart Images
Figure CN119179925A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent driving technology, and in particular to a speed bump detection method, device, equipment, medium and program product. Background Art
[0002] In the field of intelligent driving technology, speed bump detection is a data analysis method commonly used to identify and locate the area where the speed bump device is located in the driving route. During the driving process of the vehicle, accurate speed bump detection results can not only remind the vehicle control system to adjust the output power of the power mechanism in real time, but also promptly remind the driver to adjust the speed and driving behavior, thereby effectively improving the driving safety of the vehicle.
[0003] However, existing speed bump detection methods mainly rely on simple sensor data processing technology or traditional machine learning algorithms, and the detection results obtained usually have the problem of low accuracy. Summary of the invention
[0004] Based on this, it is necessary to provide a speed bump detection method, device, equipment, medium and program product to address the above technical problems.
[0005] In a first aspect, the present application provides a speed bump detection method, the method comprising:
[0006] Obtain real-time driving data of vehicles;
[0007] Acquire similarity features between the real-time driving data and speed bump reference data;
[0008] Inputting the similarity feature into a speed bump detection model to obtain a driving detection result representing the driving state of the vehicle;
[0009] Based on the driving detection result, a driving warning signal is generated.
[0010] In one embodiment, the real-time driving data is time series data collected by an IMU device; before obtaining the real-time driving data of the vehicle, the method further includes:
[0011] Acquire sample data; the sample data includes speed bump sample data and non-speed bump sample data; perform fitting processing on the speed bump sample data to obtain the speed bump reference data; obtain sample similarity features between the speed bump reference data and the non-speed bump sample data; construct a training data set based on the speed bump reference data, the non-speed bump sample data, and the sample similarity features; use the training data set to train a logistic regression model to obtain the speed bump detection model.
[0012] In one embodiment, obtaining sample data includes:
[0013] The initial sample data is subjected to denoising processing to obtain intermediate sample data; and the intermediate sample data is subjected to normalization processing to obtain the sample data.
[0014] In one embodiment, the fitting process of the speed bump sample data to obtain the speed bump reference data includes:
[0015] A dynamic time normalization algorithm is used to perform fitting processing on the speed bump sample data to obtain the speed bump reference data.
[0016] In one embodiment, generating a driving warning signal based on the driving detection result includes:
[0017] When the driving detection result indicates that the vehicle has passed through a speed bump, the driving warning signal is generated according to a preset warning mechanism; and a power assistance adjustment strategy is determined based on the current vehicle motion state.
[0018] In one embodiment, the driving warning signal includes at least one of a sound warning signal, a visual warning signal, and a vibration warning signal; the power assist adjustment strategy includes at least one of a motor output power adjustment strategy and a power assist mode adjustment strategy.
[0019] In a second aspect, the present application also provides a speed bump detection device, the device comprising:
[0020] A real-time data acquisition module is used to acquire real-time driving data of the vehicle;
[0021] A similarity acquisition module, used to acquire similarity features between the real-time driving data and the speed bump reference data;
[0022] A detection result output module, used for inputting the similarity feature into a speed bump detection model to obtain a driving detection result representing the driving state of the vehicle;
[0023] The warning signal generating module is used to generate a driving warning signal based on the driving detection result.
[0024] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.
[0025] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.
[0026] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.
[0027] The above-mentioned speed bump detection method, device, equipment, medium and program product first obtain the real-time driving data of the vehicle. Then, obtain the similarity feature between the real-time driving data and the speed bump reference data. Next, input the similarity feature into the speed bump detection model to obtain the driving detection result that characterizes the driving state of the vehicle. Finally, based on the driving detection result, generate a driving warning signal. The present application obtains the driving detection result that characterizes whether the vehicle has passed the speed bump by inputting the similarity feature between the real-time driving data and the speed bump reference data into a pre-trained speed bump detection model, and generates a corresponding driving warning signal when the driving detection result characterizes that the vehicle has passed the speed bump. This can not only improve the computational efficiency of the speed bump detection process and the accuracy of the speed bump detection results, but also can promptly remind the driver to adjust the vehicle speed and driving behavior through the driving warning signal, thereby effectively improving the driving safety of the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 A schematic flow chart of a speed bump detection method provided in one embodiment of the present application;
[0029] Figure 2 A flowchart of a specific method for obtaining a speed bump detection model provided in one embodiment of the present application;
[0030] Figure 3 A flowchart of a specific method for obtaining sample data provided in an embodiment of the present application;
[0031] Figure 4 A flowchart of a specific method of generating a driving warning signal and determining a power assistance adjustment strategy provided in one embodiment of the present application;
[0032] Figure 5 This is a structural block diagram of a speed bump detection device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0033] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.
[0035] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.
[0036] When used herein, the singular forms "a", "an" and "said / the" may also include plural forms, unless the context clearly indicates otherwise. "Multiple" means two or more, unless otherwise clearly and specifically limited. It should also be understood that the terms "include / comprise" or "have" and the like specify the presence of stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof. At the same time, the term "and / or" used in this specification includes any and all combinations of the relevant listed items.
[0037] In one embodiment, Figure 1 As shown, a speed bump detection method is provided, comprising the following steps:
[0038] Step S110, obtaining real-time driving data of the vehicle.
[0039] The real-time driving data of a vehicle refers to the real-time dynamic data generated by the vehicle during its driving process.
[0040] Specifically, the specific form of the vehicle may be a bicycle, an electric vehicle, an electric-assisted bicycle, a scooter, an electric bicycle, an electric scooter, or other means of transportation with a transportation function, which is not strictly limited in this application; the real-time driving data of the vehicle may include real-time dynamic data such as the acceleration and angular velocity generated by the vehicle during driving, which characterizes the driving state of the vehicle.
[0041] In practical applications, the specific form of the vehicle's real-time driving data may be real-time time series data recorded by real-time dynamic data collected by IMU devices fixed at key parts of the vehicle during the vehicle's driving process. The real-time time series data may include specific data characterizing the vehicle's driving state, such as acceleration and angular velocity generated by the vehicle during driving; key parts of the vehicle refer to vehicle parts that are suitable for installing IMU devices to obtain detailed dynamic data characterizing the vehicle's driving state, such as acceleration and angular velocity generated by the vehicle during driving (for example, vehicle parts such as the bottom of the vehicle and / or parts near the wheels).
[0042] It should be noted that IMU equipment, also known as inertial measurement equipment, inertial measurement system or inertial measurement unit, is a device used to measure the angular rate and acceleration of the three-axis attitude of an object, and usually includes a gyroscope for measuring the angle and angular velocity of the three axes, and an accelerometer for measuring the acceleration of the three axes. In addition, in the actual application of IMU equipment, based on the gyroscope and accelerometer, according to specific application requirements, a magnetometer for providing magnetic field orientation information and correcting posture, and / or a barometer for correcting altitude can be added.
[0043] Step S120, obtaining similarity features between the real-time driving data and the speed bump reference data.
[0044] Among them, real-time driving data refers to the real-time driving data of the vehicle; speed bump reference data refers to the speed bump reference data fitted from a large amount of dynamic data collected in advance when the vehicle passes through the speed bump during driving; similarity feature refers to the similarity feature used to characterize the degree of similarity between the real-time driving data and the speed bump reference data.
[0045] Specifically, the specific form of the speed bump reference data can be a large amount of dynamic data generated by the vehicle when passing through the speed bump during driving, which is pre-collected by the IMU device, and the recorded time series sample data is fitted into the speed bump reference data, which can be used to characterize the driving state of the vehicle when passing through the speed bump during driving.
[0046] In practical applications, the speed bump reference data can be acquired by fitting the time series sample data based on the DTW algorithm; based on this, the similarity features between the real-time driving data and the speed bump reference data can also be acquired by fitting the real-time driving data and the speed bump reference data based on the DTW algorithm.
[0047] Furthermore, after obtaining the similarity features between the real-time driving data and the speed bump reference data, the four most representative features can be selected from the aforementioned similarity features as the similarity features to be subsequently input into the speed bump detection model, so as to further improve the computational efficiency of the speed bump detection process.
[0048] It should be noted that the DTW algorithm refers to the DTW (Dynamic Time Warping, DTW) dynamic time warping algorithm, which is based on the idea of dynamic programming and is often used to measure the similarity between two time series.
[0049] Step S130, inputting the similarity feature into a speed bump detection model to obtain a driving detection result representing the driving state of the vehicle.
[0050] Among them, the similarity feature refers to the similarity feature between the real-time driving data and the speed bump reference data; the speed bump detection model refers to a speed bump detection model that can output a driving detection result that can be used to characterize the driving state of the current vehicle based on the similarity feature between the real-time driving data and the speed bump reference data.
[0051] Specifically, the specific form of the driving detection result representing the driving state of the vehicle may be a driving detection result representing whether the current vehicle has passed through a speed bump.
[0052] In practical applications, the speed bump detection model can be implemented through a pre-trained logistic regression model; the driving detection results that characterize the driving status of the vehicle can not only be used to generate driving warning signals, but also can be used for subsequent data analysis and system optimization (for example, when analyzing the time series data generated during vehicle driving, the angle changes caused by the vehicle passing through the speed bump can be filtered out, or a higher-order filtering algorithm can be used to reduce the data fluctuations caused by the vehicle passing through the speed bump).
[0053] Step S140: generating a driving warning signal based on the driving detection result.
[0054] Among them, the driving detection result is the driving detection result that characterizes the driving state of the vehicle; the driving warning signal refers to the driving warning signal generated when a driving detection result is obtained that characterizes that the current vehicle has passed through a speed bump.
[0055] Specifically, the specific manifestation of the driving warning signal may be that the vehicle control system generates the driving warning signal when a driving detection result indicating that the current vehicle has passed through a speed bump is obtained.
[0056] In practical applications, driving warning signals can be used to remind vehicle drivers to reduce speed or make corresponding adjustments to current driving behavior.
[0057] The above-mentioned speed bump detection method first obtains the real-time driving data of the vehicle. Then, obtains the similarity feature between the real-time driving data and the speed bump reference data. Next, the similarity feature is input into the speed bump detection model to obtain the driving detection result that characterizes the driving state of the vehicle. Finally, based on the driving detection result, a driving warning signal is generated. The present application obtains the driving detection result that characterizes whether the vehicle has passed through the speed bump by inputting the similarity feature between the real-time driving data and the speed bump reference data into a pre-trained speed bump detection model, and generates a corresponding driving warning signal when the driving detection result characterizes that the vehicle has passed through the speed bump. This can not only improve the computational efficiency of the speed bump detection process and the accuracy of the speed bump detection results, but also can promptly remind the driver to adjust the vehicle speed and driving behavior through the driving warning signal, thereby effectively improving the driving safety of the vehicle.
[0058] Regarding the specific method of obtaining the speed bump detection model, in one embodiment, the above-mentioned real-time driving data is time series data collected by an IMU device; Figure 2 As shown, before the above step S110, the following steps are also included:
[0059] Step S210, obtaining sample data; the aforementioned sample data includes speed bump sample data and non-speed bump sample data.
[0060] The sample data refers to a large amount of dynamic data generated by the vehicle during driving, which is pre-collected by the IMU device and recorded as time series sample data.
[0061] Specifically, the specific expression form of the above-mentioned time series sample data may include non-speed bump time series sample data representing that the vehicle has not passed through the speed bump, and speed bump time series sample data representing that the vehicle has passed through the speed bump.
[0062] Step S220, performing fitting processing on the speed bump sample data to obtain speed bump reference data.
[0063] Among them, the speed bump sample data, that is, the speed bump sample data contained in the sample data, refers to the speed bump time series sample data recorded by a large amount of dynamic data generated by a vehicle passing through a speed bump, which is pre-collected through an IMU device; the speed bump reference data refers to the speed bump reference data obtained by fitting the speed bump sample data.
[0064] Specifically, the speed bump reference data can be obtained by fitting the speed bump time series sample data based on the DTW algorithm.
[0065] Step S230, obtaining sample similarity features between the speed bump reference data and the non-speed bump sample data.
[0066] Among them, the speed bump reference data refers to the speed bump reference data obtained by fitting the speed bump sample data; the non-speed bump sample data, that is, the non-speed bump sample data included in the sample data, refers to the non-speed bump time series sample data recorded by a large amount of dynamic data generated by the vehicle before passing through the speed bump, which is pre-collected by the IMU device.
[0067] Specifically, the sample similarity features between the speed bump reference data and the non-speed bump sample data can be obtained by performing fitting processing on the speed bump reference data and the non-speed bump sample data based on the DTW algorithm.
[0068] Step S240: construct a training data set based on the speed bump reference data, the non-speed bump sample data, and the sample similarity features.
[0069] Among them, the speed bump reference data refers to the speed bump reference data obtained by fitting the speed bump sample data; the non-speed bump sample data refers to the non-speed bump sample data contained in the sample data; the sample similarity feature refers to the sample similarity feature between the speed bump reference data and the non-speed bump sample data; the training data set refers to the training data set constructed based on the speed bump reference data, the non-speed bump sample data, and the sample similarity feature.
[0070] Specifically, in the process of constructing a training data set based on speed bump reference data, non-speed bump sample data, and sample similarity features, a random forest algorithm can be used to screen sample similarity features, thereby reducing the redundancy between sample similarity features and reducing the risk of overfitting.
[0071] Step S250: Use the training data set to train the logistic regression model to obtain a speed bump detection model.
[0072] Among them, the training data set refers to a training data set constructed based on speed bump reference data, non-speed bump sample data, and sample similarity features; the speed bump detection model refers to the speed bump detection model obtained by training the logistic regression model using the training data set.
[0073] Specifically, in the process of training the logistic regression model using the training data set, the model parameters of the logistic regression model can be adjusted multiple times based on actual needs to improve the accuracy of the classification results output by the model after training is completed (i.e., to improve the accuracy of the driving detection results output by the speed bump detection model).
[0074] The embodiment of the present application constructs a training data set for training a logistic regression model based on speed bump reference data, non-speed bump sample data, and sample similarity features, and uses the trained logistic regression model as a speed bump detection model. This not only improves the computational efficiency of the speed bump detection process, but also effectively improves the accuracy of the speed bump detection results.
[0075] Regarding the specific method of obtaining sample data, in one embodiment, as Figure 3 As shown, the above step S210 specifically includes the following steps:
[0076] Step S310, denoising the initial sample data to obtain intermediate sample data.
[0077] Among them, the initial sample data refers to the initial time series sample data recorded by a large amount of dynamic data generated by the vehicle during driving, which is pre-collected by the IMU device; the intermediate sample data refers to the intermediate sample data obtained after denoising the initial sample data.
[0078] Specifically, the specific method of denoising the initial sample data may be to use a filtering algorithm to denoise the initial sample data to remove high-frequency noise that may be contained in the initial sample data; the aforementioned filtering algorithm may include filtering algorithms in the form of Kalman filtering, fourth-order BF low-pass filtering, etc.
[0079] In practical applications, in the process of denoising the initial sample data, only the Kalman filter algorithm can be used, or only the fourth-order BF low-pass filter algorithm can be used, or both the Kalman filter algorithm and the fourth-order BF low-pass filter algorithm can be used.
[0080] Step S320, normalize the intermediate sample data to obtain sample data.
[0081] The intermediate sample data refers to the intermediate sample data obtained after the initial sample data is denoised; the sample data refers to the sample data obtained after the intermediate sample data is normalized.
[0082] Specifically, the sample data includes speed bump sample data and non-speed bump sample data.
[0083] In practical applications, since there may be a certain time distribution offset between the initial sample data collected by different sensors in the IMU device, after removing the high-frequency noise in the initial sample data and obtaining the intermediate sample data, it is also necessary to normalize the intermediate sample data and scale the intermediate sample data to a uniform range to eliminate the scale differences between the data collected by different sensors, thereby improving the quality of the sample data.
[0084] The embodiment of the present application eliminates the noise and offset that may exist in the collected sample data by performing denoising and normalization processing on the initial sample data in sequence, which not only improves the quality of the sample data, but also effectively improves the accuracy of the speed bump detection results.
[0085] Regarding the specific method of obtaining the speed bump reference data, in one embodiment, the above step S220 specifically includes:
[0086] The dynamic time normalization algorithm is used to fit the speed bump sample data to obtain the speed bump reference data.
[0087] Among them, the dynamic time warping algorithm is the DTW (Dynamic Time Warping, DTW) dynamic time warping algorithm; the speed bump sample data is the speed bump sample data contained in the sample data; the speed bump reference data refers to the speed bump reference data obtained after the speed bump sample data is fitted by the dynamic time warping algorithm.
[0088] Specifically, the specific form of the speed bump sample data can be the speed bump time series sample data recorded by a large amount of dynamic data generated by the vehicle when passing through the speed bump, which is pre-collected through the IMU device; based on this, the speed bump sample data is fitted by adopting the dynamic time normalization algorithm, which can not only solve the problems of unequal length and time distribution offset that may exist in the speed bump time series sample data, but also effectively improve the accuracy of the speed bump reference data.
[0089] The embodiment of the present application adopts a dynamic time normalization algorithm to fit the speed bump sample data to obtain the speed bump reference data, thereby effectively ensuring the data quality of the speed bump reference data, thereby ensuring the computational efficiency of the speed bump detection process and the accuracy of the speed bump detection results.
[0090] Regarding the specific method of generating a driving warning signal and determining a power assist adjustment strategy, in one embodiment, as Figure 4 As shown, the above step S140 specifically includes the following steps:
[0091] Step S410: When the driving detection result indicates that the vehicle has passed through a speed bump, a driving warning signal is generated according to a preset warning mechanism.
[0092] Among them, the driving detection result is the driving detection result that characterizes the driving status of the vehicle; the preset early warning mechanism refers to the early warning mechanism pre-set in the vehicle control system for reminding the driver of the vehicle that the vehicle is currently passing through a speed bump; the driving warning signal refers to the driving warning signal generated by the vehicle control system according to the preset early warning mechanism when the vehicle control system receives the driving detection result characterizing that the vehicle has passed through a speed bump.
[0093] Specifically, the preset warning mechanism can be either a warning mechanism set by default in the vehicle control system or a warning mechanism set by the user in the vehicle control system.
[0094] In practical applications, specific forms of driving warning signals may include sound warning signals, visual warning signals, vibration warning signals and other specific types.
[0095] Step S420: determining a power assistance adjustment strategy based on the current vehicle motion state.
[0096] Among them, the current vehicle motion state refers to the current vehicle driving state detected by the vehicle control system when the driving detection result indicates that the vehicle has passed through a speed bump; the power assistance adjustment strategy refers to the power assistance adjustment strategy determined by the vehicle control system based on the current vehicle motion state after receiving the driving detection result indicating that the vehicle has passed through a speed bump.
[0097] In actual applications, when the vehicle type is an electric power-assisted bicycle with a drive motor, the specific forms of the power-assisted adjustment strategy may include specific types such as a motor output power adjustment strategy and a power-assisted mode adjustment strategy; the above-mentioned step S410 and the above-mentioned step S420 may be performed either selectively (i.e., only executing the above-mentioned step S410 or the above-mentioned step S420), or may be performed simultaneously (i.e., executing the above-mentioned step S410 or the above-mentioned step S420 simultaneously).
[0098] The embodiment of the present application generates a driving warning signal according to a preset early warning mechanism when the driving detection results indicate that the vehicle has passed over a speed bump, and determines a power assistance adjustment strategy based on the current vehicle motion state. This not only enables the driver to be reminded in time to adjust the vehicle speed and driving behavior when the vehicle passes over a speed bump, but also effectively improves the driving safety of the vehicle.
[0099] Regarding the specific forms of the driving warning signal and the power assist adjustment strategy, in one embodiment, the driving warning signal includes at least one of a sound warning signal, a visual warning signal, and a vibration warning signal; the power assist adjustment strategy includes at least one of a motor output power adjustment strategy and a power assist mode adjustment strategy.
[0100] Among them, the driving warning signal refers to the driving warning signal generated by the vehicle control system according to the preset early warning mechanism when the vehicle control system receives the driving detection result indicating that the vehicle has passed through a speed bump; the power assist adjustment strategy refers to the power assist adjustment strategy determined by the vehicle control system based on the current vehicle motion state after the vehicle control system receives the driving detection result indicating that the vehicle has passed through a speed bump; the motor output power adjustment strategy refers to the adjustment strategy of the power assist motor output power determined based on the current vehicle motion state.
[0101] Specifically, the specific form of the sound warning signal can be in the form of a voice broadcast to remind the driver of the vehicle that the vehicle he is driving is currently passing over a speed bump; the specific form of the visual warning signal can be either a warning icon displayed on the vehicle display screen, or the vehicle display screen flashing based on a preset frequency; the specific form of the vibration warning signal can include specific vibration types such as long vibration, short vibration, and cyclic vibration. When the vehicle type is an electric assisted bicycle with a drive motor, the aforementioned vibration type can be specifically manifested as handle vibration and / or seat vibration, and the intensity and frequency of the vibration can be specifically determined by the vehicle control system based on the actual road conditions detected in the speed bump area; the specific form of the motor output power adjustment strategy In the case where the vehicle type is an electric power-assisted bicycle with a drive motor, the specific value by which the output power of the power-assisted motor needs to be adjusted (for example, the specific value by which the output power of the power-assisted motor needs to be reduced) can be determined based on the measurement parameters characterizing the vehicle's motion state, such as the current vehicle speed, acceleration, and sensor data collected by the IMU device, or environmental data such as the speed bump slope and the actual road conditions in the speed bump area detected by the vehicle control system; the specific manifestation of the power-assisted mode adjustment strategy, in the case where the vehicle type is an electric power-assisted bicycle with a drive motor, can be a specific adjustment strategy for adjusting the power-assisted intensity of the power-assisted motor, or switching the power-assisted mode of the power-assisted motor (for example, switching from "strong power-assisted mode" to "balanced power-assisted mode").
[0102] In actual applications, the specific forms of the sound warning signal, visual warning signal, and vibration warning signal can be set by the user according to personal preferences (for example, the user can set the color and display style of the warning icon displayed on the vehicle display screen based on personal preferences, and can also set the specific vibration type generated by the corresponding parts of the vehicle when the vehicle passes through the speed bump area); in the case where the vehicle type is an electric assisted bicycle with a drive motor, when the vehicle control system detects that the vehicle has exited the speed bump area, it can also restore the output power of the power-assisted motor to the set value before the vehicle passed the speed bump, so as to ensure the comfort and stability of the user's riding process.
[0103] Furthermore, in the case where the vehicle type is an electric assisted bicycle with a drive motor, the vehicle control system can also detect the user's riding frequency and pedaling force in real time through sensors installed in the vehicle, so that when a driving detection result indicating that the vehicle has passed through a speed bump is received, if it is detected that the user's riding frequency suddenly decreases, a control instruction for reducing the output power of the power-assisted motor is output to reduce the power-assisted intensity of the power-assisted motor, thereby effectively reducing the safety risks that may be caused by excessive acceleration of the vehicle when the vehicle passes through a speed bump.
[0104] The embodiments of the present application provide driving warning signals in the form of sound, vision, vibration, etc., when the driving detection results indicate that the vehicle has passed over a speed bump, and determine power assistance adjustment strategies such as motor output power adjustment strategy and power assistance mode adjustment strategy according to the current vehicle motion state. This not only enables the driver to be reminded in time to adjust the vehicle speed and driving behavior when the vehicle passes over a speed bump, but also effectively ensures the driving safety of the vehicle.
[0105] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0106] Based on the same inventive concept, the embodiment of the present application also provides a speed bump detection device for implementing the speed bump detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more speed bump detection device embodiments provided below can refer to the limitations of the speed bump detection method above, and will not be repeated here.
[0107] In one embodiment, Figure 5 As shown, a speed bump detection device is provided, the device comprising:
[0108] A real-time data acquisition module 510 is used to acquire real-time driving data of the vehicle;
[0109] A similarity acquisition module 520, used to acquire similarity features between the real-time driving data and the speed bump reference data;
[0110] A detection result output module 530, used to input the similarity feature into a speed bump detection model to obtain a driving detection result representing the driving state of the vehicle;
[0111] The warning signal generating module 540 is used to generate a driving warning signal based on the driving detection result.
[0112] In one embodiment, the above-mentioned device also includes: a detection model training module, which is used to obtain sample data; the sample data includes speed bump sample data and non-speed bump sample data; the speed bump sample data is fitted to obtain the speed bump reference data; the sample similarity feature between the speed bump reference data and the non-speed bump sample data is obtained; a training data set is constructed based on the speed bump reference data, the non-speed bump sample data, and the sample similarity feature; and the logistic regression model is trained using the training data set to obtain the speed bump detection model.
[0113] In one of the embodiments, the detection model training module is further used to perform denoising processing on the initial sample data to obtain intermediate sample data; and perform normalization processing on the intermediate sample data to obtain the sample data.
[0114] In one of the embodiments, the detection model training module is further used to adopt a dynamic time normalization algorithm to perform fitting processing on the speed bump sample data to obtain the speed bump reference data.
[0115] In one embodiment, the warning signal generating module 540 is specifically used to generate the driving warning signal according to a preset warning mechanism when the driving detection result indicates that the vehicle has passed through a speed bump; and determine the power assistance adjustment strategy based on the current vehicle motion state.
[0116] In one embodiment, in the warning signal generating module 540, the driving warning signal includes at least one of a sound warning signal, a visual warning signal, and a vibration warning signal; the power assist adjustment strategy includes at least one of a motor output power adjustment strategy and a power assist mode adjustment strategy.
[0117] Each module in the above speed bump detection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.
[0118] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.
[0119] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.
[0120] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.
[0121] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0122] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.
[0123] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0124] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A speed bump detection method, characterized in that: The method comprises: Obtain real-time driving data of vehicles; Acquire similarity features between the real-time driving data and speed bump reference data; Inputting the similarity feature into a speed bump detection model to obtain a driving detection result representing the driving state of the vehicle; Based on the driving detection result, a driving warning signal is generated.
2. The method according to claim 1, characterized in that: The real-time driving data is time series data collected by an IMU device; Before acquiring the real-time driving data of the vehicle, the method further includes: Acquire sample data; the sample data includes speed bump sample data and non-speed bump sample data; Performing fitting processing on the speed bump sample data to obtain the speed bump reference data; Acquire sample similarity features between the speed bump reference data and the non-speed bump sample data; Constructing a training data set based on the speed bump sequence data, the non-speed bump sample data, and the sample similarity features; The training data set is used to train a logistic regression model to obtain the speed bump detection model.
3. The method according to claim 2, characterized in that The obtaining of sample data comprises: Perform denoising on the initial sample data to obtain intermediate sample data; The intermediate sample data is normalized to obtain the sample data.
4. The method according to claim 2, characterized in that: The fitting process is performed on the speed bump sample data to obtain the speed bump reference data, including: A dynamic time normalization algorithm is used to perform fitting processing on the speed bump sample data to obtain the speed bump reference data.
5. The method according to any one of claims 1 to 4, characterized in that The generating a driving warning signal based on the driving detection result includes: When the driving detection result indicates that the vehicle has passed through a speed bump, generating the driving warning signal according to a preset warning mechanism; Determine the power assistance adjustment strategy based on the current vehicle motion state.
6. The method according to claim 5, characterized in that The driving warning signal includes at least one of a sound warning signal, a visual warning signal, and a vibration warning signal; the power assist adjustment strategy includes at least one of a motor output power adjustment strategy and a power assist mode adjustment strategy.
7. A speed bump detection device, characterized in that: The device comprises: A real-time data acquisition module is used to acquire real-time driving data of the vehicle; A similarity acquisition module, used to acquire similarity features between the real-time driving data and the speed bump reference data; A detection result output module, used for inputting the similarity feature into a speed bump detection model to obtain a driving detection result representing the driving state of the vehicle; The warning signal generating module is used to generate a driving warning signal based on the driving detection result.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.