Method, device, storage medium and vehicle for detecting vehicle motion state

Abstract

The present application discloses a method, device, storage medium and vehicle for detecting the motion state of a vehicle. The method includes: obtaining the time domain data of the vehicle, the time domain data including the first acceleration data of the vehicle when it is stationary and the second acceleration data of the vehicle at present; converting the time domain data into frequency domain data, the frequency domain data including the first frequency domain data corresponding to the first acceleration data and the second frequency domain data corresponding to the second acceleration data; determining the motion state of the vehicle according to the second frequency domain data when the first frequency domain data meets the preset conditions; determining the current motion state of the vehicle according to the second acceleration data when the first frequency domain data does not meet the preset conditions. The above scheme can accurately detect the motion state of the vehicle, so as to provide stable and reliable navigation and positioning results in complex urban environments or GNSS-denied environments.

Description

Technical Field

[0001] The present application relates to the field of vehicle detection technology, and in particular to a method, device, storage medium and vehicle for detecting the motion state of a vehicle. Background Art

[0002] In recent years, with the rapid development of global satellite navigation systems, inertial devices, and multi-sensor fusion technologies, the positioning accuracy and robustness of integrated navigation systems in dynamic environments have significantly improved. However, in complex urban environments or GNSS-denied environments (such as underground garages), inertial device bias errors accumulate, severely limiting the stability and reliability of integrated navigation systems. While zero-speed constraints can effectively suppress inertial device bias drift, this requires accurate detection of the vehicle's current motion state. Currently, traditional stationary detection methods suffer from a high degree of false detection in low-speed, straight-line scenarios for electric vehicles with low vibration. For gasoline vehicles with high vibration, the IMU data statistics show no significant difference between stationary and low-speed motion. Traditional methods are unable to detect stationary vehicles and suffer from significant errors. This makes it difficult to provide stable and reliable navigation and positioning results in complex environments. Summary of the Invention

[0003] The purpose of the embodiments of the present application is to provide a method, device, storage medium and vehicle for detecting the motion state of a vehicle, so as to solve the problem in the prior art that the current motion state of the vehicle cannot be accurately detected.

[0004] To achieve the above objectives, the present application provides, in a first aspect, a method for detecting a vehicle motion state, the method comprising:

[0005] Acquiring time domain data of the vehicle, the time domain data including first acceleration data of the vehicle when it is in a stationary state and current second acceleration data of the vehicle;

[0006] Converting the time domain data into frequency domain data, where the frequency domain data includes first frequency domain data corresponding to the first acceleration data and second frequency domain data corresponding to the second acceleration data;

[0007] When the first frequency domain data satisfies a preset condition, determining the motion state of the vehicle according to the second frequency domain data;

[0008] When the first frequency domain data does not meet the preset condition, the current motion state of the vehicle is determined according to the second acceleration data.

[0009] In an embodiment of the present application, the first frequency domain data includes multiple one-to-one corresponding first power spectrum densities and first frequency values, and the method also includes: when the maximum value among all the first power spectrum densities is greater than the power spectrum density threshold, and the difference between the first frequency value corresponding to the maximum value and the cutoff frequency is less than the frequency difference threshold, determining that the first frequency domain data meets the preset conditions.

[0010] In an embodiment of the present application, determining the current motion state of the vehicle based on the second acceleration data includes: dividing the second acceleration data into multiple first signal segments through each first time window; determining the y-axis range of the accelerometer of each first signal segment; when the y-axis range of the accelerometer of all first signal segments is less than the stationary detection threshold corresponding to the first time window, determining that the current motion state of the vehicle is a stationary state; when the y-axis range of the accelerometer of any first signal segment corresponding to any first time window is greater than the stationary detection threshold corresponding to the any first time window, determining that the current motion state of the vehicle is a driving state.

[0011] In an embodiment of the present application, the method also includes: determining a stationary signal segment in the first acceleration data; dividing the stationary signal segment into multiple second signal segments through each first time window; determining the accelerometer y-axis range of each second signal segment; determining the first maximum value of the accelerometer y-axis range of all second signal segments corresponding to the first window in all first time windows as the first stationary detection threshold corresponding to the first window; and determining the second stationary detection threshold corresponding to the first window based on the average value and standard deviation of the accelerometer y-axis range of all second signal segments corresponding to the second windows in all first time windows.

[0012] In an embodiment of the present application, determining a stationary signal segment in the first acceleration data includes: traversing the first acceleration data in sequence through a preset sliding window to divide the first acceleration data into multiple third signal segments; dividing each third signal segment into multiple fourth signal segments through each first time window; dividing the first acceleration data into multiple fifth signal segments through each first time window; determining the second maximum value in the y-axis range of the accelerometer of all fourth signal segments corresponding to each first time window and the first minimum value in the y-axis range of the accelerometer of all fifth signal segments corresponding to each first time window; for each third signal segment, when the product of the first minimum value corresponding to each first time window and the preset multiple is greater than the corresponding second maximum value, determining that the third signal segment is a stationary signal segment in the first acceleration data, and stopping traversing the first acceleration data.

[0013] In an embodiment of the present application, the second frequency domain data includes multiple one-to-one corresponding second power spectrum densities and second frequency values. Determining the current motion state of the vehicle based on the second frequency domain data includes: when the difference between the second frequency value corresponding to the maximum value in all second power spectrum densities and the cutoff frequency is less than the frequency difference threshold, determining that the current motion state of the vehicle is a stationary state; when the difference between the second frequency value corresponding to the maximum value in all second power spectrum densities and the cutoff frequency is greater than or equal to the frequency difference threshold, determining that the current motion state of the vehicle is a driving state.

[0014] In an embodiment of the present application, the time domain data includes the three-axis modulus values ​​of the accelerometer, and the frequency domain data includes multiple one-to-one corresponding power spectrum densities and frequency values. Converting the time domain data into frequency domain data includes: performing Fourier transform on the three-axis modulus values ​​of the accelerometer to obtain a transformation result; obtaining sampling parameters for the three-axis modulus values ​​of the accelerometer; and determining multiple one-to-one corresponding power spectrum densities and frequency values ​​based on the sampling parameters and the transformation result.

[0015] A second aspect of the present application provides a device for detecting a vehicle motion state, comprising:

[0016] a memory configured to store instructions;

[0017] The processor is configured to call instructions from the memory and implement the above-mentioned method for detecting the motion state of a vehicle when executing the instructions.

[0018] A third aspect of the present application provides a vehicle, comprising:

[0019] Inertial sensors, used to detect vehicle time domain data;

[0020] According to the above device for detecting the motion state of a vehicle.

[0021] A fourth aspect of the present application provides a machine-readable storage medium having stored thereon instructions for enabling a machine to execute the above-mentioned method for detecting the motion state of a vehicle.

[0022] The above technical solution uses adaptive dual-modal combined navigation to detect vehicle stationary conditions. Time-domain acceleration data is converted into frequency-domain data to analyze the periodicity and magnitude of the vehicle's vibration. For electric vehicles with low vibration and weak periodicity, acceleration time-domain data is used to determine if the vehicle is stationary. For gasoline vehicles with high vibration and pronounced periodicity, frequency-domain data is used. This allows accurate detection of the vehicle's motion state, enabling zero-speed constraints and providing stable and reliable navigation and positioning results in complex urban environments or GNSS-denied environments.

[0023] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present application but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0025] Figure 1A schematic diagram of a flow chart of a method for detecting a vehicle motion state according to an embodiment of the present application is shown;

[0026] Figure 2a A schematic diagram schematically illustrates the results of a stationary tram detection using a traditional method according to an embodiment of the present application;

[0027] Figure 2b A schematic diagram schematically illustrates the results of a stationary tram detection using an innovative method according to an embodiment of the present application;

[0028] Figure 3a A schematic diagram schematically illustrates the results of a stationary oil truck detection using a traditional method according to an embodiment of the present application;

[0029] Figure 3b A schematic diagram schematically illustrates the results of a stationary oil truck detection using an innovative method according to an embodiment of the present application;

[0030] Figure 4 The following schematically shows a structural block diagram of a device for detecting the motion state of a vehicle according to an embodiment of the present application;

[0031] Figure 5 The schematic diagram shows the structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0032] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0033] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back, etc.), such directional indications are only used to explain the relative position relationship, movement status, etc. between the various components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0034] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0035] Figure 1 The following schematically shows a flow chart of a method for detecting the motion state of a vehicle according to an embodiment of the present application. Figure 1 As shown, an embodiment of the present application provides a method for detecting the motion state of a vehicle, the method comprising:

[0036] S102 , obtaining time domain data of the vehicle, where the time domain data includes first acceleration data of the vehicle when it is in a stationary state and current second acceleration data of the vehicle.

[0037] S104 , converting the time domain data into frequency domain data, where the frequency domain data includes first frequency domain data corresponding to the first acceleration data and second frequency domain data corresponding to the second acceleration data.

[0038] S106: Determine whether the first frequency domain data meets a preset condition. If yes, execute S108; if no, execute S110.

[0039] S108: Determine the motion state of the vehicle according to the second frequency domain data.

[0040] S110: Determine the current motion state of the vehicle according to the second acceleration data.

[0041] It can be understood that time-domain data refers to a data sequence recorded with time as the horizontal axis and physical quantities (such as voltage, acceleration, sound intensity, etc.) as the vertical axis. It directly reflects the dynamic characteristics of a signal or phenomenon over time and is the most common form of raw data. Vehicle time-domain data refers to physical quantities or state parameters that continuously change over time and are collected in real time by sensors or controllers during vehicle operation. This type of data, with time as the horizontal axis, directly reflects the dynamic behavior and operating status of various vehicle components and is a core data source for fields such as vehicle performance analysis, fault diagnosis, and intelligent driving. In the embodiments of the present application, time-domain data includes but is not limited to first acceleration data of a stationary vehicle and second acceleration data of the vehicle's current state. That is, the first acceleration data is the time-domain data of the vehicle's acceleration when stationary, and the second acceleration data is the time-domain data of the vehicle's current state. Specifically, the vehicle's time-domain data can be detected by inertial sensors. Inertial sensors (such as accelerometers, gyroscopes, and magnetometers) are core components for detecting an object's motion state. By collecting data such as acceleration, angular velocity, and magnetic field strength, they provide essential information for attitude estimation, navigation, and motion analysis. However, complex urban environments or GNSS (Global Navigation Satellite System)-denied environments, such as underground parking garages, can lead to accumulated errors in the inertial device's zero-bias, severely limiting the stability and reliability of integrated navigation systems. This problem can be effectively mitigated by applying a zero-speed constraint, but this requires accurate detection of the vehicle's current motion state—that is, whether it is stationary or moving. Electric vehicle motor vibration is typically low, primarily in medium- and high-frequency ranges, with weak periodicity and dispersed energy. The vibration frequency periodicity of gasoline vehicles is more pronounced, especially in the low-frequency range of engine ignition and mechanical vibration, which exhibit strong periodicity. On the other hand, electric vehicle motor vibration is minimal, resulting in significant discrepancies in inertial device detection data when stationary and in low-speed motion. For gasoline vehicles with high engine vibration, the jitter in the inertial device's detection data at rest is the same as, or even greater than, that at low speeds. Therefore, it's possible to analyze the vehicle's vibration frequency and periodicity characteristics and perform different static detection methods for vehicles with different vibration conditions to determine the vehicle's current motion state.

[0042] Specifically, time-domain data is the starting point for understanding dynamic systems, directly recording the changes in physical quantities over time. It is widely used in real-time monitoring, anomaly detection, and trend prediction, and is a fundamental data format in fields such as signal processing and machine learning. Time-domain analysis can extract key events and statistical features. Time-domain data can be further converted into frequency-domain data, enabling in-depth analysis of the periodicity of vehicle vibration frequencies. Frequency-domain data is a mathematical transformation (such as the Fourier transform) that converts time-domain signals (physical quantities that vary over time) into a data format with frequency on the horizontal axis and energy or amplitude on the vertical axis. It reveals the distribution patterns of different frequency components in a signal and is a core tool for analyzing phenomena such as periodicity, vibration, and noise. Specifically, first acceleration data can be converted into corresponding first frequency-domain data, and second acceleration data can be converted into corresponding second frequency-domain data. In embodiments of the present application, frequency-domain data can identify the dominant frequency of engine vibration and separate noise from valid signals. Therefore, when the vehicle is stationary, the first frequency-domain data can be used to determine whether it exhibits significant periodicity in vibration frequency. Specifically, preset conditions for distinguishing periodicity in vibration frequency can be set for the first frequency-domain data. If the first frequency domain data meets the preset conditions, it can be determined that the vehicle's vibration frequency periodicity is significant. Then, using the second frequency domain data representing the vehicle's current vibration frequency periodicity, the motion state of vehicles with high engine vibration can be detected. If the first frequency domain data does not meet the preset conditions, it can be determined that the vehicle's vibration frequency periodicity is weak. Weak periodicity is typically associated with electric vehicles, which have low vibration levels and exhibit significant differences in the time domain data of inertial devices when stationary and in low-speed motion. Therefore, the second acceleration data can be analyzed to determine the vehicle's current motion state.

[0043] The above technical solution uses adaptive dual-modal combined navigation to detect vehicle stationary conditions. Time-domain acceleration data is converted into frequency-domain data to analyze the periodicity and magnitude of the vehicle's vibration. For electric vehicles with low vibration and weak periodicity, acceleration time-domain data is used to determine if the vehicle is stationary. For gasoline vehicles with high vibration and pronounced periodicity, frequency-domain data is used. This allows accurate detection of the vehicle's motion state, enabling zero-speed constraints and providing stable and reliable navigation and positioning results in complex urban environments or GNSS-denied environments.

[0044] In an embodiment of the present application, the time domain data includes the three-axis modulus values ​​of the accelerometer, and the frequency domain data includes multiple one-to-one corresponding power spectrum densities and frequency values. Converting the time domain data into frequency domain data includes: performing Fourier transform on the three-axis modulus values ​​of the accelerometer to obtain a transformation result; obtaining sampling parameters for the three-axis modulus values ​​of the accelerometer; and determining multiple one-to-one corresponding power spectrum densities and frequency values ​​based on the sampling parameters and the transformation result.

[0045] It is understood that vehicle time-domain data can be detected using inertial sensors, such as accelerometers. Accelerometers typically measure acceleration in three orthogonal directions (X, Y, and Z axes), and the modulus is the modulus of the vector sum of these three components. In other words, the triaxial modulus of the accelerometer is obtained by adding the squares of the accelerations along the three axes and taking the square root. It comprehensively reflects the vehicle's vibration. Specifically, a Fourier transform is performed on the triaxial modulus of the accelerometer to obtain the transformed result. Furthermore, the sampling parameters used by the accelerometer when acquiring the triaxial modulus can be obtained. These sampling parameters include, but are not limited to, the sampling frequency and the number of sampling points, which is the signal length of each sample. The power spectral density (PSD) and its corresponding frequency values ​​are calculated based on the sampling parameters and the transform result. For example, for the first acceleration data, the power spectral density and corresponding frequency values ​​when the vehicle is stationary can be determined using the aforementioned scheme. For the second acceleration data, the current power spectral density and corresponding frequency values ​​of the vehicle can be determined. It is understandable that the core of calculating the power spectral density and the corresponding frequency values ​​based on the three-axis modulus values ​​of the accelerometer is to analyze the energy distribution of the quantified acceleration at different frequencies through frequency domain data, which can more comprehensively capture the multi-directional vibration characteristics and identify periodic components.

[0046] Specifically, in the embodiment of the present application, whether the time domain data has an obvious periodic pattern can be determined based on the power spectrum density value. The power spectrum density calculation process is shown in the following formula (1):

[0047] (1)

[0048] Where, It refers to the The three-axis modulus of the accelerometer, is the fast Fourier transform function, Refers to the transformation result after fast Fourier transform, is the number of sampling points, is the sampling frequency, For the The power spectrum density corresponding to the three-axis modulus value of the accelerometer is: It refers to the The frequency value corresponding to the three-axis modulus value of the accelerometer, is the frequency value and power spectrum density corresponding to the maximum power spectrum density, k refers to the The serial number of the three-axis modulus value of the accelerometer. The value of N can be 100.

[0049] In an embodiment of the present application, the first frequency domain data includes multiple one-to-one corresponding first power spectrum densities and first frequency values, and the method also includes: when the maximum value among all the first power spectrum densities is greater than the power spectrum density threshold, and the difference between the first frequency value corresponding to the maximum value and the cutoff frequency is less than the frequency difference threshold, determining that the first frequency domain data meets the preset conditions.

[0050] It's understandable that the vibration energy of gasoline vehicles is typically concentrated in the low-frequency range, resulting in high vibration levels and sharp main frequency peaks and harmonics. Therefore, the measurement dynamic range of their onboard inertial sensors is relatively small. Therefore, the raw data from their inertial devices (IMU data) is typically low-pass filtered. After low-pass filtering, the power spectral density of the IMU data is concentrated at the low-pass filter cutoff frequency. Electric vehicles, on the other hand, have dispersed energy, with a significant proportion of high frequencies. Based on these characteristics, corresponding preset conditions can be set to determine whether a vehicle is a gasoline vehicle or an electric vehicle. Specifically, if the maximum value among all first power spectral densities is greater than a power spectral density threshold, and the difference between the first frequency value corresponding to the maximum value and the cutoff frequency is less than a frequency difference threshold, the first frequency domain data is determined to meet the preset conditions. Otherwise, the first frequency domain data is considered to not meet the preset conditions. The power spectral density is normalized during calculation, and the power spectral density threshold is set based on the normalized data. Technicians can set the frequency difference threshold and power spectral density threshold based on experience.

[0051] Specifically, in an embodiment of the present application, the function expression for determining whether the first frequency domain data meets the preset condition is shown in the following formula (2):

[0052] (2)

[0053] In the formula, f is the frequency value corresponding to the maximum power spectrum density, p refers to the maximum value of the power spectrum density, is the low-pass filter cutoff frequency of the inertial sensor, is the frequency difference threshold, is the power spectrum density threshold, and the power spectrum density is normalized during calculation. If the first frequency domain data meets the preset conditions, it can be determined that the vibration frequency periodic characteristics of the vehicle are obvious. Then, using the second frequency domain data that characterizes the current vibration frequency periodic characteristics of the vehicle, the motion state of the vehicle with large engine vibration can be detected. If the first frequency domain data does not meet the preset conditions, it can be determined that the vibration frequency periodic characteristics of the vehicle are weak. Electric vehicles usually have weak periodic characteristics, and electric vehicles have small vibrations. The time domain data of inertial devices are quite different when stationary and in low-speed motion. Then, the second acceleration data can be analyzed to determine the current motion state of the vehicle. Among them, the frequency difference threshold can be 0.2, and the power spectrum density threshold can be 0.3.

[0054] In an embodiment of the present application, the second frequency domain data includes multiple one-to-one corresponding second power spectrum densities and second frequency values. Determining the current motion state of the vehicle based on the second frequency domain data includes: when the difference between the second frequency value corresponding to the maximum value in all second power spectrum densities and the cutoff frequency is less than the frequency difference threshold, determining that the current motion state of the vehicle is a stationary state; when the difference between the second frequency value corresponding to the maximum value in all second power spectrum densities and the cutoff frequency is greater than or equal to the frequency difference threshold, determining that the current motion state of the vehicle is a driving state.

[0055] It's understandable that for gasoline vehicles with high engine vibration, the jitter in IMU data at rest is the same as, or even greater than, that during low-speed motion. For gasoline vehicles with severe engine idle jitter at rest, the vibration can be greater than or equal to that during low-speed driving, resulting in similar ranges (maximum - minimum). Therefore, the range method cannot identify the stationary state. However, if the difference between the second frequency value corresponding to the maximum value in all second power spectral densities in the second frequency domain data and the cutoff frequency is less than the frequency difference threshold, the gasoline vehicle's current motion state is stationary. If the difference between the second frequency value corresponding to the maximum value in all second power spectral densities and the cutoff frequency is greater than or equal to the frequency difference threshold, the vehicle's current motion state is determined to be driving. Due to the limited dynamic range of in-vehicle integrated navigation, the raw data from the inertial navigation device is typically low-pass filtered to remove high-frequency noise and retain low-frequency signals. When the engine is vibrating strongly and at rest, the vibration frequency exceeds the low-pass filter cutoff frequency. After low-pass filtering, the power spectral density of the IMU data is concentrated at the filter cutoff frequency. Therefore, using the periodic frequency can detect the stationary state of vehicles with high engine vibration. The above solution can accurately detect the stationary state of the vehicle, and is accurate and efficient.

[0056] The above scheme not only takes into account the maximum value of the power spectrum density and its corresponding frequency value, but also introduces the cutoff frequency and frequency difference threshold as the basis for judgment. This method can overcome the limitations of the traditional range method in identifying the stationary state of a gasoline vehicle, especially when the engine idle shakes violently, it can still accurately judge whether the vehicle is in a stationary state. In this way, real-time monitoring and precise control of the vehicle's motion state can be achieved, thereby improving the safety and stability of vehicle driving. For example, in an automatic driving system, accurately judging the vehicle's motion state is the basis for realizing functions such as automatic navigation and obstacle avoidance. Therefore, the embodiments of the present application have broad application prospects in the fields of vehicle intelligence and automation.

[0057] In an embodiment of the present application, determining the current motion state of the vehicle based on the second acceleration data includes: dividing the second acceleration data into multiple first signal segments through each first time window; determining the y-axis range of the accelerometer of each first signal segment; when the y-axis range of the accelerometer of all first signal segments is less than the stationary detection threshold corresponding to the first time window, determining that the current motion state of the vehicle is a stationary state; when the y-axis range of the accelerometer of any first signal segment corresponding to any first time window is greater than the stationary detection threshold corresponding to the any first time window, determining that the current motion state of the vehicle is a driving state.

[0058] As can be understood, electric vehicle motor vibration is minimal, and the IMU data detected by the inertial sensor differs significantly when stationary and in low-speed motion. Therefore, a stationary detection method with a mixed long and short window can be used to detect the vehicle's motion state. Specifically, the first time window can group data in chronological order and by a specific time length. Technicians can pre-set multiple first time windows of varying lengths and divide the collected second acceleration data into multiple first signal segments for analyzing the vehicle's motion state. The first signal segment represents a portion of the second acceleration data, and the length of each first signal segment is the length of the first time window used to divide the data. The length of the first time window can be flexibly set based on actual application scenarios and requirements to ensure accurate reflection of the vehicle's motion state. By setting a reasonable time window, acceleration data can be more effectively utilized, improving the accuracy and reliability of vehicle motion state detection. Specifically, the second acceleration data includes the y-axis acceleration detected by the accelerometer, which reflects the vehicle's longitudinal motion (forward / reverse). Furthermore, the accelerometer's y-axis range (the difference between the maximum and minimum values) in each first signal segment is counted as a statistic. If the y-axis accelerometer range of all first signal segments is less than the stationary detection threshold corresponding to the first time window, that is, if the y-axis accelerometer range of the first signal segments, regardless of whether they are divided by a long window or a short window, is less than the corresponding stationary detection threshold, the vehicle's current state of motion can be determined to be stationary. If the y-axis accelerometer range of any first signal segment corresponding to any first time window is greater than the stationary detection threshold corresponding to that first time window, the vehicle's current state of motion can be determined to be driving. In one specific embodiment, the first time window can use a long window and a short window. The mixed long and short window stationary detection uses the range (the difference between the maximum and minimum values) of the IMU data as a statistic. A corresponding stationary detection threshold, namely the y-axis accelerometer range threshold, is set for each first time window. Long window data is used to detect stable, long-term stationary states, while short window data is used to detect short-term stationary states. This compensates for the detection delay of the long window and reduces missed detections caused by the long window.

[0059] Specifically, in a specific embodiment, the function expression of the long window stillness detection model is shown in the following formula (3):

[0060] (3)

[0061] Where, is the y-axis range of the accelerometer in the long window, and the y-axis of the accelerometer is the forward axis. refers to the amount of data in the long window, It refers to the The y-axis acceleration, k refers to the The sequence number of the y-axis acceleration, is the long window stillness detection threshold, , q refers to the The sequence number of the y-axis acceleration. In the long window detection, if the accelerometer range meets the requirements of the stationary detection threshold, it means that the vehicle is stationary. In a specific embodiment, the long window can collect data within 4 seconds, where 400 data points can be included in 4 seconds.

[0062] The function expression of the short window stillness detection model is shown in the following formula (4):

[0063] (4)

[0064] Where, is the y-axis extreme error of the accelerometer within the short window, Refers to the amount of data in a short window, It refers to the The y-axis acceleration, is the short window stillness detection threshold, , n refers to the The sequence number of the y-axis acceleration. In the short window detection, if the accelerometer range meets the requirements of the stationary detection threshold, it means that the vehicle is stationary. In a specific embodiment, the short window can collect data within 1 second, where 100 data points can be included in 1 second.

[0065] In an embodiment of the present application, the method also includes: determining a stationary signal segment in the first acceleration data; dividing the stationary signal segment into multiple second signal segments through each first time window; determining the accelerometer y-axis range of each second signal segment; determining the first maximum value of the accelerometer y-axis range of all second signal segments corresponding to the first window in all first time windows as the first stationary detection threshold corresponding to the first window; and determining the second stationary detection threshold corresponding to the first window based on the average value and standard deviation of the accelerometer y-axis range of all second signal segments corresponding to the second windows in all first time windows.

[0066] It is understood that the stationary detection threshold can be obtained through calibration. Calibration of the stationary detection threshold requires using satellite-guided velocity detection in an open environment to detect a stationary vehicle. However, a stationary vehicle may still experience complex disturbances, such as getting on and off the vehicle, or walking around inside the vehicle, which can lead to inaccurate calibration thresholds. Therefore, during the calibration process, the first acceleration data needs to be tested for stationarity, and stationary signal segments within the first acceleration data are selected. Since the data lengths detected in different first time windows vary, the corresponding stationary detection thresholds will also vary. Therefore, stationary detection thresholds corresponding to different first time windows are calibrated. During the calibration process, the stationary signal segments in the collected first acceleration data can be divided into multiple second signal segments to calibrate the stationary detection threshold. The second signal segments are local signals within the stationary signal segments, and the length of each second signal segment is the length of the first time window. In one specific embodiment, the first time window can use a long window and a short window. The first window can be a long window, and the second window can be a short window. That is, the signal length intercepted by the first window is greater than the signal length intercepted by the second window. Furthermore, the accelerometer y-axis range is determined for each second signal segment. During the calibration process, the long window detects stable, long-term inactivity, allowing for a more relaxed inactivity detection threshold. The short window, however, uses a more stringent inactivity detection threshold. Therefore, the first maximum value of the accelerometer y-axis range for all second signal segments obtained by dividing the first window can be determined as the first inactivity detection threshold corresponding to that first window. The second inactivity detection threshold corresponding to the first window is determined based on the average and standard deviation of the accelerometer y-axis range for all second signal segments corresponding to the second window.

[0067] In an embodiment of the present application, determining a stationary signal segment in the first acceleration data includes: traversing the first acceleration data in sequence through a preset sliding window to divide the first acceleration data into multiple third signal segments; dividing each third signal segment into multiple fourth signal segments through each first time window; dividing the first acceleration data into multiple fifth signal segments through each first time window; determining the second maximum value in the y-axis range of the accelerometer of all fourth signal segments corresponding to each first time window and the first minimum value in the y-axis range of the accelerometer of all fifth signal segments corresponding to each first time window; for each third signal segment, when the product of the first minimum value corresponding to each first time window and the preset multiple is greater than the corresponding second maximum value, determining that the third signal segment is a stationary signal segment in the first acceleration data, and stopping traversing the first acceleration data.

[0068] It is understood that the stationary detection threshold can be obtained through calibration. Calibration of the stationary detection threshold requires using satellite-guided velocity detection in an open environment, with the vehicle stationary. However, a stationary vehicle may still experience complex disturbances, such as getting on and off, and walking inside the vehicle, which can lead to inaccurate calibration thresholds. Therefore, during the calibration process, the first acceleration data needs to be tested for stationarity, and stationary signal segments within the first acceleration data are selected. Specifically, a preset sliding window is used to sequentially traverse the first acceleration data to divide it into multiple third signal segments. The third signal segments are local signals of the first acceleration data, and the length of each third signal segment is the length of the preset sliding window. The preset sliding window is a sliding window pre-set by technicians for detecting stationary signal segments. The preset sliding window can be moved in a time sequence and with a fixed step size over the data sequence of the first acceleration data, and can cover a continuous subsequence. Furthermore, each third signal segment within the calibration sliding window is divided into multiple fourth signal segments by each first time window, and the first acceleration data is divided into multiple fifth signal segments by each first time window. The fourth signal segment is a local signal of the third signal segment, and the length of each fourth signal segment is the length of the first time window. The implicit condition here is that the preset sliding window is much longer than the length of the first time window, that is, the difference in length between the preset sliding window and the first time window is greater than or equal to a preset threshold, which can be set based on technical experience. Further, the second maximum value of the accelerometer y-axis range for all fourth signal segments and the first minimum value of the accelerometer y-axis range for all fifth signal segments are determined. That is, the maximum value of the accelerometer y-axis range of the local signal corresponding to the preset sliding window is detected using the first time window, and the minimum value of the accelerometer y-axis range of the global signal is detected using the first time window. Then, for each third signal segment, if the product of the first minimum value corresponding to each first time window and the preset multiple is greater than the corresponding second maximum value, the third signal segment is determined to be a stationary signal segment in the first acceleration data, and traversal of the first acceleration data stops. Specifically, the preset multiple can be set to 4.

[0069] Specifically, in a specific embodiment, the above-mentioned long window and short window stationary detection thresholds need to be calculated through calibration. The calibration needs to be performed when the vehicle is stationary using satellite guidance speed detection in an open environment. Due to the complex disturbances of the vehicle during the stationary process, such as getting on and off the vehicle, walking inside the vehicle, etc., the calibrated stationary detection threshold is inaccurate. Therefore, during the calibration process, it is necessary to perform a stationary test on the time domain data when the vehicle is stationary. The functional expression of the stationary detection model is shown in the following formula (5):

[0070] (5)

[0071] Where, is the maximum value of the y-axis range of the accelerometer calculated using the long window within the preset sliding window (local long window maximum value), The bth accelerometer y-axis range calculated using a long window within the preset sliding window. R refers to the length of the preset sliding window, which is generally 20 seconds of data and 2000 sample data. is the minimum value of the y-axis range of the global long window accelerometer (global long window minimum), which means the minimum value of the y-axis range of all long window accelerometers in the open environment when the vehicle is stationary. It refers to the maximum value of the y-axis range of the accelerometer calculated using the short window within the preset sliding window (local short window maximum value). is the dth accelerometer y-axis range calculated using a short window within the preset sliding window, is the minimum value of the global short window accelerometer y-axis range, indicating the minimum value of the y-axis range of all short window accelerometers in an open environment when the vehicle is stationary (global short window minimum value). , , c refers to the sequence number of the bth accelerometer y-axis range in the preset sliding window, and e refers to the sequence number of the dth accelerometer y-axis range in the preset sliding window.

[0072] By performing long- and short-window data analysis and processing on stationary data, data support can be provided for accurately identifying a vehicle's stationary state. Long-window data analysis can capture acceleration changes over longer periods of time, effectively filtering out short-term noise interference and ensuring that the vehicle remains stationary for extended periods. Short-window data analysis, on the other hand, can respond more quickly to sudden changes in acceleration. When a vehicle transitions from a stationary state to a moving state, short-window data analysis can quickly capture this change, improving detection sensitivity and real-time performance. By combining the results of long- and short-window data analysis, accurate and reliable detection of a vehicle's motion state can be achieved, providing strong data support for subsequent navigation, safety warnings, and other functions.

[0073] When the local maximum value satisfied by both the long window and the short window is less than 4 times the global minimum value, it indicates that the current state is relatively stable and the threshold calibration can be performed. During the calibration process, the long window detects a stable and long-term static state. The long window can use a more relaxed static detection threshold, while the static detection threshold calibration of the short window is more strict. Then, the first maximum value of the accelerometer y-axis range of all second signal segments obtained by dividing the first window can be determined as the first static detection threshold corresponding to the first window. The average value of the accelerometer y-axis range of all second signal segments corresponding to the second window plus 3 times the standard deviation is used as the second static detection threshold corresponding to the first window. The larger threshold is taken as the final threshold each time it is updated.

[0074] In an embodiment of the present application, the first acceleration data is time domain data measured when the vehicle is stationary, and after being converted into the first frequency domain data, whether the first frequency domain data meets the preset conditions is used as a judgment basis, and the corresponding data is selected according to the judgment result to analyze the motion state of the vehicle. In other words, the first acceleration data is the benchmark for selecting which data to analyze the motion state. In order to ensure the accuracy of the first acceleration data, it is preferably necessary to use the satellite navigation speed measurement results when the vehicle is stationary and in an open environment and the satellite navigation has a fixed solution. When the horizontal velocity modulus of the vehicle meets the conditions, it means that the vehicle is stationary and the first acceleration data can be collected. Specifically, the processor can obtain GNSS results and inertial sensor data, and preprocess and time synchronize the data. Among them, the GNSS results include the positioning results and speed measurement results of the vehicle, and the inertial sensor data can be 100Hz raw data. After the data is preprocessed, the GNSS results and inertial sensor data can be time synchronized based on PPS timing to obtain the first acceleration data with time attributes. Among them, the horizontal velocity modulus of the vehicle m / s, the first acceleration data can be collected.

[0075] In the embodiments of the present application, in order to verify the accuracy of the above solution, two groups of tests were carried out using an electric vehicle and a gasoline vehicle respectively.

[0076] 1. Electric vehicle test: This test data is collected using an electric vehicle. The motor has a very low vibration frequency when stationary. The integrated navigation product uses a satellite navigation module and an inertial navigation device. The sampling frequency of the inertial sensor is 100Hz. High-precision fiber-optic inertial navigation is used as the true value. The vehicle repeatedly drives forward and backward slowly in a straight line under an overpass to test the stationary detection performance in extreme and complex scenarios with low-speed straight driving. Figure 2a and Figure 2b , Figure 2a This is the result of the traditional method of tram stationary detection. Figure 2b This is the result of using the method for detecting the motion state of a tram in an embodiment of the present application. Among them, the label "0" represents the driving state, and the label "1" represents the stationary state. The accuracy of the two methods for stationary detection is shown in Table 1 below. As can be seen from the figure and table, the missed detection rate of trams of the two methods is 0, but the false detection rate of the traditional method is extremely high, while the false detection rate of the method in the embodiment of the present application is only 0.49%. Compared with the traditional method, the innovative method in the embodiment of the present application significantly improves the accuracy of stationary detection in complex low-speed straight-line driving scenarios with trams with less vibration.

[0077] Table 1 Results of stationary tram detection

[0078]

[0079] 2. Gasoline vehicle test: This test data is collected using a diesel vehicle, whose engine vibration frequency is very high. The integrated navigation product still uses satellite navigation modules and inertial navigation devices. The sampling frequency of the inertial sensor is 100Hz, and high-precision fiber-optic inertial navigation is used as the true value. The vehicle repeatedly drives forward and backward slowly in a straight line under an overpass to test the static detection performance under complex low-speed straight driving with large engine vibration. Figure 3a and Figure 3b , Figure 3a This is the result of the traditional method of oil truck static detection. Figure 3b This is the result of using the method for detecting the motion state of a fuel truck in the embodiment of the present application. Among them, the label "0" represents the driving state, and the label "1" represents the stationary state. The accuracy of the two methods for stationary detection is shown in Table 2 below. It can be seen that the missed detection rate of the traditional method is extremely low, and the missed detection rate of the innovative method in the embodiment of the present application is slightly higher, but the false detection rate of the traditional method reaches 35.83%, and the false detection rate of the innovative method is only 0.18%. Compared with the traditional method, the innovative method has significantly improved the accuracy of stationary detection in complex low-speed straight driving scenarios with large engine vibration.

[0080] Table 2. Results of static test on oil truck

[0081]

[0082] Figure 1 FIG. 1 is a flow chart of a method for detecting the motion state of a vehicle in one embodiment. It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0083] Figure 4 The following schematically shows a structural block diagram of a device for detecting the motion state of a vehicle according to an embodiment of the present application. Figure 4 As shown, an embodiment of the present application provides a device for detecting the motion state of a vehicle, which may include:

[0084] a memory configured to store instructions;

[0085] The processor is configured to call instructions from the memory and implement the above-mentioned method for detecting the vehicle motion state when executing the instructions.

[0086] Specifically, in the embodiment of the present application, the processor may be configured to:

[0087] Acquiring time domain data of the vehicle, the time domain data including first acceleration data of the vehicle when it is in a stationary state and current second acceleration data of the vehicle;

[0088] Converting the time domain data into frequency domain data, where the frequency domain data includes first frequency domain data corresponding to the first acceleration data and second frequency domain data corresponding to the second acceleration data;

[0089] When the first frequency domain data satisfies a preset condition, determining the motion state of the vehicle according to the second frequency domain data;

[0090] When the first frequency domain data does not meet the preset condition, the current motion state of the vehicle is determined according to the second acceleration data.

[0091] In an embodiment of the present application, the first frequency domain data includes multiple one-to-one corresponding first power spectrum densities and first frequency values, and the method also includes: when the maximum value among all the first power spectrum densities is greater than the power spectrum density threshold, and the difference between the first frequency value corresponding to the maximum value and the cutoff frequency is less than the frequency difference threshold, determining that the first frequency domain data meets the preset conditions.

[0092] In an embodiment of the present application, determining the current motion state of the vehicle based on the second acceleration data includes: dividing the second acceleration data into multiple first signal segments through each first time window; determining the y-axis range of the accelerometer of each first signal segment; when the y-axis range of the accelerometer of all first signal segments is less than the stationary detection threshold corresponding to the first time window, determining that the current motion state of the vehicle is a stationary state; when the y-axis range of the accelerometer of any first signal segment corresponding to any first time window is greater than the stationary detection threshold corresponding to the any first time window, determining that the current motion state of the vehicle is a driving state.

[0093] In an embodiment of the present application, the method also includes: determining a stationary signal segment in the first acceleration data; dividing the stationary signal segment into multiple second signal segments through each first time window; determining the accelerometer y-axis range of each second signal segment; determining the first maximum value of the accelerometer y-axis range of all second signal segments corresponding to the first window in all first time windows as the first stationary detection threshold corresponding to the first window; and determining the second stationary detection threshold corresponding to the first window based on the average value and standard deviation of the accelerometer y-axis range of all second signal segments corresponding to the second windows in all first time windows.

[0094] In an embodiment of the present application, determining a stationary signal segment in the first acceleration data includes: traversing the first acceleration data in sequence through a preset sliding window to divide the first acceleration data into multiple third signal segments; dividing each third signal segment into multiple fourth signal segments through each first time window; dividing the first acceleration data into multiple fifth signal segments through each first time window; determining the second maximum value in the y-axis range of the accelerometer of all fourth signal segments corresponding to each first time window and the first minimum value in the y-axis range of the accelerometer of all fifth signal segments corresponding to each first time window; for each third signal segment, when the product of the first minimum value corresponding to each first time window and the preset multiple is greater than the corresponding second maximum value, determining that the third signal segment is a stationary signal segment in the first acceleration data, and stopping traversing the first acceleration data.

[0095] In an embodiment of the present application, the second frequency domain data includes multiple one-to-one corresponding second power spectrum densities and second frequency values. Determining the current motion state of the vehicle based on the second frequency domain data includes: when the difference between the second frequency value corresponding to the maximum value in all second power spectrum densities and the cutoff frequency is less than the frequency difference threshold, determining that the current motion state of the vehicle is a stationary state; when the difference between the second frequency value corresponding to the maximum value in all second power spectrum densities and the cutoff frequency is greater than or equal to the frequency difference threshold, determining that the current motion state of the vehicle is a driving state.

[0096] In an embodiment of the present application, the time domain data includes the three-axis modulus values ​​of the accelerometer, and the frequency domain data includes multiple one-to-one corresponding power spectrum densities and frequency values. Converting the time domain data into frequency domain data includes: performing Fourier transform on the three-axis modulus values ​​of the accelerometer to obtain a transformation result; obtaining sampling parameters for the three-axis modulus values ​​of the accelerometer; and determining multiple one-to-one corresponding power spectrum densities and frequency values ​​based on the sampling parameters and the transformation result.

[0097] The present application also provides a vehicle, which may include:

[0098] Inertial sensors, used to detect vehicle time domain data;

[0099] According to the above device for detecting the motion state of a vehicle.

[0100] An embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute the above-mentioned method for detecting the motion state of a vehicle.

[0101] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected via a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store data for detecting the motion state of the vehicle. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a method for detecting the motion state of the vehicle is implemented.

[0102] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0103] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0105] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0107] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0108] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0109] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can be implemented using any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0110] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0111] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for detecting the motion state of a vehicle, characterized in that: The method comprises: Acquiring time domain data of a vehicle, the time domain data including first acceleration data of the vehicle when it is in a stationary state and current second acceleration data of the vehicle; Converting the time domain data into frequency domain data, wherein the frequency domain data includes first frequency domain data corresponding to the first acceleration data and second frequency domain data corresponding to the second acceleration data; determining the motion state of the vehicle according to the second frequency domain data when the first frequency domain data satisfies a preset condition; When the first frequency domain data does not meet the preset condition, the current motion state of the vehicle is determined according to the second acceleration data.

2. The method for detecting the motion state of a vehicle according to claim 1, characterized in that: The first frequency domain data includes a plurality of one-to-one corresponding first power spectrum densities and first frequency values, and the method further includes: When the maximum value among all first power spectrum densities is greater than the power spectrum density threshold, and the difference between the first frequency value corresponding to the maximum value and the cutoff frequency is less than the frequency difference threshold, it is determined that the first frequency domain data meets the preset condition.

3. The method for detecting the motion state of a vehicle according to claim 1, wherein: Determining the current motion state of the vehicle according to the second acceleration data includes: dividing the second acceleration data into a plurality of first signal segments according to each first time window; determining the accelerometer y-axis range for each first signal segment; When the accelerometer y-axis range differences of all first signal segments are less than a stationary detection threshold corresponding to the first time window, determining that the current motion state of the vehicle is a stationary state; When the accelerometer y-axis range of any first signal segment corresponding to any first time window is greater than the stationary detection threshold corresponding to the any first time window, it is determined that the current motion state of the vehicle is a driving state.

4. The method for detecting the motion state of a vehicle according to claim 3, characterized in that: The method further comprises: determining a stationary signal segment in the first acceleration data; Dividing the stationary signal segment into a plurality of second signal segments according to each first time window; determining the y-axis range of the accelerometer for each second signal segment; determining a first maximum value of the accelerometer y-axis range of all second signal segments corresponding to the first window in all first time windows as a first stationary detection threshold corresponding to the first window; A second stationary detection threshold corresponding to the first window is determined according to an average value and a standard deviation of accelerometer y-axis ranges of all second signal segments corresponding to the second window in all first time windows.

5. The method for detecting the motion state of a vehicle according to claim 4, characterized in that: Determining the stationary signal segment in the first acceleration data includes: sequentially traversing the first acceleration data through a preset sliding window to divide the first acceleration data into a plurality of third signal segments; dividing each third signal segment into a plurality of fourth signal segments by each first time window; dividing the first acceleration data into a plurality of fifth signal segments according to each first time window; Determine a second maximum value among the y-axis ranges of the accelerometer of all fourth signal segments corresponding to each first time window and a first minimum value among the y-axis ranges of the accelerometer of all fifth signal segments corresponding to each first time window; For each third signal segment, when the product of the first minimum value corresponding to each first time window and the preset multiple is greater than the corresponding second maximum value, the third signal segment is determined to be a stationary signal segment in the first acceleration data, and traversing the first acceleration data is stopped.

6. The method for detecting the motion state of a vehicle according to claim 1, characterized in that: The second frequency domain data includes a plurality of one-to-one corresponding second power spectrum densities and second frequency values, and determining the current motion state of the vehicle according to the second frequency domain data includes: When the difference between the second frequency value corresponding to the maximum value in all second power spectrum densities and the cutoff frequency is less than the frequency difference threshold, determining that the current motion state of the vehicle is a stationary state; When the difference between the second frequency value corresponding to the maximum value in all second power spectrum densities and the cutoff frequency is greater than or equal to the frequency difference threshold, it is determined that the current motion state of the vehicle is a driving state.

7. The method for detecting the motion state of a vehicle according to claim 1, characterized in that: The time domain data includes a three-axis modulus value of the accelerometer, the frequency domain data includes a plurality of one-to-one corresponding power spectrum densities and frequency values, and converting the time domain data into frequency domain data includes: Performing Fourier transform on the three-axis modulus value of the accelerometer to obtain a transformation result; Obtaining sampling parameters for the three-axis modulus values ​​of the accelerometer; The multiple one-to-one corresponding power spectrum densities and frequency values ​​are determined according to the sampling parameters and the transformation results.

8. A device for detecting the motion state of a vehicle, characterized in that: include: a memory configured to store instructions; A processor is configured to call the instructions from the memory and implement the method for detecting the vehicle motion state according to any one of claims 1 to 7 when executing the instructions.

9. A vehicle, characterized in that: include: Inertial sensors, used to detect vehicle time domain data; The device for detecting the motion state of a vehicle according to claim 8.

10. A machine-readable storage medium, characterized in that The machine-readable storage medium stores instructions for causing a machine to execute the method for detecting a vehicle motion state according to any one of claims 1 to 7.

Images