Vehicle rapid acceleration behavior identification method and device and storage medium

Abstract

The application discloses a vehicle rapid acceleration behavior identification method and device and a storage medium, and relates to the technical field of intelligent transportation. The method comprises the following steps: acquiring vehicle motion state data in real time by using an IMU module, and performing filtering processing and fusion processing on the vehicle motion state data to obtain vehicle attitude change data; selecting a preset number of adjacent vehicle attitude data in a double-linked list; performing rapid acceleration behavior judgment on the adjacent vehicle attitude data based on a state judgment unit to obtain a rapid acceleration behavior judgment result; if the rapid acceleration behavior judgment result is yes, obtaining rapid acceleration event data, and performing alarm recording on the rapid acceleration event data based on an alarm mechanism. The technical effects of realizing real-time acquisition and processing of vehicle data by using an IMU sensor, improving environmental adaptability, reducing sensor detection cost and detection error rate, and then improving vehicle rapid acceleration behavior detection precision and ensuring timely warning of the rapid acceleration behavior are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent transportation, in particular to a vehicle rapid acceleration behavior recognition method, device and storage medium. BACKGROUND

[0002] With the improvement of the intelligent level of vehicles, the detection and early warning of vehicle rapid acceleration have become an important research direction. Traditional rapid acceleration detection methods mainly rely on sensors such as radars and cameras, but these methods are easily disturbed in complex environments and have high costs. In addition, the reliability of these sensors is poor in low visibility or extreme weather conditions. Therefore, data processing methods based on IMU have gradually attracted attention. IMU has the advantages of small size, low cost and fast response, and can provide high-frequency acceleration and angular velocity data. Through reasonable processing of IMU data, the dynamic state and driving behavior of the vehicle can be effectively judged to provide a basis for rapid acceleration detection. SUMMARY

[0003] The present application provides a vehicle rapid acceleration behavior recognition method, device and storage medium, which solves the technical problem of insufficient vehicle rapid acceleration behavior detection precision in the prior art due to easy disturbance in complex environments and high cost. The technical effects of realizing real-time acquisition and processing of vehicle data through an IMU sensor, improving environmental adaptability, reducing sensor detection cost and detection error rate, and thus improving vehicle rapid acceleration behavior detection precision and ensuring timely warning of rapid acceleration behavior are achieved.

[0004] In view of the above problems, the present application provides a vehicle rapid acceleration behavior recognition method, device and storage medium.

[0005] In a first aspect of the present application, a vehicle rapid acceleration behavior recognition method is provided, which comprises:

[0006] The IMU module is used to acquire vehicle motion state data in real time, and the vehicle motion state data includes vehicle acceleration data and vehicle angular velocity data. The data processing unit is used to filter and fuse the vehicle acceleration data and the vehicle angular velocity data to obtain vehicle attitude change data. The vehicle attitude change data is stored in a double-linked list, and a preset number of adjacent vehicle attitude data is selected in the double-linked list. The state judgment unit is used to calculate and judge the rapid acceleration behavior of the adjacent vehicle attitude data to obtain a rapid acceleration behavior judgment result. If the rapid acceleration behavior judgment result is yes, the rapid acceleration event data is obtained, the alarm mechanism is activated through the alarm and recording unit, and the rapid acceleration event data is recorded based on the alarm mechanism.

[0007] In a second aspect of the present application, a vehicle rapid acceleration behavior recognition device is provided, which comprises:

[0008] The data acquisition module acquires vehicle motion state data in real time by using an IMU module, the vehicle motion state data including vehicle acceleration data and vehicle angular velocity data; the data processing module performs filtering processing and fusion processing on the vehicle acceleration data and the vehicle angular velocity data by using a data processing unit to obtain vehicle attitude change data; the storage selection module stores the vehicle attitude change data in a double-linked list and selects a preset number of adjacent vehicle attitude data in the double-linked list; the sudden acceleration judgment module judges the sudden acceleration behavior of the adjacent vehicle attitude data based on a state judgment unit to obtain a sudden acceleration behavior judgment result; and the alarm recording module obtains sudden acceleration event data if the sudden acceleration behavior judgment result is yes, activates an alarm mechanism by using an alarm and recording unit, and records the sudden acceleration event data based on the alarm mechanism.

[0009] In a third aspect, the present application provides a computer readable storage medium storing a computer program, which, when executed by a processor, implements the vehicle sudden acceleration behavior identification method provided by the present application.

[0010] The one or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0011] The technical solution has the following advantages: the IMU module is used to acquire vehicle motion state data in real time, the data processing unit is used to perform filtering processing and fusion processing on the acquired data to obtain vehicle attitude change data, the double-linked list is used to store the vehicle attitude change data, the preset number of adjacent vehicle attitude data is selected in the double-linked list, the state judgment unit is used to judge the sudden acceleration behavior of the adjacent vehicle attitude data to obtain a sudden acceleration behavior judgment result, the sudden acceleration event data is obtained if the sudden acceleration behavior judgment result is yes, the alarm mechanism is activated by using the alarm and recording unit, and the sudden acceleration event data is recorded based on the alarm mechanism. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0013] Figure 1 The vehicle sudden acceleration behavior identification method provided by the present application is shown in the flowchart.

[0014] Figure 2 The vehicle rapid acceleration behavior recognition device structure schematic diagram provided by the embodiment of the application is shown.

[0015] The figure mark explanation: data acquisition module 11, data processing module 12, storage selection module 13, rapid acceleration judgment module 14, alarm recording module 15. DETAILED DESCRIPTION

[0016] The application provides a vehicle rapid acceleration behavior recognition method, device and storage medium, and solves the technical problem that it is difficult to evaluate the whole vehicle deflection and stability of a side fork AGV under different loads in the prior art.

[0017] The technical solutions in the embodiments of the application will be clearly and completely described below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the application.

[0018] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion, for example, a process, method, device, product or server comprising a series of steps or units need not be limited to only those steps or units clearly listed, but can include other steps or modules not clearly listed or inherent to the process, method, product or device.

[0019] Embodiment one, as shown in the application provides a vehicle rapid acceleration behavior recognition method, the method comprises: Figure 1

[0020] Step S1: acquiring vehicle motion state data in real time by using an IMU module, wherein the vehicle motion state data comprises vehicle acceleration data and vehicle angular velocity data.

[0021] Further, the step of acquiring vehicle motion state data further comprises:

[0022] According to the IMU module, a three-axis acceleration sensor and a three-axis gyroscope are acquired; offset calibration and temperature compensation are performed on the three-axis acceleration sensor and the three-axis gyroscope to obtain a standard three-axis acceleration sensor and a standard three-axis gyroscope; a data sampling frequency is set, and the standard three-axis acceleration sensor and the standard three-axis gyroscope are used to acquire vehicle acceleration data and vehicle angular velocity data in real time according to the data sampling frequency; and the vehicle motion state data is acquired based on the vehicle acceleration data and the vehicle angular velocity data.

[0023] ​Specifically, the IMU module is used to collect vehicle motion state data in real time. The IMU module is used to collect vehicle motion data. First, according to the IMU module, the three-axis acceleration sensor and three-axis gyroscope integrated in the module are obtained. Before data acquisition, the three-axis acceleration sensor and three-axis gyroscope are calibrated and temperature compensated to reduce the influence of external factors (such as temperature change and sensor drift) on data, and the corrected standard three-axis acceleration sensor and standard three-axis gyroscope are obtained. Then set the data sampling frequency, preferably set the data sampling frequency to 50Hz (i.e. collect data every 20ms), to ensure the continuity and real-time of the data. By collecting and processing IMU data at a high frequency (every 20ms), the system can quickly respond to changes in vehicle dynamics and adapt to complex driving environments. According to the data sampling frequency, the standard three-axis acceleration sensor and the standard three-axis gyroscope are used to collect vehicle acceleration data ACCx, ACCy, ACCz and vehicle angular velocity data Gyrox, Gyroy, Gyroz in real time. Based on the vehicle acceleration data and vehicle angular velocity data, the vehicle motion state data is obtained. By collecting and processing vehicle motion data through the IMU module, the real-time performance is significantly improved, so that the rapid acceleration detection can more quickly and accurately reflect the dynamic state of the vehicle, and the IMU sensor is not affected by light and weather conditions, and can provide more reliable data.

[0024] Step S2: filtering and fusion processing of the vehicle acceleration data and vehicle angular velocity data by the data processing unit to obtain vehicle attitude change data.

[0025] Further, the vehicle attitude change data is obtained, and the step of the application further includes:

[0026] The vehicle acceleration data and vehicle angular velocity data are low-pass filtered by the data processing unit to obtain filtered vehicle acceleration data and filtered vehicle angular velocity data; the filtered vehicle acceleration data and filtered vehicle angular velocity data are Kalman filtered to obtain available filtered vehicle acceleration data and available vehicle angular velocity data; the available filtered vehicle acceleration data and available vehicle angular velocity data are fused using a six-axis fusion algorithm to obtain the vehicle attitude change data.

[0027] Specifically, the vehicle acceleration data and the vehicle angular velocity data are filtered and fused by a data processing unit, wherein the data processing unit is configured to perform low-pass filtering, Kalman filtering and six-axis fusion algorithm processing on the collected data. First, the vehicle acceleration data and the vehicle angular velocity data are subjected to low-pass filtering by the data processing unit to remove high-frequency noise, which can be achieved by using Discrete Fourier Transform (DFT) or Butterworth filter. Specifically, a first-order low-pass filter is used for processing, with the formula being y[n] = a * x[n] + (1-a) * y[n-1], wherein y[n] is the current output, x[n] is the current input (i.e. the original data), y[n-1] is the last output, and a is the filter coefficient. The filter coefficient a is usually in the range of 0.1 to 0.3 to balance the smoothing degree and response speed. A smaller a value will make the filtered data smoother, but the response speed will be slower; a larger a value will make the response speed faster, but it may retain more high-frequency noise. The filtered vehicle acceleration data and the filtered vehicle angular velocity data are obtained. Then, the filtered vehicle acceleration data and the filtered vehicle angular velocity data are subjected to Kalman filtering, which includes initializing state estimation and covariance matrix, setting state transition model and observation model, using IMU data for state prediction, and combining measurement values to correct state estimation through an update step to obtain more accurate usable filtered vehicle acceleration data and usable vehicle angular velocity data. Finally, the six-axis fusion algorithm is used to fuse the usable filtered vehicle acceleration data and the usable vehicle angular velocity data. The attitude is represented by a quaternion, and the measurements of the accelerometer and the gyroscope are subjected to complementary filtering to update the quaternion to obtain the changes in the direction and position of the vehicle. The acceleration and angular velocity data are fused to calculate the real dynamic state of the vehicle and obtain the corresponding vehicle attitude change data. The fused Euler angles can accurately reflect the attitude changes of the vehicle, including pitch angle, yaw angle and roll angle. By combining low-pass filtering, Kalman filtering and six-axis fusion algorithm, the multi-dimensional data provided by the IMU is fully utilized, and the accuracy and reliability of the data are significantly improved.

[0028] Step S3: storing the vehicle attitude change data in a double-linked list, and selecting a preset number of adjacent vehicle attitude data in the double-linked list.

[0029] Further, the double-linked list comprises the following steps:

[0030] defining a linked list structure and a node structure, wherein the linked list structure comprises a linked list number and a linked list size, and based on the linked list structure and the node structure, a double-linked list is obtained; determining a time window length according to the data sampling frequency; setting a time window size according to the data processing requirement; and using a sliding window mechanism to update the double-linked list based on the time window length and the time window size.

[0031] Specifically, the vehicle posture change data is stored by using a double-linked list. First, a linked list structure and a node structure are defined. The linked list structure includes a number of linked lists and a size of the linked list. Preferably, two double-linked lists (or ring buffer) are defined, and the size of each linked list is N, which is used to store the data of ACCy and ACCz respectively. Each node contains two floating-point numbers (ACCy and ACCz) and pointers to the previous and next nodes to support bidirectional traversal. If it is a ring buffer, the new data will overwrite the old data when the buffer reaches the maximum size N. This way can effectively manage memory and improve performance. Based on the linked list structure and the node structure, a double-linked list is obtained. According to the data sampling frequency, the length of the time window is determined. Preferably, the IMU data sampling frequency is set to 50 Hz, that is, acceleration data is collected every 20 ms. This means that the length of each time window is 20 ms. According to the data processing requirements, the size of the time window is set, that is, when analyzing the acceleration data, a fixed-size time window N is set to determine how many data are considered at each judgment. The selection of N is usually based on actual requirements, for example, 5, 10, or 20 data can be selected. The double-linked list is updated by using a sliding window mechanism based on the length of the time window and the size of the time window, that is, by using a sliding window mechanism, the latest ACCy and ACCz values are added to the data set every time new data is collected, and the old data is removed. In this way, the latest N data is always maintained for judgment, which improves the sensitivity of the system to real-time changes. The data in the window is dynamically updated every time new data arrives, ensuring that the judgment of the current state is based on the latest data. According to actual requirements, a predetermined number of adjacent vehicle posture data is selected from the double-linked list, for example, 10 latest posture data is selected. The processed data is stored by using a double-linked list. The design of the double-linked list makes the data storage and management more flexible and efficient, and supports real-time analysis of dynamic data.

[0032] Step S4: The state judgment unit calculates the sudden acceleration behavior judgment result based on the adjacent vehicle posture data.

[0033] Further, the sudden acceleration behavior judgment result is obtained, and the step of the application further includes:

[0034] According to the adjacent vehicle posture data, an ACCy value set and an ACCz value set are obtained; an average change value of the ACCy value set is calculated based on a state judgment unit; a preset acceleration threshold value, a preset uneven road section maximum value and a preset uneven road section minimum value are obtained; the average change value of the ACCy value set and the ACCz value set are subjected to a rapid acceleration behavior judgment based on the preset acceleration threshold value, the preset uneven road section maximum value and the preset uneven road section minimum value, and a rapid acceleration behavior judgment result is obtained.

[0035] Further, the rapid acceleration behavior judgment result is obtained, and the step further includes:

[0036] The average change value of the ACCy value set is compared based on the preset acceleration threshold value, and it is judged whether the average change value is greater than the preset acceleration threshold value, and an acceleration judgment result is obtained; the ACCz value set is compared based on the preset uneven road section maximum value and the preset uneven road section minimum value, and the number of times that the ACCz value set exceeds the preset uneven road section maximum value and the preset uneven road section minimum value is counted, and an acceleration out-of-range number is obtained; and the acceleration judgment result and the acceleration out-of-range number are used to determine the rapid acceleration behavior judgment result.

[0037] Further, the rapid acceleration behavior judgment result is determined, and the step further includes:

[0038] If the acceleration judgment result is no, the rapid acceleration behavior judgment result is that the vehicle does not perform rapid acceleration; if the acceleration judgment result is yes, it is judged whether the acceleration out-of-range number is greater than a preset out-of-range number, and an out-of-range number judgment result is obtained; and the out-of-range number judgment result is used to determine the rapid acceleration behavior judgment result.

[0039] Further, the rapid acceleration behavior judgment result is determined, and the step further includes:

[0040] If the out-of-range number judgment result is yes, the rapid acceleration behavior judgment result is that the vehicle does not perform rapid acceleration; if the out-of-range number judgment result is no, the rapid acceleration behavior judgment result is that the vehicle performs rapid acceleration.

[0041] Specifically, the state judgment unit is used to calculate the average change value of the ACCy value set based on the adjacent vehicle posture data, and the average change value of the ACCy value set is calculated based on the state judgment unit. The state judgment unit is used to judge the rapid acceleration state and detect the uneven road section according to the processed data. The latest N ACCy values are selected from the double-linked list, and the average value is calculated: The preset acceleration threshold value is set as a vehicle rapid acceleration judgment range, and the preset uneven road section maximum value and the preset uneven road section minimum value are set. The latest data is stored by a dynamic linked list and real-time calculation is performed. Through analysis of real-time data, the threshold value setting can be adjusted according to the actual driving condition, and the adaptability and flexibility of the system are improved. Based on the preset acceleration threshold value, the preset uneven road section maximum value and the preset uneven road section minimum value, the average change value of the ACCy value set and the ACCz value set are judged for the rapid acceleration behavior. Specifically, based on the preset acceleration threshold value, the average change value of the ACCy value set is compared to determine whether the average change value is greater than the preset acceleration threshold value, and an acceleration judgment result is obtained. When the average value of ACCy is greater than the threshold value, a rapid acceleration flag bit is set to 1, and related data is started. Then, based on the preset uneven road section maximum value and the preset uneven road section minimum value, the ACCz value set is compared, the number of times that the ACCz value set exceeds the preset uneven road section maximum value and the preset uneven road section minimum value is counted, and the corresponding acceleration out-of-range number is obtained. Based on the acceleration judgment result and the acceleration out-of-range number, a rapid acceleration behavior judgment result is determined. If the acceleration judgment result is no, the rapid acceleration behavior judgment result is that the vehicle does not perform rapid acceleration. If the acceleration judgment result is yes, it is judged whether the acceleration out-of-range number is greater than a preset out-of-range number, an out-of-range number judgment result is obtained, and the rapid acceleration behavior judgment result is determined according to the out-of-range number judgment result. If the out-of-range number judgment result is yes, the rapid acceleration behavior judgment result is that the vehicle does not perform rapid acceleration, and it is judged that it is an uneven road section, so as to avoid misjudgment of rapid acceleration. If the out-of-range number judgment result is no, the rapid acceleration behavior judgment result is that the vehicle performs rapid acceleration. The analysis of ACCz is introduced to distinguish normal road conditions and uneven road sections, reduce misjudgment of rapid acceleration, and improve the reliability of the system. When the average value of ACCy is less than the threshold value, and the ACCz determination method confirms that the vehicle is not on an uneven road section, the related counters and flag bits are reset. The environment in which the vehicle is located is intelligently judged to avoid false judgment of rapid acceleration on an uneven road section, thereby improving the intelligent level of the system.

[0042] Step S5: If the rapid acceleration behavior judgment result is yes, rapid acceleration event data is obtained, an alarm mechanism is activated by an alarm and recording unit, and the rapid acceleration event data is recorded and alarmed based on the alarm mechanism.

[0043] Specifically, if the rapid acceleration behavior judgment result is yes, it indicates that the vehicle is accelerating rapidly, and rapid acceleration event data associated therewith is obtained. An alarm mechanism is activated through an alarm and recording unit, wherein the alarm and recording unit is used to alarm when detecting a rapid acceleration or potential rapid acceleration risk, and record relevant data, and the alarm mechanism is a relevant alarm program designed when the rapid acceleration state is activated. The rapid acceleration event data is recorded based on the alarm mechanism, and the rapid acceleration event related data is stored in the non-volatile memory, facilitating subsequent driving behavior analysis and safety evaluation. Through real-time monitoring of the dynamic state of the vehicle, the rapid acceleration behavior can be quickly identified and timely alarm can be issued, thereby improving the alertness of the driver and reducing the possibility of accidents.

[0044] In summary, the embodiments of the present application have at least the following technical effects:

[0045] Due to the use of the IMU module to collect and obtain vehicle motion state data in real time, the data processing unit is used to filter and fuse the obtained data, the vehicle attitude change data is obtained, the double-linked list is used to store the vehicle attitude change data, the preset number of adjacent vehicle attitude data is selected in the double-linked list, the state judgment unit is used to calculate and judge the rapid acceleration behavior of the adjacent vehicle attitude data, the rapid acceleration behavior judgment result is obtained, if the rapid acceleration behavior judgment result is yes, the rapid acceleration event data is obtained, the alarm mechanism is activated through the alarm and recording unit, and the rapid acceleration event data is recorded based on the alarm mechanism. The technical scheme achieves the technical effects of realizing real-time collection and processing of vehicle data through the IMU sensor, improving environmental adaptability, reducing sensor detection cost and detection error rate, and further improving vehicle rapid acceleration behavior detection accuracy and ensuring timely warning of rapid acceleration behavior.

[0046] In the second embodiment, based on the same inventive concept as the vehicle rapid acceleration behavior identification method in the foregoing embodiments, as shown in Figure 2 The present application provides a vehicle rapid acceleration behavior identification device, wherein the device comprises:

[0047] The data acquisition module 11 acquires vehicle motion state data in real time by using an IMU module, wherein the vehicle motion state data includes vehicle acceleration data and vehicle angular velocity data; the data processing module 12 performs filtering processing and fusion processing on the vehicle acceleration data and the vehicle angular velocity data by using a data processing unit to obtain vehicle attitude change data; the storage selection module 13 stores the vehicle attitude change data in a double-linked list and selects a preset number of adjacent vehicle attitude data in the double-linked list; the sudden acceleration judgment module 14 performs sudden acceleration behavior judgment on the adjacent vehicle attitude data based on a state judgment unit to obtain a sudden acceleration behavior judgment result; and the alarm recording module 15 obtains sudden acceleration event data if the sudden acceleration behavior judgment result is yes, activates an alarm mechanism by using an alarm and recording unit, and records the sudden acceleration event data based on the alarm mechanism.

[0048] Further, the device is also used to execute the following method:

[0049] According to the IMU module, a three-axis acceleration sensor and a three-axis gyroscope are obtained; offset calibration and temperature compensation are performed on the three-axis acceleration sensor and the three-axis gyroscope to obtain a standard three-axis acceleration sensor and a standard three-axis gyroscope; a data sampling frequency is set, and the standard three-axis acceleration sensor and the standard three-axis gyroscope are used to collect vehicle acceleration data and vehicle angular velocity data in real time according to the data sampling frequency; and the vehicle motion state data is obtained based on the vehicle acceleration data and the vehicle angular velocity data.

[0050] Further, the device is also used to execute the following method:

[0051] The data processing unit is used to perform low-pass filtering processing on the vehicle acceleration data and the vehicle angular velocity data to obtain filtered vehicle acceleration data and filtered vehicle angular velocity data; Kalman filtering processing is performed on the filtered vehicle acceleration data and the filtered vehicle angular velocity data to obtain available filtered vehicle acceleration data and available vehicle angular velocity data; and a six-axis fusion algorithm is used to perform fusion processing on the available filtered vehicle acceleration data and the available vehicle angular velocity data to obtain the vehicle attitude change data.

[0052] Further, the device is also used to execute the following method:

[0053] A linked list structure and a node structure are defined, wherein the linked list structure includes a linked list number and a linked list size; a double-linked list is obtained based on the linked list structure and the node structure; a time window length is determined according to the data sampling frequency; a time window size is set according to data processing requirements; and a sliding window mechanism is used to update the double-linked list based on the time window length and the time window size.

[0054] Further, the device is also used to execute the following method:

[0055] According to the adjacent vehicle posture data, a set of ACCy values and a set of ACCz values are obtained; an average change value of the set of ACCy values is calculated based on a state judgment unit; a preset acceleration threshold value, a preset uneven road section maximum value and a preset uneven road section minimum value are obtained; based on the preset acceleration threshold value, the preset uneven road section maximum value and the preset uneven road section minimum value, the average change value of the set of ACCy values and the set of ACCz values are compared to determine an aggressive acceleration behavior judgment result.

[0056] Further, the device is also used to execute the following method:

[0057] Based on the preset acceleration threshold value, the average change value of the set of ACCy values is compared to determine whether the average change value is greater than the preset acceleration threshold value, and an acceleration judgment result is obtained; based on the preset uneven road section maximum value and the preset uneven road section minimum value, the set of ACCz values is compared to count the number of times the set of ACCz values exceeds the preset uneven road section maximum value and the preset uneven road section minimum value, and an acceleration out-of-range number is obtained; based on the acceleration judgment result and the acceleration out-of-range number, an aggressive acceleration behavior judgment result is determined.

[0058] Further, the device is also used to execute the following method:

[0059] If the acceleration judgment result is no, the aggressive acceleration behavior judgment result is that the vehicle does not perform aggressive acceleration; if the acceleration judgment result is yes, it is determined whether the acceleration out-of-range number is greater than a preset out-of-range number, and an out-of-range number judgment result is obtained; according to the out-of-range number judgment result, the aggressive acceleration behavior judgment result is determined.

[0060] Further, the device is also used to execute the following method:

[0061] If the out-of-range number judgment result is yes, the aggressive acceleration behavior judgment result is that the vehicle does not perform aggressive acceleration; if the out-of-range number judgment result is no, the aggressive acceleration behavior judgment result is that the vehicle performs aggressive acceleration.

[0062] Embodiment three, based on the same inventive concept as the vehicle rapid acceleration behavior recognition method in the foregoing embodiments, provides a computer readable storage medium, which can be used to store a software program, a computer executable program and a module, such as the program instructions / modules corresponding to the vehicle rapid acceleration behavior recognition method in the embodiments of the present application. The processor executes various functions of the computer device and data processing by running the software program, instructions and modules stored in the memory, that is, implements the vehicle rapid acceleration behavior recognition method described above.

[0063] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of the present application are described. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0064] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0065] The present application and the drawings are only exemplary description of the present application, and are considered to cover any and all modifications, changes, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalent technology, the present application intends to include these modifications and changes.

Claims

1. A method for identifying a vehicle rapid acceleration behavior, characterized in that, The method comprises: Real-time acquisition of vehicle motion state data by an IMU module, wherein the vehicle motion state data comprises vehicle acceleration data and vehicle angular velocity data; Filtering and fusion processing of the vehicle acceleration data and vehicle angular velocity data by a data processing unit to obtain vehicle attitude change data; Storage of the vehicle attitude change data using a double-linked list, and selection of a preset number of adjacent vehicle attitude data in the double-linked list; Calculation of an acceleration behavior judgment result for the adjacent vehicle attitude data by a state judgment unit; If the acceleration behavior judgment result is yes, an acceleration event data is obtained, an alarm mechanism is activated by an alarm and recording unit, and the acceleration event data is recorded based on the alarm mechanism; The acquisition of vehicle motion state data comprises: Obtaining a three-axis acceleration sensor and a three-axis gyroscope according to the IMU module; Offset calibration and temperature compensation of the three-axis acceleration sensor and the three-axis gyroscope to obtain a standard three-axis acceleration sensor and a standard three-axis gyroscope; Setting a data sampling frequency, and real-time acquisition of vehicle acceleration data and vehicle angular velocity data using the standard three-axis acceleration sensor and the standard three-axis gyroscope according to the data sampling frequency; Acquisition of the vehicle motion state data based on the vehicle acceleration data and the vehicle angular velocity data; The double-linked list comprises: Defining a linked list structure and a node structure, wherein the linked list structure comprises a linked list number and a linked list size, and a double-linked list is obtained based on the linked list structure and the node structure; Determining a time window length according to the data sampling frequency; Setting a time window size according to data processing requirements; Time window updating of the double-linked list based on the time window length and the time window size using a sliding window mechanism.

2. The vehicle sudden acceleration behavior recognition method according to claim 1, wherein The acquisition of vehicle attitude change data comprises: Low-pass filtering of the vehicle acceleration data and the vehicle angular velocity data by a data processing unit to obtain filtered vehicle acceleration data and filtered vehicle angular velocity data; Kalman filtering of the filtered vehicle acceleration data and the filtered vehicle angular velocity data to obtain available filtered vehicle acceleration data and available vehicle angular velocity data; Fusion processing of the available filtered vehicle acceleration data and the available vehicle angular velocity data using a six-axis fusion algorithm to obtain the vehicle attitude change data.

3. The vehicle sudden acceleration behavior recognition method according to claim 1, wherein The acquisition of the acceleration behavior judgment result comprises: Obtaining an ACCy value set and an ACCz value set according to the adjacent vehicle attitude data; Calculation of an average change value of the ACCy value set based on a state judgment unit; Obtaining a preset acceleration threshold value, a preset uneven road segment maximum value, and a preset uneven road segment minimum value; Acceleration behavior judgment of the average change value of the ACCy value set and the ACCz value set based on the preset acceleration threshold value, the preset uneven road segment maximum value, and the preset uneven road segment minimum value to obtain an acceleration behavior judgment result.

4. The vehicle sudden acceleration behavior recognition method according to claim 3, characterized by, The acquisition of the acceleration behavior judgment result comprises: comparing an average change value of the ACCy value set based on the preset acceleration threshold value, judging whether the average change value is greater than the preset acceleration threshold value, and obtaining an acceleration judgment result; comparing the ACCz value set based on the preset uneven road section maximum value and the uneven road section minimum value, counting a number of times that the ACCz value set exceeds the preset uneven road section maximum value and the uneven road section minimum value, and obtaining an acceleration out-of-range number of times; determining a sudden acceleration behavior judgment result based on the acceleration judgment result and the acceleration out-of-range number of times.

5. The vehicle sudden acceleration behavior recognition method according to claim 4, characterized by, The determination of the sudden acceleration behavior judgment result includes: if the acceleration judgment result is no, the sudden acceleration behavior judgment result is that the vehicle does not perform sudden acceleration; if the acceleration judgment result is yes, judging whether the acceleration out-of-range number of times is greater than a preset out-of-range number of times, and obtaining an out-of-range number of times judgment result; determining a sudden acceleration behavior judgment result according to the out-of-range number of times judgment result.

6. The vehicle abrupt acceleration behavior recognition method according to claim 5, wherein The determination of the sudden acceleration behavior judgment result includes: if the out-of-range number of times judgment result is yes, the sudden acceleration behavior judgment result is that the vehicle does not perform sudden acceleration; if the out-of-range number of times judgment result is no, the sudden acceleration behavior judgment result is that the vehicle performs sudden acceleration.

7. The vehicle rapid acceleration behavior recognition apparatus characterized by The device for implementing the vehicle sudden acceleration behavior identification method of any one of claims 1-6 includes: a data acquisition module that acquires vehicle motion state data in real time using an IMU module, the vehicle motion state data including vehicle acceleration data and vehicle angular velocity data; a data processing module that performs filtering and fusion processing on the vehicle acceleration data and the vehicle angular velocity data using a data processing unit to obtain vehicle attitude change data; a storage selection module that stores vehicle attitude change data using a double-linked list and selects a preset number of adjacent vehicle attitude data in the double-linked list; a sudden acceleration judgment module that performs sudden acceleration behavior judgment on the adjacent vehicle attitude data based on a state judgment unit to obtain a sudden acceleration behavior judgment result; an alarm recording module that, if the sudden acceleration behavior judgment result is yes, obtains sudden acceleration event data, activates an alarm mechanism using an alarm and recording unit, and records the sudden acceleration event data based on the alarm mechanism.

8. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by a processor to implement the vehicle sudden acceleration behavior identification method of any one of claims 1-6.

Images