A vehicle sharp turning identification method and device and a storage medium

Abstract

The application discloses a vehicle sharp turning identification method and device and a storage medium. The method comprises the following steps: acquiring a plurality of steering wheel turning angle data and a plurality of lateral acceleration data of a target vehicle in a preset driving period; identifying N sharp turning periods from the preset driving period based on the plurality of steering wheel turning angle data and the plurality of lateral acceleration data, wherein N is a positive integer; and determining the category of each sharp turning period based on the driving data of the target vehicle in each sharp turning period, wherein the category of the sharp turning period is a sharp turning period or a sharp lane changing period. The above scheme improves the accuracy of vehicle sharp turning identification and can obtain more detailed driving states.

Description

Technical Field

[0001] The present invention relates to the field of vehicles, and in particular to a method, device and storage medium for identifying sudden turns of a vehicle. Background Art

[0002] As cars become increasingly popular, car accidents are receiving increasing attention. Currently, a major cause of traffic accidents is poor driving habits. Sharp turns are a particularly dangerous driving behavior. In severe cases, they can cause the vehicle to roll over. Even mild sharp turns can cause discomfort to passengers. Therefore, accurately identifying sharp turns during driving is an urgent problem to be solved. Summary of the Invention

[0003] Embodiments of the present application provide a method, device, and storage medium for identifying sudden turns of a vehicle.

[0004] In a first aspect, the present application provides a method for identifying a sudden turn of a vehicle, the method comprising:

[0005] Acquiring multiple steering wheel angle data and multiple lateral acceleration data of the target vehicle within a preset driving period;

[0006] Based on the plurality of steering wheel angle data and the plurality of lateral acceleration data, identifying N sharp turning periods within the preset driving period, where N is a positive integer;

[0007] Based on the driving data of the target vehicle in each sharp turning period, the category of each sharp turning period is determined, wherein the category of the sharp turning period is a sharp turn period or a sharp lane change period.

[0008] Optionally, the identifying N sharp turning periods within the preset driving period based on the plurality of steering wheel angle data and the plurality of lateral acceleration data includes:

[0009] Based on the plurality of steering wheel angle data and the plurality of lateral acceleration data, performing a first type of turning moment marking and a second type of turning moment marking on the preset driving period;

[0010] Merging the first-type turning moments and the second-type turning moments into time periods, and identifying N sharp turning time periods within the preset driving time period;

[0011] The first type of turning moment indicates that the target vehicle performs a turning operation in a first direction, and the second type of turning moment indicates that the target vehicle performs a turning operation in a second direction.

[0012] Optionally, the first type turning time point marking and the second type turning time point marking of the preset driving period based on the plurality of steering wheel angle data and the plurality of lateral acceleration data, comprises:

[0013] If the steering wheel angle data is positive and greater than a first preset angle, or the lateral acceleration data is negative and greater than a first preset acceleration, the corresponding data acquisition time is marked as a first initial time;

[0014] If the steering wheel angle data is negative and greater than a second preset angle, or the lateral acceleration data is positive and greater than a second preset acceleration, the corresponding data acquisition time is marked as a second initial time;

[0015] The first type turning time point is screened from the first initial time, and the second type turning time point is screened from the second initial time.

[0016] Optionally, the first type turning time point is screened from the first initial time, and the second type turning time point is screened from the second initial time, comprising:

[0017] Determine whether there is a vehicle speed greater than zero in a period of time interval from the first initial time, if yes, mark the first initial time as the first type turning time point;

[0018] Determine whether there is a vehicle speed greater than zero in a period of time interval from the first initial time, if yes, mark the first initial time as the first type turning time point;

[0019] Optionally, the first type turning time point and the second type turning time point are merged to obtain the N sharp turning periods, comprising:

[0020] The first type turning time point and the second type turning time point are sorted in time sequence;

[0021] Based on the sorting result, the period is merged to obtain M candidate turning periods, M is a positive integer;

[0022] Based on the maximum value of the absolute value of the lateral acceleration corresponding to each candidate turning period and the maximum vehicle speed, the N sharp turning periods are determined from the M candidate turning periods.

[0023] Optionally, the period is merged based on the sorting result to obtain M candidate turning periods, comprising:

[0024] merge the continuous same type turning time instants based on the sorting result to obtain K initial turning time periods and a time length of each initial turning time period, wherein an interval between adjacent same type time instants in the each initial turning time period is less than a second preset time interval, and K is a positive integer;

[0025] For the each initial turning time period, if the time length of the initial turning time period satisfies a first preset time length range, the initial turning time period is taken as the candidate turning time period.

[0026] For the each initial turning time period, if the time length of the initial turning time period is greater than the first preset time length range, the first preset turning angle is increased to a third preset turning angle, and the second preset turning angle is increased to a fourth preset turning angle, the first type turning time instant and the second type turning time instant of the initial turning time period are re-marked and determined, and the initial turning time period satisfying a second preset time length range is taken as the candidate turning time period.

[0027] Optionally, when the driving data is the steering wheel turning angle data, the determining the category of the each sharp turning time period based on the driving data of the target vehicle in the each sharp turning time period comprises:

[0028] For the each sharp turning time period, a target steering wheel turning angle with a maximum absolute value is determined from the steering wheel turning angle data of the sharp turning time period.

[0029] If the target steering wheel turning angle of the sharp turning time period is greater than a fifth preset turning angle, it is determined that the category of the sharp turning time period is a sharp turning time period.

[0030] If the target steering wheel turning angle of the sharp turning time period is greater than a sixth preset turning angle and less than or equal to the fifth preset turning angle, and a duration in which the steering wheel turning angle data of the sharp turning time period is greater than a seventh preset turning angle is greater than a first preset time length, it is determined that the category of the sharp turning time period is a sharp turning time period, wherein the seventh preset turning angle is less than the sixth preset turning angle.

[0031] Optionally, when the driving data is the longitude and latitude data, the determining the category of the each sharp turning time period based on the driving data of the target vehicle in the each sharp turning time period comprises:

[0032] a front and rear time period extension is performed on the each sharp turning time period to obtain an extended time period of the each sharp turning time period;

[0033] For each extended period, obtain the latitude and longitude data in a first sub-period and the latitude and longitude data in a second sub-period in the extended period, wherein the starting time of the first sub-period is the starting time of the extended period, and the ending time of the second sub-period is the ending time of the extended period;

[0034] Based on the latitude and longitude data in the first sub-period and the latitude and longitude data in the second sub-period, determine the target included angle between the starting route and the ending route corresponding to the extended period;

[0035] Compare the target included angle with a preset included angle, and determine the category of the corresponding sharp turning period according to the comparison result.

[0036] In a second aspect, the present application further provides a vehicle sharp turning identification device, comprising:

[0037] An acquisition module is configured to acquire a plurality of steering wheel turning angle data and a plurality of lateral acceleration data of a target vehicle in a preset driving period;

[0038] An identification module is configured to identify N sharp turning periods from the preset driving period based on the plurality of steering wheel turning angle data and the plurality of lateral acceleration data, wherein N is a positive integer;

[0039] A processing module is configured to determine the category of each sharp turning period based on the driving data of the target vehicle in each sharp turning period, wherein the category of the sharp turning period is a sharp turning period or a sharp lane changing period.

[0040] In a third aspect, an embodiment of the present application provides a vehicle sharp turning identification device, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors to perform the operation instructions included in the one or more programs for performing the vehicle sharp turning identification method provided in the first aspect.

[0041] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to implement the steps corresponding to the vehicle sharp turning identification method provided in the first aspect.

[0042] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0043] The scheme in the embodiment of the application can obtain multiple steering wheel angle data and multiple lateral acceleration data of a target vehicle in a preset driving period when identifying the sharp turning of the target vehicle, identify N sharp turning periods from the preset driving period based on the multiple steering wheel angle data and the multiple lateral acceleration data, where N is a positive integer, and determine the category of each sharp turning period based on driving data of the target vehicle in each sharp turning period, where the category of the sharp turning period is a sharp turning period or a sharp lane changing period. In the scheme, the steering wheel angle and the lateral acceleration can both reflect the turning trend of the vehicle, so that the sharp turning period of the target vehicle can be determined more comprehensively through the steering wheel angle data and the lateral acceleration data, avoiding the omission of the sharp turning period. In addition, the type of the sharp turning can be classified based on the driving data in each sharp turning period, and each sharp turning period is specifically classified into a sharp turning period or a sharp lane changing period, so that the judgment of the sharp turning of the vehicle is more accurate, the accuracy of the vehicle sharp turning identification is improved, and more detailed driving states can be obtained. BRIEF DESCRIPTION OF DRAWINGS

[0044] 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 some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0045] Figure 1 A flowchart of a vehicle sharp turning identification method provided for the embodiment of the present application is shown in the figure.

[0046] Figure 2 A schematic diagram of a vehicle body coordinate system provided for the embodiment of the present application is shown in the figure.

[0047] Figure 3 A schematic diagram of a vehicle sharp turning identification device provided for the embodiment of the present application is shown in the figure.

[0048] Figure 4 A schematic diagram of a vehicle sharp turning identification device provided for the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0049] The embodiment of the present application provides a vehicle sharp turning identification method, device and storage medium to improve the accuracy of vehicle sharp turning identification.

[0050] The general idea of the technical scheme of the embodiment of the present application is as follows: a plurality of steering wheel angle data and a plurality of lateral acceleration data of a target vehicle in a preset driving period are acquired; N sudden turning periods are identified from the preset driving period based on the plurality of steering wheel angle data and the plurality of lateral acceleration data, N being a positive integer; and a category of each sudden turning period is determined based on driving data of the target vehicle in each sudden turning period, wherein the category of the sudden turning period is a sudden turning period or a sudden lane-changing period.

[0051] The scheme in the present application can comprehensively determine the sudden turning period of the target vehicle through the steering wheel angle data and the lateral acceleration data, because the steering wheel angle and the lateral acceleration can both reflect the turning trend of the vehicle, thereby avoiding omission of the sudden turning period. In addition, the type of the sudden turning can be classified based on the driving data in each sudden turning period, and each sudden turning period is specifically classified into a sudden turning period or a sudden lane-changing period, so that the judgment of the sudden turning of the vehicle is more accurate, the accuracy of the vehicle sudden turning identification is improved, and a more detailed driving state can be obtained.

[0052] In order to better understand the above technical scheme, the above technical scheme will be described in detail in combination with the drawings of the specification and the specific embodiments.

[0053] Firstly, the term "and / or" appearing in the present text is only to describe the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B can mean that there are three cases of A alone, A and B together, and B alone. In addition, the character " / " in the present text generally represents an "or" relationship between the front and rear associated objects.

[0054] The embodiment of the present specification provides a vehicle sudden turning identification method, as shown in Figure 1 The method comprises the following steps:

[0055] Step S101: acquiring a plurality of steering wheel angle data and a plurality of lateral acceleration data of a target vehicle in a preset driving period;

[0056] Step S102: identifying N sudden turning periods from the preset driving period based on the plurality of steering wheel angle data and the plurality of lateral acceleration data, N being a positive integer;

[0057] Step S103: determining a category of each sudden turning period based on driving data of the target vehicle in each sudden turning period, wherein the category of the sudden turning period is a sudden turning period or a sudden lane-changing period.

[0058] The scheme in the embodiments of the present specification can be applied to a vehicle terminal, a server capable of being in communication connection with a vehicle, and a system composed of a vehicle terminal and a server, and is not limited herein.

[0059] It should be noted that in order to collect various data of the vehicle in the driving process, various sensors can be arranged in the vehicle, such as a sensor for detecting vehicle speed, a sensor for detecting steering wheel angle, a sensor for detecting vehicle acceleration, a sensor for detecting vehicle position information, and the like. After the vehicle is started, each sensor can enter a working state to collect various data of the vehicle. The data collection frequency of each sensor can be set according to actual needs, for example, the data collection frequency is 3 Hz, 5 Hz, etc.

[0060] In the embodiments of the present specification, the data collected by each sensor can be used to identify the sharp turning of the vehicle. However, the original data collected may have abnormalities, such as data missing, data drift, data extreme value abnormality, etc. In order to ensure the accuracy of the final identification result, the original data needs to be preprocessed in the specific implementation process, and the sharp turning of the vehicle is identified based on the preprocessed data. In the specific implementation process, after the sensor collects the original data, the original data can be uploaded to the server, and the server performs preprocessing operation on the original data.

[0061] The way of preprocessing the original data can be set according to actual needs, which is not limited herein. In the following examples, the following ways of data preprocessing can be used for different types of data collected by different sensors.

[0062] I. Abnormal data repair

[0063] In the embodiments of the present specification, for each type of data, there can be a normal fluctuation interval corresponding to each type of data. For example, for lateral acceleration, the normal fluctuation interval is [-20 m / s 2 , 20 m / s 2 ], wherein, as shown in Figure 2 , it is a schematic diagram of the body coordinate system, and the lateral acceleration is the acceleration in the Y direction of Figure 2 . For another example, the normal fluctuation interval of the steering wheel angle can be [-540°, 540°], and the normal fluctuation interval of the vehicle speed is [0 km / h, 200 km / h]. If the collected original data has data exceeding the normal fluctuation interval or has local missing, the average value of the data before and after the abnormal data can be used as the repair value of the abnormal data.

[0064] Specifically, taking the vehicle speed as an example, if the vehicle speeds collected in the time sequence are 80 km / h, 210 km / h, and 100 km / h, since 210 km / h exceeds the normal fluctuation range of the vehicle speed, it is an abnormal data, and thus the average value of the data adjacent to 210 km / h can be used as the repair value, i.e., the repair value is 90 km / h.

[0065] II. Abnormal data deletion

[0066] For continuous abnormal data over a long period of time, for example, for the vehicle speed, if there are ten minutes of continuous data greater than 200 km / h, the abnormal data cannot be repaired, and thus the abnormal data can be deleted or nullified.

[0067] III. Drift repair

[0068] For data such as lateral acceleration and steering wheel angle, due to some reasons of the sensor, the collected data can be overall shifted, for example, the steering wheel is not 0 when it is straightened, but there is a certain angle of drift. Therefore, the data with drift can be overall repaired, for example, for a kind of data such as lateral acceleration, the median (or average value) of all data is calculated, each original data is subtracted from the median (or average value), and the difference is used as the repaired data.

[0069] IV. Data smoothing

[0070] For data such as lateral acceleration, due to the reasons of the sensor, there can be more error fluctuations, and in the embodiments of the present specification, mean filtering or median smoothing can be used to smooth the original data.

[0071] Of course, in addition to the above data preprocessing methods, other data preprocessing processes can also be used according to actual needs, which will not be illustrated one by one here. After obtaining the preprocessed data, the vehicle can be identified based on the preprocessed data.

[0072] In step S101, the target vehicle can be any vehicle that needs to be identified for sharp turning. The preset driving period can be selected according to actual needs, for example, the preset driving period can be the driving period corresponding to the historical journey (such as x years x months x days from place A to place B) of the target vehicle, or a specified driving period (such as x years x months x days from 9:00 to 10:00 in the morning).

[0073] It should be noted that each data of the target vehicle collected by the sensor corresponds to a respective data collection time, and the steering wheel angle data and the lateral acceleration data corresponding to multiple collection times within the preset driving period are filtered from the set of historical data collected from the target vehicle within the preset driving period. The data used in step S101 are all preprocessed data.

[0074] In step S102, the target vehicle may have multiple driving states in the preset driving period, such as straight line, normal steering, and sharp steering. The sharp steering includes sharp turning and sharp lane changing. For sharp turning and sharp lane changing, there are their own driving characteristics, for example, sharp turning usually has a large steering wheel angle, and sharp lane changing usually has a large lateral acceleration. Therefore, the sharp steering state can be distinguished from other driving states by the steering wheel angle and the lateral acceleration, and N sharp steering periods are identified within the preset driving period, where N is a positive integer.

[0075] In the specific implementation process, the identification of the sharp steering period according to the steering wheel angle and the lateral acceleration can be realized in various ways. For example, a steering wheel angle threshold and a lateral acceleration threshold corresponding to sharp steering are set, the actually collected steering wheel angle data is compared with the steering wheel angle threshold, and / or the collected lateral acceleration data is compared with the lateral acceleration threshold, to determine the steering wheel angle data and / or the lateral acceleration data that meet the sharp steering, and the data collection time corresponding to the data is used to determine the sharp steering period.

[0076] In the embodiments of the present specification, the sharp steering period can be identified in the following way: based on the plurality of steering wheel angle data and the plurality of lateral acceleration data, the preset driving period is marked with a first type of steering time and a second type of steering time; the first type of steering time and the second type of steering time are merged to identify N sharp steering periods from the preset driving period; wherein the first type of steering time indicates that the target vehicle performs a steering operation in a first direction, and the second type of steering indicates that the target vehicle performs a steering operation in a second direction.

[0077] Specifically, steering can be divided into left steering and right steering, corresponding to the first direction of steering and the second direction of steering. That is, according to the different settings of the actual direction, when the first direction of steering is left steering, the second direction of steering is right steering; when the first direction of steering is right steering, the second direction of steering is left steering.

[0078] Since the steering wheel angle data and the lateral acceleration data correspond to the direction information, for example, the steering wheel angle data is positive or the lateral acceleration is negative, indicating that the vehicle is turning left, the steering wheel angle is negative or the lateral acceleration is positive, indicating that the vehicle is turning right. Therefore, based on the steering wheel angle data and the lateral acceleration data, the turning direction of the vehicle at the data collection time can be determined, and the turning type of the data collection time is marked.

[0079] In the specific implementation process, the time marking of the preset driving period can be realized through the following steps: if the steering wheel angle data is positive and greater than a first preset angle, or the lateral acceleration data is negative and greater than a first preset acceleration, the corresponding data collection time is marked as a first initial time; if the steering wheel angle data is negative and greater than a second preset angle, or the lateral acceleration data is positive and greater than a second preset acceleration, the corresponding data collection time is marked as a second initial time; the first type turning time is selected from the first initial time, and the second type turning time is selected from the second initial time.

[0080] Specifically, the first preset angle, the second preset angle, the first preset acceleration and the second preset acceleration can be set according to actual needs, which are not limited here. In order to facilitate the description, the following parameters are taken as an example to explain the marking of the turning time: the first preset angle and the second preset angle are the same, both are 15°, and are represented by angleThre1, the first preset acceleration and the second preset acceleration are the same, both are 2m / s 2 , and are represented by accThre1, the first direction is left, and the second direction is right. Then, when the steering wheel angle data > angleThre1, or the lateral acceleration data <- accThre1, the time corresponding to the steering wheel angle data or the lateral acceleration data, i.e. the data collection time, is marked as the first initial time, i.e. the left turning initial time. When the steering wheel angle data <- angleThre1, or the lateral acceleration data > accThre1, the time corresponding to the steering wheel angle data or the lateral acceleration data, i.e. the data collection time, is marked as the second initial time, i.e. the right turning initial time.

[0081] Through the above steps, all left turning initial times and all right turning initial times in the preset driving period can be marked. However, considering that some turning times may be steering wheel rotation performed by the target vehicle in a non-driving state or abnormal data, the initial times can be further filtered to filter out the turning times of the vehicle driving, i.e. the first type turning time (left turning time) and the second type turning time (right turning time), for the sharp turning identification.

[0082] In the implementation process, the first type turning time and the second type turning time are determined according to the first initial time and the second initial time, which can be performed according to actual needs. In an embodiment, the first type turning time can be achieved by the following steps: determining whether there is a vehicle speed greater than zero in a time period with a first preset time interval from the first initial time; if yes, marking the first initial time as the first type turning time. The second type turning time can be achieved by the following steps: determining whether there is a vehicle speed greater than zero in a time period with the first preset time interval from the second initial time, if yes, marking the second initial time as the second type turning time.

[0083] Specifically, the first preset time interval can be set according to actual needs, for example, the first preset time interval is 1s, 2s, 3s, etc. Taking 2s as the first preset time interval for example, for the first initial time, it is determined whether there is a vehicle speed greater than zero in a time period of 2s before and after the first initial time, if yes, it indicates that the vehicle is in the driving process, and the first initial time can be marked as the first type turning time. Similarly, for the second type turning time, the same way can be used to determine, which will not be repeated here.

[0084] Of course, in addition to determining the first type turning time and the second type turning time by judging whether the vehicle speed is greater than zero, other ways that can determine whether the vehicle is driving can also be used to determine, for example, judging the vehicle position at a time before or after the first initial time or the second initial time, if the vehicle position changes, it indicates that the vehicle is in the driving process, and the first initial time or the second initial time can be marked as the corresponding first type turning time and the second type turning time.

[0085] Further, the first type turning time and the second type turning time can be combined according to the marked first type turning time and the second type turning time to determine the sharp turning time period. In the embodiment of the present application, the turning time period in the preset driving time period, such as the left turning time period and / or the right turning time period, can be determined first, and then the final sharp turning time period can be further identified from the turning time period.

[0086] In the implementation process, the sharp turning time period can be determined by the following steps: sorting the first type turning time and the second type turning time in time sequence; based on the sorting result, the time period is combined to obtain M candidate turning time periods, M is a positive integer; based on the maximum value of the absolute value of the lateral acceleration corresponding to each candidate turning time period and the maximum vehicle speed, the N sharp turning time periods are determined from the M candidate turning time periods.

[0087] Specifically, the first type of turning time and the second type of turning time are arranged in chronological order. For continuous same type of turning time, such as continuous first type of turning time, a turning time period in the first direction can be obtained by merging the continuous first type of turning time. For continuous second type of turning time, a turning time period in the second direction can be obtained by merging the continuous second type of turning time.

[0088] In actual driving, the driving process of the vehicle is complex and variable. For example, the target vehicle needs to perform a plurality of same direction turning on the driving route, such as performing a plurality of left turning. Then, a plurality of left turning time periods can be determined by a plurality of left turning time. For another example, the target vehicle passes through a ramp with a small turning angle and a long passing time, but cannot be classified as a turning of the vehicle, so this case is excluded from the turning time period.

[0089] Therefore, in order to make the identified time period more accurate, in the embodiments of the present specification, the M candidate turning time periods can be determined by the following method: based on the sorting result, the continuous same type of turning time is merged to obtain K initial turning time periods and the length of each initial turning time period, wherein the interval between adjacent same type of turning time in each initial turning time period is less than the second preset time interval, and K is a positive integer; for each initial turning time period, if the length of the time period satisfies the first preset length range, the time period is taken as the candidate turning time period; for each initial turning time period, if the length of the initial turning time period is greater than the first preset length range, the first preset turning angle is increased to a third preset turning angle, and the second preset turning angle is increased to a fourth preset turning angle, so as to re-label the first type of turning time and the second type of turning time of the initial turning time period and determine the initial turning time period, and the initial turning time period satisfying the second preset length range is taken as the candidate turning time period.

[0090] Specifically, each candidate turning time period corresponds to a turning or lane changing of the target vehicle. For ease of description, in the following description, the first type of turning time is taken as the left turning time, and the second type of turning time is taken as the right turning time. After arranging the left turning time and the right turning time in the preset driving time period, for continuous same type of turning time, it is judged whether the interval between adjacent two time points is less than the second preset time interval. The second preset time interval can be set according to actual needs, for example, the second preset time interval is 2s, 5s, 10s, etc. If the interval between adjacent two time points is less than the second preset time interval, it is determined that the two time points belong to the same initial turning time period, otherwise, it is determined that the two time points do not belong to the same initial turning time period.

[0091] For example, taking the second preset time interval of 2s as an example, if there are five continuous left turning time points, time point 1, time point 2, time point 3, time point 4, and time point 5, wherein the interval between time point 1 and time point 2 is less than 2s, the interval between time point 2 and time point 3 is less than 2s, the interval between time point 3 and time point 4 is greater than 2s, and the interval between time point 4 and time point 5 is less than 2s. Then, time point 1, time point 2, and time point 3 are merged into an initial turning time period, and time point 4 and time point 5 are merged into an initial turning time period.

[0092] It should be noted that for each initial turning time period, the starting time of the period is the earliest time point in the continuous same type time points, and the ending time of the period is the latest time point in the continuous same type time points.

[0093] In the above manner, K initial turning time periods in the preset driving time period can be obtained, K being a positive integer. The initial turning time period may include some abnormal data or time periods that need to be further screened, and therefore, in the embodiments of the present specification, after obtaining the initial turning time period, the initial turning time period needs to be further processed.

[0094] In the specific implementation process, the initial turning time period can be divided into three types according to the time length: the initial turning time period less than the first preset time length range is an extremely short time period, the initial turning time period meeting the first preset time length range is a normal time period, and the initial turning time period greater than the first preset time length range is an extremely long time period. The first preset time length range can be set according to actual needs, for example, the first preset time length range is 2s-30s, 1s-1min, etc.

[0095] For the extremely short time period, it can be directly filtered.

[0096] For the normal time period, each normal time period can be taken as a candidate turning time period.

[0097] For the extremely long time period, for example, the turning time period of the ramp with a small turning angle and a long time, or a traffic jam, the duration will be relatively long. In order to make the obtained candidate turning time period more in line with the characteristics of the sharp turning, further time period screening can be performed on the extremely long time period. Specifically, for the extremely long time period, the threshold of the steering wheel turning angle can be increased, that is, the first preset turning angle is increased to the third preset turning angle, and the second preset turning angle is increased to the fourth preset turning angle, for example, the third preset turning angle and the fourth preset turning angle are both 90°.

[0098] Further, based on the improved turning angle threshold, the above-mentioned candidate time period identification step is re-executed, that is, for an extremely long time period, if the steering wheel turning angle data in the time period is positive and greater than a third preset turning angle, or the lateral acceleration is negative and greater than a first preset acceleration, the data collection time is marked as a first initial time, and the first type turning time is determined based on the vehicle speed in the first preset time interval before and after the first initial time. At the same time, if the steering wheel turning angle data in the time period is negative and greater than a fourth preset turning angle, or the lateral acceleration is positive and greater than the first preset acceleration, the data collection time is marked as a second initial time, and the second type turning time is determined based on the vehicle speed in the first preset time interval before and after the second initial time. The time period merging is performed based on the first type turning time and the second type turning time, the initial turning time period is obtained, and the time period meeting the second preset time length range is taken as the candidate turning time period. The second preset time length range can be the same as or different from the first preset time length range. In the embodiment of the present application, the second preset time length can be 2-120s, that is, the time period less than 2s and the time period greater than 120s after re-identification are filtered out.

[0099] Of course, the above-mentioned re-identification of the extremely long time period can be repeatedly executed for different actual situations, which is not limited here. For the extremely long time period, there can be a case of small turning angle in the extremely long time period. By improving the turning angle threshold and re-identifying the candidate time period, the time period with small turning angle can be filtered out, and the remaining time period is more likely to be the time period of sharp turning with large turning angle.

[0100] In the above-mentioned manner, all the turning and lane changing time periods in the preset driving time period can be identified, that is, M candidate turning time periods are obtained, which provides a more comprehensive candidate time period for subsequent sharp turning time period identification. In the embodiment of the present application, the sharp turning time period can be selected from the candidate time period by the following manner: based on the maximum value of the absolute value of the lateral acceleration corresponding to each candidate turning time period and the maximum vehicle speed, the N sharp turning time periods are determined from the M candidate turning time periods.

[0101] Specifically, for each candidate turning time period, the maximum value of the absolute value of the lateral acceleration in the time period is determined, and the maximum value of the absolute value of the lateral acceleration is compared with a first threshold value, wherein the first threshold value can be set according to actual needs, for example, the first threshold value can be 4m / s 2 , 5m / s 2 , 6m / s 2etc. In addition, the maximum vehicle speed in the period is obtained, and the maximum vehicle speed is compared with a second threshold value, which can be set according to actual needs, for example, the second threshold value is 15 km / h, 20 km / h, 25 km / h, etc. If the maximum absolute value of the lateral acceleration is greater than the first threshold value, and the maximum vehicle speed is less than the second threshold value, the candidate period is determined as the sharp turning period.

[0102] Further, after the sharp turning period is determined, the period can be identified as a sharp turning corner period or a sharp lane changing period through step S103. In step S103, the sharp turning corner period or the sharp lane changing period can be identified in various ways, and different identification ways use different driving data. Hereinafter, two identification ways are taken as examples to be described.

[0103] The first way

[0104] In this way, the steering wheel angle is used to determine whether the sharp turning period is a sharp turning corner period, and the driving data is the steering wheel angle data of the target vehicle. The specific implementation is as follows: for each sharp turning period, the maximum absolute value of the target steering wheel angle is determined from the steering wheel angle data of the period; if the target steering wheel angle of the period is greater than a fifth preset steering angle, it is determined that the category of the period is a sharp turning corner period; or if the target steering wheel angle of the period is greater than a sixth preset steering angle and less than or equal to the fifth preset steering angle, and the duration of the steering wheel angle data of the period being greater than a seventh preset steering angle is greater than a first preset time length, it is determined that the category of the period is a sharp turning corner period, wherein the seventh preset steering angle is less than the sixth preset steering angle.

[0105] Specifically, the steering angle corresponding to the sharp turning corner is usually large, so the steering angle can be used to determine whether it is a sharp turning corner. In the embodiment of the present application, for a sharp turning period, the maximum absolute value of the target steering wheel angle of the period is determined first, and when the target steering wheel angle is greater than a fifth preset steering angle, the period is directly determined as a sharp turning corner period. The fifth preset steering angle can be set according to actual needs, for example, the fifth preset steering angle is 120°, 125°, etc.

[0106] For the target steering wheel angle between the sixth preset steering angle and the fifth preset steering angle, i.e. greater than the sixth preset steering angle and less than or equal to the fifth preset steering angle, since the maximum steering angle does not reach the fifth preset steering angle, it can be further considered whether the steering angle is continuously greater than a preset steering angle, and if so, it can also be determined as a sharp turning corner period.

[0107] For example, the sixth preset turning angle is 90°, the seventh preset turning angle is 60°, and the first preset time length is 2s. Of course, the above parameters can also be set according to actual needs, which are not limited here. For an acute turning period, when the maximum absolute value of the turning angle is greater than 90° and less than 120°, it is further judged whether there is a period in which the steering wheel turning angle is greater than 60° and maintained for more than 2s. If so, the period is regarded as an acute turning period.

[0108] Optionally, when the acute turning category is determined by the steering wheel turning angle, each acute turning period can be first extended, and the above steps of determining the acute turning period by the steering wheel turning angle are performed for each extended acute turning period.

[0109] The second mode

[0110] In this mode, the acute turning and the acute lane changing can be distinguished based on the route angle of the target vehicle. For the acute turning, the route angle before and after the acute turning is large because the angle of the acute turning is usually large. For the acute lane changing, the route angle before and after the acute lane changing is small because the target vehicle usually travels in the same direction before and after the acute lane changing.

[0111] In this mode, the driving data is the latitude and longitude data of the target vehicle, and the specific implementation can be: extending the front and rear periods of each acute turning period to obtain the extended period of each acute turning period; for each extended period, obtaining the latitude and longitude data in a first sub-period and the latitude and longitude data in a second sub-period in the extended period, wherein the start time of the first sub-period is the start time of the extended period, and the end time of the second sub-period is the end time of the extended period; determining the target angle between the starting route and the ending route corresponding to the extended period based on the latitude and longitude data in the first sub-period and the latitude and longitude data in the second sub-period; comparing the target angle with a preset angle, and determining the category of the corresponding acute turning period according to the comparison result.

[0112] Specifically, in order to accurately describe the positions before and after the acute turning, the acute turning period is extended, for example, a certain time length is extended before and after each acute turning period. The extended time length can be set according to actual needs, such as 2s, 3s, etc., which are not limited here.

[0113] For the extended time period after the time period extension, a first sub-time period and a second sub-time period are determined. The lengths of the first sub-time period and the second sub-time period can be set according to actual needs, for example, 2s, 3s, and in an embodiment, the first sub-time period is a time period of 3s located at the beginning of the extended time period, and the starting time of the first sub-time period is the starting time of the extended time period. The second sub-time period is a time period of 3s located at the end of the extended time period, and the end time of the second sub-time period is the end time of the extended time period.

[0114] Further, based on the latitude and longitude data of the first sub-time period and the latitude and longitude data of the second sub-time period, a target angle between the starting route and the ending route corresponding to the extended time period is determined. The target angle can be achieved in various ways. For example, the latitude and longitude data of each collection time of the first sub-time period is obtained, and based on the latitude and longitude data of each collection time, the driving route of the target vehicle is fitted as the starting route. Similarly, the latitude and longitude data of each collection time of the second sub-time period is obtained, and based on the latitude and longitude data of each collection time, the driving route of the target vehicle is fitted as the ending route. Based on the starting route and the ending route, the target angle is determined.

[0115] In order to save computing resources, in the embodiments of the present specification, the first collected latitude and longitude data and the last collected latitude and longitude data in the first sub-time period are determined in the order of collection time, and the vector of the starting route is determined based on the two data. Similarly, the first collected latitude and longitude data and the last collected latitude and longitude data in the second sub-time period are determined, and the vector of the ending route is determined based on the two data.

[0116] After obtaining the latitude and longitude, the latitude and longitude data can be converted into three-dimensional coordinates. Specifically, the latitude and longitude data (lng, lat) can be converted into three-dimensional coordinates (x, y, z) by the following formula.

[0117]

[0118]

[0119]

[0120] wherein lng is the longitude, lat is the latitude, and R is the radius of the earth.

[0121] By the above formula, the first collected latitude and longitude data in the first sub-time period is converted to obtain the corresponding coordinates (x A ,y A ,z A ) The last collected latitude and longitude data in the first sub-time period is converted to obtain the corresponding coordinates (x B ,y Bz B Based on the two coordinates, a vector p1 of the starting route can be obtained, where p1 can be expressed as:

[0122] p1 = (x1, y1, z1) = (x B -x A ,y B -y A ,z B -z A )

[0123] Similarly, the latitude and longitude data collected in the first sub-period are converted to obtain the corresponding coordinates (x C ,y C ,z C ) The latitude and longitude data collected in the last sub-period are converted to obtain the corresponding coordinates (x D ,y D ,z D ). Based on the two coordinates, a vector p2 of the end route can be obtained, where p2 can be expressed as:

[0124] p2 = (x2, y2, z2) = (x D -x C ,y D -y C ,z D -z C )

[0125] Further, based on p1 and p2, the target angle can be obtained, and the target angle θ can be calculated by the following formula:

[0126]

[0127] After obtaining the target angle, the target angle is compared with the preset angle, where the preset angle can be set according to actual needs, for example, the preset angle is 15°, 20°, etc. When the target angle is less than the preset angle, it is determined that the sharp turning period is a sharp lane changing period, and when the target angle is greater than or equal to the preset angle, it is determined that the sharp turning period is a sharp turning period.

[0128] Of course, different preset angles can also be set for the sharp lane changing and sharp turning periods, such as when the target angle is less than the first preset angle, it is a sharp lane changing period, and when the target angle is greater than the second preset angle, it is a sharp turning period. Wherein, the first preset angle is less than the second preset angle.

[0129] In the embodiments of the present specification, the first mode and the second mode can be implemented alone or in combination. In an embodiment, the first mode and the second mode are combined to determine the category of the sharp turning period. In the specific implementation process, each sharp turning period is first extended, and according to the extended period, the first mode is first executed, that is, whether the period is a sharp turning period is determined according to the steering wheel angle, if it is not a sharp turning period, the second mode is further executed, the target angle is determined through the latitude and longitude data, and whether the period is a sharp turning period or a sharp lane changing period is determined according to the target angle.

[0130] In the embodiments of the present specification, after the category of the sharp turning period is determined, the related data of the period can be further output, including but not limited to the identification of the sharp turning event (left sharp turning identification, right sharp turning identification, left sharp lane changing identification or right sharp lane changing identification), the start time of the event, the end time, the latitude and longitude at the start of the event, the latitude and longitude at the end of the event, the maximum lateral acceleration during the event, the maximum vehicle speed during the event, the maximum steering wheel angle during the event, and the route angle before and after the event.

[0131] In the determination of the identification of the sharp turning event, the first type turning time and the second type turning time corresponding to the initial period merging can be determined, and the direction of the maximum lateral acceleration in each period can also be determined.

[0132] For example, if the time in the sharp turning or sharp lane changing period is the first type turning time, and the first type turning time represents left turning, the sharp turning or sharp lane changing period is a left sharp turning or left sharp lane changing period. Correspondingly, if the time in the sharp turning or sharp lane changing period is the second type turning time, and the second type turning time represents right turning, the sharp turning or sharp lane changing period is a right sharp turning or right sharp lane changing period. When the lateral acceleration is determined, if the direction corresponding to the maximum absolute value of the lateral acceleration in the sharp turning or sharp lane changing period is positive, and the positive direction is right, the sharp turning or sharp lane changing period is a right sharp turning or right sharp lane changing period. Correspondingly, if the direction corresponding to the maximum absolute value of the lateral acceleration in the sharp turning or sharp lane changing period is negative, and the negative direction is left, the sharp turning or sharp lane changing period is a left sharp turning or left sharp lane changing period.

[0133] In summary, the scheme of the embodiments of the present specification can comprehensively determine the sharp turning period of the target vehicle through the steering wheel angle data and the lateral acceleration data, and avoid missing the sharp turning period. In addition, based on the driving data in each sharp turning period, the type of sharp turning can be divided, and each sharp turning period can be specifically divided into a sharp turning period or a sharp lane changing period, so that the judgment of the sharp turning of the vehicle is more accurate, the accuracy of the vehicle sharp turning recognition is improved, and more detailed driving state can be obtained.

[0134] Based on the same inventive concept, the embodiments of the present specification also provide a vehicle sharp turning identification device, as shown in the drawings, the device comprises: Figure 3

[0135] An acquisition module 301 is configured to acquire a plurality of steering wheel angle data and a plurality of lateral acceleration data of a target vehicle in a preset driving period;

[0136] An identification module 302 is configured to identify N sharp turning periods from the preset driving period based on the plurality of steering wheel angle data and the plurality of lateral acceleration data, wherein N is a positive integer;

[0137] A processing module 303 is configured to determine the category of each sharp turning period based on the driving data of the target vehicle in each sharp turning period, wherein the category of the sharp turning period is a sharp turning period or a sharp lane changing period.

[0138] Optionally, the identification module 302 is configured to:

[0139] mark the preset driving period with a first type of turning time and a second type of turning time based on the plurality of steering wheel angle data and the plurality of lateral acceleration data;

[0140] merge the first type of turning time and the second type of turning time to identify N sharp turning periods from the preset driving period;

[0141] The first type of turning time indicates that the target vehicle performs a turning operation in a first direction, and the second type of turning indicates that the target vehicle performs a turning operation in a second direction.

[0142] Optionally, the identification module 302 is configured to:

[0143] If the steering wheel angle data is positive and greater than a first preset angle, or the lateral acceleration data is negative and greater than a first preset acceleration, mark the corresponding data acquisition time as a first initial time;

[0144] If the steering wheel angle data is negative and greater than a second preset angle, or the lateral acceleration data is positive and greater than a second preset acceleration, mark the corresponding data acquisition time as a second initial time;

[0145] Screen the first type of turning time from the first initial time, and screen the second type of turning time from the second initial time.

[0146] Optionally, the identification module 302 is configured to:

[0147] ​determining whether there is a vehicle speed greater than zero in a time period with a first preset time interval from the first initial moment, and if so, marking the first initial moment as the first type of turning moment;

[0148] determining whether there is a vehicle speed greater than zero in a time period with the first preset time interval from the second initial moment, and if so, marking the second initial moment as the second type of turning moment.

[0149] Optionally, the identification module 302 is configured to:

[0150] sorting the first type of turning moment and the second type of turning moment in time sequence;

[0151] merging time periods based on the sorting result to obtain M candidate turning time periods, M being a positive integer;

[0152] determining the N sharp turning time periods from the M candidate turning time periods based on the maximum value of the absolute value of the lateral acceleration corresponding to each candidate turning time period and the maximum vehicle speed.

[0153] Optionally, the identification module 302 is configured to:

[0154] merging continuous same type of turning moments based on the sorting result to obtain K initial turning time periods and the length of each initial turning time period, wherein the interval between adjacent same type of turning moments in each initial turning time period is less than a second preset time interval, K being a positive integer;

[0155] for each initial turning time period, if the length of the initial turning time period meets a first preset length range, taking the initial turning time period as the candidate turning time period;

[0156] for each initial turning time period, if the length of the initial turning time period is greater than the first preset length range, increasing the first preset steering angle to a third preset steering angle and increasing the second preset steering angle to a fourth preset steering angle, re-marking the first type of turning moment and the second type of turning moment of the initial turning time period and determining the initial turning time period, and taking the initial turning time period meeting a second preset length range as the candidate turning time period.

[0157] Optionally, when the driving data is steering wheel angle data, the processing module 303 is configured to:

[0158] for each sharp turning time period, determining a target steering wheel angle with the maximum absolute value from the steering wheel angle data of the sharp turning time period;

[0159] if the target steering wheel angle of the sharp turning period is greater than a fifth preset angle, it is determined that the category of the sharp turning period is a sharp turning corner period;

[0160] if the target steering wheel angle of the sharp turning period is greater than a sixth preset angle and less than or equal to the fifth preset angle, and the duration that the steering wheel angle data of the sharp turning period is greater than a seventh preset angle is greater than a first preset time length, it is determined that the category of the sharp turning period is a sharp turning corner period, wherein the seventh preset angle is less than the sixth preset angle.

[0161] Optionally, when the driving data is latitude and longitude data, the processing module 303 is configured to:

[0162] perform front and rear period extension on each of the sharp turning periods to obtain an extended period of each of the sharp turning periods;

[0163] for each of the extended periods, obtain latitude and longitude data in a first sub-period and latitude and longitude data in a second sub-period in the extended period, wherein the start time of the first sub-period is the start time of the extended period, and the end time of the second sub-period is the end time of the extended period;

[0164] determine a target included angle between a start route and an end route corresponding to the extended period based on the latitude and longitude data in the first sub-period and the latitude and longitude data in the second sub-period;

[0165] compare the target included angle with a preset included angle, and determine the category of the corresponding sharp turning period according to the comparison result.

[0166] As to the device in the above embodiments, the specific manners in which various modules perform operations have been described in detail in the above-described embodiments of the vehicle sharp turning identification method, and thus will not be described in detail here.

[0167] Based on the same inventive concept, the embodiments of the present disclosure further provide a vehicle sharp turning identification device, as shown in Figure 4 which comprises a memory 808, a processor 802, and a computer program stored in the memory 808 and executable on the processor 802, wherein the processor 802 implements the steps of any method of the vehicle sharp turning identification method described above when executing the program.

[0168] wherein, in Figure 4In one embodiment, the bus architecture (represented by bus 800) includes any one or combination of busses known in the art to implement a bus architecture having a bus 800 that can include any number of interconnected buses and bridges, which are used to link various circuits including the one or more processors represented by processor 802, and memory represented by memory 808. Bus 800 can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, and therefore, not further described herein. Bus interface 806 provides an interface between bus 800, and receiver 801 and transmitter 803. Receiver 801 and transmitter 803 can be the same device, i.e., a transceiver, providing a unit for communicating with various other apparatus over a transmission medium. Processor 802 is responsible for managing bus 800 and general processing, while memory 808 can be used to store data used by processor 802 in executing its operations.

[0169] Based on the same inventive concept, the application further provides a computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the steps of any of the vehicle sharp turning identification methods described above.

[0170] The specification is presented with reference to flow diagrams and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each block of the flow diagrams and / or block diagrams, and combinations of blocks in the flow diagrams and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks.

[0171] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow diagram and / or block diagram block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks.

[0172] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow diagram and / or block diagram block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks.Figure 1 the steps of the functions specified in the one or more blocks.

[0173] While the preferred embodiments of the application have been described, additional variations and modifications can be made to the preferred embodiments by those of skill in the art once they have the benefit of the present disclosure. Therefore, the appended claims are intended to encompass within their scope all possible variations and modifications of the preferred embodiments. 1

[0174] It is apparent that those skilled in the art can make various changes and modifications to the application without departing from the spirit and scope of the application. Therefore, the application intends to cover all such changes and modifications of the application within the scope of the application and its equivalents.

Claims

1. A method for identifying a vehicle's sudden turn, characterized in that: include: Acquiring multiple steering wheel angle data and multiple lateral acceleration data of the target vehicle within a preset driving period; Based on the plurality of steering wheel angle data and the plurality of lateral acceleration data, N sharp turning periods are identified from the preset driving period, where N is a positive integer, wherein if the steering wheel angle data is positive and greater than a first preset angle, or the lateral acceleration data is negative and greater than a first preset acceleration, the corresponding data collection moment is marked as a first initial moment; if the steering wheel angle data is negative and greater than a second preset angle, or the lateral acceleration data is positive and greater than a second preset acceleration, the corresponding data collection moment is marked as a second initial moment; a first type of turning moment is selected from the first initial moment, and a second type of turning moment is selected from the second initial moment; the first type of turning moment and the second type of turning moment are sorted in chronological order; time periods are merged based on the sorting results to obtain M candidate turning periods, where M is a positive integer; and the N sharp turning periods are determined from the M candidate turning periods based on the maximum absolute value of the lateral acceleration and the maximum vehicle speed corresponding to each candidate turning period; Determining a category of each sharp turning period based on driving data of the target vehicle in each sharp turning period, wherein the category of the sharp turning period is a sharp turn period or a sharp lane change period; The time periods are merged based on the sorting results to obtain M candidate turning time periods, including: Based on the sorting result, consecutive turning moments of the same type are merged to obtain K initial turning periods and the duration of each initial turning period, wherein, in each initial turning period, the interval between adjacent moments of the same type is less than the second preset time interval, and K is a positive integer; for each initial turning period, if the duration of the initial turning period meets the first preset duration range, the initial turning period is used as the candidate turning period; for each initial turning period, if the duration of the initial turning period is greater than the first preset duration range, the first preset turning angle is increased to the third preset turning angle, and the second preset turning angle is increased to the fourth preset turning angle, so as to re-mark the first type turning moment and the second type turning moment of the initial turning period and determine the initial turning period, and the initial turning period that meets the second preset duration range is used as the candidate turning period.

2. The method according to claim 1, wherein The first-type turning timing indicates that the target vehicle performs a turning operation in a first direction, and the second-type turning timing indicates that the target vehicle performs a turning operation in a second direction.

3. The method according to claim 1, wherein The filtering out the first type of turning moment from the first initial moment, and filtering out the second type of turning moment from the second initial moment, comprises: determining whether there is a vehicle speed greater than zero within a period of a first preset time interval from the first initial moment, and if so, marking the first initial moment as the first type of turning moment; Determine whether there is a vehicle speed greater than zero within a period of time between the second initial moment and the first preset time interval, and if so, mark the second initial moment as the second type turning moment.

4. The method according to claim 1, wherein When the driving data is steering wheel angle data, determining the category of each sharp turning period based on the driving data of the target vehicle in each sharp turning period includes: For each sharp steering period, determining a target steering wheel angle having a maximum absolute value from the steering wheel angle data of the sharp steering period; If the target steering wheel angle of the sharp turning period is greater than the fifth preset angle, determining that the sharp turning period is a sharp turning period; If the target steering wheel angle of the sharp steering period is greater than the sixth preset angle and less than or equal to the fifth preset angle, and the duration of the steering wheel angle data of the sharp steering period being greater than the seventh preset angle is greater than the first preset duration, then the category of the sharp steering period is determined to be a sharp turn period, wherein the seventh preset angle is less than the sixth preset angle.

5. The method according to claim 1, wherein When the driving data is latitude and longitude data, determining the category of each sharp turn period based on the driving data of the target vehicle in each sharp turn period includes: Extending each sharp turning period before and after the period to obtain an extended period of each sharp turning period; For each extended period, obtain the longitude and latitude data of a first sub-period and the longitude and latitude data of a second sub-period in the extended period, wherein the start time of the first sub-period is the start time of the extended period, and the end time of the second sub-period is the end time of the extended period; Determining a target angle between a starting route and an ending route corresponding to the extended period based on the longitude and latitude data within the first sub-period and the longitude and latitude data within the second sub-period; The target angle is compared with a preset angle, and the category of the corresponding sharp turning period is determined according to the comparison result.

6. A vehicle sudden turn recognition device, characterized in that: include: An acquisition module is used to acquire a plurality of steering wheel angle data and a plurality of lateral acceleration data of a target vehicle within a preset driving period; an identification module for identifying, based on the plurality of steering wheel angle data and the plurality of lateral acceleration data, N sharp turning periods within the preset driving period, where N is a positive integer, wherein if the steering wheel angle data is positive and greater than a first preset angle, or the lateral acceleration data is negative and greater than a first preset acceleration, marking the corresponding data collection moment as a first initial moment; and if the steering wheel angle data is negative and greater than a second preset angle, or the lateral acceleration data is positive and greater than a second preset acceleration, marking the corresponding data collection moment as a second initial moment; filtering out first-type turning moments from the first initial moment, and filtering out second-type turning moments from the second initial moment; sorting the first-type turning moments and the second-type turning moments in chronological order; merging time periods based on the sorting results to obtain M candidate turning periods, where M is a positive integer; and determining the N sharp turning periods from the M candidate turning periods based on the maximum absolute value of the lateral acceleration corresponding to each candidate turning period and the maximum vehicle speed; a processing module, configured to determine a category of each sharp turning period based on driving data of the target vehicle in each sharp turning period, wherein the category of the sharp turning period is a sharp turn period or a sharp lane change period; The identification module is also used to merge consecutive turning moments of the same type based on the sorting result to obtain K initial turning periods and the duration of each initial turning period, wherein, in each initial turning period, the interval between adjacent moments of the same type is less than a second preset time interval, and K is a positive integer; for each initial turning period, if the duration of the initial turning period meets the first preset duration range, the initial turning period is used as the candidate turning period; for each initial turning period, if the duration of the initial turning period is greater than the first preset duration range, the first preset turning angle is increased to the third preset turning angle, and the second preset turning angle is increased to the fourth preset turning angle, so as to re-mark the first type turning moment and the second type turning moment of the initial turning period and determine the initial turning period, and the initial turning period that meets the second preset duration range is used as the candidate turning period.

7. A vehicle sudden turn recognition device, characterized in that: The invention comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors to execute the operating instructions corresponding to the method according to any one of claims 1 to 5 contained in the one or more programs.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method steps according to any one of claims 1 to 5 are implemented.

Images