Vehicle turning detection method, device, equipment and storage medium

Abstract

The present invention provides a vehicle turn detection method, apparatus, device, and storage medium. The method comprises: collecting inertial data and vehicle speed information of a target vehicle to be detected; determining the target vehicle's yaw rate based on the inertial data, and identifying the target vehicle's motion state based on the yaw rate and vehicle speed information; and detecting whether the target vehicle is turning based on the motion state. The vehicle turn detection method provided by the present invention identifies the target vehicle's state by combining inertial data and vehicle speed information. Based on the target vehicle's yaw rate, the accuracy of identifying the target vehicle's motion state can be improved, thereby more accurately identifying the target vehicle's turning scenario and reducing false alarms.

Description

Technical Field

[0001] The present invention relates to the field of vehicle detection technology, and in particular to a vehicle turning detection method, device, equipment and storage medium. Background Art

[0002] Currently, large vehicles have numerous blind spots, making them prone to serious traffic accidents during turns. With technological advancements, numerous detection and warning methods have emerged to reduce accidents caused by large vehicles during turns. However, most existing detection methods rely on a comprehensive assessment of the vehicle's external environment to determine whether a turn could result in a collision or other accident. However, these methods lack the accuracy to accurately identify the vehicle's own turning scenario, which can easily lead to false alarms. Summary of the Invention

[0003] The present invention provides a vehicle turning detection method, device, equipment and storage medium, which are used to solve the problem in the prior art that the detection of whether a collision will occur when the vehicle turns is based on a comprehensive assessment of the vehicle's external environment, resulting in insufficient recognition accuracy of the vehicle's own turning scene and prone to false alarms, and realize accurate recognition of the vehicle's turning scene.

[0004] The present invention provides a vehicle turning detection method, comprising:

[0005] Collect inertial data and speed information of the target vehicle to be detected;

[0006] determining a yaw rate of the target vehicle based on the inertial data, and identifying a motion state of the target vehicle based on the yaw rate and the vehicle speed information;

[0007] and detecting whether the target vehicle is turning according to the motion state.

[0008] According to a vehicle turning detection method provided by the present invention, the step of detecting whether the target vehicle is turning according to the motion state includes:

[0009] Determining a state switching process of the target vehicle according to the motion state, and calculating operating parameters of the target vehicle when the state is switched based on the inertia data and the vehicle speed information;

[0010] Whether the target vehicle turns is detected according to the state switching process and the operating parameters.

[0011] According to a vehicle turning detection method provided by the present invention, the motion states include a straight-ahead state, a left-turn state, a right-turn state, and a parking state, and the operating parameters include parking time, straight-ahead distance, turning radius, turning angle, small radius distance, and large radius distance. The step of calculating the operating parameters of the target vehicle when the motion state is switched based on the inertial data and the vehicle speed information according to the motion state includes:

[0012] When the target vehicle's motion state switches from any one of a straight-ahead state, a left-turn state, and a right-turn state to a parking state, the parking time is recorded;

[0013] When the motion state of the target vehicle switches from a parking state to a straight-moving state, calculating a straight-moving distance based on the vehicle speed information;

[0014] When the motion state of the target vehicle switches from a straight state to a left turn state or a right turn state, a turning radius and a turning angle are calculated based on the inertial data and the vehicle speed information, and a large radius driving distance and a small radius driving distance are calculated according to the turning radius.

[0015] According to a vehicle turning detection method provided by the present invention, the step of calculating the large-radius driving distance and the small-radius driving distance according to the turning radius includes:

[0016] Get the small radius threshold and the large radius threshold;

[0017] Based on the vehicle speed information, a large radius distance traveled by the target vehicle when the turning radius is greater than the large radius threshold is calculated, and a small radius distance traveled by the target vehicle when the turning radius is less than the small radius threshold is calculated.

[0018] According to a vehicle turning detection method provided by the present invention, the step of determining the yaw angular velocity of the target vehicle based on the inertial data includes:

[0019] Performing Butterworth filtering on the inertial data to obtain target inertial data, where the target inertial data includes a gyroscope value and an acceleration value;

[0020] The gyro value is mapped to the body coordinate system of the target vehicle to obtain the yaw angular velocity of the body of the target vehicle.

[0021] According to a vehicle turning detection method provided by the present invention, the step of mapping the gyroscope value to the body coordinate system of the target vehicle includes:

[0022] When the target vehicle is stationary, performing an initial calibration on an inertial measurement device that collects the inertial data, and calculating an intrinsic parameter between the inertial measurement device and a body of the target vehicle;

[0023] Calculating a transformation matrix between a local coordinate system of the inertial measurement device and a body coordinate system of the target vehicle based on the internal parameters, wherein the internal parameters include a roll angle and a pitch angle;

[0024] The gyro value is mapped into a body coordinate system of the target vehicle according to the conversion matrix.

[0025] According to a vehicle turning detection method provided by the present invention, after the step of detecting whether the target vehicle is turning according to the motion state, the method further includes:

[0026] If the target vehicle turns, detecting whether the target vehicle has committed any violation during the turning process based on the inertial data and the vehicle speed information, the violation including failure to stop while turning and / or speeding while turning;

[0027] If it exists, an alarm message will be generated and output.

[0028] The present invention also provides a vehicle turning detection device, comprising:

[0029] A data acquisition module is used to collect inertial data and speed information of the target vehicle to be detected;

[0030] a state recognition module, configured to determine the yaw rate of the target vehicle based on the inertial data, and to identify the motion state of the target vehicle based on the yaw rate and the vehicle speed information;

[0031] The turning detection module is used to detect whether the target vehicle is turning according to the motion state.

[0032] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the above-described vehicle turning detection methods is implemented.

[0033] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described vehicle turning detection methods.

[0034] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned vehicle turning detection methods.

[0035] The vehicle turning detection method, device, equipment and storage medium provided by the present invention identify the state of a target vehicle by combining inertial data and vehicle speed information. Based on the yaw angular velocity of the target vehicle's body, the accuracy of identifying the target vehicle's motion state can be improved, thereby more accurately identifying the target vehicle's turning scenario and reducing false alarms. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 This is one of the flow charts of the vehicle turning detection method provided by the present invention;

[0038] Figure 2 This is one of the intentions of the right turn process of the vehicle turn detection method provided by the present invention;

[0039] Figure 3 It is a structural schematic diagram of the vehicle turning detection device provided by the present invention;

[0040] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0041] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0042] The following combination Figure 1-Figure 2 The vehicle turning detection method of the present invention is described.

[0043] Reference Figure 1 , Figure 1 This is a flow chart of a vehicle turning detection method provided by an embodiment of the present invention, based on Figure 1 The vehicle turning detection method provided by the embodiment of the present invention includes the following steps:

[0044] Step 100: collecting inertial data and speed information of the target vehicle to be detected;

[0045] First, inertial data and vehicle speed information of the target vehicle to be detected are collected. Inertial data can be collected using an inertial measurement device, i.e., an inertial measurement unit (IMU), which is installed on the target vehicle and is used to measure the inertial data of the target vehicle's body (i.e., IMU data). Vehicle speed information can be collected using a controller area network (CAN). It is understood that inertial data and vehicle speed information can also be collected using other devices, which are not specifically limited here.

[0046] It should be noted that IMU data is sampled at a certain inertial sampling frequency and includes gyroscope and acceleration values. Based on the gyroscope values, the yaw rate and turning heading of the target vehicle can be calculated. Vehicle speed information is sampled at a certain speed sampling frequency by sampling the target vehicle's driving speed.

[0047] Step 200, determining the yaw rate of the target vehicle based on the inertial data, and identifying the motion state of the target vehicle based on the yaw rate and the vehicle speed information;

[0048] In this embodiment, the collected inertial data (i.e., IMU data) and CAN vehicle speed information are combined to identify the turning scenarios of the target vehicle to be detected, which can improve the accuracy of the recognition of the turning scenarios. Specifically, the yaw angular velocity of the target vehicle is first determined from the IMU data, and then the turning angle of the vehicle is determined. The yaw angular velocity of the target vehicle is the yaw angular velocity of the target vehicle's body. The motion state of the target vehicle is determined based on the yaw angular velocity and speed information of the body. The motion state includes a straight-ahead state, a left-turn state, a right-turn state, and a parked state. Furthermore, the motion state of the target vehicle also includes ordinary states other than the above-mentioned straight-ahead, left-turn, right-turn, and parked states, such as a U-turn or lane change.

[0049] Step 300: Detect whether the target vehicle is turning according to the motion state.

[0050] Generally speaking, when a vehicle turns left or right, it is not necessarily turning, but may also be changing lanes. The turning angle of the vehicle is determined by combining the yaw angular velocity of the vehicle body, and the motion state of the target vehicle is identified by combining the speed information of the target vehicle. Therefore, it is possible to determine whether the target vehicle is turning based on the identified motion state, thereby improving the recognition accuracy of the target vehicle's turning scene.

[0051] Furthermore, step 300 may also include:

[0052] Step 301, determining a state switching process of the target vehicle according to the motion state, and calculating operating parameters of the target vehicle when the state is switched based on the inertial data and the vehicle speed information;

[0053] Step 302: Detect whether the target vehicle is turning according to the state switching process and the operating parameters.

[0054] When detecting whether a vehicle is turning, the detection is performed based on the identified motion state of the target vehicle. Specifically, according to the identified motion state of the target vehicle, the state switching process of the target vehicle during driving is determined, and the operating parameters of the target vehicle when the state is switched are calculated. According to the switching process of the motion state of the target vehicle and the operating parameters when the state is switched, it is determined whether the target vehicle is turning, and the turn can be a left turn or a right turn.

[0055] It can be seen that when a vehicle turns, the driving process has certain rules. Take right turning as an example, refer to Figure 2 When a vehicle turns right, it generally includes Figure 2 The illustrated stages begin with the stationary phase, during which the vehicle is parked. This parking state can be transitioned from any state, such as going straight, turning left, or turning right. After a period of parking, the vehicle switches from the parking state to going straight, entering the straight-ahead phase. After traveling a certain distance, the vehicle switches from going straight to turning right. The turning radius and angle during this right-turn state differ from those during lane changes, allowing detection of whether the vehicle is turning. After traveling a certain distance, the vehicle switches from turning right to going straight, completing the turn. By combining the state transitions of "parking-going straight-turning-left / right-turning-going straight" and the operating parameters during the target vehicle's motion state transitions, accurate identification of the target vehicle's turning scenarios can be achieved, reducing false alarms.

[0056] Furthermore, after step 300, the following steps may be further included:

[0057] Step 310: If the target vehicle turns, detecting whether the target vehicle has committed any violations during the turning process based on the inertial data and the vehicle speed information, wherein the violations include failure to stop while turning and / or speeding while turning;

[0058] Step 320: If it exists, generate and output an alarm prompt message.

[0059] After detecting a target vehicle turning, the system detects whether the target vehicle has committed any violations during the turn based on the collected IMU data and vehicle speed information. These violations include failure to stop for a turn and / or speeding. If the target vehicle has committed any violations during the turn, a warning message is generated and output to regulate the driver's driving behavior. The warning message can be output in one or more of the following ways: a signal light, an alarm, or a voice prompt, which are also not limited here.

[0060] In this embodiment, the state of the target vehicle is identified by combining inertial data and vehicle speed information. Based on the yaw angular velocity of the target vehicle's body, the accuracy of identifying the target vehicle's motion state can be improved, thereby more accurately identifying the target vehicle's turning scenario and reducing false alarms.

[0061] Furthermore, when it is detected that the target vehicle has violated the regulations during the turning process, by generating and outputting an alarm prompt information, the driver's driving behavior can be regulated in a timely manner, driving safety can be improved, and the possibility of traffic accidents such as collisions caused by the target vehicle during the turning process can be reduced.

[0062] In one embodiment, in step 200, the step of determining the yaw rate of the target vehicle based on the IMU data may further include:

[0063] Step 201: performing Butterworth filtering on the inertial data to obtain target inertial data, where the target inertial data includes gyroscope values ​​and acceleration values.

[0064] Step 202 : Map the gyro value to the body coordinate system of the target vehicle to obtain the yaw angular velocity of the body of the target vehicle.

[0065] When determining the yaw angular velocity of the target vehicle's body, the raw IMU data collected by the IMU is first subjected to Butterworth filtering using a Butterworth filter to obtain filtered target IMU data. The target IMU data includes gyroscope values ​​and acceleration values. The gyroscope values ​​are mapped to the body coordinate system of the target vehicle to obtain the yaw angular velocity of the target vehicle's body. The raw IMU data can be filtered using a second-order Butterworth filter, or filtered using a first-order Butterworth filter, or filtered using other filters, which are not specifically limited here. It is understandable that the speed information of the target vehicle is collected based on the body coordinate system of the target vehicle, which can be an earth coordinate system, etc., while the IMU data is collected based on the local coordinate system of the IMU. Therefore, it is necessary to use the body coordinate system as a global coordinate system, map the IMU data, convert the collected data into the same coordinate system, and complete the fusion of the collected IMU data and the speed information. The gyro value in the target IMU data is mapped to the vehicle body coordinate system to obtain the yaw angular velocity of the target vehicle body.

[0066] Furthermore, step 202 may further include:

[0067] Step 2021, when the target vehicle is stationary, performing an initial calibration on the inertial measurement device that collects the inertial data, and calculating an intrinsic parameter between the inertial measurement device and the body of the target vehicle;

[0068] Step 2022: Calculate a transformation matrix between the local coordinate system of the inertial measurement device and the body coordinate system of the target vehicle based on the internal parameters, wherein the internal parameters include a roll angle and a pitch angle;

[0069] Step 2023: Map the gyro value to the body coordinate system of the target vehicle according to the conversion matrix.

[0070] When mapping gyroscope values ​​to the vehicle coordinate system, the IMU is initially calibrated while the target vehicle is stationary. Specifically, the intrinsic parameters between the IMU and the target vehicle's body are calculated, including the roll and pitch angles between the IMU and the vehicle body. Based on these roll and pitch angles, a transformation matrix is ​​calculated between the IMU coordinate system and the vehicle body coordinate system. Based on this transformation matrix, the target IMU data, including the gyroscope values, is transformed into the vehicle body coordinate system, achieving the fusion of the IMU data and vehicle speed information.

[0071] In this embodiment, the IMU data is filtered and converted into a coordinate system, and the IMU data is converted into a vehicle body coordinate system to achieve fusion of the IMU data and vehicle speed information. Based on the fused IMU data and vehicle speed information, the accuracy of identifying the vehicle's motion state can be improved, thereby achieving accurate identification of the target vehicle's motion state.

[0072] In one embodiment, in step 301, the step of calculating the operating parameters of the target vehicle when the state is switched based on the IMU data and the vehicle speed information may further include:

[0073] Step 3011: When the target vehicle's motion state switches from any one of a straight-ahead state, a left-turn state, and a right-turn state to a parking state, the parking time is recorded;

[0074] Step 3012: When the target vehicle's motion state switches from a parking state to a straight-moving state, calculating a straight-moving distance based on the vehicle speed information;

[0075] Step 3013, when the motion state of the target vehicle switches from a straight state to a left turn state or a right turn state, the turning radius and the turning angle are calculated based on the inertial data and the vehicle speed information, and the large radius driving distance and the small radius driving distance are calculated according to the turning radius.

[0076] The target vehicle's motion states include straight ahead, left turn, right turn, and parked. The target vehicle's operating parameters during motion state switching include parking duration, straight ahead distance, turning radius, turning angle, small radius distance, and large radius distance. It can be seen that a target vehicle's motion state switching marks the end of one motion state and the beginning of another. Therefore, after identifying the target vehicle's motion state, the target vehicle's operating parameters under different motion states can be calculated based on the target vehicle's motion state switching process. When calculating the operating parameters of the target vehicle when the motion state switches, specifically, when the motion state of the target vehicle switches from any one of the states such as straight driving, left turn, and right turn to the parking state, the parking time is recorded; when the motion state of the target vehicle switches from the parking state to the straight driving state, the straight driving distance is calculated based on the collected vehicle speed information; when the motion state of the target vehicle switches from the straight driving state to the left turn state or the right turn state, the turning radius and turning angle are calculated based on the target IMU data and vehicle speed information, specifically, the turning radius and turning angle are calculated based on the yaw angular velocity and vehicle speed of the vehicle body; then, based on the calculated turning radius, the small radius distance and large radius distance traveled by the target vehicle when turning left or right are further calculated.

[0077] Furthermore, step 3031 may further specifically include:

[0078] Step A1, obtaining a small radius threshold and a large radius threshold;

[0079] Step A2: Calculate, based on the vehicle speed information, the large radius distance traveled by the target vehicle when the turning radius is greater than the large radius threshold, and calculate the small radius distance traveled by the target vehicle when the turning radius is less than the small radius threshold.

[0080] When calculating the small radius distance and the large radius distance traveled by the target vehicle when turning left or right based on the turning radius of the target vehicle, first obtain the small radius threshold and the large radius threshold. According to the collected vehicle speed information, calculate the turning distance when the turning radius of the target vehicle is greater than the large radius threshold, that is, obtain the large radius distance. Calculate the distance traveled when the turning radius of the target vehicle is less than the small radius threshold, that is, obtain the small radius distance.

[0081] In this embodiment, the collected IMU data and vehicle speed information are used to calculate the operating parameters such as the parking time, straight-line distance, turning radius, turning angle, small radius distance and large radius distance when the target vehicle switches its motion state. Combined with the motion state switching process of the target vehicle, the turning scene of the target vehicle can be accurately identified, thereby improving the accuracy of turning detection of the target vehicle.

[0082] The following describes in detail the process of the vehicle turning detection method provided by the present invention through another embodiment:

[0083] In this embodiment, an IMU inertial measurement device is installed on the target vehicle to be detected. When the target vehicle is stationary, the IMU is initially calibrated to calculate the roll angle θ between the IMU and the target vehicle body. r and pitch angle θ p , according to the calculated roll angle θ r and pitch angle θ p , for example, the roll angle θ r is 0.021rad, the pitch angle θ p =-0.039rad, calculate the transformation matrix between the IMU device navigation coordinate system and the vehicle body coordinate system The target vehicle's raw IMU data and speed information are collected via the target vehicle's controller area network (CAN). The speed information is collected based on the vehicle's body coordinate system. The IMU data includes gyroscope and accelerometer values. The collected raw IMU data is filtered using a preset filter, such as a second-order Butterworth filter, to obtain filtered target IMU data. The filtered target IMU data contains gyroscope values ​​wx, wy, and wz, and acceleration values ​​ax, ay, and az, respectively.

[0084] Based on the transformation matrix between the IMU coordinate system and the vehicle coordinate system Map the gyro value to the vehicle coordinate system to obtain the vehicle's yaw angular velocity wz v , as shown in the following formula 1:

[0085]

[0086] According to the collected CAN vehicle speed information and the calculated vehicle yaw angular velocity wz v , identify the target vehicle's motion state, which includes straight ahead, left turn, right turn, parking and normal state. For example, when the vehicle speed is greater than the first speed threshold of 5m / s, the vehicle body yaw angular velocity wz v When the angular velocity is less than the first threshold value of 0.05rad / s and greater than the second threshold value of -0.05rad / s, the target vehicle is judged to be in a high-speed straight-moving state; when the vehicle body yaw angular velocity wz v When the yaw angular velocity wz is greater than the third angular velocity threshold of 0.1 rad / s, the target vehicle is judged to be turning right. v When the vehicle's speed is less than the fourth angular velocity threshold of -0.1 rad / s, the target vehicle is determined to be turning left; when the vehicle's speed is less than the second speed threshold of 0.01 m / s, the target vehicle is determined to be parked; otherwise, the target vehicle is determined to be in normal motion. A left or right turn generally consists of four phases: a stationary phase, a straight-ahead phase after parking, a turning phase, and a turn completion phase. After identifying the target vehicle's motion state, the target vehicle's motion state transition process is determined, and the target vehicle's operating parameters during the motion state transition are calculated. Specifically, for example, when the target vehicle is turning, when the target vehicle's motion state is a parking state, it enters a stationary stage, and this stage records the parking time of the target vehicle; when the target vehicle's motion state switches from a parking state to a straight-ahead state, it enters a straight-ahead stage after parking, and this stage records the straight-ahead distance. When the straight-ahead distance is greater than the straight-ahead distance threshold, the straight-ahead distance and parking time recorded this time can be cleared. For example, when the straight-ahead distance threshold is 25 meters, if it is detected that the straight-ahead distance of the target vehicle in the straight-ahead stage after parking is 10 meters, there is no need to clear the parking time. If the straight-ahead distance of the target vehicle in the straight-ahead stage after parking exceeds 25 meters, the parking time recorded this time is cleared; when the target vehicle's motion state switches from a straight-ahead state to a non-straight-ahead state, that is, a left turn state or a right turn state, it enters a turning stage, and this stage calculates the turning radius and turning angle, wherein the calculation method of the turning radius r and the turning angle θ is as shown in the following formula 2-3:

[0087] r=v / wz v (2)

[0088] θ=wz v *dtimu (3)

[0089] Among them, v represents the vehicle speed collected through CAN, dt imu Indicates the sampling frequency of the IMU.

[0090] Get the small radius threshold and the large radius threshold, and calculate the small radius distance d that the target vehicle travels when turning based on the calculated turning radius r small and the large radius distance d big Specifically, during the turning process of the target vehicle, the small radius distance d traveled by the target vehicle when the turning radius r is less than the small radius threshold is calculated. small , and the large radius distance d traveled when the turning radius is greater than the large radius threshold big , small radius distance d small and the large radius distance d big Specifically, it can be calculated according to the following formula 4:

[0091] d=v*dt v (4)

[0092] Among them, dt v is the CAN vehicle speed sampling frequency.

[0093] When the target vehicle's motion state switches from turning left or right to going straight, it enters the turning end stage. According to the calculated small radius distance d small , large radius distance d big , turning angle θ and parking time and other operating parameters to determine whether the target vehicle turns. Specifically, if the small radius threshold r small is 35 meters, the maximum radius threshold r big is 60 meters. If the target vehicle travels a small radius distance d when the turning radius is less than 35 meters, small The maximum radius distance d is less than the preset first distance threshold of 7 meters and is traveled when the turning radius is greater than 60 meters. bigIf the distance is less than a preset second threshold of 20 meters and θ is greater than a preset angle threshold of 50°, the target vehicle is determined to be turning. The turning direction can be further determined to be a left or right turn. Specifically, the turning direction can be determined based on the sign of the turning angle θ. For example, when θ is greater than 50°, it indicates a right turn, and when it is less than -50°, it indicates a left turn. The sign of the turning angle θ can be used to determine the target vehicle's turning direction and, therefore, whether the target vehicle is turning left or right. Based on this, the duration of the stop phase during the turning process and the vehicle speed at each phase are used to detect whether the target vehicle has committed any violations during the turning process. These violations include failure to stop during a turn and / or speeding during a turn. If a violation is present, for example, if the target vehicle's stop duration is less than a preset time threshold of 1 second, the target vehicle is determined to have failed to stop during a turn. A warning message is generated and outputted via one or more of an indicator light, a ringing alarm, or voice notification. This serves to regulate the driver's driving behavior, improve driving safety, and reduce the possibility of traffic accidents such as collisions during the turning process.

[0094] It should be noted that the specific parameter values ​​in the above embodiments are only for illustrative purposes and do not constitute a limitation to the present invention.

[0095] The vehicle turning detection device provided by the present invention is described below. The vehicle turning detection device described below and the vehicle turning detection method described above can be referenced to each other.

[0096] Reference Figure 3 The vehicle turning detection device provided by the present invention includes:

[0097] The data acquisition module 10 is used to collect inertial data and vehicle speed information of the target vehicle to be detected;

[0098] a state recognition module 20, configured to determine the yaw rate of the target vehicle based on the inertial data, and to identify the motion state of the target vehicle based on the yaw rate and the vehicle speed information;

[0099] The turning detection module 30 is configured to detect whether the target vehicle is turning according to the motion state.

[0100] In one embodiment, the turn detection module 30 is further configured to:

[0101] Determining a state switching process of the target vehicle according to the motion state, and calculating operating parameters of the target vehicle when the state is switched based on the inertia data and the vehicle speed information;

[0102] Whether the target vehicle turns is detected according to the state switching process and the operating parameters.

[0103] In one embodiment, the motion state includes a straight-ahead state, a left-turn state, a right-turn state, and a parking state; the operating parameters include parking time, straight-ahead distance, turning radius, turning angle, small radius distance, and large radius distance; and the turning detection module 30 is further configured to:

[0104] When the target vehicle's motion state switches from any one of a straight-ahead state, a left-turn state, and a right-turn state to a parking state, the parking time is recorded;

[0105] When the motion state of the target vehicle switches from a parking state to a straight-moving state, calculating a straight-moving distance based on the vehicle speed information;

[0106] When the motion state of the target vehicle switches from a straight state to a left turn state or a right turn state, a turning radius and a turning angle are calculated based on the inertial data and the vehicle speed information, and a large radius driving distance and a small radius driving distance are calculated according to the turning radius.

[0107] In one embodiment, the turn detection module 30 is further configured to:

[0108] Get the small radius threshold and the large radius threshold;

[0109] Based on the vehicle speed information, a large radius distance traveled by the target vehicle when the turning radius is greater than the large radius threshold is calculated, and a small radius distance traveled by the target vehicle when the turning radius is less than the small radius threshold is calculated.

[0110] In one embodiment, the state identification module 20 is further configured to:

[0111] Performing Butterworth filtering on the inertial data to obtain target inertial data, where the target inertial data includes a gyroscope value and an acceleration value;

[0112] The gyro value is mapped to the body coordinate system of the target vehicle to obtain the yaw angular velocity of the body of the target vehicle.

[0113] In one embodiment, the state identification module 20 is further configured to:

[0114] When the target vehicle is stationary, performing an initial calibration on an inertial measurement device that collects the inertial data, and calculating an intrinsic parameter between the inertial measurement device and a body of the target vehicle;

[0115] Calculating a transformation matrix between a local coordinate system of the inertial measurement device and a body coordinate system of the target vehicle based on the internal parameters, wherein the internal parameters include a roll angle and a pitch angle;

[0116] The gyro value is mapped into a body coordinate system of the target vehicle according to the conversion matrix.

[0117] In one embodiment, the vehicle turning detection device further includes an alarm prompt module for:

[0118] If the target vehicle turns, detecting whether the target vehicle has committed any violation during the turning process based on the inertial data and the vehicle speed information, the violation including failure to stop while turning and / or speeding while turning;

[0119] If it exists, an alarm message will be generated and output.

[0120] Figure 4 An example of a physical structure diagram of an electronic device is shown below. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other via the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the vehicle turn detection method, which includes:

[0121] Collect inertial data and speed information of the target vehicle to be detected;

[0122] determining a yaw rate of the target vehicle based on the inertial data, and identifying a motion state of the target vehicle based on the yaw rate and the vehicle speed information;

[0123] and detecting whether the target vehicle is turning according to the motion state.

[0124] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0125] In another aspect, the present invention further provides a computer program product, comprising a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the vehicle turn detection method provided by each of the above methods, which includes:

[0126] Collect inertial data and speed information of the target vehicle to be detected;

[0127] determining a yaw rate of the target vehicle based on the inertial data, and identifying a motion state of the target vehicle based on the yaw rate and the vehicle speed information;

[0128] and detecting whether the target vehicle is turning according to the motion state.

[0129] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the vehicle turn detection method provided by the above methods is implemented, and the method includes:

[0130] Collect inertial data and speed information of the target vehicle to be detected;

[0131] determining a yaw rate of the target vehicle based on the inertial data, and identifying a motion state of the target vehicle based on the yaw rate and the vehicle speed information;

[0132] and detecting whether the target vehicle is turning according to the motion state.

[0133] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0134] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A vehicle turning detection method, characterized in that: The following steps are involved: Collect inertial data and speed information of the target vehicle to be detected; determining a yaw rate of the target vehicle based on the inertial data, and identifying a motion state of the target vehicle based on the yaw rate and the vehicle speed information; the motion state including a straight ahead state, a left turn state, a right turn state, and a parked state; detecting whether the target vehicle is turning according to the motion state; The step of detecting whether the target vehicle is turning according to the motion state includes: Determining a state switching process of the target vehicle according to the motion state, and calculating operating parameters of the target vehicle when the state is switched based on the inertial data and the vehicle speed information; the operating parameters include parking time, straight distance, turning radius, turning angle, small radius travel distance, and large radius travel distance; detecting whether the target vehicle is turning according to the state switching process and the operating parameters; The step of calculating the operating parameters of the target vehicle when the state is switched based on the inertial data and the vehicle speed information includes: When the target vehicle's motion state switches from any one of a straight-ahead state, a left-turn state, and a right-turn state to a parking state, the parking time is recorded; When the motion state of the target vehicle switches from a parking state to a straight-moving state, calculating a straight-moving distance based on the vehicle speed information; When the motion state of the target vehicle switches from a straight state to a left turn state or a right turn state, a turning radius and a turning angle are calculated based on the inertial data and the vehicle speed information, and a large radius driving distance and a small radius driving distance are calculated according to the turning radius.

2. The vehicle turning detection method according to claim 1, characterized in that: The step of calculating the large-radius driving distance and the small-radius driving distance according to the turning radius includes: Get the small radius threshold and the large radius threshold; Based on the vehicle speed information, a large radius distance traveled by the target vehicle when the turning radius is greater than the large radius threshold is calculated, and a small radius distance traveled by the target vehicle when the turning radius is less than the small radius threshold is calculated.

3. The vehicle turning detection method according to claim 1, wherein: The step of determining the yaw rate of the target vehicle based on the inertial data comprises: Performing Butterworth filtering on the inertial data to obtain target inertial data, where the target inertial data includes a gyroscope value and an acceleration value; The gyro value is mapped to the body coordinate system of the target vehicle to obtain the yaw angular velocity of the body of the target vehicle.

4. The vehicle turning detection method according to claim 3, characterized in that: The step of mapping the gyro value to the body coordinate system of the target vehicle comprises: When the target vehicle is stationary, performing an initial calibration on an inertial measurement device that collects the inertial data, and calculating an intrinsic parameter between the inertial measurement device and a body of the target vehicle; Calculating a transformation matrix between a local coordinate system of the inertial measurement device and a body coordinate system of the target vehicle based on the internal parameters, wherein the internal parameters include a roll angle and a pitch angle; The gyro value is mapped into a body coordinate system of the target vehicle according to the conversion matrix.

5. The vehicle turning detection method according to claim 1, characterized in that: After the step of detecting whether the target vehicle is turning according to the motion state, the method further includes: If the target vehicle turns, detecting whether the target vehicle has committed any violation during the turning process based on the inertial data and the vehicle speed information, the violation including failure to stop while turning and / or speeding while turning; If it exists, an alarm message will be generated and output.

6. A vehicle turning detection device, characterized in that: include: A data acquisition module is used to collect inertial data and speed information of the target vehicle to be detected; a state recognition module, configured to determine the yaw rate of the target vehicle based on the inertial data, and to identify the motion state of the target vehicle based on the yaw rate and the vehicle speed information; the motion state including a straight ahead state, a left turn state, a right turn state, and a parked state; A turning detection module, configured to detect whether the target vehicle is turning according to the motion state; The turn detection module is further configured to: Determining a state switching process of the target vehicle according to the motion state, and calculating operating parameters of the target vehicle when the state is switched based on the inertial data and the vehicle speed information; the operating parameters include parking time, straight distance, turning radius, turning angle, small radius travel distance, and large radius travel distance; detecting whether the target vehicle is turning according to the state switching process and the operating parameters; The turn detection module is further configured to: When the target vehicle's motion state switches from any one of a straight-ahead state, a left-turn state, and a right-turn state to a parking state, the parking time is recorded; When the motion state of the target vehicle switches from a parking state to a straight-moving state, calculating a straight-moving distance based on the vehicle speed information; When the motion state of the target vehicle switches from a straight state to a left turn state or a right turn state, a turning radius and a turning angle are calculated based on the inertial data and the vehicle speed information, and a large radius driving distance and a small radius driving distance are calculated according to the turning radius.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the vehicle turning detection method according to any one of claims 1 to 5 is implemented.

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

Images