A vehicle state recognition method, system, device, and medium

Abstract

The application belongs to the field of vehicle-mounted millimeter wave radar data processing, and particularly relates to a vehicle state recognition method applied to a millimeter wave radar, comprising: acquiring a yaw rate of a current frame of a vehicle and a previous frame state, and the current frame and the previous frame are separated by a preset time; recognizing the yaw rate to obtain a single recognition result, and recording the single recognition result into a lane changing start state machine and / or a lane changing end state machine, and the lane changing start state machine / lane changing end state machine is used for accumulating multiple recognition results; and recognizing a current state of the vehicle according to the accumulated multiple recognition results in the lane changing start state machine and / or the lane changing end state machine and the previous frame state. The application can self-adaptively judge the driving state of the vehicle by inputting the yaw rate to the millimeter wave radar, is not easily affected by external environment, improves the accuracy of lane changing behavior recognition, further calculates the lateral distance between the vehicle and other vehicles, timely warns the driver, and reduces false alarms and missed alarms caused by the vehicle body being not straight.

Description

Technical Field

[0001] This invention belongs to the field of vehicle-mounted millimeter-wave radar data processing, specifically relating to a vehicle status recognition method, system, device, and medium. Background Technology

[0002] Advanced driving assistance systems (ADAS) are systems that extract data from various sensors installed on a vehicle, sense the surrounding environment while the vehicle is in motion, and identify and predict potential hazards through computational analysis. ADAS systems can increase vehicle safety, and therefore, vehicles that support automated driving are usually equipped with ADAS.

[0003] In the application of ADAS, it is often necessary to identify the lane-changing behavior of vehicles. Currently, the technology for detecting lane changes mainly relies on camera sensors. Based on image recognition of lane lines and the lateral distance of the vehicle target, the lateral distance between the vehicle and the lane line is determined to judge whether the vehicle is changing lanes.

[0004] Meanwhile, when a vehicle equipped with millimeter-wave radar is driving normally in a straight line, the vehicle body is basically parallel to the lane lines. When the vehicle changes lanes, there will be an angle between the vehicle body and the lane lines. At this time, there is an angle between the millimeter-wave radar coordinate system and the earth's coordinate system, generally called the yaw angle. When this angle is large, it will cause deviations in the lateral and longitudinal distances of the target vehicle measured by the millimeter-wave radar. Among them, the direction along the lane line is called the longitudinal distance, and the direction perpendicular to the lane line is called the lateral distance. When the lateral deviation of the target is greater than the width of the lane line, the alarm functions based on millimeter-wave radar (FCW, BSD, LCA, etc.) will usually have serious false alarm and missed alarm problems. Summary of the Invention

[0005] In view of the shortcomings of the prior art described above, the purpose of this invention is to provide a vehicle state recognition method that is applied to millimeter-wave radar. This method can adaptively determine the vehicle's driving state by measuring the yaw rate, making it less susceptible to external environmental influences and improving the accuracy of lane change behavior recognition.

[0006] To achieve the above and other related objectives, the present invention provides a vehicle state recognition method applied to millimeter-wave radar, comprising: acquiring the yaw rate of the vehicle in the current frame and the state of the previous frame, wherein the current frame and the previous frame are spaced apart by a preset time; recognizing the yaw rate to obtain a single recognition result, and recording it in a lane change start state machine and / or a lane change end state machine, wherein the lane change start state machine / lane change end state machine is used to accumulate multiple recognition results; and recognizing the current state of the vehicle based on the accumulated multiple recognition results in the lane change start state machine and / or lane change end state machine and the state of the previous frame.

[0007] According to a specific embodiment of the present invention, the step of identifying the yaw rate to obtain a single identification result includes: identifying the yaw rate according to a preset first threshold: if the absolute value of the yaw rate is greater than the first threshold, it is identified as vehicle deflection, and the count value of the lane change initiation state machine is incremented by 1; otherwise, it is identified as vehicle not deflecting, and the count value of the lane change initiation state machine is set to 0. Identifying the yaw rate according to a preset second threshold: if the absolute value of the yaw rate is less than the second threshold, it is identified as vehicle not deflecting, and the count value of the lane change end state machine is incremented by 1; otherwise, it is identified as vehicle deflection, and the count value of the lane change end state machine is set to 0; wherein, the first threshold is greater than the second threshold.

[0008] According to a specific embodiment of the present invention, the step of identifying the current state of a vehicle based on the accumulated recognition results in the lane change initiation state machine and the previous frame state includes: identifying the current state of the vehicle based on the count value of the lane change initiation state machine and the previous frame state: if the count value of the lane change initiation state machine is greater than a preset lane change initiation threshold, then the current state is identified as lane change in progress; otherwise, the previous frame state is taken as the current state; wherein, the count value of the lane change initiation state machine is the accumulated recognition result of the lane change initiation state machine.

[0009] According to a specific embodiment of the present invention, the step of identifying the current state of a vehicle based on the accumulated recognition results in the lane change end state machine and the previous frame state includes: identifying the current state of the vehicle based on the count value of the lane change end state machine and the previous frame state: if the count value of the lane change end state machine is greater than a preset lane change end threshold, then the current state is identified as straight driving; otherwise, the previous frame state is taken as the current state; wherein, the count value of the lane change end state machine is the accumulated recognition result of the lane change end state machine.

[0010] According to a specific embodiment of the present invention, the method further includes: calculating the lateral distance to other vehicles based on the current state.

[0011] According to a specific embodiment of the present invention, the step of calculating the lateral distance to other vehicles based on the current state includes: if the current state is straight-line driving, then the formula for calculating the lateral distance X is:

[0012] X = range * sinθ

[0013] Where range is the straight-line distance between the vehicle and other vehicles, and θ is the angle between the vehicle and other vehicles.

[0014] According to a specific embodiment of the present invention, the step of calculating the lateral distance to other vehicles based on the current state further includes:

[0015] If the current state is a lane change, then the formula for calculating the lateral distance X is:

[0016] X = range * sin(θ + yaw)

[0017] yaw = old yaw + yawrate *t

[0018] Where range is the straight-line distance between the vehicle and other vehicles, θ is the angle between the vehicle and other vehicles, yaw is the yaw angle of the vehicle in the current frame, old yaw is the yaw angle of the vehicle in the previous frame, t is the interval between the current frame and the previous frame, and yawrate is the yaw rate of the vehicle.

[0019] A vehicle state recognition system, applied to millimeter-wave radar, includes: a data acquisition module for acquiring the yaw rate of the vehicle in the current frame and the state of the previous frame, wherein the current frame and the previous frame are spaced apart by a preset time; a data processing module for recognizing the yaw rate to obtain a single recognition result and recording it in a lane change start state machine and / or a lane change end state machine; and a data recognition module for recognizing the current state of the vehicle based on the accumulated recognition results in the lane change start state machine and / or lane change end state machine and the state of the previous frame.

[0020] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the steps described above.

[0021] A computer-readable storage medium includes a program that, when run on a computer, causes the computer to perform the aforementioned car cockpit music interaction method.

[0022] The technical advantage of this invention lies in its ability to adaptively determine the vehicle's driving status by inputting the yaw rate to the millimeter-wave radar, making it less susceptible to external environmental influences and improving the accuracy of lane change recognition. Furthermore, the use of a state machine for counting during lane change judgment is more stable and less susceptible to individual erroneous (or large-error) data, reducing the probability of incorrect state judgment. Additionally, calculating the lateral distance between the vehicle and other vehicles based on its driving status and promptly alerting the driver significantly reduces false alarms and missed alarms caused by the vehicle's misalignment. Attached Figure Description

[0023] Figure 1 This is a flowchart illustrating a specific embodiment of the vehicle state recognition method provided by the present invention.

[0024] Figure 2 A graph illustrating a specific embodiment of the comparison of lateral distance calculation between this vehicle and other vehicles provided by the present invention;

[0025] Figure 3 A graph comparing the lateral distance calculation of this vehicle with that of other vehicles provided by the present invention;

[0026] Figure 4 This is a flowchart illustrating a specific embodiment of the vehicle status recognition system provided by the present invention.

[0027] Figure 5 This is a structural block diagram of a specific embodiment of the electronic device provided by the present invention. Detailed Implementation

[0028] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0029] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0030] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0031] First, it should be noted that, in order to enable those skilled in the art to better understand the solution of this application, some technical terms in the embodiments of this application will be explained accordingly.

[0032] Millimeter-wave radar is a type of radar that operates in the millimeter-wave band. Millimeter waves typically refer to the 30–300 GHz frequency range (wavelength 1–10 mm). Since the wavelength of millimeter waves falls between microwaves and centimeter waves, millimeter-wave radar combines some advantages of both microwave and electro-optical radar.

[0033] Compared to centimeter-wave seekers, millimeter-wave seekers are smaller, lighter, and have higher spatial resolution. Compared to optical seekers such as infrared, laser, and television seekers, millimeter-wave seekers have stronger penetration capabilities through fog, smoke, and dust, and are suitable for all weather conditions (except heavy rain). Furthermore, millimeter-wave seekers have superior anti-jamming and anti-stealth capabilities compared to other microwave seekers. Millimeter-wave radar can distinguish and identify very small targets and can simultaneously identify multiple targets; it has imaging capabilities and a small size.

[0034] With the development of automotive intelligence, millimeter-wave radar has begun to be applied in the field of automotive radar technology. However, when a vehicle is driving on the road and changing lanes, the radar coordinate system is essentially rotated due to the angle between the vehicle body and the lane lines. This causes a deviation in the radar's estimation of the lateral distance to other vehicles, resulting in serious false alarms and missed alarms in millimeter-wave radar-based alarm functions (FCW, BSD, LCA, etc.).

[0035] Therefore, this application proposes a vehicle state recognition method for use on vehicle-mounted millimeter-wave radar. It does not require data from cameras or high-precision maps. It only needs to input the yaw rate of the vehicle body signal. The radar itself can estimate the lateral distance of other vehicles in the geodetic coordinate system, thereby providing timely warnings to the driver.

[0036] Example 1

[0037] Please see Figure 1 As shown, a vehicle state recognition method includes:

[0038] Step S10: Obtain the yaw rate of the vehicle in the current frame and the state of the previous frame, wherein the current frame and the previous frame are spaced apart by a preset time.

[0039] The vehicle data acquisition device collects the yaw rate of the vehicle in each frame during its road driving process and inputs it into the vehicle millimeter-wave radar for identification and processing. The vehicle millimeter-wave radar identifies the state of the vehicle in the current frame based on the state of the vehicle in the previous frame and the current yaw rate, and inputs a feedback signal to the vehicle terminal to make a corresponding response.

[0040] The yaw rate is obtained based on the preset time parameters of the vehicle-mounted data acquisition device. Specifically, the time interval between each frame in this embodiment is within the range of 0.01-0.1s, depending on actual needs.

[0041] Step S20: Identify the yaw rate to obtain a single identification result, and record it in the lane change start state machine and / or lane change end state machine. The lane change start state machine / lane change end state machine is used to accumulate multiple identification results.

[0042] Specifically, the recognition result of a single frame of yaw rate is recorded as a count value in the lane change start state machine or lane change end state machine. The count value in the lane change start state machine or lane change end state machine is the accumulated result of multiple yaw rate recognitions. The lane change start state machine and lane change end state machine are similar to counters; after a single yaw rate recognition, the counter is incremented or reset to zero according to the recognition result. Since judging the vehicle's current state based on a single recognition result is not accurate enough, and incorrect judgments can lead to traffic accidents, to avoid recognition errors or unexpected situations, the vehicle's current state is judged by accumulating multiple recognition results, and the count values ​​of the lane change start state machine and lane change end state machine are updated accordingly based on the single recognition result.

[0043] Generally, yaw rate has positive and negative values, corresponding to left and right yaws respectively. In this embodiment, continuous left or right yaws within a preset time period are categorized as lane changes. Therefore, the vehicle's driving state is divided into straight-line driving and lane changing. Thus, the onboard millimeter-wave radar identifies the vehicle's driving state by recording changes in yaw rate. Simultaneously, both the lane change start state machine and the lane change end state machine record the change in vehicle yaw rate for each frame. When the recorded value reaches a preset value, the lateral distance between the vehicle and other surrounding vehicles is calculated to determine if the vehicle is in a dangerous state and a corresponding warning signal is given to the driver.

[0044] The specific steps are as follows:

[0045] Step S21: Identify the yaw rate based on a preset first threshold:

[0046] Specifically, in application, when the absolute value of the yaw rate is greater than a preset first threshold, it is identified as a deflection of the vehicle in the current frame, and the count value of the corresponding lane change initiation state machine is incremented by 1; otherwise, the count value of the lane change initiation state machine is cleared to 0. In this embodiment, the first threshold is within the range of 0.1° / s to 2° / s based on experimental data and experience.

[0047] Step S22: Identify the yaw rate based on a preset second threshold:

[0048] Specifically, in application, when the absolute value of the yaw rate is less than a preset second threshold, it is identified that the vehicle in the current frame has not deflected, and the count value of the corresponding lane change end state machine is incremented by 1; otherwise, the count value of the lane change end state machine is cleared to 0. In this embodiment, the second threshold is also within the range of 0.1° / s to 2° / s, based on experimental data and empirical values.

[0049] The above description only refers to the recognition result of yaw rate for a single frame. The vehicle's yaw rate is compared with a threshold to determine whether it has veered, thus judging its lane-changing status. However, due to road conditions or driver input, vehicles may not travel in a straight line and may veer. To avoid this being identified as a lane change, the number of consecutive veers is accumulated. If an interruption occurs, it indicates the vehicle is not changing lanes, and the accumulated count is reset. Similarly, the vehicle's status is identified by accumulating the number of consecutive periods without veergence. Specifically, statistical analysis shows that the yaw rate changes continuously during lane changes, consistently exceeding the first threshold, while occasional slight steering wheel movements do not continuously exceed the first threshold. Similarly, after a lane change and while traveling straight, the yaw rate generally fluctuates around 0, not exceeding the second threshold for extended periods, while occasional slight steering wheel movements do not continuously fall below the second threshold.

[0050] Therefore, the vehicle's state begins to change when the cumulative count value of the lane change start state machine or lane change end state machine is greater than / less than a preset threshold. The specific identification steps are as follows:

[0051] Step S30: Identify the current state of the vehicle based on the accumulated identification results in the lane change start state machine and / or lane change end state machine and the previous frame state.

[0052] First, the determination is made based on the accumulated count values ​​of the lane change initiation state machine and the lane change end state machine. In this embodiment, the yaw rate when the vehicle deflects is greater than the yaw rate when the vehicle does not deflect, i.e., the first threshold is greater than the second threshold. Therefore, when the lane change initiation state machine has a count value, the count value of the lane change end state machine is 0; or when the lane change end state machine has a count value, the count value of the lane change initiation state machine is 0.

[0053] In one specific embodiment, the current state of the vehicle is determined based on the accumulated count value in the lane change initiation state machine and the state of the previous frame.

[0054] Specifically, in application, if the vehicle was driving in a straight line in the previous frame, and the count value of the lane change initiation state machine is greater than the lane change initiation threshold, the millimeter-wave radar identifies that the vehicle is changing lanes; otherwise, it identifies that the vehicle is driving in a straight line. If the vehicle was changing lanes in the previous frame, the count value of the lane change initiation state machine is still greater than the lane change initiation threshold or is 0, so the current state of the vehicle is still identified as changing lanes.

[0055] The lane change start threshold is set within the range of 0.1-2s based on experimental data and empirical values. For example, if the lane change start threshold is 0.1, it means that when the yaw rate of consecutive frames within 0.1s is greater than the first threshold, the vehicle is considered to be changing lanes. Further, based on the frame interval time, it is assumed to be 0.01s. Therefore, the lane change start threshold is set to 10.

[0056] In one specific embodiment, the current state of the vehicle is determined based on the accumulated count value in the lane change end state machine and the state of the previous frame.

[0057] Specifically, in application, if the vehicle was traveling in a straight line in the previous frame, the count value of the lane change end state machine is greater than the lane change end threshold or is 0. Therefore, it is considered that the vehicle has not yet deflected, and the current state of the vehicle is still traveling in a straight line. If the vehicle was changing lanes in the previous frame, when the count value of the lane change end state machine is greater than the lane change end threshold, the millimeter-wave radar identifies the vehicle as traveling in a straight line; otherwise, it identifies the vehicle as still changing lanes.

[0058] The lane change end threshold is also within the range of 0.1-2s based on experimental data and empirical values. Similarly, for example, if the lane change start threshold is 0.1, that is, when the yaw rate of consecutive frames within 0.1s is less than the second threshold, and the frame interval time is 0.01s, the lane change end threshold is set to 10.

[0059] Based on the identification of the vehicle's current status, the lateral distance between the vehicle and other vehicles is calculated. When the distance is too close, an alarm signal is promptly sent to the vehicle terminal to warn the driver. The lateral distance is the distance between the two vehicles in the direction perpendicular to the direction of travel, which is the straight-line distance when the two vehicles are parallel.

[0060] It should be noted that in this embodiment, in order to facilitate the distinction between the cumulative number of times the lane change start state machine and the lane change end state machine have been accumulated, 0 is used as the initial state, and the current state of the vehicle is determined based on the recognition results of multiple accumulations.

[0061] Therefore, this embodiment also includes: the vehicle-mounted millimeter-wave radar calculating the lateral distance to other vehicles based on the current state.

[0062] The specific calculation method is as follows:

[0063] If the millimeter-wave radar identifies the vehicle as currently traveling in a straight line, then the formula for calculating the lateral distance X is:

[0064] X = range * sinθ

[0065] Furthermore, according to the definition of yawrate: In the formula, yaw is the yaw angle at time t, and the yaw rate is the partial derivative of the yaw angle with respect to time.

[0066] Assume the vehicle is traveling in a straight line at t=0, with an initial yaw angle of 0; the value of yaw at time T is...

[0067]

[0068] For a specific radar, the frame interval is fixed, typically between 0.01s and 0.1s. Since the frame interval is generally small, the vehicle's yaw angle can be approximated as constant within this interval. In the time interval 0 to T, X = range * sinθ can be approximated as multiple uses. Where dt is the frame interval time.

[0069] If the millimeter-wave radar identifies the vehicle as currently changing lanes, then the formula for calculating the lateral distance X is:

[0070] X = range * sin(θ + yaw)

[0071] yaw = old yaw + yawrate *t

[0072] Where range is the straight-line distance between the vehicle and other vehicles, θ is the angle between the vehicle and other vehicles, yaw is the yaw angle of the vehicle in the current frame, old yaw is the yaw angle of the vehicle in the previous frame, t is the interval between the current frame and the previous frame, and yawrate is the yaw rate of the vehicle.

[0073] By calculating the lateral distance between the vehicle and other vehicles, when the lateral distance is less than the safe distance, the millimeter-wave radar-based alarm function will promptly alert the driver, improving road safety. Specifically, as follows... Figure 2 , 3 As shown, Figure 2 When other vehicles are directly behind the vehicle, the lateral distance between the vehicle and other vehicles changes during lane changes. Before optimization, when the vehicle is changing lanes, the lateral distance to the target vehicle continuously increases. This is because the yaw angle of the vehicle is not calculated, leading to errors in distance recognition. As shown by the dotted line in the figure, the distance between the vehicle and the target vehicle is constantly decreasing, and the two vehicles are getting closer. The driver needs to be alerted to the possibility of a collision during the lane change process. Figure 3 When other vehicles are located to the side and rear of this vehicle, the lateral distance between this vehicle and other vehicles changes when changing lanes. Similarly, before optimization, the lateral distance recognition between the vehicle and the target vehicle was too large, even though the two vehicles were actually getting closer, requiring timely reminders to the driver to avoid traffic accidents. Therefore, it is evident that based on this vehicle state recognition method, the lateral distance calculation between vehicles is more accurate, enabling more timely warnings to the driver.

[0074] It should be noted that the steps of the various methods described above are only for clarity. In practice, they can be combined into one step or some steps can be split into multiple steps. As long as they contain the same logical relationship, they are all within the scope of protection of this patent. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, but without changing the core design of the algorithm and process, are also within the scope of protection of this patent.

[0075] Example 2

[0076] Please see Figure 4 As shown, this application embodiment also provides a vehicle state recognition system applied to millimeter-wave radar, including:

[0077] The data acquisition module 10 is used to acquire the yaw rate of the vehicle in the current frame and the state of the previous frame, and the interval between the current frame and the previous frame is a preset time.

[0078] The data processing module 20 is used to identify the yaw rate, obtain the identification result of a single transaction, and record it in the lane change start state machine and / or lane change end state machine.

[0079] The data recognition module 30 is used to recognize the current state of the vehicle based on the accumulated recognition results in the lane change start state machine and / or lane change end state machine and the previous frame state.

[0080] It should be noted that the vehicle status recognition system provided in the above embodiments and the vehicle status recognition method provided in Embodiment 1 belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the vehicle status recognition method provided in Embodiment 1 can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0081] Example 3

[0082] Please see Figure 5 As shown, embodiments of this application also provide an electronic device, including a memory 2, a processor 1, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0083] The memory includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory can be an internal storage unit of an electronic device, such as a portable hard drive. In other embodiments, the memory can be an external storage device of the electronic device, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc. Furthermore, the memory can include both internal and external storage units of the electronic device. The memory can be used not only to store application software and various types of data installed on the electronic device, but also to temporarily store data that has been output or will be output.

[0084] In some embodiments, a processor may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions. This includes combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor is the control unit of the electronic device, connecting various components of the device via various interfaces and lines. It executes programs or modules stored in the memory and calls data stored in the memory to perform various functions and process data within the electronic device.

[0085] The processor executes the operating system of the electronic device and various installed applications. The processor executes the applications to implement the steps in the above method embodiments.

[0086] For example, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0087] The integrated unit, implemented as a software functional module, can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to execute some functions of the lithium battery cold solder joint detection method of the various embodiments of the present invention.

[0088] In summary, the technical advantages of this invention lie in its ability to adaptively determine the vehicle's driving status by inputting yaw rate to the millimeter-wave radar, making it less susceptible to external environmental influences and improving the accuracy of lane change behavior recognition. Furthermore, the use of a state machine for counting during lane change behavior determination ensures stability and prevents susceptibility to individual erroneous (or large) data, reducing the probability of incorrect status assessment. Additionally, calculating the lateral distance between the vehicle and other vehicles based on its driving status and promptly alerting the driver significantly reduces false alarms and missed alarms caused by the vehicle's misalignment.

[0089] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A vehicle state recognition method, characterized in that, The vehicle state recognition method, applied to millimeter-wave radar, includes: The vehicle's yaw rate in the current frame and its state in the previous frame are obtained, and the interval between the current frame and the previous frame is a preset time. The yaw rate is identified to obtain a single identification result, and the steps include: identifying the yaw rate according to a preset first threshold: if the absolute value of the yaw rate is greater than the first threshold, it is identified as vehicle deflection, and the count value of the lane change start state machine is incremented by 1; otherwise, it is identified as vehicle not deflecting, and the count value of the lane change start state machine is set to 0; and / or, identifying the yaw rate according to a preset second threshold: if the absolute value of the yaw rate is less than the second threshold, it is identified as vehicle not deflecting, and the count value of the lane change end state machine is incremented by 1; otherwise, it is identified as vehicle deflecting, and the count value of the lane change end state machine is set to 0; wherein, the first threshold is greater than the second threshold; The identification results are recorded in the lane change start state machine and / or lane change end state machine; wherein, the lane change start state machine / lane change end state machine is used to accumulate multiple identification results; The vehicle's current state is identified based on the accumulated recognition results from the lane change start state machine and / or lane change end state machine, and the previous frame state. The steps include: identifying the vehicle's current state based on the count value of the lane change start state machine and the previous frame state: if the count value of the lane change start state machine is greater than a preset lane change start threshold, then the current state is identified as lane changing; otherwise, the previous frame state is used as the current state. Furthermore, the vehicle's current state is identified based on the count value of the lane change end state machine and the previous frame state: if the count value of the lane change end state machine is greater than a preset lane change end threshold, then the current state is identified as straight driving; otherwise, the previous frame state is used as the current state. Wherein, the count value of the lane change start state machine is the accumulated recognition result of the lane change start state machine, and the count value of the lane change end state machine is the accumulated recognition result of the lane change end state machine.

2. The vehicle state recognition method according to claim 1, characterized in that, Also includes: Calculate the lateral distance to other vehicles based on the current state.

3. The vehicle state recognition method according to claim 2, characterized in that, The step of calculating the lateral distance to other vehicles based on the current state includes: If the current state is straight-line driving, then the formula for calculating the lateral distance X is: ， Where range represents the straight-line distance between the vehicle and other vehicles. The angle between the vehicle and other vehicles.

4. The vehicle state recognition method according to claim 2, characterized in that, The step of calculating the lateral distance to other vehicles based on the current state further includes: If the current state is a lane change, then the formula for calculating the lateral distance X is: Where range represents the straight-line distance between the vehicle and other vehicles. yaw is the angle between the vehicle and other vehicles, old yaw is the yaw angle of the vehicle in the current frame, t is the interval between the current frame and the previous frame, and yawrate is the yaw rate of the vehicle.

5. A vehicle status recognition system, characterized in that, The vehicle status recognition system, applied to millimeter-wave radar, includes: The data acquisition module is used to acquire the yaw rate of the vehicle in the current frame and the state of the previous frame, and the interval between the current frame and the previous frame is a preset time. A data processing module is used to identify the yaw rate and obtain a single identification result. The steps include: identifying the yaw rate according to a preset first threshold; if the absolute value of the yaw rate is greater than the first threshold, it is identified as vehicle deflection, and the count value of the lane change start state machine is incremented by 1; otherwise, it is identified as vehicle not deflecting, and the count value of the lane change start state machine is set to 0; and / or, identifying the yaw rate according to a preset second threshold; if the absolute value of the yaw rate is less than the second threshold, it is identified as vehicle not deflecting, and the count value of the lane change end state machine is incremented by 1; otherwise, it is identified as vehicle deflecting, and the count value of the lane change end state machine is set to 0; wherein, the first threshold is greater than the second threshold; The data processing module is further configured to record the identification result into the lane change start state machine and / or lane change end state machine; wherein the lane change start state machine / lane change end state machine is used to accumulate multiple identification results; A data recognition module is used to recognize the current state of a vehicle based on the accumulated recognition results of the lane change start state machine and / or lane change end state machine and the previous frame state, and the steps include: recognizing the current state of the vehicle based on the count value of the lane change start state machine and the previous frame state: if the count value of the lane change start state machine is greater than a preset lane change start threshold, then the current state is recognized as lane changing; otherwise, the previous frame state is used as the current state; and recognizing the current state of the vehicle based on the count value of the lane change end state machine and the previous frame state: if the count value of the lane change end state machine is greater than a preset lane change end threshold, then the current state is recognized as straight driving; otherwise, the previous frame state is used as the current state; wherein, the count value of the lane change start state machine is the accumulated recognition result of the lane change start state machine, and the count value of the lane change end state machine is the accumulated recognition result of the lane change end state machine.

6. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, Includes a program that, when run on a computer, causes the computer to perform the vehicle state recognition method as described in any one of claims 1 to 4.

Images