Data processing method and device of vehicle-mounted millimeter wave radar, equipment and medium

Abstract

This application provides a data processing method, apparatus, device, and medium for vehicle-mounted millimeter-wave radar. The method includes: acquiring radial velocity data of a target object detected by the vehicle's millimeter-wave radar within a preset time period, wherein the radial velocity data includes lateral velocity data and longitudinal velocity data. Then, error removal processing is performed on the lateral velocity data within the radial velocity data of the preset time period to obtain processed lateral velocity data. The processed lateral velocity data and longitudinal velocity data within the preset time period are then input into a Universal Transverse Mercator (UTM) projection model for coordinate transformation processing to obtain target lateral velocity data and target longitudinal velocity data in the UTM coordinate system. Finally, the target lateral velocity data and target longitudinal velocity data are fused for driving guidance. The method of this application reduces errors in the lateral velocity data and improves the accuracy of the obtained velocity data.

Description

Technical Field

[0001] This application relates to data processing technology, and more particularly to a data processing method, apparatus, equipment and medium for vehicle-mounted millimeter-wave radar. Background Technology

[0002] In the field of autonomous driving, millimeter-wave radar has been widely used due to its advantages such as high radar resolution and strong anti-interference capabilities. After detecting the velocity data of an object, namely radial velocity, millimeter-wave radar transmits it to a fusion center so that the fusion center can provide driving guidance based on the obtained velocity data. Among them, radial velocity can be decomposed into lateral velocity and longitudinal velocity.

[0003] In existing technologies, when processing radial data of objects detected by millimeter-wave radar, the lateral and longitudinal velocities in the millimeter-wave radar coordinate system are usually first converted to the lateral and longitudinal velocities in the Universal Transverse Mercator Grid System (UTM) coordinate system. Then, the lateral and longitudinal velocities in the UTM coordinate system are sent to the fusion center. After the fusion center performs fusion filtering on the velocities, the final radial velocity data is obtained.

[0004] However, existing technology vehicles are affected by body bumps during driving, resulting in a large error in the final lateral speed. Summary of the Invention

[0005] This application provides a data processing method, apparatus, device, and medium for vehicle-mounted millimeter-wave radar to solve the problem that the lateral speed obtained by a vehicle during driving is subject to large errors due to the influence of vehicle body bumps.

[0006] In a first aspect, this application provides a data processing method for vehicle-mounted millimeter-wave radar, including:

[0007] The radial velocity data of the vehicle's millimeter-wave radar detecting the target object within a preset time period is acquired separately. The radial velocity data includes lateral velocity data and longitudinal velocity data.

[0008] Error removal processing is performed on the lateral velocity data in the radial velocity data within the preset time period to obtain the processed lateral velocity data.

[0009] Within the preset time period, the processed lateral velocity data and the longitudinal velocity data are input into the Universal Transverse Mercator Projection (UTM) model for coordinate transformation to obtain the target lateral velocity data and target longitudinal velocity data in the UTM coordinate system.

[0010] The target lateral velocity data and the target longitudinal data are fused together for driving guidance.

[0011] Optionally, the step of performing error removal processing on the lateral velocity data in the radial velocity data within the preset time period to obtain processed lateral velocity data includes:

[0012] For each moment within the preset time period, determine whether the lateral velocity at that moment is an error lateral velocity caused by the lateral vibration of the vehicle;

[0013] If the lateral velocity at the specified moment is an error lateral velocity caused by the lateral vibration of the vehicle, then the lateral velocity at the specified moment is set to zero, and the processed lateral velocity data within the preset time period is obtained.

[0014] Optionally, the step of performing error removal processing on the lateral velocity data in the radial velocity data within the preset time period to obtain processed lateral velocity data includes:

[0015] Based on a preset Kalman filter algorithm, noise data in the lateral velocity data of the radial velocity data within the preset time period is filtered to obtain the processed lateral velocity data.

[0016] Optionally, the step of performing error removal processing on the lateral velocity data in the radial velocity data within the preset time period to obtain processed lateral velocity data includes:

[0017] For each moment within the preset time period, determine whether the lateral velocity at that moment is an error lateral velocity caused by the lateral vibration of the vehicle;

[0018] If the lateral velocity at the specified moment is an error lateral velocity caused by the lateral vibration of the vehicle, then the lateral velocity at the specified moment is set to zero to obtain the intermediate lateral velocity data within the preset time period.

[0019] Based on a preset Kalman filter algorithm, noise data in the intermediate lateral velocity data within the preset time period is filtered to obtain the processed lateral velocity data.

[0020] Optionally, determining whether the lateral velocity at the specified moment is an error lateral velocity caused by vehicle lateral vibration includes:

[0021] Obtain the vehicle yaw rate at the specified moment;

[0022] The vehicle's operating state is determined based on the preset vehicle yaw rate threshold range where the vehicle's yaw rate is located. The operating state includes any one of the following: straight driving state, lane changing state, and turning state.

[0023] If the vehicle is in a straight-ahead or lane-changing state at the time, then based on a preset sliding window algorithm, it is determined whether the lateral speed at the time is an error lateral speed caused by the vehicle's lateral vibration.

[0024] Optionally, determining whether the lateral velocity at the given moment is an error lateral velocity caused by lateral vehicle vibration, based on a preset sliding window algorithm, includes:

[0025] If the lateral velocity at the specified moment is less than a preset lateral velocity threshold, then the identifier of the lateral velocity at the specified moment is set to 1;

[0026] If the lateral velocity at the specified moment is greater than or equal to the preset lateral velocity threshold, then the identification information of the lateral velocity at the specified moment is set to 0;

[0027] Based on the preset sliding window size N, when the sliding window moves along the time axis, it is determined whether the number of times the horizontal velocity identification information in the sliding window is 1 is greater than or equal to a preset number threshold, where N represents more than one detection time.

[0028] If the number of times when the lateral velocity identifier in the sliding window is 1 is greater than or equal to the preset number threshold, then the lateral velocity at the time when the lateral velocity in the sliding window is less than the preset lateral velocity threshold is the error lateral velocity caused by the lateral vibration of the vehicle.

[0029] Secondly, this application provides a data processing device for vehicle-mounted millimeter-wave radar, comprising:

[0030] The acquisition module is used to acquire radial velocity data of the target object detected by the vehicle's millimeter-wave radar within a preset time period. The radial velocity data includes lateral velocity data and longitudinal velocity data.

[0031] The processing module is used to perform error removal processing on the lateral velocity data in the radial velocity data within the preset time period to obtain the processed lateral velocity data.

[0032] The coordinate transformation module is used to input the processed lateral velocity data and the longitudinal velocity data within the preset time period into the Universal Transverse Mercator Projection (UTM) model for coordinate transformation processing to obtain the target lateral velocity data and target longitudinal velocity data in the UTM coordinate system.

[0033] The sending module is used to fuse the target lateral velocity data and the target longitudinal data for driving guidance.

[0034] Thirdly, this application provides an electronic device, including: at least one processor and a memory;

[0035] The memory stores computer-executed instructions;

[0036] The at least one processor executes computer execution instructions stored in the memory to perform the data processing method for vehicle-mounted millimeter-wave radar according to any one of the first aspects.

[0037] Fourthly, embodiments of this application provide a readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the data processing method for vehicle-mounted millimeter-wave radar as described in any of the first aspects.

[0038] Fifthly, embodiments of this application provide a computer program product, including a computer program, which, when executed by a processor, is used to implement the data processing method for vehicle-mounted millimeter-wave radar as described in any of the first aspects.

[0039] This application provides a data processing method, apparatus, device, and medium for vehicle-mounted millimeter-wave radar. It acquires radial velocity data of a target object detected by the vehicle's millimeter-wave radar within a preset time period. This radial velocity data includes lateral velocity data and longitudinal velocity data. The lateral velocity data within the radial velocity data of the preset time period is then subjected to error removal processing to obtain processed lateral velocity data. The processed lateral velocity data and longitudinal velocity data of the preset time period are then input into a Universal Transverse Mercator (UTM) projection model for coordinate transformation processing to obtain the target's lateral velocity data and target's longitudinal velocity data in the UTM coordinate system. Finally, the target's lateral velocity data and target's longitudinal velocity data are fused for driving guidance. This method, by performing error removal processing on the lateral velocity data, effectively reduces the impact of vehicle body bumps on the lateral velocity data, reduces errors in the lateral velocity data, and improves the accuracy of the final obtained lateral velocity data. Attached Figure Description

[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0041] Figure 1 A schematic diagram illustrating an application scenario for a vehicle-mounted millimeter-wave radar provided in this application;

[0042] Figure 2A This is a schematic diagram illustrating the processing of radial velocity data provided in an embodiment of this application;

[0043] Figure 2B This is a schematic diagram illustrating another method for processing radial velocity data provided in an embodiment of this application;

[0044] Figure 3 This is a schematic diagram illustrating the processing of radial velocity data provided in an embodiment of this application;

[0045] Figure 4 A flowchart illustrating a data processing method for a vehicle-mounted millimeter-wave radar provided in an embodiment of this application;

[0046] Figure 5 A flowchart illustrating a method for determining whether the lateral velocity at a certain moment is an error lateral velocity caused by the lateral vibration of a vehicle, provided in an embodiment of this application;

[0047] Figure 6 A flowchart illustrating a method for determining lateral velocity errors provided in an embodiment of this application;

[0048] Figure 7 A schematic diagram of a method for determining the lateral velocity of an error based on a sliding window algorithm provided in an embodiment of this application;

[0049] Figure 8 A schematic diagram of speed data comparison provided in an embodiment of this application;

[0050] Figure 9A A schematic diagram showing a comparison between the speed and the positioning speed after setting the lateral speed error to 0, as provided in an embodiment of this application.

[0051] Figure 9B This is a schematic diagram illustrating the comparison between the lateral velocity after setting the lateral velocity error to 0 and the positioning velocity, provided as an embodiment of this application;

[0052] Figure 10 A schematic diagram of the structure of a data processing device for a vehicle-mounted millimeter-wave radar provided in an embodiment of this application;

[0053] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0054] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0055] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0056] It should be noted that in the description of the embodiments of this application, the terms "inner" and "outer", etc., which indicate the direction or positional relationship, are based on the direction or positional relationship shown in the drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or component must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this application.

[0057] Furthermore, it should be noted that, in the description of the embodiments of this application, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of this application according to the specific circumstances.

[0058] First, let me explain the terms used in this application:

[0059] Universal Transverse Mercator (UTM) projection, or UTM coordinate system for short, is a projected coordinate system. It uses a grid-based method to represent coordinates, converting spherical latitude and longitude coordinates into planar coordinates, specifically XY coordinates, through a projection algorithm.

[0060] Kalman filtering is an algorithm that uses the state equations of a linear system to make an optimal estimate of the system state using observed input and output data. Since the observed data includes noise and interference from the system, the optimal estimation can also be viewed as a filtering process.

[0061] The Doppler effect is characterized by the change in wavelength of radiation emitted by an object due to the relative motion between the wave source and the observer.

[0062] The rapid development of intelligent driving technology is inseparable from various environmental perception sensors. Among them, vehicle-mounted millimeter-wave radar is widely used in the field of autonomous driving due to its advantages such as high radar resolution, strong anti-interference ability, wide detection range, and near all-weather operation.

[0063] Millimeter-wave radar refers to radar operating in the millimeter-wave frequency band. The wavelength of its electromagnetic waves is typically in the range of 1–10 mm, corresponding to a frequency range of 30–300 GHz. Commonly used vehicle-mounted millimeter-wave radars operate at frequencies of 76–81 GHz. Its speed measurement principle is based on the Doppler effect. When there is relative movement between the emitted electromagnetic wave and the target, the frequency of the echo will differ from the frequency of the emitted wave. When the target approaches the radar antenna, the frequency of the reflected signal will be higher than the frequency of the emitted signal; when the target moves away from the radar antenna, the frequency of the reflected signal will be lower than the frequency of the emitted signal. This frequency change caused by the Doppler effect is called the Doppler shift, which is directly proportional to the relative velocity v and inversely proportional to the vibration frequency. Therefore, by detecting this frequency difference, the target's velocity relative to the radar, i.e., its radial velocity, can be measured. The radial velocity can be decomposed into lateral velocity and longitudinal velocity.

[0064] Figure 1 A schematic diagram illustrating an application scenario for an automotive millimeter-wave radar provided in this application, such as... Figure 1 As shown, millimeter-wave radar can be used as a forward-facing radar for vehicles, forming a forward-facing perception system with lidar and cameras to detect objects in front of the vehicle in various weather conditions. These objects can include vehicles, traffic lights, traffic cones, etc. Weather conditions can include rainy weather, foggy weather, and smoggy weather.

[0065] It is understood that the above scenarios are for illustrative purposes only and are not intended to limit this application.

[0066] In existing technologies, the radial data of objects detected by millimeter-wave radar are typically processed in the following ways:

[0067] Figure 2A This is a schematic diagram of processing radial velocity data provided in an embodiment of this application, as shown below. Figure 2A As shown, after obtaining the radial velocity detected by the millimeter-wave radar, the lateral and longitudinal velocities in the millimeter-wave radar coordinate system are first converted into the lateral and longitudinal velocities in the UTM coordinate system. Then, the lateral and longitudinal velocities in the UTM coordinate system are sent to the fusion center. After the fusion center performs fusion filtering on the velocities, the final radial velocity data is obtained.

[0068] but Figure 2A In the method shown, the vehicle body is bumpy during driving, which causes poor angular resolution of the millimeter-wave radar and deviation of the detection angle. As a result, there is a large error in the output lateral velocity. After the lateral velocity is converted into the UTM coordinate system, the obtained lateral velocity also has a large error and the velocity is not smooth enough.

[0069] Figure 2B This is a schematic diagram illustrating another method for processing radial velocity data provided in an embodiment of this application, as shown below. Figure 2B As shown, after obtaining the radial velocity detected by the millimeter-wave radar, the lateral and longitudinal velocities in the millimeter-wave radar coordinate system are first converted into the lateral and longitudinal velocities in the UTM coordinate system. Then, the lateral velocity in the UTM coordinate system is subjected to Kalman filtering to obtain the filtered lateral velocity. This filtered lateral velocity is then sent to the fusion center along with the longitudinal velocity. After the fusion center performs fusion filtering on the velocity, the final radial velocity data is obtained.

[0070] but Figure 2B The method shown improves the smoothness of the velocity, but introduces a velocity delay, resulting in a large error in the obtained lateral velocity.

[0071] In summary, existing technologies result in significant errors in the final lateral velocity.

[0072] Therefore, in view of the above-mentioned technical problems in the prior art, this application proposes a data processing method, apparatus, device, and medium for vehicle-mounted millimeter-wave radar. Figure 3 This is a schematic diagram of processing radial velocity data provided in an embodiment of this application, as shown below. Figure 3 As shown, after obtaining the radial velocity detected by millimeter-wave radar, the lateral velocity in the radial velocity of the millimeter-wave radar coordinate system is first processed to remove errors. Then, the processed lateral velocity and the longitudinal velocity in the radial velocity are converted into lateral and longitudinal velocities in the UTM coordinate system. These lateral and longitudinal velocities in the UTM coordinate system are then sent to the fusion center. After fusion filtering by the fusion center, the final radial velocity data is obtained. The method of this application reduces the error in the lateral velocity data and improves the accuracy of the final obtained lateral velocity data.

[0073] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0074] Figure 4 This is a flowchart illustrating a data processing method for a vehicle-mounted millimeter-wave radar provided in an embodiment of this application. The executing entity of this method can be a vehicle-mounted terminal with data processing capabilities, or other devices, equipment, or systems that can communicate and control with the vehicle-mounted terminal. The method in this embodiment can be implemented through software, hardware, or a combination of both. Figure 4 As shown, the method specifically includes the following steps:

[0075] S401. Acquire radial velocity data of the target object detected by the vehicle's millimeter-wave radar within a preset time period. The radial velocity data includes lateral velocity data and longitudinal velocity data.

[0076] In this embodiment, the executing entity is a vehicle-mounted terminal, and the type of millimeter-wave radar is an ARS-408 millimeter-wave radar. The vehicle-mounted terminal can acquire the detection data of objects by the ARS-408 millimeter-wave radar installed on the vehicle.

[0077] Millimeter-wave radar detects the velocity data of objects in front of it in real time. The velocity data is radial velocity. Therefore, the vehicle terminal can obtain the radial velocity data of the target object detected by the millimeter-wave radar within a preset time period.

[0078] The preset time period can be several hours, several minutes, etc., and can be set according to the actual usage situation. This application does not limit it.

[0079] It is understood that this application does not limit the type of millimeter-wave radar.

[0080] S402. Perform error removal processing on the lateral velocity data in the radial velocity data within the preset time period to obtain the processed lateral velocity data.

[0081] During vehicle operation, the vehicle body is subject to bumps and instability due to road conditions, causing the millimeter-wave radar mounted at the front of the vehicle to swing laterally significantly. This results in a large error in the detected lateral velocity, while the longitudinal velocity is less affected. Therefore, this application only processes the lateral velocity data.

[0082] By performing error removal processing on the lateral velocity data, the lateral velocity data after error elimination is obtained.

[0083] It should be noted that the lateral velocity data and longitudinal velocity data obtained at this time within the preset time period are both data in the millimeter-wave radar coordinate system.

[0084] Specifically, error removal can be performed in the following three ways:

[0085] One possible implementation method is:

[0086] For each moment within a preset time period, determine whether the lateral velocity at that moment is an error lateral velocity caused by the vehicle's lateral vibration.

[0087] If the lateral velocity at that moment is an error lateral velocity caused by the vehicle's lateral vibration, then the lateral velocity at that moment is set to zero, and the processed lateral velocity data within the preset time period is obtained.

[0088] Another possible implementation method 2 is:

[0089] Based on a preset Kalman filter algorithm, noise data in the lateral velocity data of the radial velocity data within a preset time period is filtered to obtain the processed lateral velocity data.

[0090] Another possible implementation method 3 is:

[0091] For each moment within a preset time period, determine whether the lateral velocity at that moment is an error lateral velocity caused by the vehicle's lateral vibration.

[0092] If the lateral velocity at that moment is an error lateral velocity caused by the lateral vibration of the vehicle, then the lateral velocity at that moment is set to zero, and the intermediate lateral velocity data within the preset time period is obtained.

[0093] Based on a preset Kalman filter algorithm, noise data in the intermediate lateral velocity data within a preset time period is filtered to obtain the processed lateral velocity data.

[0094] For a detailed explanation of the above implementation method, please refer to the following examples.

[0095] S403. Input the processed lateral velocity data and longitudinal velocity data within the preset time period into the Universal Transverse Mercator Projection (UTM) model for coordinate transformation to obtain the target lateral velocity data and target longitudinal velocity data in the UTM coordinate system.

[0096] After step S402 performs error removal processing on the lateral velocity data, the processed lateral velocity data and longitudinal velocity data are input into the Universal Transverse Mercator Projection (UTM) model to convert the lateral velocity data in the millimeter-wave radar coordinate system into velocity data in the UTM coordinate system. Thus, the target lateral velocity data and target longitudinal velocity data in the UTM coordinate system are obtained.

[0097] S404. The target's lateral velocity data and target's longitudinal data are fused together for driving guidance.

[0098] After obtaining the target's lateral velocity data and longitudinal velocity data, they are input into the fusion center to fuse the target's lateral velocity data and longitudinal velocity data, resulting in fused radial velocity data.

[0099] The fused radial velocity data is used to provide driving guidance for the vehicle, including speed control, braking control, and operating status control.

[0100] Understandably, the more accurate the final fused radial velocity data, the more accurate the driving guidance for the vehicle.

[0101] In the above embodiments of this application, radial velocity data of the target object detected by the vehicle's millimeter-wave radar within a preset time period is acquired, wherein the radial velocity data includes lateral velocity data and longitudinal velocity data. Then, error removal processing is performed on the lateral velocity data within the radial velocity data of the preset time period to obtain processed lateral velocity data. The processed lateral velocity data and longitudinal velocity data within the preset time period are then input into a Universal Transverse Mercator (UTM) projection model for coordinate transformation processing to obtain the target lateral velocity data and target longitudinal velocity data in the UTM coordinate system. Finally, the target lateral velocity data and target longitudinal velocity data are fused and used for driving guidance. The method of this embodiment reduces the error in the lateral velocity data and improves the accuracy of the final obtained velocity data.

[0102] Furthermore, based on the above embodiments, the following embodiments will describe in detail the process of performing error removal processing on the lateral velocity data in the radial velocity data within a preset time period in step S402 to obtain the processed lateral velocity data.

[0103] In the three implementation methods of step S402, the process of determining whether the lateral velocity at each moment within the preset time period is the error lateral velocity caused by the lateral vibration of the vehicle, which is involved in methods 1 and 3, will be explained below.

[0104] Figure 5 This application provides a flowchart illustrating a method for determining whether a lateral velocity at a certain moment is an error lateral velocity caused by lateral vehicle vibration, as illustrated in the embodiments of this application. Figure 5 As shown, the method includes the following steps:

[0105] S501. For each moment within a preset time period, obtain the vehicle yaw rate at that moment.

[0106] Obtain the vehicle's yaw rate at each moment within a preset time period.

[0107] S502. Determine the vehicle's operating state based on the preset vehicle yaw rate threshold range where the vehicle's yaw rate is located. The operating state includes any one of the following: straight driving state, lane changing state, and turning state.

[0108] For example,

[0109] Assume the preset vehicle yaw rate threshold ranges are as shown in Table 1:

[0110] Table 1

[0111] interval Vehicle yaw rate Running status Interval 1 0-0.02rads straight Interval 2 Approximately 0.04 rads lane change Interval 3 >0.05rads Turn

[0112] Assuming the vehicle's yaw rate at that moment is 0.18 rads, it can be determined from Table 1 that the vehicle's yaw rate is in interval 1, and the vehicle's running state corresponding to interval 1 is straight-line state.

[0113] Assuming the vehicle's yaw rate at that moment is 0.41 rads, it can be determined from Table 1 that the vehicle's yaw rate is in interval 2, and the vehicle's running state corresponding to interval 2 is a lane change state.

[0114] Assuming the vehicle's yaw rate at that moment is 0.07 rads, it can be determined from Table 1 that the vehicle's yaw rate is in interval 3, and the vehicle's running state corresponding to interval 3 is turning.

[0115] S503. If the vehicle is in a straight-ahead or lane-changing state at that moment, then based on the preset sliding window algorithm, determine whether the lateral speed at that moment is the error lateral speed caused by the lateral vibration of the vehicle.

[0116] Optional, such as Figure 6 As shown, Figure 6 This application provides a flowchart illustrating a method for determining lateral velocity errors, which includes the following steps:

[0117] S601. If the lateral velocity at that moment is less than the preset lateral velocity threshold, then the lateral velocity identifier at that moment is set to 1.

[0118] S602. If the lateral velocity at that moment is greater than or equal to the preset lateral velocity threshold, then the lateral velocity identifier at that moment is set to 0.

[0119] For example,

[0120] Assuming the preset time period includes n moments, the acquired lateral velocity data within the preset time period are as follows: The lateral velocity at each moment corresponds to an identifier Z, assuming the preset lateral velocity threshold is 0.4 m / s.

[0121] If the lateral velocity data at time 1 If the velocity is 0.3 m / s, which is less than the lateral velocity threshold of 0.4 m / s, then its identification information Z1 is set to "1".

[0122] If the lateral velocity data at time 1 If the value is 0.4 m / s, which is equal to the lateral velocity threshold of 0.4 m / s, then its identification information Z1 is set to "0".

[0123] S603. Based on the preset sliding window size N, when the sliding window moves along the time axis, determine whether the number of times the horizontal velocity indicator information in the sliding window is 1 is greater than or equal to a preset number threshold, where N represents more than one detection time.

[0124] S604. If the number of times the lateral velocity indicator in the sliding window is 1 is greater than or equal to a preset threshold, then the lateral velocity at the time when the lateral velocity in the sliding window is less than the preset lateral velocity threshold is the error lateral velocity caused by the lateral vibration of the vehicle.

[0125] After step S602, the identifier information Z corresponding to each of the n times within the preset time period can be obtained, resulting in the following: Figure 7 The diagram shown is as follows. Figure 7 This is a schematic diagram of a method for determining the lateral velocity of an error based on a sliding window algorithm, provided in an embodiment of this application.

[0126] exist Figure 7 In this context, assuming the preset sliding window size N is 5, meaning a single sliding window can include lateral velocity information at 5 different times, denoted as Z... i Z i+1 Z i+2 Z i+3 Z i+4 Assuming the preset quantity threshold m is 2, it can be determined that the number of times the lateral velocity indicator information in the sliding window is 1 is k, which is 3. Since k is greater than the preset quantity threshold m, the lateral velocities at time i, time i+2, and time i+3 are the error lateral velocities caused by the lateral vibration of the vehicle.

[0127] In the above embodiments of this application, for each moment within a preset time period, the vehicle yaw rate at that moment is obtained, and the vehicle's operating state is determined based on the preset yaw rate threshold range within which the vehicle yaw rate falls. The operating state includes any one of straight-ahead, lane-changing, or turning states. If the vehicle's operating state at that moment is straight-ahead or lane-changing, a preset sliding window algorithm is used to determine whether the lateral velocity at that moment is an error lateral velocity caused by vehicle lateral vibration. The method in this embodiment effectively reduces the error in lateral velocity data by determining and processing the error lateral velocity.

[0128] Of the three implementation methods in step S402, the process of filtering noise data based on a preset Kalman filter algorithm to obtain processed lateral velocity data in methods 2 and 3 will be described below.

[0129] Specifically,

[0130] Based on a preset Kalman filter algorithm, noise data in the lateral velocity data of the radial velocity data within a preset time period is filtered to obtain the processed lateral velocity data.

[0131] One possible implementation is:

[0132] Based on the lateral velocity data at the initial moment within a preset time period, the predicted lateral velocity data at the preset initial moment, and the lateral velocity data at subsequent moments, iterative calculations are performed using a preset Kalman filter algorithm to determine the predicted lateral velocity data at different moments, thus obtaining the processed lateral velocity data.

[0133] The predicted lateral velocity data at different times is determined using the following formula:

[0134]

[0135]

[0136]

[0137]

[0138] P k|k =(IK k H k )P k|k -1

[0139] Where k represents the k-th time; This represents the determined predicted lateral velocity data; F represents the preset state transition matrix. P represents the covariance matrix, and the initial covariance matrix is... Q represents the model covariance matrix Q = 2*R; K represents the gain matrix; H represents the preset observation matrix. R represents the measurement covariance matrix. z represents the detected lateral velocity data, which includes the lateral position and velocity value.

[0140] This application also provides statistical results, which show that the method of this application effectively reduces the error in lateral velocity, as shown in Table 2. Figure 8 As shown, Figure 8 This is a schematic diagram of speed data comparison provided in an embodiment of this application.

[0141] Table 2

[0142] plan speed error Longitudinal velocity error Lateral velocity error Existing technology 0.13 0.0929 0.0739 This application 0.04 0.0826 0.0244

[0143] From Table 2 and Figure 8As can be seen from the data, the method described in this application yields the smallest speed error.

[0144] Figure 9A This is a schematic diagram illustrating the comparison between the velocity and the positioning velocity after setting the lateral velocity error to 0, as provided in an embodiment of this application. Figure 9B This application provides an embodiment of a comparison diagram between the velocity and the positioning velocity after setting the lateral velocity error to 0 and filtering the lateral velocity. Figures 9A-9B As can be seen, the velocity of the object detected by the millimeter-wave radar after being set to zero, or after being set to zero and filtered, is similar to the actual positioning velocity collected by the vehicle. This also demonstrates that the method of this application effectively reduces the error of the velocity data and improves the accuracy of the final velocity data.

[0145] Figure 10 This is a schematic diagram of a data processing device for a vehicle-mounted millimeter-wave radar provided in an embodiment of this application. The device includes: an acquisition module 1001, a processing module 1002, a coordinate transformation module 1003, and a transmission module 1004.

[0146] The acquisition module 1001 is used to acquire radial velocity data of the target object detected by the vehicle's millimeter-wave radar within a preset time period. The radial velocity data includes lateral velocity data and longitudinal velocity data.

[0147] The processing module 1002 is used to perform error removal processing on the lateral velocity data in the radial velocity data within a preset time period to obtain the processed lateral velocity data.

[0148] The coordinate transformation module 1003 is used to input the processed lateral velocity data and longitudinal velocity data within a preset time period into the Universal Transverse Mercator Projection (UTM) model for coordinate transformation processing, so as to obtain the target lateral velocity data and target longitudinal velocity data in the UTM coordinate system.

[0149] The sending module 1004 is used to fuse the target's lateral velocity data and target's longitudinal data for driving guidance.

[0150] In one possible implementation, processing module 1002 is specifically used for:

[0151] For each moment within a preset time period, determine whether the lateral velocity at that moment is an error lateral velocity caused by the vehicle's lateral vibration.

[0152] If the lateral velocity at that moment is an error lateral velocity caused by the vehicle's lateral vibration, then the lateral velocity at that moment is set to zero, and the processed lateral velocity data within the preset time period is obtained.

[0153] In one possible implementation, processing module 1002 is specifically used for:

[0154] Based on a preset Kalman filter algorithm, noise data in the lateral velocity data of the radial velocity data within a preset time period is filtered to obtain the processed lateral velocity data.

[0155] In one possible implementation, processing module 1002 is specifically used for:

[0156] For each moment within a preset time period, determine whether the lateral velocity at that moment is an error lateral velocity caused by the vehicle's lateral vibration.

[0157] If the lateral velocity at that moment is an error lateral velocity caused by the lateral vibration of the vehicle, then the lateral velocity at that moment is set to zero, and the intermediate lateral velocity data within the preset time period is obtained.

[0158] Based on a preset Kalman filter algorithm, noise data in the intermediate lateral velocity data within a preset time period is filtered to obtain the processed lateral velocity data.

[0159] In one possible implementation, the processing module 1002 is further used for:

[0160] Obtain the vehicle's yaw rate at that moment.

[0161] The vehicle's operating state is determined based on the preset vehicle yaw rate threshold range where the vehicle's yaw rate is located. The operating state includes any one of the following: straight driving state, lane changing state, and turning state.

[0162] If the vehicle is in a straight-ahead or lane-changing state at that moment, the lateral speed at that moment is determined based on the preset sliding window algorithm to determine whether it is an error lateral speed caused by the vehicle's lateral vibration.

[0163] In one possible implementation, the processing module 1002 is further used for:

[0164] If the lateral velocity at that moment is less than the preset lateral velocity threshold, then the lateral velocity identifier at that moment is set to 1.

[0165] If the lateral velocity at that moment is greater than or equal to a preset lateral velocity threshold, then the lateral velocity identifier at that moment is set to 0.

[0166] Based on the preset sliding window size N, when the sliding window moves along the time axis, it is determined whether the number of times when the horizontal velocity indicator information in the sliding window is 1 is greater than or equal to the preset number threshold, where N represents more than one detection time.

[0167] If the number of times when the lateral velocity indicator in the sliding window is 1 is greater than or equal to a preset threshold, then the lateral velocity at the time when the lateral velocity in the sliding window is less than the preset lateral velocity threshold is the error lateral velocity caused by the vehicle's lateral vibration.

[0168] The data processing device for vehicle-mounted millimeter-wave radar provided in this embodiment is used to execute any of the aforementioned method embodiments. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0169] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 11 As shown, the electronic device may include at least one processor 1101 and a memory 1102.

[0170] The memory 1102 is used to store programs. Specifically, the program may include program code, which includes computer operation instructions.

[0171] The memory 1102 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage.

[0172] The processor 1101 is used to execute computer-executable instructions stored in the memory 1102 to implement the methods described in any of the foregoing embodiments. The processor 1101 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0173] Optionally, the electronic device may also include a communication interface 1103. In specific implementations, if the communication interface 1103, memory 1102, and processor 1101 are implemented independently, they can be interconnected via a bus to complete communication. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc., but this does not imply that there is only one bus or one type of bus.

[0174] Optionally, in a specific implementation, if the communication interface 1103, memory 1102, and processor 1101 are integrated on a single chip, then the communication interface 1103, memory 1102, and processor 1101 can communicate through an internal interface.

[0175] The electronic device provided in this embodiment is used to execute the data processing method of the vehicle-mounted millimeter-wave radar described above. Its implementation principle and technical effect are similar to those of the method embodiment, and will not be repeated here.

[0176] This application also provides a computer-readable storage medium, which may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a disk, or an optical disk. Specifically, the computer-readable storage medium stores computer-executable instructions, which are executed by a processor to implement the aforementioned data processing method for vehicle-mounted millimeter-wave radar.

[0177] This application also provides a computer program product comprising a computer program stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium, and the processor executes the program to cause the electronic device to implement the data processing method for vehicle-mounted millimeter-wave radar provided in the various embodiments described above.

[0178] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0179] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A data processing method for a vehicle-mounted millimeter wave radar, characterized by, include: The radial velocity data of the vehicle's millimeter-wave radar detecting the target object within a preset time period is acquired separately. The radial velocity data includes lateral velocity data and longitudinal velocity data. Error removal processing is performed on the lateral velocity data in the radial velocity data within the preset time period to obtain the processed lateral velocity data. Within the preset time period, the processed lateral velocity data and the longitudinal velocity data are input into the Universal Transverse Mercator Projection (UTM) model for coordinate transformation to obtain the target lateral velocity data and target longitudinal velocity data in the UTM coordinate system. The target lateral velocity data and the target longitudinal data are fused together for driving guidance; The step of performing error removal processing on the lateral velocity data in the radial velocity data within the preset time period to obtain processed lateral velocity data includes: For each moment within the preset time period, determine whether the lateral velocity at that moment is an error lateral velocity caused by the lateral vibration of the vehicle; If the lateral velocity at the specified moment is an error lateral velocity caused by vehicle lateral vibration, then the lateral velocity at the specified moment is set to zero, obtaining the processed lateral velocity data within the preset time period; or, For each moment within the preset time period, determine whether the lateral velocity at that moment is an error lateral velocity caused by the lateral vibration of the vehicle; If the lateral velocity at the specified moment is an error lateral velocity caused by the lateral vibration of the vehicle, then the lateral velocity at the specified moment is set to zero to obtain the intermediate lateral velocity data within the preset time period. Based on a preset Kalman filter algorithm, noise data in the intermediate lateral velocity data within the preset time period is filtered to obtain the processed lateral velocity data.

2. The method of claim 1, wherein, The determination of whether the lateral velocity at the specified moment is an error lateral velocity caused by the vehicle's lateral vibration includes: Obtain the vehicle yaw rate at the specified moment; The vehicle's operating state is determined based on the preset vehicle yaw rate threshold range where the vehicle's yaw rate is located. The operating state includes any one of the following: straight driving state, lane changing state, and turning state. If the vehicle is in a straight-ahead or lane-changing state at the time, then based on a preset sliding window algorithm, it is determined whether the lateral speed at the time is an error lateral speed caused by the vehicle's lateral vibration.

3. The method of claim 2, wherein, The method based on a preset sliding window algorithm for determining whether the lateral velocity at the given moment is an erroneous lateral velocity caused by lateral vehicle vibration includes: If the lateral velocity at the specified moment is less than a preset lateral velocity threshold, then the identifier of the lateral velocity at the specified moment is set to 1; If the lateral velocity at the specified moment is greater than or equal to the preset lateral velocity threshold, then the identification information of the lateral velocity at the specified moment is set to 0; Based on the preset sliding window size N, when the sliding window moves along the time axis, it is determined whether the number of times the horizontal velocity identification information in the sliding window is 1 is greater than or equal to a preset number threshold, where N represents more than one detection time. If the number of times when the lateral velocity identifier in the sliding window is 1 is greater than or equal to the preset number threshold, then the lateral velocity at the time when the lateral velocity in the sliding window is less than the preset lateral velocity threshold is the error lateral velocity caused by the lateral vibration of the vehicle.

4. A data processing device for vehicle-mounted millimeter-wave radar, characterized in that, include: The acquisition module is used to acquire radial velocity data of the target object detected by the vehicle's millimeter-wave radar within a preset time period. The radial velocity data includes lateral velocity data and longitudinal velocity data. The processing module is used to perform error removal processing on the lateral velocity data in the radial velocity data within the preset time period to obtain the processed lateral velocity data. The processing module is specifically used to determine, for each moment within the preset time period, whether the lateral velocity at that moment is an error lateral velocity caused by the lateral vibration of the vehicle. If the lateral velocity at the specified moment is an error lateral velocity caused by vehicle lateral vibration, then the lateral velocity at the specified moment is set to zero, obtaining the processed lateral velocity data within the preset time period; or, For each moment within the preset time period, determine whether the lateral velocity at that moment is an error lateral velocity caused by the lateral vibration of the vehicle; If the lateral velocity at the specified moment is an error lateral velocity caused by the lateral vibration of the vehicle, then the lateral velocity at the specified moment is set to zero to obtain the intermediate lateral velocity data within the preset time period. Based on a preset Kalman filter algorithm, noise data in the intermediate lateral velocity data within the preset time period is filtered to obtain the processed lateral velocity data. The coordinate transformation module is used to input the processed lateral velocity data and the longitudinal velocity data within the preset time period into the Universal Transverse Mercator Projection (UTM) model for coordinate transformation processing to obtain the target lateral velocity data and target longitudinal velocity data in the UTM coordinate system. The sending module is used to fuse the target lateral velocity data and the target longitudinal data for driving guidance.

5. An electronic device, characterized in that, include: At least one processor and memory; The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the electronic device to perform the data processing method for vehicle-mounted millimeter-wave radar according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the data processing method for vehicle-mounted millimeter-wave radar as described in any one of claims 1 to 3.

7. A computer program product, characterized in that, The system includes a computer program that, when executed by a processor, implements the data processing method for vehicle-mounted millimeter-wave radar as described in any one of claims 1 to 3.

Images