Vehicle platooning status simulation method and apparatus

Abstract

The application discloses a vehicle queuing state simulation method and device, and belongs to the field of traffic simulation. The vehicle queuing state simulation method comprises the following steps: performing fusion processing on radar data and video data corresponding to at least one first queuing vehicle from a starting position to a target intersection, to obtain target radar and video trajectory data; determining a blocked vehicle in the at least one first queuing vehicle and a target vehicle that blocks the blocked vehicle based on the target radar and video trajectory data; and performing simulation queuing processing on the blocked vehicle based on at least one of the actual driving state of the target vehicle, the first distance between the target vehicle and a first vehicle behind the target vehicle, and the queuing situation of the vehicle corresponding to the rear of the target vehicle. The vehicle queuing state simulation method has a wide application scenario and high detection accuracy, and solves the problem of reduced accuracy of traffic condition detection results caused by large vehicle blocking under complex roads.

Description

Technical Field

[0001] This application belongs to the field of traffic simulation technology, and in particular relates to a method and apparatus for simulating vehicle queuing status. Background Technology

[0002] When detecting traffic conditions at intersections, vehicles obscured by large trucks are easily missed, leading to low accuracy in detecting traffic flow and other traffic conditions. Related technologies, when detecting traffic conditions in environments with many large trucks, cannot detect vehicles obscured by them, resulting in low accuracy and significant fluctuations in traffic detection at intersections. Summary of the Invention

[0003] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a vehicle queuing state simulation method and apparatus, which ensures that trajectory data can be associated when the radar detects vehicles again, resulting in relatively stable detection results. This enables accurate detection of traffic conditions at intersections even in complex road environments, and has a wide range of applicable scenarios and high detection accuracy. It solves the problem of reduced accuracy of traffic condition detection results due to large vehicles obstructing traffic in complex road conditions.

[0004] Firstly, this application provides a method for simulating vehicle queuing status, the method comprising:

[0005] The radar data and video data corresponding to at least one first queued vehicle between the starting position and the target intersection are fused to obtain the target radar-visual trajectory data.

[0006] Based on the target radar trajectory data, the obscured vehicle in the at least one first queue of vehicles and the target vehicle obscuring the obscured vehicle are determined.

[0007] Based on at least one of the following: the actual driving state of the target vehicle, the first distance between the target vehicle and the first vehicle behind the target vehicle, and the queuing situation of the vehicles behind the target vehicle, the obscured vehicle is subjected to simulated queuing processing; the first vehicle is the first vehicle in the at least one first queue of vehicles other than the target vehicle.

[0008] According to the vehicle queuing state simulation method provided in this application embodiment, the radar data and video data of the first queued vehicles are fused to obtain the target radar trajectory corresponding to the motor vehicle. After eliminating the interference of non-motorized vehicles at the intersection, the method can also simulate the queuing of the obscured vehicles based on at least one of the actual driving state of the target vehicle, the first distance between the target vehicle and the first vehicle, and the queuing situation of the vehicles behind the target vehicle, so as to simulate the obscured vehicles and restore the current intersection state. This ensures that the trajectory data can be associated when the radar detects vehicles again, and the detection results are relatively stable. This enables accurate detection of traffic conditions at intersections even in complex road environments. The method has a wide range of applicable scenarios and high detection accuracy, solving the problem of reduced accuracy of traffic condition detection results due to large vehicles obstructing traffic in complex road conditions.

[0009] One embodiment of this application provides a vehicle queuing state simulation method, which simulates queuing for the obscured vehicle based on at least one of the following: the actual driving state of the target vehicle, a first distance between the target vehicle and a first vehicle behind the target vehicle, and the queuing situation of the vehicles behind the target vehicle. The method includes:

[0010] Based on the target radar trajectory data corresponding to the target vehicle, it is determined that the target vehicle has been in a stopped state, the first distance is greater than the first distance threshold, there is a second queue of vehicles behind the target vehicle, the second queue of vehicles is not stationary, and the second distance between the target vehicle and the stop line corresponding to the target intersection is less than the second distance threshold, a third distance between the simulated queue target and the target vehicle is generated based on the road condition information corresponding to the target intersection; the simulated queue target is a simulated vehicle generated after simulating the queueing of the obscured vehicles; the road condition information includes the obscured area corresponding to the obscured vehicle;

[0011] Based on the third distance, simulated queuing is performed on the obscured vehicles.

[0012] A vehicle queuing state simulation method according to an embodiment of this application, wherein the method simulates queuing processing for the obscured vehicle based on at least one of the actual driving state of the target vehicle, a first distance between the target vehicle and a first vehicle behind the target vehicle, and the queuing situation of the vehicles corresponding to the rear of the target vehicle, further includes:

[0013] When the target vehicle is stationary, there are no vehicles within a fourth distance behind the target vehicle, and there are vehicles beyond a fifth distance, and the vehicle is stationary, simulated queuing is performed on the obscured vehicle based on the fifth distance.

[0014] One embodiment of this application provides a vehicle queuing state simulation method, which simulates queuing for the obscured vehicle based on at least one of the following: the actual driving state of the target vehicle, a first distance between the target vehicle and a first vehicle behind the target vehicle, and the queuing situation of the vehicles behind the target vehicle. The method includes:

[0015] When the target vehicle is stationary or when the target vehicle has not been stopped based on the target radar trajectory data, and when the first distance is less than the third distance threshold and the target radar trajectory data of the obscured vehicle disappears, the original driving speed of the obscured vehicle is obtained; the original driving speed is the driving speed of the obscured vehicle when the first distance is not less than the third distance threshold.

[0016] Based on the original driving speed, simulated queuing is performed on the obscured vehicles.

[0017] One embodiment of the vehicle queuing state simulation method of this application includes performing simulated queuing processing on the obscured vehicles based on the original driving speed to obtain the simulated queuing target, comprising:

[0018] The original driving speed is used as the initial speed; and the detection gate corresponding to the simulated queuing target corresponding to the obscured vehicle is magnified to obtain the target gate corresponding to the simulated queuing target; the target gate is used to associate the obscured vehicle with the simulated queuing target when the obscured vehicle changes lanes;

[0019] Based on the target gate and the initial velocity, a simulated queuing process is performed on the blocked vehicles to obtain the simulated queuing target.

[0020] One embodiment of the vehicle queuing state simulation method of this application, before fusing radar data and video data corresponding to at least one first queuing vehicle between the starting position and the target intersection to obtain target radar-visual trajectory data, the method further includes:

[0021] Acquire initial radar data and initial video data corresponding to at least one first queued vehicle between the starting position and the target intersection;

[0022] The initial radar data and the initial video data are converted to the same coordinate system to obtain the radar data and the video data.

[0023] One embodiment of the vehicle queuing state simulation method of this application, wherein the step of determining, based on the target radar trajectory data, a censored vehicle in the at least one first queue of vehicles and the target vehicle censoring the censored vehicle includes:

[0024] If the target radar trajectory data disappears, the duration of the target radar trajectory data exceeds a first duration threshold, and the target vehicle is in front of the first queue of vehicles corresponding to the target radar trajectory data, then the first queue of vehicles is identified as the obscured vehicle.

[0025] Secondly, this application provides a vehicle queuing state simulation device, the device comprising:

[0026] The first processing module is used to fuse radar data and video data corresponding to at least one first queued vehicle between the starting position and the target intersection to obtain target radar-visual trajectory data.

[0027] The second processing module is used to determine, based on the target radar trajectory data, the obscured vehicle in the at least one first queue of vehicles and the target vehicle obscuring the obscured vehicle.

[0028] The third processing module is used to simulate queuing for the obscured vehicle based on at least one of the following: the actual driving state of the target vehicle, the first distance between the target vehicle and the first vehicle behind the target vehicle, and the queuing situation of the vehicles behind the target vehicle; the first vehicle is the first vehicle in the at least one first queue of vehicles other than the target vehicle.

[0029] According to the vehicle queuing state simulation device provided in this application embodiment, the radar data and video data of the first queued vehicles are fused to obtain the target radar trajectory corresponding to the motor vehicle. After eliminating the interference of non-motorized vehicles at the intersection, the device can also simulate the queuing of the obscured vehicles based on at least one of the actual driving state of the target vehicle, the first distance between the target vehicle and the first vehicle, and the queuing situation of the vehicles behind the target vehicle. This simulates the obscured vehicles and restores the current intersection state, ensuring that the trajectory data can be associated when the radar detects vehicles again. The detection results are relatively stable, which enables accurate detection of traffic conditions at intersections even in complex road environments. The device has a wide range of applicable scenarios and high detection accuracy, solving the problem of reduced accuracy of traffic condition detection results due to large vehicles obstructing traffic in complex road conditions.

[0030] Thirdly, this application provides an electronic device including 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 implement the vehicle queuing state simulation method as described in the first aspect above.

[0031] Fourthly, this application provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle queuing state simulation method as described in the first aspect above.

[0032] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the vehicle queuing state simulation method as described in the first aspect above.

[0033] The above-described one or more technical solutions in the embodiments of this application have at least one of the following technical effects:

[0034] By fusing radar and video data of the first queue of vehicles, the target radar trajectory of the motor vehicle is obtained. After eliminating interference from non-motorized vehicles at the intersection, the system can simulate the queuing of obscured vehicles based on at least one of the following: the actual driving status of the target vehicle, the first distance between the target vehicle and the first vehicle, and the queuing situation of the vehicles behind the target vehicle. This simulates the obscured vehicles and restores the current intersection state, ensuring that the trajectory data can be associated when the radar detects vehicles again. The detection results are relatively stable, enabling accurate detection of traffic conditions at intersections even in complex road environments. The system has a wide range of applications and high detection accuracy, solving the problem of reduced accuracy of traffic condition detection results due to large vehicles obstructing traffic in complex road conditions.

[0035] Furthermore, based on the actual driving status of the large vehicle and the queuing situation of the vehicles behind it, different simulated queuing methods are selected to simulate the queuing of the obscured vehicles. Various vehicle obstruction situations are considered, which improves the accuracy and precision of the queuing status simulation results corresponding to the obscured vehicles, and broadens the applicable scenarios and improves the flexibility of the method.

[0036] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0037] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0038] Figure 1This is a flowchart illustrating the vehicle queuing state simulation method provided in this application embodiment;

[0039] Figure 2 This is a schematic diagram of the vehicle queuing state simulation device provided in the embodiments of this application;

[0040] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0041] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0042] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0043] The following is combined Figure 1 This application describes a method for simulating vehicle queuing status according to an embodiment of the present application.

[0044] It should be noted that the execution entity of the vehicle queuing status simulation method can be a server, a vehicle queuing status simulation device, or a user's terminal, including but not limited to mobile terminals and non-mobile terminals.

[0045] For example, mobile terminals include, but are not limited to, mobile phones, PDA smart terminals, tablets, and in-vehicle smart terminals; non-mobile terminals include, but are not limited to, PCs.

[0046] like Figure 1 As shown, the vehicle queuing state simulation method includes steps 110, 120 and 130.

[0047] Step 110: Fusion processing is performed on the radar data and video data corresponding to at least one first queue vehicle between the starting position and the target intersection to obtain the target radar-visual trajectory data.

[0048] In this step, at least one of the first queued vehicles is a vehicle that has not crossed the stop line corresponding to the target intersection between the starting position and the target intersection.

[0049] Radar and video data can be collected along the lane using a data acquisition device, such as a radar-video integrated machine.

[0050] For example, radar data can be collected based on the radar detector in the radar-visual integrated machine, and video data can be collected based on the video capture device in the radar-visual integrated machine.

[0051] Radar data includes basic target data acquired by the radar. For example, basic target data may include: the location information, vehicle direction, vehicle speed and scattering area of ​​the first queue of vehicles. Radar data may also include extended data acquired by the radar. For example, extended data may include: the type of the first queue of vehicles identified by the radar.

[0052] Radar data can be used to characterize the radar trajectory of the first queuing vehicles from their starting position to the target intersection.

[0053] Video data can include multiple frames of vehicle images. By parsing the video data, targets in the video data can be detected. These targets can be various types of motor vehicles, non-motor vehicles, and pedestrians.

[0054] Video data can be used to characterize the video trajectory of the first queuing vehicles from the starting position to the target intersection.

[0055] The starting position can be the edge of the collection range of the collection device. For example, the starting position can be a position 20m away from the stop line of the target intersection along the lane direction. It can be user-defined and is not limited in this application.

[0056] The target intersections are those where traffic incidents, road incidents, and traffic flow need to be detected.

[0057] In some embodiments, prior to step 110, the vehicle queuing state simulation method may further include:

[0058] Acquire initial radar data and initial video data for at least one first queuing vehicle between the starting position and the target intersection;

[0059] The initial radar data and initial video data are converted to the same coordinate system to obtain radar data and video data.

[0060] In this embodiment, the initial radar data may include stationary targets.

[0061] The initial radar data can be data in the radar coordinate system.

[0062] The initial video data can be data in the camera coordinate system.

[0063] Before processing the initial radar data and initial video data, it is necessary to convert the initial radar data and initial video data to the same coordinate system.

[0064] The initial radar data and initial video data can be converted to the radar-view standard coordinate system based on the basic calibration algorithm and the automatic calibration algorithm of the coordinate system. The radar-view standard coordinate system can be determined based on the installation status of the radar-view integrated machine. The radar-view standard coordinate system can be used to correct the real lane in the simulation. The radar-view standard coordinate system can be used to delineate the limited lane area of ​​the intersection boundary.

[0065] For example, when converting initial radar data to the radar-view standard coordinate system, lane tilt conversion can be performed on the initial radar data.

[0066] In actual execution, the initial radar data and initial video data can be converted to the same coordinate system based on the spatial coordinate system transformation module.

[0067] In some embodiments, the initial radar data and initial video data can be filtered separately to obtain radar data and video data.

[0068] In this embodiment, the initial radar data can be subjected to operations such as clustering, filtering, and removal of stationary points to obtain radar data.

[0069] It can perform operations such as tracking, filtering, and trajectory optimization on the initial video data to obtain the final video data.

[0070] In actual execution, the initial radar data can be tracked and filtered using the radar trajectory module to obtain the radar data.

[0071] The target can be detected in the initial video data through the video vehicle recognition algorithm module, and the initial video data can be filtered through the video trajectory module to obtain the video data.

[0072] Among these methods, the Kalman filter algorithm can be used to track and filter the trajectory of motion.

[0073]

[0074]

[0075]

[0076] Where x and y are state transition matrices, and A is the gain matrix. For the measurement equation, z kLet H be the measured value at time k, and H be the measurement system parameters. The state values ​​are estimated using Kalman spectroscopy, where x′ is the lateral coordinate, y′ is the longitudinal coordinate, Δx is the lateral velocity, and Δy is the longitudinal velocity.

[0077] If the initial video data exhibits jitter and Kalman filtering, resulting in video rewinding, a video trajectory module can be used to perform specific processing on the video data to prevent video rewinding.

[0078] In some embodiments, step 110 may include:

[0079] Based on radar and video data corresponding to each first queue vehicle, determine at least one of the following: position coordinates, horizontal axis velocity, vertical axis velocity, and RCS value of each first queue vehicle in each collection period.

[0080] Based on at least one of the position coordinates, horizontal axis velocity, vertical axis velocity, and RCS value, a gate matrix is ​​constructed for each first queue vehicle. Based on the gate matrix, radar data and video data of the target first queue vehicle in multiple acquisition cycles are fused to obtain the target radar-visual trajectory data corresponding to the target first queue vehicle.

[0081] In this embodiment, the position coordinates corresponding to the first queued vehicle are the coordinate information of the first queued vehicle in the radar standard coordinate system, wherein the position coordinates may include the horizontal coordinate and the vertical coordinate in the radar standard coordinate system.

[0082] Based on radar data, the first horizontal axis velocity and the first vertical axis velocity corresponding to the first queue of vehicles can be obtained.

[0083] The horizontal axis is the x-axis in the standard coordinate system of the radar vision system, and the vertical axis is the y-axis in the standard coordinate system of the radar vision system.

[0084] Based on the video data, the second horizontal axis velocity and the second vertical axis velocity corresponding to the first queue of vehicles can be obtained.

[0085] The horizontal axis speed corresponding to the first queue of vehicles can include the first horizontal axis speed and the second horizontal axis speed.

[0086] The longitudinal speed corresponding to the first queue of vehicles can include the first longitudinal speed and the second longitudinal speed.

[0087] The RCS (Radar Cross Section) value corresponding to the first vehicle in the queue is the radar cross-section. The RCS value can be used to measure the vehicle's ability to reflect radar signals in the direction of radar reception.

[0088] The RCS value can also reflect the vehicle model corresponding to the first vehicle in the queue.

[0089] For example, the RCS value for non-motorized vehicles may be much smaller than that for motorized vehicles.

[0090] Depending on the data collection period, the position coordinates, horizontal axis velocity, vertical axis velocity, and RCS value of the first queue of vehicles may all be different.

[0091] Based on at least one of the position coordinates, horizontal axis velocity, vertical axis velocity, and RCS value, the gate matrix corresponding to each first queue vehicle can be constructed.

[0092] Position coordinates, horizontal axis velocity, vertical axis velocity, and RCS value are at least one of the parameters included in the gate matrix.

[0093] Each parameter in the gate matrix has a corresponding weight, and the weights for each parameter may be the same or different.

[0094] The target vehicle in the first queue is any one of the multiple vehicles in the first queue.

[0095] Based on the gate matrix corresponding to each vehicle in the first queue, the target vehicle in the first queue can be determined from multiple vehicles in the first queue.

[0096] The radar and video data of the first vehicle in the target queue can be fused and processed over multiple acquisition cycles to obtain the target radar-visual trajectory data corresponding to the first vehicle in the target queue.

[0097] The radar and video data corresponding to the first queuing vehicle of the target can be fused based on the radar-visual fusion algorithm to obtain the target radar-visual trajectory data.

[0098] The target radar trajectory data is data in the radar standard coordinate system.

[0099] The target radar trajectory data includes the coordinate data of the target vehicle, the vehicle type data of the first vehicle in the target queue, and the vehicle color data of the first vehicle in the target queue.

[0100] In the process of fusing radar data and video data of the first queuing vehicle of the target in multiple acquisition cycles, radar data and video data of the first queuing vehicle of the target in the previous one or several acquisition cycles can be fused to obtain initial radar-visual trajectory data.

[0101] If new radar data and new video data are acquired in the next acquisition cycle, the radar data and video data of the first queuing vehicle of the target in this acquisition cycle can be associated with the initial radar-visual trajectory data. Then, the initial radar-visual trajectory data and the radar data and video data in this acquisition cycle are fused to obtain the target radar-visual trajectory data.

[0102] In actual execution, the radar data and video data corresponding to the first vehicle in the target queue can be input into the radar-view trajectory module. Based on the radar-view trajectory module, the radar data and video data of the first vehicle in the target queue in multiple collection cycles are fused to obtain the target radar-view trajectory data corresponding to the first vehicle in the target queue output by the radar-view trajectory module.

[0103] The Rayvision trajectory module can include various trajectory fusion mechanisms. For example, the Rayvision trajectory module can include a video trajectory initiation mechanism. By processing video data based on the video trajectory initiation mechanism, the trajectory can be made more adaptable to the environment.

[0104] In some embodiments, a gate matrix corresponding to each first queue vehicle is constructed based on at least one of position coordinates, horizontal axis velocity, vertical axis velocity, and RCS value. Based on the gate matrix, radar data and video data of the target first queue vehicle within multiple acquisition cycles are fused to obtain target radar-visual trajectory data corresponding to the target first queue vehicle. This may include:

[0105] The parameters included in the gate matrix corresponding to each first queue vehicle are weighted to obtain the weighted average value corresponding to each first queue vehicle.

[0106] The radar and video data of the target vehicle in the first queue are fused based on the weighted average value within multiple acquisition periods to obtain the target radar-visual trajectory data corresponding to the target vehicle in the first queue.

[0107] In this embodiment, the parameters included in the gate matrix may include at least one of the following: position coordinates, horizontal axis velocity, vertical axis velocity, and RCS value.

[0108] Each parameter in the gate matrix has a corresponding weight, and the weights for each parameter may be the same or different.

[0109] For example, when the weights corresponding to each parameter are different, the weight corresponding to the vertical axis velocity can be the highest weight among the weights corresponding to each parameter in the gate matrix.

[0110] Based on the weights corresponding to each parameter, the parameters included in the gate matrix corresponding to each first queue vehicle can be weighted to obtain the weighted average value corresponding to each first queue vehicle.

[0111] Different first-queue vehicles correspond to different gate matrices, and the weighted average values ​​corresponding to different first-queue vehicles are also different.

[0112] The target first queue vehicle can be determined from multiple first queue vehicles based on the weighted average value of each first queue vehicle.

[0113] After identifying the first vehicle in the target queue, radar data and video data of the first vehicle in the target queue can be fused over multiple acquisition cycles to obtain the target radar-visual trajectory data corresponding to the first vehicle in the target queue.

[0114] In some embodiments, fusing radar data and video data of a target vehicle in a first queue of multiple first queues over multiple acquisition periods based on a weighted average value to obtain target radar-visual trajectory data corresponding to the target vehicle in the first queue may include:

[0115] The vehicle in the first queue corresponding to the smallest weighted average value is determined as the target vehicle in the first queue.

[0116] The radar and video data corresponding to the first acquisition cycle of the target first queue vehicle in multiple acquisition cycles are fused with the initial radar-visual trajectory data corresponding to the target first queue vehicle to obtain the target radar-visual trajectory data. The initial radar-visual trajectory data is obtained by fusing the radar and video data corresponding to the target first queue vehicle in historical acquisition cycles. The historical acquisition cycles are the cycles that are before the first acquisition cycle in multiple acquisition cycles.

[0117] In this embodiment, the target first queue vehicle is the vehicle corresponding to the smallest weighted average among multiple weighted averages.

[0118] The target vehicle in the first queue is a motor vehicle.

[0119] The radar data and video data corresponding to the first queuing vehicle of the target in the historical collection period can be fused to obtain the initial radar-visual trajectory data.

[0120] When entering the next historical data collection cycle, the radar data and video data collected in the next cycle can be correlated with the initial radar-visual trajectory data.

[0121] The first data collection cycle is the next cycle corresponding to the historical data collection cycle.

[0122] In actual implementation, a gate interval can be set, which can be used to limit the vehicle's coordinates and speed, etc.

[0123] The parameters included in the gate matrix corresponding to at least one first queue vehicle falling into the gate interval are weighted to obtain the weighted average value corresponding to each first queue vehicle.

[0124] The vehicle corresponding to the minimum value among at least one weighted average is identified as the target first queue vehicle.

[0125] During the process of collecting radar data and video data corresponding to the first queue of vehicles based on the collection period, the radar data and video data corresponding to the first queue of vehicles can be fused to obtain the initial radar-visual trajectory data of the first queue of vehicles within the historical collection period.

[0126] Acquire the radar data and video data corresponding to the first queue of vehicles in the target within the first acquisition period, which is the next period of the historical acquisition period.

[0127] Then, the radar data and video data corresponding to the first queue of vehicles of the target collected in the first collection cycle are associated with the initial radar-visual trajectory data and fused to obtain the target radar-visual trajectory data.

[0128] Step 120: Based on the target radar trajectory data, identify at least one obscured vehicle in the first queue of vehicles and the target vehicle that obscures the obscured vehicle.

[0129] In this step, the obscured vehicle is one that is blocked by a large vehicle. When detecting traffic conditions at intersections using non-overhead equipment, such as radar detectors and integrated radar-visual systems, the detection target of the obscured vehicle is easily lost.

[0130] The target vehicle is a large vehicle that is obscuring the vehicle being obscured.

[0131] The target radar trajectory data can be distinguished based on the lane. By traversing the target radar trajectory data corresponding to each lane after distinction, the position of the target vehicle in the lane can be determined.

[0132] When the first queue of vehicles is close to the large vehicle, the first queue of vehicles may be obscured by the large vehicle, making it impossible to detect the first queue of vehicles. In this case, the first queue of vehicles can be identified as the obscured vehicles, and the large vehicle can be identified as the target vehicle.

[0133] Based on the target radar trajectory data corresponding to each vehicle in the first queue, the obscured vehicle can be identified from at least one vehicle in the first queue.

[0134] For example, if the first queue of vehicles is close to the large vehicle, the target radar trajectory data corresponding to the first queue of vehicles may suddenly disappear, and the first queue of vehicles can be identified as obscured vehicles.

[0135] In some embodiments, step 120 may further include:

[0136] If the target radar trajectory data disappears, the duration of the target radar trajectory data exceeds the first duration threshold, and there is a target vehicle in front of the first queue of vehicles corresponding to the target radar trajectory data, the first queue of vehicles is identified as the obscured vehicle.

[0137] In this embodiment, the duration of the target radar trajectory data is the duration from the appearance of the trajectory data to its disappearance.

[0138] The first duration threshold can be 20s or 30s, etc., and can be user-defined; this application does not impose any restrictions.

[0139] If the duration of the target radar trajectory data exceeds the first duration threshold, it can be considered that the duration of the target radar trajectory data is relatively long and the reliability of the target radar trajectory data is relatively high.

[0140] If the duration of the target radar trajectory data is no greater than the first duration threshold, it can be considered that the duration of the target radar trajectory data is short and the reliability of the target radar trajectory data is low.

[0141] It can be determined whether there is a target vehicle within a distance of the sixth unit ahead of the first queue of vehicles.

[0142] For example, the sixth distance can be 4m or 5m, etc., and can be customized by the user. This application does not impose any restrictions.

[0143] If the target radar trajectory data corresponding to the first queue of vehicles disappears, the duration of the target radar trajectory data exceeds the first duration threshold, and there is a target vehicle within a certain distance in front of the first queue of vehicles, it can be determined that the first queue of vehicles is obscured by the target vehicle, and the first queue of vehicles is identified as the obscured vehicle.

[0144] Step 130: Based on at least one of the following: the actual driving state of the target vehicle, the first distance between the target vehicle and the first vehicle behind the target vehicle, and the queuing situation of the vehicles behind the target vehicle, simulate queuing processing is performed on the obscured vehicles; the first vehicle is the first vehicle in at least one first queue of vehicles other than the target vehicle.

[0145] In this step, the actual driving state of the target vehicle can include: being close to the stop line after starting the queue, not having stopped moving, and being stationary.

[0146] There may be one or more vehicles behind the target vehicle, or there may be no vehicles behind the target vehicle.

[0147] Based on the radar or video data corresponding to each vehicle in the first queue, the first vehicle behind the target vehicle can be detected, which is the first vehicle.

[0148] If the target radar trajectory data corresponding to the first vehicle is stable, there may be an obscured vehicle between the first vehicle and the target vehicle.

[0149] If the target radar trajectory data corresponding to the first vehicle disappears when the distance between the first vehicle and the target vehicle reaches the target threshold, the first vehicle may be an obscured vehicle.

[0150] If there is a first vehicle behind the target vehicle, the first distance between the target vehicle and the first vehicle can be obtained.

[0151] The queue status of vehicles behind the target vehicle can include: vehicles without a queue, vehicles in a dynamic queue, and vehicles in a stationary queue.

[0152] Among them, if there are queued vehicles behind the target vehicle, the distance between each queued vehicle is less than the fifth distance threshold, and the speed of the queued vehicles is less than the first speed threshold, the queued vehicles can be determined to be in a dynamic queue.

[0153] For example, the speed of the vehicles in the queue can be determined based on their coordinates and speed information. The first speed threshold can be 5 km / h or 6 km / h, and can be user-defined. This application does not limit the speed threshold.

[0154] The fifth distance threshold can be 2m or 2.5m, etc., and can be user-defined; this application does not impose any restrictions.

[0155] Simulated queuing processing of obscured vehicles can generate simulated queuing targets corresponding to the obscured vehicles.

[0156] Simulated queue targets can be used to simulate obscured vehicles to restore the current intersection status and ensure that trajectory data can be linked when the radar detects the vehicle again.

[0157] Simulated queuing can include: standard simulated queuing, interval simulated queuing, and tail simulated queuing.

[0158] Based on at least one of the following: the actual driving status of the target vehicle, the first distance between the target vehicle and the first vehicle, and the queuing situation of the vehicles behind the target vehicle, the specific method for simulating queuing of the obscured vehicles can be determined.

[0159] In this application, radar data and video data of the first queue of vehicles are fused to obtain the target radar-visual trajectory of each vehicle in the first queue. In complex intersections, the trajectory data of motor vehicles can be detected without extensive calibration of the acquisition device. Furthermore, the radar data and video data of motor vehicles can be accurately fused, making it applicable to a wide range of scenarios. This reduces the cost of the acquisition device while improving its acquisition accuracy.

[0160] Based on the target radar trajectory data corresponding to each vehicle in the first queue, the obscured vehicle and the target vehicle obscuring the obscured vehicle can be identified from at least one vehicle in the first queue. Then, based on at least one of the following: the actual driving state of the target vehicle, the first distance between the target vehicle and the first vehicle, and the queuing situation of the vehicles behind the target vehicle, the obscured vehicle is simulated to queue up, thereby simulating the obscured vehicle and restoring the current intersection state. This ensures that the trajectory data can be associated when the radar detects vehicles again, and the detection results are relatively stable. This enables accurate detection of traffic conditions at intersections even in complex road environments. It has a wide range of applicable scenarios and high detection accuracy, solving the problem of reduced accuracy of traffic condition detection results due to large vehicles obscuring the traffic in complex road conditions.

[0161] In actual execution, the radar trajectory data of each lane can be traversed to obtain the position of the target vehicle in the lane. Based on parameters such as the driving status of the target vehicle, different simulated queuing processes can be performed on the obscured vehicle.

[0162] In some embodiments, step 130 may include:

[0163] Based on the target vehicle's target radar trajectory data, it is determined that the target vehicle has been in a stopped state, the first distance is greater than the first distance threshold, there is a second queue of vehicles behind the target vehicle, the second queue of vehicles is not stationary, and the second distance between the target vehicle and the stop line corresponding to the target intersection is less than the second distance threshold. Then, a third distance is generated between the simulated queue target and the target vehicle based on the road condition information corresponding to the target intersection. The simulated queue target is a simulated vehicle generated after simulating the queuing of the obscured vehicles. The road condition information includes the obscured area corresponding to the obscured vehicle.

[0164] Simulated queuing processing of obscured vehicles is performed based on the third distance.

[0165] In this embodiment, the historical driving status of the target vehicle can be determined based on the target vehicle's target radar trajectory data.

[0166] The target vehicle's historical driving status may include instances where the target vehicle has been stopped, instances where the target vehicle has not been stopped, or other driving statuses.

[0167] The first distance threshold can be 4m or 4.5m, etc., and can be user-defined; this application does not impose any restrictions.

[0168] If the first distance is greater than the first distance threshold, the distance to the first vehicle behind the target vehicle is relatively far, and there may be an obscured vehicle between the target vehicle and the first vehicle.

[0169] There may be a target number of second queue vehicles behind the target vehicle. For example, the target number could be 3 or 4, etc., which can be customized by the user and is not limited in this application.

[0170] The queuing status of the second queue of vehicles can include: dynamic queuing or static queuing.

[0171] When the queuing status of the second queue of vehicles is dynamic, the vehicles in the second queue are not stationary.

[0172] The distance between the target vehicle and the stop line corresponding to the target intersection is the second distance. If the second distance is less than the second distance threshold, the target vehicle can be considered to be close to the stop line.

[0173] The second distance threshold can be 2m or other values, and can be user-defined; this application does not impose any restrictions.

[0174] The third distance can be determined based on the traffic information at the target intersection. The third distance is the distance between the simulated queuing target and the target vehicle.

[0175] The simulated queuing target is the simulated vehicle generated after simulating the queuing process of the obscured vehicles.

[0176] Road condition information can include the obscured area of ​​the obscured vehicle. For example, when the installation angle of the radar-visual integrated machine is different, the obscured area of ​​the obscured vehicle may be different in the radar-visual trajectory data of the obscured vehicle and the target vehicle obtained by the radar-visual integrated machine.

[0177] The obscured vehicles can be simulated for queuing based on a third distance. For example, a simulated queue target corresponding to the obscured vehicle can be generated at a third distance behind the target vehicle. In some embodiments, if a simulated queue target is not successfully generated or other anomalies occur after simulating queuing of the obscured vehicles based on interval queuing or tail queuing, a simulated queue target can be generated based on the third distance.

[0178] In actual execution, all unassociated simulated queuing targets in the lane can be traversed, and then the target vehicles corresponding to the front trajectory data and the vehicles corresponding to the rear trajectory data of the simulated queuing targets can be obtained.

[0179] The distance between the simulated queue target and the vehicle in front can be set as the third distance, and the distance between the simulated queue target and the vehicle behind can also be set as the third distance.

[0180] When the distance between the simulated queue target and the vehicle in front reaches the minimum distance threshold, the speed of the simulated queue target can be reduced.

[0181] When the distance between the simulated queuing target and the vehicle in front reaches the maximum distance threshold, a positive acceleration can be provided to the simulated queuing target to increase the speed of the obscured vehicle; the maximum distance threshold is greater than the minimum distance threshold, and both the maximum and minimum distance thresholds can be user-defined, which is not limited in this application.

[0182] When the distance between the simulated queuing target and the vehicle behind it reaches the minimum distance threshold, a positive acceleration can be provided to the simulated queuing target to increase the speed of the obscured vehicle.

[0183] When the distance between the simulated queue target and the vehicle behind it reaches the maximum distance threshold, the speed of the simulated queue target can be reduced.

[0184] In some embodiments, if the first distance is not greater than a first distance threshold, no simulated queuing process is performed on the obscured vehicles.

[0185] In this embodiment, for example, when the first distance is 2m, there are no motor vehicles between the target vehicle and the first vehicle, and the first vehicle can be identified as the obscured vehicle.

[0186] In some embodiments, step 130 may further include:

[0187] When the target vehicle is stationary, there are no vehicles within a fourth distance behind the target vehicle, and there are vehicles beyond a fifth distance that are stationary, simulated queuing is performed on the obscured vehicles based on the fifth distance.

[0188] In this embodiment, the values ​​of the fourth distance and the fifth distance are different, with the fifth distance being greater than the fourth distance.

[0189] Both the fourth and fifth distances can be user-defined; for example, the fourth distance can be 5m and the fifth distance can be 7m.

[0190] If there are no vehicles within the fourth distance behind the target vehicle, but there are vehicles outside the fifth distance behind the target vehicle in a stationary queue, it can be assumed that the target vehicle is obstructed and the simulated queue was not successfully generated.

[0191] In actual execution, all vehicle trajectory targets on the lane can be traversed to obtain the vehicle corresponding to the trajectory data that is about to disappear and identify it as the second vehicle.

[0192] Acquire the target radar trajectory data of the vehicle in front of the second vehicle (the target vehicle), and the target radar trajectory data of at least two vehicles behind the second vehicle.

[0193] If the distance between the target radar trajectory data corresponding to the target vehicle and the target radar trajectory data corresponding to the second vehicle is not less than the target distance threshold, the existence duration of the target radar trajectory data corresponding to the target vehicle and the target radar trajectory data corresponding to the second vehicle is greater than the first duration threshold, the target radar trajectory data corresponding to the target vehicle and the target radar trajectory data corresponding to the second vehicle are both in a near-stop state, the target vehicle and the first vehicle behind the target vehicle are both in a queue state, and both the target vehicle and the second vehicle are motor vehicles, at least one simulated queue target can be generated between the target vehicle and the second vehicle to perform interval simulated queuing.

[0194] When the number of simulated queue targets is one, the distance between the simulated queue target and the target vehicle and the second vehicle can be determined as the fifth distance; wherein, the simulated queue target can be normally associated with the trajectory target.

[0195] When there are multiple simulated queuing targets, the distance between multiple simulated queuing targets can be the fifth distance. The distance between a vehicle adjacent to the target vehicle and the target vehicle is also the fifth distance. The distance between a vehicle adjacent to the second vehicle and the second vehicle is also the fifth distance.

[0196] When the distance between the simulated queue target and the second vehicle reaches the minimum distance threshold, a positive acceleration can be provided to the simulated queue target to increase the speed of the obscured vehicle.

[0197] When the distance between the simulated queue target and the second vehicle reaches the maximum distance threshold, the speed of the simulated queue target can be reduced.

[0198] When the distance between the simulated queue target and the target vehicle reaches the minimum distance threshold, the speed of the simulated queue target can be reduced.

[0199] When the distance between the simulated queuing target and the target vehicle reaches the maximum distance threshold, a positive acceleration can be provided to the simulated queuing target to increase the speed of the obscured vehicle.

[0200] In some embodiments, step 130 may further include:

[0201] If the target vehicle is stationary or the target vehicle has not been stopped based on the target radar trajectory data corresponding to the target vehicle, and the target radar trajectory data corresponding to the obscured vehicle disappears when the first distance is less than the third distance threshold, the original driving speed of the obscured vehicle is obtained; the original driving speed is the driving speed of the obscured vehicle when the first distance is not less than the third distance threshold.

[0202] Based on the original driving speed, simulated queuing is performed on the obscured vehicles.

[0203] In this embodiment, the historical driving status of the target vehicle can be obtained based on the target radar trajectory data corresponding to the target vehicle. If the historical driving status has not shown a stopped state, the tail of the obscured vehicles behind the target vehicle can be simulated to form a queue.

[0204] Even when the target vehicle is stationary, a simulated queue can be formed at the rear of the obscured vehicles.

[0205] The original driving speed of the obscured vehicle is the driving speed of the target radar trajectory data of the obscured vehicle at the end time, provided that the first distance is not less than the third distance threshold.

[0206] The end time is the moment when the target radar trajectory data corresponding to the obscured vehicle disappears.

[0207] The third distance threshold can be 1m or other values, and can be user-defined; this application does not impose any restrictions.

[0208] If the duration of the target radar trajectory data corresponding to the obscured vehicle exceeds the first duration threshold, the trajectory data of the obscured vehicle can be considered relatively stable.

[0209] In actual execution, all vehicle trajectory targets on the lane can be traversed to obtain the vehicles corresponding to the trajectory data that is about to disappear and identify them as the obscured vehicles.

[0210] Obtain the target radar trajectory data of the vehicle in front of the obscured vehicle (the target vehicle).

[0211] If both the obscured vehicle and the target vehicle are motor vehicles, the target vehicle exists within the sixth distance in front of the obscured vehicle, the target radar trajectory data corresponding to the obscured vehicle does not show a tendency to change lanes outward, there are no similar trajectories in the vicinity, and the target radar trajectory corresponding to the obscured vehicle disappears when the distance between the obscured vehicle and the target vehicle is less than the third distance threshold, then the tail-end queuing of the obscured vehicle can be simulated.

[0212] For example, a simulated queuing flag can be set for the target radar trajectory data of the obscured vehicle to prevent the target radar trajectory data of the obscured vehicle from disappearing. The simulated queuing target can be normally associated with the trajectory target.

[0213] When the distance between the obscured vehicle and the target vehicle reaches the minimum distance threshold, the speed of the obscured vehicle can be reduced.

[0214] When the distance between the obscured vehicle and the target vehicle reaches the maximum distance threshold, positive acceleration can be provided to the obscured vehicle to increase its speed.

[0215] When the distance between the obscured vehicle and the following vehicle reaches the minimum distance threshold, positive acceleration can be provided to the obscured vehicle to increase its speed.

[0216] The distance between the obscured vehicle and the vehicle behind it is such that the speed of the obscured vehicle is reduced.

[0217] In some embodiments, if the speed of the first queue of vehicles behind the target vehicle in the horizontal direction is relatively high, the first queue of vehicles may not be required to undergo simulated queuing.

[0218] After obtaining the original driving speed of the obscured vehicle, a simulated queuing process can be performed on the obscured vehicle based on the original driving speed.

[0219] In some embodiments, simulating queuing for obscured vehicles based on their original driving speed may include:

[0220] The original driving speed is used as the initial speed; and the detection gate corresponding to the simulated queuing target of the obscured vehicle is magnified to obtain the target gate corresponding to the simulated queuing target; the target gate is used to associate the obscured vehicle with the simulated queuing target when the obscured vehicle changes lanes.

[0221] Simulated queuing processing of obscured vehicles is performed based on the target gate and initial velocity.

[0222] In this embodiment, the detection gate is used to determine the area that the radar needs to detect. For example, once the detection gate is determined, the radar only needs to detect the targets included in the detection gate corresponding to the radar.

[0223] During the process of simulating queuing of obscured vehicles, the detection gate corresponding to the simulated queuing target can be enlarged, that is, the gate range of the radar can be expanded to obtain the target gate.

[0224] The gate interval corresponding to the target gate is larger than the gate interval corresponding to the detection gate.

[0225] When a vehicle whose lane has been blocked changes lanes, the radar can detect it based on the target gate. Once the radar detects the blocked vehicle again, it can be accurately associated with the simulated queue target.

[0226] In actual execution, there is a first queue of vehicles behind the target vehicle that is relatively stable and has no tendency to change lanes outward. When the first queue of vehicles approaches the target vehicle, the target radar trajectory data corresponding to the first queue of vehicles disappears, and there are no similar trajectories in the vicinity. The original driving speed of the first queue of vehicles is obtained and used as the initial speed. The vehicle type retains the trajectory type before the target radar trajectory data corresponding to the first queue of vehicles disappeared.

[0227] Simultaneously, the detection gate corresponding to the simulated queuing target can be expanded to obtain the target gate.

[0228] Then, based on the initial velocity and the target gate, the tail of the first queue of vehicles (the obscured vehicles) is simulated and queued. Then, standard simulation queuing can be used to ensure that the trajectory can be operated normally.

[0229] In some embodiments, when traversing the target radar trajectory data corresponding to the target vehicle, it is also possible to query all simulated queuing trajectory data behind the target vehicle.

[0230] If, at a given historical moment, there is a lane-changing or turning trajectory near the simulated queuing trajectory data, simulated queuing targets with a similarity greater than the target similarity threshold can be deleted.

[0231] The target similarity threshold can be 98% or 99%, etc., and can be user-defined; this application does not impose any restrictions.

[0232] In this application, in addition to increasing the detection gate in the horizontal direction corresponding to the simulated queuing target, when there is a lane change and turning trajectory near the simulated queuing trajectory data behind the target vehicle, the simulated queuing target closest to the lane change and turning trajectory is deleted, thus preventing the situation of multiple detections of targets due to vehicle lane changes when queuing the obscured vehicle.

[0233] According to the vehicle queuing state simulation method provided in the embodiments of this application, based on the actual driving state of the large vehicle and the queuing situation of the vehicles behind the large vehicle, different queuing simulation methods are selected to simulate the queuing of the obscured vehicles. This method considers various vehicle obstruction situations, improves the accuracy and precision of the queuing state simulation results corresponding to the obscured vehicles, broadens the applicable scenarios, and improves the flexibility of the method.

[0234] The vehicle queuing state simulation device provided in this application is described below. The vehicle queuing state simulation device described below can be referred to in correspondence with the vehicle queuing state simulation method described above.

[0235] The vehicle queuing state simulation method provided in this application can be executed by a vehicle queuing state simulation device. This application uses the vehicle queuing state simulation device executing the vehicle queuing state simulation method as an example to illustrate the vehicle queuing state simulation device provided in this application.

[0236] This application also provides a vehicle queuing state simulation device.

[0237] like Figure 2 As shown, the vehicle queuing state simulation device includes: a first processing module 210, a second processing module 220 and a third processing module 230.

[0238] The first processing module 210 is used to fuse radar data and video data corresponding to at least one first queued vehicle between the starting position and the target intersection to obtain target radar-visual trajectory data.

[0239] The second processing module 220 is used to determine at least one obscured vehicle in the first queue of vehicles and the target vehicle that obscures the obscured vehicle based on the target radar trajectory data.

[0240] The third processing module 230 is used to simulate queuing processing of the obscured vehicle based on at least one of the following: the actual driving state of the target vehicle, the first distance between the target vehicle and the first vehicle behind the target vehicle, and the queuing situation of the corresponding vehicles behind the target vehicle; the first vehicle is the first vehicle in at least one first queue of vehicles other than the target vehicle.

[0241] According to the vehicle queuing state simulation device provided in this application embodiment, the radar data and video data of the first queued vehicles are fused to obtain the target radar trajectory corresponding to the motor vehicle. After eliminating the interference of non-motorized vehicles at the intersection, the device can also simulate the queuing of the obscured vehicles based on at least one of the actual driving state of the target vehicle, the first distance between the target vehicle and the first vehicle, and the queuing situation of the vehicles behind the target vehicle. This simulates the obscured vehicles and restores the current intersection state, ensuring that the trajectory data can be associated when the radar detects vehicles again. The detection results are relatively stable, which enables accurate detection of traffic conditions at intersections even in complex road environments. The device has a wide range of applicable scenarios and high detection accuracy, solving the problem of reduced accuracy of traffic condition detection results due to large vehicles obstructing traffic in complex road conditions.

[0242] In some embodiments, the third processing module 230 can also be used for:

[0243] Based on the target vehicle's target radar trajectory data, it is determined that the target vehicle has been in a stopped state, the first distance is greater than the first distance threshold, there is a second queue of vehicles behind the target vehicle, the second queue of vehicles is not stationary, and the second distance between the target vehicle and the stop line corresponding to the target intersection is less than the second distance threshold. Then, a third distance is generated between the simulated queue target and the target vehicle based on the road condition information corresponding to the target intersection. The simulated queue target is a simulated vehicle generated after simulating the queuing of the obscured vehicles. The road condition information includes the obscured area corresponding to the obscured vehicle.

[0244] Simulated queuing processing of obscured vehicles is performed based on the third distance.

[0245] In some embodiments, the third processing module 230 can also be used for:

[0246] When the target vehicle is stationary, there are no vehicles within a fourth distance behind the target vehicle, and there are vehicles beyond a fifth distance that are stationary, simulated queuing is performed on the obscured vehicles based on the fifth distance.

[0247] In some embodiments, the third processing module 230 can also be used for:

[0248] If the target vehicle is stationary or the target vehicle has not been stopped based on the target radar trajectory data corresponding to the target vehicle, and the target radar trajectory data corresponding to the obscured vehicle disappears when the first distance is less than the third distance threshold, the original driving speed of the obscured vehicle is obtained; the original driving speed is the driving speed of the obscured vehicle when the first distance is not less than the third distance threshold.

[0249] Based on the original driving speed, simulated queuing is performed on the obscured vehicles.

[0250] In some embodiments, the third processing module 230 can also be used for:

[0251] The original driving speed is used as the initial speed; and the detection gate corresponding to the simulated queuing target of the obscured vehicle is magnified to obtain the target gate corresponding to the simulated queuing target; the target gate is used to associate the obscured vehicle with the simulated queuing target when the obscured vehicle changes lanes.

[0252] Simulated queuing processing of obscured vehicles is performed based on the target gate and initial velocity.

[0253] In some embodiments, the vehicle queuing state simulation device may further include a fourth processing module, which is used to obtain initial radar data and initial video data corresponding to at least one first queuing vehicle between the starting position and the target intersection before performing fusion processing on radar data and video data corresponding to at least one first queuing vehicle between the starting position and the target intersection to obtain target radar-visual trajectory data.

[0254] The initial radar data and initial video data are converted to the same coordinate system to obtain radar data and video data.

[0255] In some embodiments, the second processing module 220 may also be used for:

[0256] If the target radar trajectory data disappears, the duration of the target radar trajectory data exceeds the first duration threshold, and there is a target vehicle in front of the first queue of vehicles corresponding to the target radar trajectory data, the first queue of vehicles is identified as the obscured vehicle.

[0257] The vehicle queuing state simulation device in this application embodiment can be an electronic device or a component of an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be a server, network attached storage (NAS), personal computer (PC), television set (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the device.

[0258] The vehicle queuing status simulation device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.

[0259] The vehicle queuing state simulation device provided in this application embodiment can achieve... Figure 1The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0260] In some embodiments, such as Figure 3 As shown, this application embodiment also provides an electronic device 300, including a processor 301, a memory 302, and a computer program stored in the memory 302 and executable on the processor 301. When the program is executed by the processor 301, it implements the various processes of the above-described vehicle queuing state simulation method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0261] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0262] On the other hand, this application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the various processes of the above-described vehicle queuing state simulation method embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0263] In another aspect, this application also provides a non-transitory computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the various processes of the above-described vehicle queuing state simulation method embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0264] On another note, this application also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-described vehicle queuing state simulation method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0265] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0266] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0267] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0268] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for simulating vehicle queuing status, characterized in that, include: The radar data and video data corresponding to at least one first queued vehicle between the starting position and the target intersection are fused to obtain the target radar-visual trajectory data. Based on the target radar trajectory data, determining the obscured vehicle and the target vehicle obscuring the obscured vehicle in the at least one first queue of vehicles includes: when the target radar trajectory data disappears, the duration of the existence of the target radar trajectory data is greater than a first duration threshold, and the target vehicle is in front of the first queue of vehicles corresponding to the target radar trajectory data, determining the first queue of vehicles as the obscured vehicle. Based on at least one of the following: the actual driving state of the target vehicle, the first distance between the target vehicle and a first vehicle behind it, and the queuing situation of the vehicles behind the target vehicle, a simulated queuing process is performed on the obscured vehicle; the first vehicle is the first vehicle in the at least one first queue of vehicles other than the target vehicle, including: when it is determined based on the target radar trajectory data corresponding to the target vehicle that the target vehicle has been in a stopped state, the first distance is greater than a first distance threshold, there is a second queue of vehicles behind the target vehicle of the target number, the second queue of vehicles is in a non-stationary state, and the second distance between the target vehicle and the stop line corresponding to the target intersection is less than a second distance threshold, a third distance between the simulated queuing target and the target vehicle is generated based on the road condition information corresponding to the target intersection; the simulated queuing target is a simulated vehicle generated after performing simulated queuing processing on the obscured vehicle; the road condition information includes the obscured area corresponding to the obscured vehicle; and the simulated queuing processing is performed on the obscured vehicle based on the third distance.

2. The vehicle queuing state simulation method according to claim 1, characterized in that, The step of simulating queuing processing for the obscured vehicle based on at least one of the following: the actual driving state of the target vehicle, the first distance between the target vehicle and the first vehicle behind the target vehicle, and the queuing situation of the vehicles behind the target vehicle, further includes: When the target vehicle is stationary, there are no vehicles within a fourth distance behind the target vehicle, and there are vehicles beyond a fifth distance, and the vehicle is stationary, simulated queuing is performed on the obscured vehicle based on the fifth distance.

3. The vehicle queuing state simulation method according to claim 1 or 2, characterized in that, The step of simulating queuing for the obscured vehicle based on at least one of the following: the actual driving state of the target vehicle, the first distance between the target vehicle and the first vehicle behind it, and the queuing situation of the vehicles behind the target vehicle, includes: When the target vehicle is stationary or when the target vehicle has not been stopped based on the target radar trajectory data, and when the first distance is less than the third distance threshold and the target radar trajectory data of the obscured vehicle disappears, the original driving speed of the obscured vehicle is obtained; the original driving speed is the driving speed of the obscured vehicle when the first distance is not less than the third distance threshold. Based on the original driving speed, simulated queuing is performed on the obscured vehicles.

4. The vehicle queuing state simulation method according to claim 3, characterized in that, The simulated queuing process for the obscured vehicles based on the original driving speed includes: The original driving speed is used as the initial speed; and the detection gate corresponding to the simulated queuing target corresponding to the obscured vehicle is magnified to obtain the target gate corresponding to the simulated queuing target; the target gate is used to associate the obscured vehicle with the simulated queuing target when the obscured vehicle changes lanes; Based on the target gate and the initial velocity, simulated queuing is performed on the blocked vehicles.

5. The vehicle queuing state simulation method according to claim 1 or 2, characterized in that, Before fusing radar data and video data corresponding to at least one first queued vehicle between the starting position and the target intersection to obtain target radar-visual trajectory data, the method further includes: Acquire initial radar data and initial video data corresponding to at least one first queued vehicle between the starting position and the target intersection; The initial radar data and the initial video data are converted to the same coordinate system to obtain the radar data and the video data.

6. A vehicle queuing state simulation device, characterized in that, include: The first processing module is used to fuse radar data and video data corresponding to at least one first queued vehicle between the starting position and the target intersection to obtain target radar-visual trajectory data. The second processing module is used to determine, based on the target radar trajectory data, the obscured vehicle and the target vehicle obscuring the obscured vehicle in the at least one first queue of vehicles, including: when the target radar trajectory data disappears, the duration of the existence of the target radar trajectory data is greater than a first duration threshold, and the target vehicle is in front of the first queue of vehicles corresponding to the target radar trajectory data, the first queue of vehicles is determined as the obscured vehicle. The third processing module is used to simulate queuing for the obscured vehicle based on at least one of the following: the actual driving state of the target vehicle, a first distance between the target vehicle and a first vehicle behind it, and the queuing situation of the vehicles behind the target vehicle. The first vehicle is the first vehicle in the at least one first queue of vehicles other than the target vehicle. The process includes: if, based on target radar trajectory data corresponding to the target vehicle, it is determined that the target vehicle has been in a stopped state, the first distance is greater than a first distance threshold, there is a target number of second queued vehicles behind the target vehicle, the second queued vehicles are not stationary, and the second distance between the target vehicle and the stop line corresponding to the target intersection is less than a second distance threshold, a third distance is generated between the simulated queuing target and the target vehicle based on the road condition information corresponding to the target intersection. The simulated queuing target is a simulated vehicle generated after simulating queuing for the obscured vehicle. The road condition information includes the obscured area corresponding to the obscured vehicle. The simulated queuing is then performed on the obscured vehicle based on the third distance.

7. The vehicle queuing state simulation device according to claim 6, characterized in that, The third processing module is also used for: When the target vehicle is stationary, there are no vehicles within a fourth distance behind the target vehicle, and there are vehicles beyond a fifth distance, and the vehicle is stationary, simulated queuing is performed on the obscured vehicle based on the fifth distance.

8. The vehicle queuing state simulation device according to claim 6, characterized in that, The third processing module is also used for: When the target vehicle is stationary or when it is determined from the target radar trajectory data corresponding to the target vehicle that the target vehicle has never stopped, and when the first distance is less than the third distance threshold and the target radar trajectory data corresponding to the obscured vehicle disappears, the original driving speed of the obscured vehicle is obtained. The original driving speed is the driving speed of the obscured vehicle when the first distance is not less than the third distance threshold. Based on the original driving speed, simulated queuing is performed on the obscured vehicles.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the vehicle queuing state simulation method as described in any one of claims 1-5.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the vehicle queuing state simulation method as described in any one of claims 1-5.

Images