A trajectory prediction method, system, and related equipment based on traffic flow detection
The trajectory prediction method based on traffic flow detection uses traffic flow information to simulate and detect road areas, solving the problems of inaccurate speed and direction and low efficiency in the prediction of new trajectories, and achieving more accurate and efficient trajectory prediction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- JIANGSU HIRAIN AUTOMOTIVE ELECTRONICS CO LTD
- Filing Date
- 2025-08-08
- Publication Date
- 2026-07-31
AI Technical Summary
Existing methods for predicting new flight paths are inaccurate in calculating velocity direction under extended target and zero Doppler conditions, and the prediction speed is slow when the number of frames is small, resulting in low accuracy and efficiency in flight path prediction. Outliers are also prone to occur when high point cloud azimuth accuracy is required.
Traffic flow is determined by a preset judgment method and the current target's heading. If the traffic flow judgment result meets the preset conditions, the direction and area of traffic flow formed by moving targets in the road area at the current moment are simulated, the speed and direction of the new trajectory are predicted, and the traffic flow information is used to simulate and detect the road area.
This effectively avoids the impact of extended targets and zero Doppler conditions on the velocity estimation of new paths, thus improving the accuracy and efficiency of new path prediction.
Smart Images
Figure CN120913398B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of data processing technology for road traffic detection, and more specifically, to a trajectory prediction method, system and related equipment based on traffic detection. Background Technology
[0002] New trajectory prediction is a prediction method used to estimate the velocity and direction of a target. Existing new trajectory prediction generally uses two methods: one is to perform difference or fitting on the target's position in the previous few frames and calculate the velocity and direction from the difference or fitting results; the other is to calculate the velocity and direction from the points detected on the target, thereby completing the new trajectory prediction.
[0003] The first prediction method described above cannot calculate the velocity direction for extended targets and has a limited number of frames, resulting in inaccurate velocity direction calculations. However, using a larger number of frames for differencing or fitting leads to slower prediction speeds, resulting in low accuracy and efficiency in trajectory prediction. The second prediction method requires high accuracy in the point cloud azimuth angle and is prone to outliers when calculating velocity for targets with large slant ranges or small azimuth angles, further contributing to low accuracy in trajectory prediction.
[0004] Therefore, how to improve the accuracy and efficiency of new trajectory prediction is a problem that this application urgently needs to solve. Summary of the Invention
[0005] In view of this, this application discloses a trajectory prediction method, system and related equipment based on traffic flow detection, aiming to improve the accuracy and efficiency of new trajectory prediction.
[0006] To achieve the above objectives, the disclosed technical solution is as follows:
[0007] The first aspect of this application discloses a trajectory prediction method based on traffic flow detection, the method comprising:
[0008] Identify the current target present in the current driving environment and determine the current target's heading;
[0009] Traffic flow is determined by a preset judgment method and the current target's heading, and the traffic flow judgment result is obtained.
[0010] If the traffic flow determination result meets the preset conditions, a new road for the current target is obtained; wherein, the new road is a road whose traffic flow direction is inconsistent with the road direction at the current moment;
[0011] The road area corresponding to the newly created road at the current moment is simulated using a preset simulation method;
[0012] The process of predicting the target speed and target direction of the current target within the road area at the current moment is completed.
[0013] Preferably, determining the current target present in the current driving environment and determining the current target's heading includes:
[0014] Globally search for current targets in the current driving environment;
[0015] The heading of the current target is calculated according to a preset number of directions.
[0016] Preferably, the step of determining traffic flow using a preset judgment method and the current target's heading to obtain a traffic flow judgment result includes:
[0017] Count the number of all vehicles on the current target's course;
[0018] Determine the percentage of vehicles traveling in the same direction among all vehicles heading towards the current target.
[0019] Traffic flow is determined by the proportion of vehicles traveling in the same direction among all vehicles heading towards the current target.
[0020] Preferably, if the traffic flow determination result meets preset conditions, obtaining the new road for the current target includes:
[0021] If the proportion of vehicles traveling in the same direction among all vehicles in the current target's heading is greater than or equal to a preset proportion, the traffic flow judgment result indicates that traffic flow information exists.
[0022] If the traffic flow assessment result indicates the existence of traffic flow information and there is no road with the same heading as the current target, then the traffic flow assessment result is determined to meet the preset conditions.
[0023] Under the condition that the traffic flow judgment result meets the preset conditions, the direction and area of the traffic flow formed by moving targets in the road area at the current moment are simulated;
[0024] Based on the direction and area of traffic flow formed by moving targets in the road area at the current moment, the new road for the current target is obtained.
[0025] Preferred options also include:
[0026] If the proportion of vehicles traveling in the same direction among all vehicles heading towards the current target is less than the preset proportion, the traffic flow judgment result indicates that there is no traffic flow information.
[0027] Preferably, the step of simulating the road region corresponding to the newly created road at the current moment through a preset simulation method includes:
[0028] Obtain traffic flow information in the current driving environment, the road area at the previous moment, and the traffic flow information at the current moment;
[0029] The road heading of the newly built road is filtered and corrected using traffic flow information in the current driving environment;
[0030] By using the road area from the previous moment and the traffic flow information from the current moment, the road heading of the newly created road after filtering and correction is adjusted to complete the simulation of the road area corresponding to the newly created road at the current moment.
[0031] Preferably, the process of predicting the target speed and target direction of the current target within the road area at the current time to complete the trajectory prediction includes:
[0032] Obtain the road area heading, the Doppler velocity of the current target, and the azimuth of the current target within the road area at the current moment;
[0033] Calculate the cosine of the angle between the Doppler velocity direction of the current target and the heading of the road area within the road area at the current moment, using the Doppler velocity and azimuth of the current target.
[0034] Calculate the absolute value of the current target's velocity based on the cosine value of the included angle;
[0035] The target velocity and target direction of the current target are calculated based on the absolute value of the current target's velocity to complete the trajectory prediction process.
[0036] A second aspect of this application discloses a trajectory prediction system based on traffic flow detection, the system comprising:
[0037] The first determining unit is used to determine the current target existing in the current driving environment and to determine the heading of the current target;
[0038] The traffic flow judgment unit is used to judge the traffic flow through a preset judgment method and the heading of the current target, and obtain the traffic flow judgment result;
[0039] The acquisition unit is used to obtain the newly created road of the current target if the traffic flow judgment result meets the preset conditions; wherein the newly created road is a road whose traffic flow direction is inconsistent with the road direction at the current moment;
[0040] The simulation unit is used to simulate the road area corresponding to the newly created road at the current moment using a preset simulation method;
[0041] The prediction unit is used to predict the target speed and target direction of the current target within the road area at the current time, in order to complete the trajectory prediction process.
[0042] A third aspect of this application discloses a storage medium comprising stored instructions, wherein, when the instructions are executed, the device in which the storage medium is located executes the trajectory prediction method based on traffic flow detection as described in any one of the first aspects.
[0043] The fourth aspect of this application discloses an electronic device including a memory and one or more instructions, wherein one or more instructions are stored in the memory and configured to be executed by one or more processors as described in any of the first aspects of the trajectory prediction method based on traffic flow detection.
[0044] As can be seen from the above technical solution, this application discloses a trajectory prediction method, system and related equipment based on traffic flow detection. It determines the current target existing in the current driving environment and the heading of the current target. Traffic flow judgment is performed by using a preset judgment method and the heading of the current target to obtain the traffic flow judgment result. If the traffic flow judgment result meets the preset conditions, a new road for the current target is obtained. The new road is a road where the traffic flow heading is inconsistent with the road heading at the current moment. The road area corresponding to the new road at the current moment is simulated by a preset simulation method, and the target speed and target direction of the current target in the road area at the current moment are predicted to complete the trajectory prediction process.
[0045] The above scheme uses a preset judgment method and the current target's heading to determine traffic flow. If the traffic flow judgment result meets the preset conditions, it simulates the direction and area of traffic flow formed by moving targets in the road area at the current moment, so as to predict the speed direction of the new trajectory. This scheme can effectively avoid the influence of extended targets and zero Doppler cases on the speed estimation of the new trajectory, and accurately estimate the speed of the new trajectory in the road area, thereby achieving the goal of improving the accuracy and efficiency of new trajectory prediction. Attached Figure Description
[0046] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0047] Figure 1 This is a flowchart illustrating a trajectory prediction method based on traffic flow detection disclosed in an embodiment of this application;
[0048] Figure 2 This is a schematic diagram showing the directional distribution of the preset quantity disclosed in the embodiments of this application;
[0049] Figure 3This is a schematic diagram of the maximum connected region disclosed in an embodiment of this application;
[0050] Figure 4 This is a schematic diagram simulating the road area and heading at this moment, as disclosed in the embodiments of this application;
[0051] Figure 5 This is a schematic diagram of the structure of a trajectory prediction system based on traffic flow detection disclosed in an embodiment of this application;
[0052] Figure 6 This is a schematic diagram of the structure of the electronic device disclosed in the embodiments of this application. Detailed Implementation
[0053] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0054] In this application, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
[0055] As the background technology shows, existing technologies cannot calculate the velocity direction for extended targets and have a limited number of frames, resulting in inaccurate velocity direction calculations. However, using more frames for differencing or fitting leads to slower prediction speeds, resulting in low accuracy and efficiency in trajectory prediction. Furthermore, existing technologies require high accuracy in point cloud azimuth angles, and velocity calculations for targets with large slant ranges or small azimuth angles are prone to outliers, further reducing trajectory prediction accuracy. Therefore, improving the accuracy and efficiency of new trajectory prediction is a problem that this application urgently needs to solve.
[0056] To address the aforementioned issues, this application discloses a trajectory prediction method, system, and related equipment based on traffic flow detection. Traffic flow is determined using a preset judgment method and the current target's heading. If the traffic flow judgment result meets preset conditions, the direction and area of traffic flow formed by moving targets in the road region at the current moment are simulated to predict the velocity direction of newly generated trajectories. This solution effectively avoids the influence of extended targets and zero Doppler conditions on the velocity estimation of newly generated trajectories. It effectively utilizes traffic flow information to simulate road regions and detect road headings, accurately estimating the velocity of newly generated trajectories within the road region, thereby improving the accuracy and efficiency of newly generated trajectory prediction. Specific implementation methods are described in detail through the following embodiments.
[0057] refer to Figure 1 The image shows a trajectory prediction method based on traffic flow detection disclosed in this application. This method mainly includes the following steps:
[0058] S101: Determine the current target present in the current driving environment and determine the heading of the current target.
[0059] In S101, a global search is performed on the current targets existing in the current driving environment (the number of current targets can be multiple), and the headings of the current targets are counted according to a preset number of directions.
[0060] The system performs a global search for existing targets, dividing them into a preset number of directions (e.g., eight directions, dividing 0-180° into eight directions) and calculating the heading of the current target. A diagram illustrating the eight directions is shown below. Figure 2 As shown.
[0061] Figure 2 In the equation, the unit vectors in the eight directions are: (cos(22.5*(i-1)), sin(22.5*(i-1)))(i=1, 2, ..., 8)).
[0062] S102: Traffic flow is determined by a preset judgment method and the current target's heading, and the traffic flow judgment result is obtained.
[0063] The specific process of determining traffic flow using a preset judgment method and the current target's heading, and obtaining the traffic flow judgment result, is shown in A1-A3.
[0064] A1: Count the number of all vehicles on the current target's course.
[0065] A2: Determine the percentage of vehicles traveling on the same heading among all vehicles heading towards the current target.
[0066] A3: Traffic flow is determined based on the proportion of vehicles traveling in the same direction among all vehicles on the current target's heading, and the traffic flow determination result is obtained.
[0067] In A3, traffic flow is determined based on the proportion of vehicles traveling in the same direction among all vehicles on the current target's heading, as well as a preset ratio, to obtain the traffic flow determination result.
[0068] The preset ratio can be set according to the actual situation, and this application does not impose specific limitations.
[0069] S103: If the traffic flow judgment result meets the preset conditions, the new road of the current target is obtained; wherein, the new road is the road whose traffic flow direction is inconsistent with the road direction at the current moment.
[0070] The preset conditions are the conditions required for the generation of new roads.
[0071] Specifically, if the traffic flow judgment result meets the preset conditions, the process of obtaining the new road for the current target is shown in B1-B3.
[0072] B1: If the proportion of vehicles traveling in the same direction among all vehicles on the current target's course is greater than or equal to a preset proportion, the traffic flow judgment result indicates that traffic flow information exists.
[0073] Among them, traffic flow information refers to the main driving direction and driving area of moving targets in the confirmed driving environment.
[0074] If the proportion of vehicles traveling in the same direction relative to the current target is greater than or equal to a preset ratio, it indicates that there is traffic flow at this moment. For example, if there are 10 moving vehicles in the driving environment, with a preset ratio of 0.6, and 8 of them are traveling in direction 4, the ratio between these 8 and 10 vehicles is 0.8, which is greater than the preset ratio of 0.6. This indicates that there is traffic flow at this moment, and the other 2 moving vehicles are traveling in other directions. Therefore, the direction of the surrounding traffic flow is considered to be direction 4.
[0075] If the proportion of vehicles traveling in the same direction among all vehicles on the current target's course is less than a preset proportion, the traffic flow assessment result indicates that there is no traffic flow information.
[0076] For example, if there are 6 moving vehicles in the driving environment, with a preset ratio of 0.6, and 3 of these moving vehicles are traveling along direction 4, the ratio between the 3 moving vehicles traveling along direction 4 and the 10 moving vehicles is 0.5, which is less than the preset ratio of 0.6. Therefore, the traffic flow judgment result indicates that there is no traffic flow information.
[0077] B2: If the traffic flow judgment result indicates that there is traffic flow information and there is no road with the same heading as the current target, the traffic flow judgment result is determined to meet the preset conditions.
[0078] If the traffic flow assessment result indicates the existence of traffic flow information, but there is no road with the same heading as the current target, then a new road is created. The origin of the road's coordinate system is initialized to the origin of the radar coordinate system, and the road's heading is the traffic flow heading (i.e., the y-axis of the road coordinate system).
[0079] If the traffic flow assessment result indicates the existence of traffic flow information, then roads with the same traffic flow direction can continue to exist, while roads with other directions will disappear.
[0080] B3: If the traffic flow judgment result meets the preset conditions, obtain the new road for the current target.
[0081] S104: Simulate the road area corresponding to the newly created road at the current moment through a preset simulation method.
[0082] The preset simulation method is used to simulate the road area at the current moment. It needs to combine traffic flow information, that is, the driving area where the current target vehicle is traveling in the same direction and the main driving direction of the target in the corresponding area, to filter or correct the road heading. At the same time, it needs to combine the road area at the previous moment and the traffic flow information at the current moment to simulate the road area at the current moment.
[0083] The process of simulating the road region corresponding to the newly created road at the current moment can be found in [reference needed]. Figure 3 As shown.
[0084] Figure 3 In the diagram, P0 represents the road region at the previous time step; P i Let Q be the projection interval; Q is the maximum connected interval, which is the expanded road region, as shown in the figure. Figure 4 As shown.
[0085] Filtering or correcting road heading is done based on the main driving direction and driving area of the moving target in the driving environment. Within that driving area, when predicting the target heading, the main driving direction can be referenced for correction.
[0086] Specifically, the process of simulating the road area corresponding to the newly created road at the current moment is achieved through a preset simulation method, as shown in C1-C3.
[0087] C1: Obtain traffic flow information in the current driving environment (heading of traffic flow, position information of all targets in traffic flow (horizontal coordinate x, vertical coordinate y)), the road area at the previous moment, and traffic flow information at the current moment.
[0088] When calculating the current road area, the heading of the traffic flow and the position information of all targets in the traffic flow (horizontal coordinate x, vertical coordinate y) are first obtained. The above information can be statistically analyzed in the process of determining the current targets existing in the current driving environment.
[0089] Then obtain the origin of the road region's coordinates at the previous moment, the unit vector along the y-axis (and the main heading of the road region). The process of obtaining the origin of the road region coordinates at the previous moment and the unit vector in the y-axis direction is updated during the process of simulating the road region corresponding to the newly created road at the current moment through a preset simulation method, and the following steps (1) to (4) are executed:
[0090] (1) Traverse all targets in the traffic flow and calculate the distance vector between the current target and the origin of the road area coordinate system. On the road heading Projection a on i This yields the set of projected values A;
[0091] (2) Combining the road region P0=[x_min,x_max] from the previous moment with the a in the set A obtained above, the projection interval is extended. i Each traffic flow target can have its projection interval P obtained based on the threshold Thes. i =[a i -Thes, a i Given [+Thes], i=1, ...,n, find P. i The maximum connected interval of (i=0,…,n) is used as the horizontal range of the road region at the current moment;
[0092] Among them, the threshold Thes is a constant threshold setting in the algorithm, and the setting of Thes is determined through debugging experience.
[0093] The following is a schematic diagram illustrating the maximum connected region in the lateral direction of the road area at the current moment, calculated in detail:
[0094] Calculate the projection of the moving target onto the road heading, and calculate the maximum connected interval between the lateral range of the road area and the projection interval at the previous moment.
[0095] (3) Traverse all targets in the traffic flow and calculate the distance vector between the target and the origin of the radar coordinate system. In the vertical main heading Projection b in the direction i This yields the set of projected values, B.
[0096] (4) Combining the road region P0=[y at the previous moment] min y max [and the current motion target and b in the set B obtained above]i The road area is extended by projection interval, and the projection interval P for each traffic flow target can be obtained based on the threshold Thes. i =[b i -Thes, b i Given [+Thes], i=1, ...,n, find P. i The maximum connected interval Q of (i=0,…,n) is used as the longitudinal range of the road region at the current time, and Q is the expanded road region.
[0097] The maximum connected interval of the longitudinal range of the road area at the current moment is as follows:
[0098] Calculate the projection of the moving target in the direction perpendicular to the road heading, and calculate the maximum connected interval between the longitudinal range of the road area and the projection interval at the previous moment.
[0099] C2: Filter and correct the road heading of the newly built road using traffic flow information in the current driving environment.
[0100] C3: By using the road area from the previous moment and the traffic flow information from the current moment, the road direction of the newly created road after filtering and correction is adjusted to complete the simulation of the road area corresponding to the newly created road at the current moment.
[0101] In C3, the road region with the current heading is maintained based on information such as the current vehicle speed and the current yaw rate. That is, the road region of the newly created road is adjusted and corrected based on the vehicle speed and yaw rate, which simulates the road region at the current moment.
[0102] The traffic flow information at the current moment includes at least the vehicle speed and the YawRate information at the current moment.
[0103] The road region for maintaining the current heading is maintained based on vehicle speed and YawRate information. Maintaining the road region for heading is used to keep the traffic flow area in an accurate relative position according to the vehicle's movement and rotation. The specific process of maintaining the road region for heading is as follows:
[0104] 1. Place the origin of the road coordinate system at the center of the road area;
[0105] 2. Rotate the origin and heading of the road area based on vehicle speed and YawRate information.
[0106] S105: Predict the target speed and target direction of the current target within the road area at the current moment to complete the trajectory prediction process.
[0107] Specifically, the target speed and direction of the current target within the road area at the current moment are predicted to complete the trajectory prediction process, as shown in D1-D4.
[0108] D1: Obtain the road area heading, Doppler velocity of the current target, and azimuth of the current target within the road area at the current moment.
[0109] The road area heading is represented by [a, b]; the current target's Doppler velocity is represented by v. d This indicates that the Doppler velocity of the current target is the radial component of the current target's velocity relative to the radar; the azimuth angle of the current target is represented by θ.
[0110] For newly generated tracks within the road area, the road area is simulated using the road heading and initial target speed. That is, the default initial target is used to verify the traffic flow direction, and the initial speed of the target is assigned a value.
[0111] D2: Calculate the cosine of the angle between the Doppler velocity direction of the current target and the heading of the road area within the road area at the current moment, using the Doppler velocity and azimuth of the current target.
[0112] In D2, calculate the cosine of the angle between the Doppler velocity and direction of the current target and the heading of the road area within the road area at the current moment, cos(α).
[0113] The formula for calculating the cosine of the angle between the headings in a specific road area, cos(α), is shown in formula (1).
[0114] cos(α)=sinθ*a+cosθ*b(1)
[0115] Where a and b are the headings in the road area; θ is the azimuth of the current target.
[0116] D3: Calculate the absolute value of the current target's velocity based on the cosine of the included angle.
[0117] The absolute value of the current target's velocity is calculated based on the cosine of the included angle, as shown in formula (2).
[0118] absV=v d / cos(α)(2)
[0119] Where absV is the absolute value of the current target's velocity; v d α is the Doppler velocity of the current target; cos(α) is the cosine of the angle between the headings in the road area and the target.
[0120] D4: Calculate the target speed and target direction of the current target based on the absolute value of the current target's speed to complete the trajectory prediction process.
[0121] The road area is simulated based on the initial target speed of the road heading, that is, the default starting target verifies the traffic flow direction and assigns an initial speed to the target.
[0122] The formulas for calculating the target velocity of the current target are shown in formulas (3) and (4).
[0123] V x =a*absV(3)
[0124] V y =b*absV(4)
[0125] Among them, V x V represents the target velocity of the current target in the x-direction. y Let be the target velocity of the current target in the y-direction.
[0126] This application obtains traffic flow based on all target information at the current moment, manages the simulated road based on the traffic flow status, simulates the road at the current moment based on the traffic flow information at the current moment and the simulated road at the previous moment, and assigns a speed to the newly generated track in the road area that is consistent with the direction of the road area based on the simulated road at the current moment, so as to complete the process of simulating the starting track of the road.
[0127] The beneficial effects of this application's embodiments are as follows: Traffic flow is judged by a preset judgment method and the current target's heading. If the traffic flow judgment result meets the preset conditions, the newly formed road of the current target and the road area corresponding to the simulated newly formed road at the current moment are simulated to predict the speed direction of the newly formed track. This solution can effectively avoid the influence of extended targets, zero Doppler cases, etc. on the speed estimation of the newly formed track, effectively utilize traffic flow information to simulate the road area and detect the road heading, and accurately estimate the speed of the newly formed track in the road area, thereby achieving the goal of improving the accuracy and efficiency of the prediction of the newly formed track.
[0128] Based on the above embodiments Figure 1 This application discloses a trajectory prediction method based on traffic flow detection, and also provides a corresponding trajectory prediction system based on traffic flow detection. Figure 5 As shown, the trajectory prediction system based on traffic flow detection includes:
[0129] The first determining unit 501 is used to determine the current target existing in the current driving environment and to determine the heading of the current target;
[0130] The judgment unit 502 is used to judge the traffic flow by using a preset judgment method and the current target's heading, and to obtain the traffic flow judgment result;
[0131] The acquisition unit 503 is used to obtain the new road of the current target if the traffic flow judgment result meets the preset conditions; wherein, the new road is a road whose traffic flow direction is inconsistent with the road direction at the current moment;
[0132] Simulation unit 504 is used to simulate the road area corresponding to the newly created road at the current moment through a preset simulation method;
[0133] The prediction unit 505 is used to predict the target speed and target direction of the current target in the road area at the current moment, so as to complete the trajectory prediction process.
[0134] Furthermore, the first determining unit 501 includes:
[0135] The global search module is used to globally search for current targets in the current driving environment;
[0136] The first statistics module is used to count the heading of the current target according to a preset number of directions.
[0137] Furthermore, the traffic flow determination unit 502 includes:
[0138] The second statistics module is used to count the number of all vehicles heading towards the current target;
[0139] The first determining module is used to determine the proportion of vehicles traveling in the same direction among all vehicles traveling at the current target.
[0140] The traffic flow judgment module is used to judge the traffic flow based on the proportion of vehicles traveling in the same direction among all vehicles in the current target's heading, and obtain the traffic flow judgment result.
[0141] Furthermore, the acquisition unit 503 includes:
[0142] The second determining module is used to determine that if the proportion of vehicles traveling in the same direction among all vehicles in the current target's heading is greater than or equal to a preset proportion, the traffic flow judgment result indicates that traffic flow information exists.
[0143] The third determination module is used to determine that the traffic flow judgment result meets the preset conditions if the traffic flow judgment result indicates that there is traffic flow information and there is no road with the same heading as the current target.
[0144] The first simulation module is used to simulate the direction and area of traffic flow formed by moving targets in the road area at the current moment, provided that the traffic flow judgment result meets the preset conditions.
[0145] The first acquisition module is used to obtain the new road of the current target based on the direction and area of traffic flow formed by moving targets in the road area at the current moment.
[0146] Furthermore, it also includes:
[0147] The second determining unit is used to determine that there is no traffic flow information if the proportion of vehicles traveling in the same direction among all vehicles in the current target's heading is less than a preset proportion.
[0148] Furthermore, the simulation unit 504 includes:
[0149] The second acquisition module is used to acquire traffic flow information in the current driving environment, the road area at the previous moment, and the traffic flow information at the current moment.
[0150] The processing module is used to filter and correct the road heading of the newly built road based on the traffic flow information in the current driving environment;
[0151] The second simulation module is used to adjust the road heading of the newly created road after filtering and correction by using the road area at the previous time and the traffic flow information at the current time, so as to complete the simulation of the road area corresponding to the newly created road at the current time.
[0152] Furthermore, the prediction unit 505 includes:
[0153] The third acquisition module is used to acquire the road area heading, the Doppler velocity of the current target, and the azimuth of the current target within the road area at the current moment;
[0154] The first calculation module is used to calculate the cosine of the angle between the Doppler velocity direction of the current target and the heading of the road area within the road area at the current moment, based on the Doppler velocity of the current target and the azimuth angle of the current target.
[0155] The second calculation module is used to calculate the absolute value of the current target's velocity based on the cosine of the included angle.
[0156] The third calculation module is used to calculate the target speed and target direction of the current target based on the absolute value of the current target's speed, in order to complete the trajectory prediction process.
[0157] The beneficial effects of this application's embodiments are as follows: Traffic flow is judged by a preset judgment method and the current target's heading. If the traffic flow judgment result meets the preset conditions, the direction and area of traffic flow formed by moving targets in the road area at the current moment are simulated to predict the speed direction of the new trajectory. This solution can effectively avoid the influence of extended targets, zero Doppler cases, etc. on the speed estimation of the new trajectory, effectively utilize traffic flow information to simulate the road area and detect the road heading, and accurately estimate the speed of the new trajectory in the road area, thereby achieving the goal of improving the accuracy and efficiency of new trajectory prediction.
[0158] This application embodiment also provides a storage medium, the storage medium including stored instructions, wherein, when the instructions are executed, the device where the storage medium is located is controlled to execute the trajectory prediction method based on traffic flow detection as described above.
[0159] This application also provides an electronic device, the structural schematic diagram of which is shown below. Figure 6 As shown, it specifically includes a memory 601 and one or more instructions 602, wherein one or more instructions 602 are stored in the memory 601 and are configured to be executed by one or more processors 603 to perform the above-mentioned trajectory prediction method based on traffic flow detection.
[0160] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.
[0161] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For system-type embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.
[0162] The steps in the methods of the various embodiments of this application can be adjusted, combined, or deleted according to actual needs.
[0163] Finally, it should be noted that in this paper, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.
[0164] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
[0165] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.
Claims
1. A traffic flow detection based trajectory prediction method, characterized in that, The method includes: Identify the current target present in the current driving environment and determine the current target's heading; Traffic flow is determined by a preset judgment method and the current target's heading, and the traffic flow judgment result is obtained. If the traffic flow determination result meets the preset conditions, a new road for the current target is obtained; wherein, the new road is a road whose traffic flow direction is inconsistent with the road direction at the current moment; The road area corresponding to the newly created road at the current moment is simulated using a preset simulation method; The process of predicting the target speed and target direction of the current target within the road area at the current moment is completed.
2. The method according to claim 1, characterized in that, The process of determining the current target present in the current driving environment and determining the current target's heading includes: Globally search for current targets in the current driving environment; The heading of the current target is calculated according to a preset number of directions.
3. The method of claim 1, wherein, The step of determining traffic flow using a preset judgment method and the current target's heading to obtain traffic flow judgment results includes: Count the number of all vehicles heading towards the current target; Determine the percentage of vehicles traveling in the same direction among all vehicles heading towards the current target. Traffic flow is determined by the proportion of vehicles traveling in the same direction among all vehicles heading towards the current target.
4. The method of claim 3, wherein, If the traffic flow determination result meets the preset conditions, the newly generated road for the current target is obtained, including: If the proportion of vehicles traveling in the same direction among all vehicles in the current target's heading is greater than or equal to a preset proportion, the traffic flow judgment result indicates that traffic flow information exists. If the traffic flow assessment result indicates the existence of traffic flow information and there is no road with the same heading as the current target, then the traffic flow assessment result is determined to meet the preset conditions. Under the condition that the traffic flow judgment result meets the preset conditions, the direction and area of the traffic flow formed by moving targets in the road area at the current moment are simulated; Based on the direction and area of traffic flow formed by moving targets in the road area at the current moment, the new road for the current target is obtained.
5. The method of claim 4, wherein, Also includes: If the proportion of vehicles traveling in the same direction among all vehicles heading towards the current target is less than the preset proportion, the traffic flow judgment result indicates that there is no traffic flow information.
6. The method of claim 1, wherein, The simulation of the road region corresponding to the newly created road at the current moment using a preset simulation method includes: Obtain traffic flow information in the current driving environment, the road area at the previous moment, and the traffic flow information at the current moment; The road heading of the newly built road is filtered and corrected using traffic flow information in the current driving environment; By using the road area from the previous moment and the traffic flow information from the current moment, the road direction of the newly created road after filtering and correction is adjusted to complete the simulation of the road area corresponding to the newly created road at the current moment.
7. The method of claim 1, wherein, The process of predicting the target speed and target direction of the current target within the road area at the current moment to complete the trajectory prediction includes: Obtain the road area heading, the Doppler velocity of the current target, and the azimuth of the current target within the road area at the current moment; Calculate the cosine of the angle between the Doppler velocity direction of the current target and the heading of the road area within the road area at the current moment, using the Doppler velocity and azimuth of the current target. Calculate the absolute value of the current target's velocity based on the cosine value of the included angle; The target velocity and target direction of the current target are calculated based on the absolute value of the current target's velocity to complete the trajectory prediction process.
8. A traffic flow detection based trajectory prediction system, characterized in that, The system includes: The first determining unit is used to determine the current target existing in the current driving environment and to determine the heading of the current target; The traffic flow judgment unit is used to judge the traffic flow through a preset judgment method and the heading of the current target, and obtain the traffic flow judgment result; The acquisition unit is used to obtain the newly created road of the current target if the traffic flow judgment result meets the preset conditions; wherein the newly created road is a road whose traffic flow direction is inconsistent with the road direction at the current moment; The simulation unit is used to simulate the road area corresponding to the newly created road at the current moment using a preset simulation method; The prediction unit is used to predict the target speed and target direction of the current target within the road area at the current time, in order to complete the trajectory prediction process.
9. A storage medium, characterized by The storage medium includes stored instructions, wherein, when the instructions are executed, the device containing the storage medium is controlled to perform the trajectory prediction method based on traffic flow detection as described in any one of claims 1 to 7.
10. An electronic device, comprising: It includes a memory, and one or more instructions, wherein one or more instructions are stored in the memory and configured to be executed by one or more processors as described in any one of claims 1 to 7.