An initial heading angle determination method, apparatus and electronic device

Abstract

The application discloses a method, device and electronic equipment for determining an initial heading angle. The method comprises: when a target vehicle needs to be given an initial heading angle in a lane line free area, acquiring an image grid corresponding to the target vehicle, wherein a road image of the lane line free area is divided into a plurality of image grids, and each image grid has more than one initial heading angle; if the image grid corresponding to the target vehicle has one initial heading angle, taking the one initial heading angle of the image grid as the initial heading angle of the target vehicle; and if the image grid corresponding to the target vehicle has more than two initial heading angles, acquiring a current traffic direction of the lane line free area, and determining the initial heading angle of the target vehicle from the more than two initial heading angles according to the current traffic direction. The technical scheme can quickly and accurately calculate the initial heading angle of a vehicle in a lane line free area.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, and in particular to a method, apparatus and electronic device for determining an initial heading angle. Background Technology

[0002] Currently, roadside tracking typically involves first performing 2D or 3D detection on vehicles and targets on the road. Then, the detection results from different frames are matched and correlated using a tracking matching algorithm. This ensures that the same target in different frames has a globally unique ID, thus achieving target tracking. Based on the target tracking results, the historical trajectory of each tracked target can be obtained. The heading angle of the target in the current frame can be further calculated using the historical trajectory, providing data support for vehicle-side driving decisions and visualization.

[0003] However, the calculation of the heading angle can be inaccurate due to various circumstances. For example, due to abnormal target tracking algorithms, missed detections by detection algorithms, or occlusion, the target may be lost during tracking and cannot be matched when it reappears, thus assigning a new ID to the target. In this case, since the heading angle cannot be calculated, only an initial heading angle can be set. Another example is when the target has just appeared in the camera's field of view. Since there is not enough data to calculate the heading angle, only a default initial heading angle can be set. Or, when the vehicle is stationary, the calculated heading angle is 0 because the historical frame positions are the same when the vehicle is stationary, but it is not actually 0.

[0004] All of these situations can lead to a large deviation between the set heading angle and the actual situation, resulting in the inability to provide accurate data support for the vehicle. At the same time, in 3D display scenarios such as digital twins, the vehicle may appear to suddenly change from a certain driving angle to 0 degrees or suddenly return to the normal angle from a certain default angle, causing the displayed vehicle to appear to be spinning.

[0005] To address the aforementioned issues, some existing technologies calculate the initial heading angle of the target vehicle based on the lane line detection results of the area where the target vehicle is located and the surrounding vehicle situation. For example, when the target vehicle is in an area without lane lines and there are vehicles traveling alongside it, the heading angle of the passing vehicles can be used as the initial heading angle of the target vehicle. However, when there are no vehicles traveling alongside it, the initial heading angle of the target vehicle is calculated based on the heading angle of the lost vehicle or the nearest lane line information.

[0006] It is evident that existing technologies require real-time execution of multiple judgment logics when assigning initial heading angles to target vehicles in areas without lane markings. The algorithms are relatively complex and may consume a significant amount of computing resources at the roadside. Summary of the Invention

[0007] In view of the above-mentioned problems existing in the prior art, this application provides an initial heading angle determination method, device and electronic device to quickly and accurately calculate the initial heading angle of a vehicle in a laneless area.

[0008] The embodiments of this application adopt the following technical solutions:

[0009] In a first aspect, embodiments of this application provide a method for determining an initial heading angle, the method comprising:

[0010] When there is a target vehicle in the area without lane lines that needs to be assigned an initial heading angle, the image grid corresponding to the target vehicle is obtained, wherein the road image of the area without lane lines is divided into multiple image grids, and each image grid has more than one initial heading angle.

[0011] If the image grid corresponding to the target vehicle has an initial heading angle, then the initial heading angle of the image grid is taken as the initial heading angle of the target vehicle.

[0012] If the image grid corresponding to the target vehicle has two or more initial heading angles, the current traffic flow direction of the laneless area is obtained, and the initial heading angle of the target vehicle is determined from the two or more initial heading angles based on the current traffic flow direction.

[0013] Optionally, the road image of the laneless area is divided into multiple image grids through the following steps:

[0014] The road image of the laneless area is acquired using a camera;

[0015] The road image is divided into multiple image grids, and all drivable directions corresponding to each image grid are obtained;

[0016] Obtain all initial heading angles for each image grid based on all drivable directions corresponding to that image grid.

[0017] Optionally, obtaining all drivable directions corresponding to each image grid includes:

[0018] The road region corresponding to each image grid is obtained based on the calibration relationship between camera images and high-precision maps;

[0019] The high-precision map is used to obtain one or more driving lanes corresponding to the road area and the driving direction of each driving lane. The driving lanes include lanes generated based on the extension lines of lane lines.

[0020] All drivable directions for each image grid are obtained by using the driving directions of one or more driving lanes corresponding to the road area.

[0021] Optionally, the road image includes lane lines at intersections, and obtaining all drivable directions corresponding to each image grid includes:

[0022] Obtain the historical trajectories of vehicles within the laneless area;

[0023] Based on the historical vehicle trajectories within the laneless area, the lane lines at the intersection are extended to obtain a driving lane formed by the extended lane lines.

[0024] Obtain one or more driving lanes corresponding to each image grid and the driving direction of each driving lane, and obtain all driving directions of each image grid through the driving directions of the one or more driving lanes.

[0025] Optionally, obtaining the image grid corresponding to the target vehicle includes:

[0026] Obtain the image position of the target vehicle in the current frame and the image position of each image grid;

[0027] Based on the image position of the target vehicle in the current frame and the image position of each image grid, the image grid corresponding to the target vehicle is obtained.

[0028] Optionally, obtaining the current traffic flow direction in the laneless area includes:

[0029] Obtain the tracking trajectories of all vehicles within the laneless area in the current frame;

[0030] The tracking trajectories of all vehicles in the laneless area are tracked in the current frame to detect the trajectory direction and obtain the number of vehicles corresponding to each trajectory direction.

[0031] Based on the number of vehicles corresponding to each trajectory direction, the current traffic flow direction of the laneless area is obtained.

[0032] Optionally, obtaining the current traffic flow direction in the laneless area based on the number of vehicles corresponding to each trajectory direction includes:

[0033] The trajectory directions with fewer than a vehicle number threshold are filtered out, and the filtered trajectory directions are used as the current traffic flow direction in the laneless area.

[0034] Optionally, determining the initial heading angle of the target vehicle from the two or more initial heading angles based on the current traffic flow direction includes:

[0035] Obtain the angular deviation between the current traffic flow direction and each initial heading angle of the image grid;

[0036] The initial heading angle of the image grid corresponding to the minimum angular deviation is taken as the initial heading angle of the target vehicle.

[0037] Secondly, embodiments of this application also provide an initial heading angle determination device, the device comprising:

[0038] The acquisition unit is used to acquire the image grid corresponding to the target vehicle when there is a target vehicle in the area without lane lines that needs to be given an initial heading angle. The road image of the area without lane lines is divided into multiple image grids, and each image grid has more than one initial heading angle.

[0039] The first determining unit is configured to, if the image grid corresponding to the target vehicle has an initial heading angle, take the initial heading angle of the image grid as the initial heading angle of the target vehicle.

[0040] The second determining unit is used to obtain the current traffic flow direction of the laneless area if the image grid corresponding to the target vehicle has two or more initial heading angles, and determine the initial heading angle of the target vehicle from the two or more initial heading angles according to the current traffic flow direction.

[0041] Thirdly, embodiments of this application also provide an electronic device, including:

[0042] Processor; and

[0043] A memory is configured to store computer-executable instructions, which, when executed, cause the processor to perform an initial heading angle determination method.

[0044] Fourthly, embodiments of this application also provide a computer-readable storage medium storing one or more programs that, when executed by an electronic device including multiple applications, cause the electronic device to perform an initial heading angle determination method.

[0045] The above-mentioned technical solutions adopted in this application embodiment can achieve the following beneficial effects: When it is necessary to assign an initial heading angle to a target vehicle in a laneless area, this application embodiment can calculate a more reasonable heading angle that is closer to the real situation based on the initial heading angle of the image grid and the current traffic flow direction, which solves the problem of large deviation in the initial heading angle setting when the vehicle is stationary or in motion, and improves the accuracy and rationality of the initial heading angle setting; In addition, this application embodiment can pre-calculate the image grid corresponding to the laneless area and the initial heading angle of the image grid, which can reduce the resource occupation of roadside equipment during the real-time calculation of the initial heading angle, improve the calculation efficiency, and obtain the initial heading angle of the target vehicle more quickly. Attached Figure Description

[0046] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0047] Figure 1 This is a flowchart illustrating an initial heading angle determination method in an embodiment of this application;

[0048] Figure 2 This is a schematic diagram of a driving lane in a laneless area shown in an embodiment of this application;

[0049] Figure 3 This is a schematic diagram of the initial heading angle determination device shown in the embodiments of this application;

[0050] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0051] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0052] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0053] The execution subject of the initial heading angle determination method for laneless areas provided in this application embodiment can be roadside equipment (such as roadside cameras or roadside computing devices), servers, or cloud platforms, etc.

[0054] Please refer to Figure 1 , Figure 1 Taking roadside equipment as an example, this application provides a method for determining the initial heading angle. Figure 1 As shown, an initial heading angle determination method provided in this application embodiment may include the following steps S110 to S130:

[0055] Step S110: When it is necessary to assign an initial heading angle to a target vehicle in a laneless area, obtain the image grid corresponding to the target vehicle, wherein the road image of the laneless area is divided into multiple image grids, and each image grid has more than one initial heading angle.

[0056] The roadside equipment in this application embodiment can determine whether there is a target vehicle in the area without lane lines that needs to be assigned an initial heading angle based on the vehicle tracking results. For example, if the current tracking status of the target is a newly appeared state, it means that the detection box of the target in the current frame cannot be matched with all the detection boxes in the previous frame, which means that it may be a newly appeared target. In this case, a new initial heading angle needs to be assigned to the target.

[0057] It should be noted that a newly appearing target tracking status does not necessarily mean that the target is being detected for the first time. For example, the target may have appeared before and been continuously detected, but due to reasons such as tracking matching algorithm errors, detection algorithm omissions, or target occlusion, the target's detection box in the current frame may not match the detection box in the previous frame. In any case, the target's heading angle cannot be calculated based on historical trajectories, so a new initial heading angle needs to be assigned.

[0058] To address the scenario where an initial heading angle needs to be assigned to a target vehicle, this embodiment of the application pre-divides the road image of the laneless area into multiple image grids. Based on the actual drivable direction of the corresponding road, a corresponding number of initial heading angles are set for each image grid. For example, if the road area corresponding to the first image grid allows straight travel, left turns, and U-turns, then the first image grid should have three initial heading angles, corresponding to straight travel, left turns, and U-turns, respectively. Thus, when a target vehicle requiring an initial heading angle is identified within the laneless area, the image grid corresponding to the target vehicle can be determined based on its position, and the initial heading angle of the target vehicle can be obtained through the initial heading angles of the image grids.

[0059] Step S120: If the image grid corresponding to the target vehicle has an initial heading angle, then the initial heading angle of the image grid is used as the initial heading angle of the target vehicle.

[0060] Step S130: If the image grid corresponding to the target vehicle has two or more initial heading angles, then obtain the current traffic flow direction of the laneless area, and determine the initial heading angle of the target vehicle from the two or more initial heading angles according to the current traffic flow direction.

[0061] The current traffic flow direction within the laneless area indicates the direction vehicles can travel at the current time, providing a reference for determining the initial heading angle of the target vehicle. When the image grid has more than two initial heading angles, combining the current traffic flow direction to determine the initial heading angle of the target vehicle can yield a more reasonable heading angle that is closer to reality.

[0062] It should be noted that in this embodiment, the current traffic flow direction can be one or more, which is related to the type of intersection without lane lines, traffic rules, etc. For example, at the same time, the traffic flow direction at an intersection can include both incoming and outgoing traffic directions.

[0063] like Figure 1 As can be seen from the initial heading angle determination method shown, when assigning an initial heading angle to a target vehicle in a laneless area, this embodiment can calculate a more reasonable heading angle that is closer to the actual situation based on the initial heading angle of the image grid and the current traffic flow direction. This solves the problem of large deviations in the initial heading angle setting when the vehicle is stationary or in motion, and improves the accuracy and rationality of the initial heading angle setting. Furthermore, this embodiment can pre-calculate the image grid corresponding to the laneless area and the initial heading angle of the image grid. This can reduce the resource occupation of roadside equipment during the real-time calculation of the initial heading angle, improve the calculation efficiency, and obtain the initial heading angle of the target vehicle more quickly.

[0064] In some embodiments of this application, the road image of the laneless area is divided into multiple image grids by the following steps:

[0065] The road image of the laneless area is acquired using a camera;

[0066] The road image is divided into multiple image grids, and all drivable directions corresponding to each image grid are obtained;

[0067] Obtain all initial heading angles for each image grid based on all drivable directions corresponding to that image grid.

[0068] In this embodiment, the road image can be an original road image captured by a single camera, or a stitched image of original road images captured by multiple cameras. When dividing the road image into grids, the lane width can be referenced to ensure that the road area corresponding to each image grid includes a complete lane. Optionally, the road image can be divided into multiple rectangular grids. Of course, the shape of the image grid is not limited to a matrix; it can also be other shapes, and the image grid size can be flexibly set.

[0069] In real-world traffic scenarios, certain areas in the middle of an intersection may overlap with multiple travel directions. For example, some vehicles in this overlapping area may be traveling both north and east. In this case, the image grid corresponding to the overlapping area should have multiple initial heading angles. On the other hand, areas within the stop line generally have only one travel direction, and the image grid corresponding to such areas typically has one initial heading angle.

[0070] This embodiment can combine a high-definition map (HD map) or the vehicle's historical trajectory to obtain all drivable directions corresponding to each image grid.

[0071] The steps for obtaining all drivable directions corresponding to each image grid by combining high-precision maps are as follows:

[0072] The road area corresponding to each image grid is obtained based on the calibration relationship between the camera image and the high-definition map. Here, the calibration relationship between the camera image and the high-definition map refers to the fact that the ground truth data used in the camera calibration process is obtained from the high-definition map. The calibration relationship calculated in this way is the calibration relationship between the camera image and the high-definition map.

[0073] The high-precision map is used to obtain one or more driving lanes corresponding to the road area and the driving direction of each driving lane. The driving lanes include lanes generated based on the extension lines of lane lines.

[0074] All drivable directions for each image grid are obtained by using the driving directions of one or more driving lanes corresponding to the road area.

[0075] The high-precision maps in this application embodiment can be derived from high-precision maps designed for vehicle driving, especially high-precision maps designed for autonomous vehicles. Figure 1 On the one hand, high-precision maps have higher absolute coordinate accuracy, which refers to the precision between a target on the map and objects in the real external world. On the other hand, high-precision maps contain richer and more detailed road traffic information elements. The absolute accuracy of high-precision maps used in autonomous driving is generally at the sub-meter level, that is, within 1 meter, and the lateral relative accuracy (e.g., the relative positional accuracy between lanes, and between lane lines) is often even higher. High-precision maps not only have high-precision coordinates but also accurate road shapes, and include data on the slope, curvature, heading, elevation, and lateral tilt of each lane. Therefore, this embodiment can obtain autonomous driving lanes in areas without lane lines using high-precision maps.

[0076] like Figure 2 As shown, in real traffic scenarios, there are no lane lines in the middle of an intersection. However, in a high-precision map, a virtual autonomous driving lane is generated in the middle of the intersection to assist the safe driving of autonomous vehicles. Thus, this embodiment can use these virtual autonomous driving lanes in the high-precision map to determine that each image grid location includes an autonomous driving lane, and each autonomous driving lane corresponds to a driving direction.

[0077] In addition, embodiments of this application can also combine the vehicle's historical trajectory to obtain all drivable directions corresponding to each image grid, with the specific steps as follows:

[0078] Obtain the historical trajectories of vehicles within the laneless area, for example, obtain the historical trajectories of all tracked vehicles before the current frame.

[0079] Based on the historical vehicle trajectories within the laneless area, the lane lines at the intersection are extended to obtain a driving lane formed by the extended lane lines.

[0080] Obtain one or more driving lanes corresponding to each image grid and the driving direction of each driving lane, and obtain all driving directions of each image grid through the driving directions of the one or more driving lanes.

[0081] Vehicle historical trajectories can provide a certain reference for the delineation of drivable lanes in areas without lane markings. Figure 2 For areas without lane lines where intersection lane lines exist at the boundary, the lane lines on this side of the intersection are extended based on vehicle historical trajectories, extending to the lane lines on the opposite side corresponding to the vehicle's historical trajectory. This lane extension allows for the identification of driving lanes in areas without lane lines, thus determining that each image grid location includes a driving lane, with each driving lane corresponding to a driving direction. To make the driving lanes defined in areas without lane lines more realistic, the number and types of vehicle historical trajectories can be enriched.

[0082] After setting up each image grid in the laneless area through the above embodiments, the initial heading angle of the target vehicle that needs to be assigned an initial heading angle in the laneless area can be set using each image grid in the laneless area.

[0083] In some embodiments of this application, step S110 above, obtaining the image grid corresponding to the target vehicle, includes:

[0084] Obtain the image position of the target vehicle in the current frame and the image position of each image grid;

[0085] Based on the image position of the target vehicle in the current frame and the image position of each image grid, the image grid corresponding to the target vehicle is obtained.

[0086] In some possible implementations of this embodiment, if the current frame tracking result of the target vehicle includes a target detection box based on the camera image, the image position of the target vehicle in the current frame can be obtained through the following steps:

[0087] The current image position of the target vehicle is obtained based on the target detection box, that is, the center pixel position of the target detection box is taken as the current image position of the target vehicle.

[0088] In some other possible implementations of this embodiment, the image position of the target vehicle in the current frame can also be obtained through the following steps:

[0089] Obtain the current location information (e.g., latitude and longitude information) of the target vehicle, and obtain the image location corresponding to the current location information of the target vehicle based on the calibration relationship between the camera image and the high-precision map.

[0090] In some embodiments of this application, obtaining the current traffic flow direction in the laneless area in step S130 above includes:

[0091] Obtain the tracking trajectories of all vehicles in the current frame within the area without lane lines;

[0092] The tracking trajectories of all vehicles in the laneless area are tracked in the current frame to detect the trajectory direction and obtain the number of vehicles corresponding to each trajectory direction.

[0093] Based on the number of vehicles corresponding to each trajectory direction, the current traffic flow direction of the laneless area is obtained.

[0094] In some possible implementations of this embodiment, obtaining the current traffic flow direction in the laneless area based on the number of vehicles corresponding to each trajectory direction includes:

[0095] Trajectory directions with fewer than a vehicle number threshold are filtered out. The filtered trajectory directions are then used as the current traffic flow direction in the laneless area. The vehicle number threshold can be a pre-set empirical value or dynamically set based on the total number of vehicles in the laneless area. For example, a correspondence can be established between the total number of vehicles in the laneless area and the vehicle number threshold. When obtaining the current traffic flow direction in the laneless area based on the number of vehicles corresponding to each trajectory direction, the total number of vehicles in the laneless area is first counted. Based on the above correspondence, the current vehicle number threshold is determined. In this way, trajectory directions can be filtered based on the determined vehicle number threshold.

[0096] The track direction filtering process in this embodiment can filter out the influence of vehicles changing lanes in areas without lane lines, thereby improving the accuracy of traffic flow direction detection.

[0097] In addition, this embodiment can also combine traffic rules to obtain the current traffic flow direction. For example, the trajectory directions can be sorted from most to least number of vehicles corresponding to each trajectory direction to obtain the most traffic flow direction N (N is a positive integer and N≥1) corresponding to the current traffic rule, and the first N trajectory directions are selected from the sorted sequence as the current traffic flow direction.

[0098] Thus, when the image grid corresponding to the target vehicle has more than two initial heading angles, the angular deviation between the current traffic flow direction and each initial heading angle of the image grid is obtained; the initial heading angle of the image grid corresponding to the smallest angular deviation is taken as the initial heading angle of the target vehicle.

[0099] In summary, when dealing with a target vehicle in an area without lane lines that requires an initial heading angle, this application can obtain the possible driving direction of the target vehicle's location based on the image grid. When there are multiple possible driving directions at the target vehicle's location, the heading angle that is close to the traffic flow direction is used as the initial heading angle of the target vehicle. Through simple calculation rules, a more reasonable heading angle that is closer to the actual situation can be quickly calculated.

[0100] This application embodiment also provides an initial heading angle determination device 300, such as... Figure 3 The diagram shows a schematic representation of an initial heading angle determination device according to an embodiment of this application. The initial heading angle determination device 300 includes: an acquisition unit 310, a first determination unit 320, and a second determination unit 330, wherein:

[0101] The acquisition unit 310 is used to acquire the image grid corresponding to the target vehicle when there is a target vehicle that needs to be given an initial heading angle in the area without lane lines, wherein the road image of the area without lane lines is divided into multiple image grids, and each image grid has more than one initial heading angle.

[0102] The first determining unit 320 is configured to, if the image grid corresponding to the target vehicle has an initial heading angle, use an initial heading angle of the image grid as the initial heading angle of the target vehicle.

[0103] The second determining unit 330 is used to obtain the current traffic flow direction of the laneless area if the image grid corresponding to the target vehicle has two or more initial heading angles, and determine the initial heading angle of the target vehicle from the two or more initial heading angles according to the current traffic flow direction.

[0104] In some embodiments of this application, the initial heading angle determination device 300 further includes a preprocessing unit;

[0105] The preprocessing unit is used to acquire road images of the laneless area through a camera; divide the road images into multiple image grids and acquire all driving directions corresponding to each image grid; and acquire all initial heading angles of each image grid based on all driving directions corresponding to each image grid.

[0106] In some embodiments of this application, the preprocessing unit is specifically used to obtain the road region corresponding to each image grid based on the calibration relationship between the camera image and the high-precision map; obtain one or more driving lanes corresponding to the road region and the driving direction of each driving lane through the high-precision map, wherein the driving lanes include lanes generated based on lane line extensions; and obtain all drivable directions for each image grid through the driving directions of the one or more driving lanes corresponding to the road region.

[0107] In some embodiments of this application, the road image includes intersection lane lines. A preprocessing unit is specifically used to acquire the historical trajectory of vehicles in the area without lane lines; extend the intersection lane lines according to the historical trajectory of vehicles in the area without lane lines to obtain driving lanes formed by the extended lane lines; acquire one or more driving lanes corresponding to each image grid and the driving direction of each driving lane; and acquire all driving directions of each image grid through the driving directions of the one or more driving lanes.

[0108] In some embodiments of this application, the acquisition unit 310 is used to acquire the image position of the target vehicle in the current frame and the image position of each image grid; and to acquire the image grid corresponding to the target vehicle based on the image position of the target vehicle in the current frame and the image position of each image grid.

[0109] In some embodiments of this application, the second determining unit 330 is further configured to obtain the tracking trajectories of all vehicles in the laneless area in the current frame; perform trajectory direction detection on the tracking trajectories of all vehicles in the laneless area in the current frame to obtain the number of vehicles corresponding to each trajectory direction; and obtain the current traffic flow direction of the laneless area based on the number of vehicles corresponding to each trajectory direction.

[0110] In some embodiments of this application, the second determining unit 330 is specifically used to filter out trajectory directions where the number of vehicles is less than a vehicle number threshold, and to use the filtered trajectory direction as the current traffic flow direction in the laneless area.

[0111] In some embodiments of this application, the second determining unit 330 is specifically used to obtain the angular deviation between the current traffic flow direction and each initial heading angle of the image grid; and to take the initial heading angle of the image grid corresponding to the smallest angular deviation as the initial heading angle of the target vehicle.

[0112] It is understood that the above-described initial heading angle determination device can implement each step of the initial heading angle determination method provided in the foregoing embodiments. The relevant explanations of the initial heading angle determination method are applicable to the initial heading angle determination device, and will not be repeated here.

[0113] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Please refer to it. Figure 4 At the hardware level, the electronic device includes a processor and memory, and optionally also includes an internal bus and a network interface. The memory may include main memory, such as high-speed random-access memory (RAM), or non-volatile memory, such as at least one disk drive. Of course, the electronic device may also include other hardware required for other business operations.

[0114] The processor, network interface, and memory can be interconnected via an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 4 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0115] Memory is used to store programs. Specifically, programs may include program code, which includes computer operation instructions. Memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0116] The processor reads the corresponding computer program from non-volatile memory into main memory and then executes it, forming the initial heading angle determination mechanism at the logical level. The processor executes the program stored in memory and specifically performs the following operations:

[0117] When there is a target vehicle in the area without lane lines that needs to be assigned an initial heading angle, the image grid corresponding to the target vehicle is obtained, wherein the road image of the area without lane lines is divided into multiple image grids, and each image grid has more than one initial heading angle.

[0118] If the image grid corresponding to the target vehicle has an initial heading angle, then the initial heading angle of the image grid is taken as the initial heading angle of the target vehicle.

[0119] If the image grid corresponding to the target vehicle has two or more initial heading angles, the current traffic flow direction of the laneless area is obtained, and the initial heading angle of the target vehicle is determined from the two or more initial heading angles based on the current traffic flow direction.

[0120] The above is as stated in this application. Figure 1 The method for determining the initial heading angle disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads the information from the memory and, in conjunction with its hardware, completes the steps of the initial heading angle determination method described above.

[0121] The electronic device can also perform Figure 1 The method for the initial heading angle determination device is described, and the implementation of the initial heading angle determination device in... Figure 1 The functions of the embodiments shown are not described again in this application.

[0122] This application also proposes a computer-readable storage medium that stores one or more programs, the programs including instructions that, when executed by an electronic device including multiple applications, enable the electronic device to perform... Figure 1 The method executed by the initial heading angle determination device in the illustrated embodiment is specifically used to perform the following operations:

[0123] When there is a target vehicle in the area without lane lines that needs to be assigned an initial heading angle, the image grid corresponding to the target vehicle is obtained, wherein the road image of the area without lane lines is divided into multiple image grids, and each image grid has more than one initial heading angle.

[0124] If the image grid corresponding to the target vehicle has an initial heading angle, then the initial heading angle of the image grid is taken as the initial heading angle of the target vehicle.

[0125] If the image grid corresponding to the target vehicle has two or more initial heading angles, the current traffic flow direction of the laneless area is obtained, and the initial heading angle of the target vehicle is determined from the two or more initial heading angles based on the current traffic flow direction.

[0126] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0127] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0128] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0129] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0130] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0131] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0132] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0133] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover 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.

[0134] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0135] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for determining an initial heading angle, characterized in that, The method includes: When there is a target vehicle in the area without lane lines that needs to be assigned an initial heading angle, the image grid corresponding to the target vehicle is obtained, wherein the road image of the area without lane lines is divided into multiple image grids, and each image grid has more than one initial heading angle. If the image grid corresponding to the target vehicle has an initial heading angle, then the initial heading angle of the image grid is taken as the initial heading angle of the target vehicle. If the image grid corresponding to the target vehicle has two or more initial heading angles, then the current traffic flow direction of the laneless area is obtained, and the initial heading angle of the target vehicle is determined from the two or more initial heading angles based on the current traffic flow direction. The road image of the laneless area is divided into multiple image grids using the following steps: The road image of the laneless area is acquired using a camera; The road image is divided into multiple image grids, and all drivable directions corresponding to each image grid are obtained; Obtain all initial heading angles for each image grid based on all drivable directions corresponding to that image grid. Each image grid corresponds to a road area that includes a complete lane.

2. The method for determining the initial heading angle as described in claim 1, characterized in that, The step of obtaining all drivable directions corresponding to each image grid includes: The road region corresponding to each image grid is obtained based on the calibration relationship between camera images and high-precision maps; The high-precision map is used to obtain one or more driving lanes corresponding to the road area and the driving direction of each driving lane. The driving lanes include lanes generated based on the extension lines of lane lines. All drivable directions for each image grid are obtained by using the driving directions of one or more driving lanes corresponding to the road area.

3. The method for determining the initial heading angle as described in claim 1, characterized in that, The road image includes lane lines at intersections, and obtaining all drivable directions corresponding to each image grid includes: Obtain the historical trajectory of vehicles within the laneless area; Based on the historical vehicle trajectories within the laneless area, the lane lines at the intersection are extended to obtain a driving lane formed by the extended lane lines. Obtain one or more driving lanes corresponding to each image grid and the driving direction of each driving lane, and obtain all driving directions of each image grid through the driving directions of the one or more driving lanes.

4. The method for determining the initial heading angle as described in claim 1, characterized in that, The step of obtaining the image grid corresponding to the target vehicle includes: Obtain the image position of the target vehicle in the current frame and the image position of each image grid; Based on the image position of the target vehicle in the current frame and the image position of each image grid, the image grid corresponding to the target vehicle is obtained.

5. The method for determining the initial heading angle as described in claim 1, characterized in that, The step of obtaining the current traffic flow direction in the laneless area includes: Obtain the tracking trajectories of all vehicles within the laneless area in the current frame; The tracking trajectories of all vehicles in the laneless area are tracked in the current frame to detect the trajectory direction and obtain the number of vehicles corresponding to each trajectory direction. Based on the number of vehicles corresponding to each trajectory direction, the current traffic flow direction of the laneless area is obtained.

6. The method for determining the initial heading angle as described in claim 5, characterized in that, The step of obtaining the current traffic flow direction in the laneless area based on the number of vehicles corresponding to each trajectory direction includes: The trajectory directions with fewer than a vehicle number threshold are filtered out, and the filtered trajectory directions are used as the current traffic flow direction in the laneless area.

7. The method for determining the initial heading angle as described in claim 1, characterized in that, Determining the initial heading angle of the target vehicle from two or more initial heading angles based on the current traffic flow direction includes: Obtain the angular deviation between the current traffic flow direction and each initial heading angle of the image grid; The initial heading angle of the image grid corresponding to the minimum angular deviation is taken as the initial heading angle of the target vehicle.

8. An initial heading angle determination device, characterized in that, The device includes: The acquisition unit is used to acquire the image grid corresponding to the target vehicle when there is a target vehicle in the area without lane lines that needs to be given an initial heading angle. The road image of the area without lane lines is divided into multiple image grids, and each image grid has more than one initial heading angle. The first determining unit is configured to, if the image grid corresponding to the target vehicle has an initial heading angle, take the initial heading angle of the image grid as the initial heading angle of the target vehicle. The second determining unit is used to obtain the current traffic flow direction of the laneless area if the image grid corresponding to the target vehicle has two or more initial heading angles, and determine the initial heading angle of the target vehicle from the two or more initial heading angles according to the current traffic flow direction. The initial heading angle determination device further includes a preprocessing unit, which is used for: The road image of the laneless area is acquired using a camera; The road image is divided into multiple image grids, and all drivable directions corresponding to each image grid are obtained; Obtain all initial heading angles for each image grid based on all drivable directions corresponding to that image grid. Each image grid corresponds to a road area that includes a complete lane.

9. An electronic device, comprising: processor; as well as A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the initial heading angle determination method as described in any one of claims 1 to 7.

Images