Lane binding method, device and equipment and storage medium

Abstract

The invention discloses a lane binding method, device and equipment and a storage medium, and relates to the technical field of automatic driving, and the lane binding method comprises the steps: obtaining the coordinates of a lane track point and the coordinates of a vehicle; filtering the lane track points according to the coordinates of the lane track points to obtain filtered lane track points; calculating the projection distance from the vehicle to the lane according to the filtered coordinates of the lane track points and the vehicle coordinates; and determining a target lane meeting a preset binding condition based on the projection distance, and binding the vehicle with the target lane. According to the invention, the accuracy of lane binding can be improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a lane binding method, device, equipment and storage medium. Background Art

[0002] In the process of intelligent driving, it is necessary to frequently calculate the lanes that the vehicle is in as the data set for intelligent driving. The accuracy of lane calculation directly affects the quality of the data set. Accurate lane information can ensure that the lane labels produced in the data set, the identification of vehicle lane changes, and the design of interactive labels between vehicles are more accurate. However, the traditional lane binding method has many shortcomings. For example, when the curvature of the lane line changes greatly or the lane width is uneven, it is easy to make misjudgments and fail to accurately identify the lane where the vehicle is located.

[0003] Therefore, how to improve the accuracy of lane binding is a problem that needs to be solved urgently.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a lane binding method, device, equipment and storage medium, aiming to solve the technical problem of how to improve the accuracy of lane binding.

[0006] To achieve the above object, the present application provides a lane binding method, the lane binding method comprising:

[0007] Get the coordinates of lane trajectory points and vehicle coordinates;

[0008] filtering the lane trajectory points according to the coordinates of the lane trajectory points to obtain filtered lane trajectory points;

[0009] Calculating a projection distance from the vehicle to the lane based on the coordinates of the filtered lane trajectory points and the vehicle coordinates;

[0010] A target lane that meets a preset binding condition is determined based on the projection distance, and the vehicle is bound to the target lane.

[0011] In one embodiment, the step of filtering the lane trajectory points according to the coordinates of the lane trajectory points to obtain filtered lane trajectory points comprises:

[0012] Traversing the lane trajectory points to obtain pairwise adjacent lane trajectory points;

[0013] Calculating offset information of the pairwise adjacent lane trajectory points according to the coordinates of the pairwise adjacent lane trajectory points;

[0014] The lane trajectory points are filtered according to the offset information and a preset offset threshold to obtain filtered lane trajectory points.

[0015] In one embodiment, the step of calculating the offset information of the pairwise adjacent lane trajectory points according to the coordinates of the pairwise adjacent lane trajectory points comprises:

[0016] Calculating the lateral offset and the longitudinal offset of the two adjacent lane trajectory points according to the coordinates of the two adjacent lane trajectory points;

[0017] Calculating an offset angle according to the lateral offset and the longitudinal offset;

[0018] The offset information of the pairwise adjacent lane trajectory points is obtained according to the offset angle.

[0019] In one embodiment, the step of calculating the projection distance from the vehicle to the lane according to the coordinates of the filtered lane trajectory points and the vehicle coordinates comprises:

[0020] Traversing the filtered lane trajectory points to obtain the filtered lane trajectory points that are adjacent to each other;

[0021] Calculating the projection distance from the vehicle to the lane trajectory points adjacent to each other after filtering according to the coordinates of the lane trajectory points adjacent to each other after filtering and the vehicle coordinates, to obtain a plurality of projection distances;

[0022] The plurality of projection distances are compared, and a minimum projection distance is obtained as the projection distance from the vehicle to the lane.

[0023] In one embodiment, the step of calculating the projection distance from the vehicle to the filtered pairwise adjacent lane trajectory points according to the filtered pairwise adjacent lane trajectory points and the vehicle coordinates comprises:

[0024] Calculating vectors between the vehicle and the pairwise adjacent lane trajectory points after filtering according to the coordinates of the pairwise adjacent lane trajectory points after filtering and the vehicle coordinates;

[0025] Calculating the cosine value of the angle between the vehicle and the filtered lane trajectory points adjacent to each other according to the vector;

[0026] The projection distance from the vehicle to the lane line is calculated according to the cosine value of the angle, the coordinates of the lane trajectory points adjacent to each other after filtering, and the vehicle coordinates.

[0027] In one embodiment, the filtered pairwise adjacent lane trajectory points include a first trajectory point and a second trajectory point, and the step of calculating the vectors between the vehicle and the filtered pairwise adjacent lane trajectory points according to the coordinates of the filtered pairwise adjacent lane trajectory points and the vehicle coordinates includes:

[0028] Calculating a first vector from the first trajectory point to the vehicle coordinates according to the first trajectory point and the vehicle coordinates;

[0029] Calculating a second vector from the second trajectory point to the vehicle coordinates according to the second trajectory point and the vehicle coordinates;

[0030] Calculating a lane trajectory vector from the first trajectory point to the second trajectory point according to the first trajectory point and the second trajectory point;

[0031] According to the first vector, the second vector and the lane trajectory vector, vectors of the vehicle and the lane trajectory points adjacent to each other after filtering are obtained.

[0032] In one embodiment, the step of determining a target lane that meets a preset binding condition based on the projection distance and binding the vehicle to the target lane includes:

[0033] Compare the minimum projection distance with a preset distance threshold to obtain a comparison result;

[0034] If the comparison result is that the minimum projection distance is less than the preset distance threshold, then obtaining the lane trajectory point corresponding to the minimum projection distance;

[0035] A target lane is determined according to a lane trajectory point corresponding to the minimum projection distance, and the vehicle is bound to the target lane.

[0036] In addition, to achieve the above-mentioned purpose, the present application also provides a lane binding device, the lane binding device comprising:

[0037] An acquisition module, used to acquire the coordinates of lane trajectory points and vehicle coordinates;

[0038] A trajectory point filtering module, used for filtering lane trajectory points according to the coordinates of the lane trajectory points to obtain filtered lane trajectory points;

[0039] A projection distance calculation module, used to calculate the projection distance from the vehicle to the lane according to the coordinates of the filtered lane trajectory points and the vehicle coordinates;

[0040] A lane binding module is used to determine a target lane that meets a preset binding condition based on the projection distance, and bind the vehicle to the target lane.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a lane binding device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the lane binding method described above.

[0042] In addition, to achieve the above-mentioned purpose, the present application also provides a storage medium, which is a computer-readable storage medium, and a program for implementing the lane binding method is stored on the computer-readable storage medium. The program for implementing the lane binding method is executed by a processor to implement the steps of the lane binding method as described above.

[0043] The present application provides a lane binding method, which obtains the coordinates of lane trajectory points and filters out abnormal lane trajectory points that may appear during normal driving, thereby enhancing the adaptability to complex road environments and reducing the possibility of lane binding misjudgment. By calculating the projection distance from the vehicle to the lane, the relative position relationship between the vehicle and the lane can be accurately reflected. Based on the projection distance and the preset binding conditions, the target lane can be dynamically selected according to real-time data and bound to the vehicle. Accurate lane calculation helps to improve the quality of the intelligent driving data set, thereby improving the accuracy of intelligent driving decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0046] Figure 1 A flowchart of the first embodiment of the lane binding method of the present application is provided;

[0047] Figure 2 A schematic diagram of a first relative position between a vehicle and a lane in the lane binding method of the present application;

[0048] Figure 3 A schematic diagram of a second relative position between a vehicle and a lane in the lane binding method of the present application;

[0049] Figure 4 This is a schematic diagram of the module structure of the lane binding device according to an embodiment of the present application;

[0050] Figure 5This is a schematic diagram of the device structure of the hardware operating environment involved in the lane binding method in the embodiment of the present application.

[0051] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0053] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0054] The main solution of the present application is: obtaining the coordinates of lane trajectory points and vehicle coordinates; filtering the lane trajectory points according to the coordinates of the lane trajectory points to obtain filtered lane trajectory points; calculating the projection distance from the vehicle to the lane according to the coordinates of the filtered lane trajectory points and the vehicle coordinates; determining the target lane that meets the preset binding conditions based on the projection distance, and binding the vehicle to the target lane.

[0055] In the process of intelligent driving, it is necessary to frequently calculate the lane where the vehicle is located as the data set for intelligent driving. The accuracy of lane calculation directly affects the quality of the data set. Accurate lane information can ensure that the lane labels made in the data set, the identification of vehicle lane changes, and the design of interactive labels between vehicles are more accurate. However, the traditional lane binding method has many shortcomings. For example, when the curvature of the lane line changes greatly or the lane width is uneven, it is easy to make misjudgments and fail to accurately identify the lane where the vehicle is located. Therefore, how to improve the accuracy of lane binding is a problem that needs to be solved urgently.

[0056] This application obtains the coordinates of lane trajectory points and filters out abnormal lane trajectory points that may appear during regular driving, thereby enhancing the adaptability to complex road environments and reducing the possibility of lane binding misjudgment. By calculating the projection distance from the vehicle to the lane, the relative position relationship between the vehicle and the lane can be accurately reflected. Based on the projection distance and preset binding conditions, the target lane can be dynamically selected and bound to the vehicle according to real-time data. Accurate lane calculation helps to improve the quality of the intelligent driving data set, thereby improving the accuracy of intelligent driving decisions.

[0057] It should be noted that the execution subject of this embodiment may be a lane binding system, or a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a lane binding device capable of realizing the above functions, etc., and this embodiment does not specifically limit this. The following takes the lane binding system as an example to illustrate this embodiment and the following embodiments.

[0058] Based on this, this application proposes a lane binding method of the first embodiment, please refer to Figure 1 , the lane binding method comprises steps S10 to S40:

[0059] Step S10, obtaining the coordinates of the lane trajectory points and the vehicle coordinates;

[0060] It should be noted that the map of the vehicle at a certain moment consists of multiple lanes (assuming that it consists of N lanes). Each lane can be recorded as lane1, lane2, ..., laneN. Each lane is defined by two or more track points. The coordinates of the lane track points can be obtained through map data, GPS positioning or other sensors. The track points are distributed along the lane line and describe the actual shape of the lane. The vehicle coordinates can be determined by the vehicle's positioning system (such as GPS, inertial navigation system, etc.) and the vehicle's internal sensors (such as wheel speed sensors, steering wheel angle sensors, etc.). The sensors can provide real-time information such as the vehicle's position, speed, direction, etc., so as to obtain the vehicle's precise position in the map or lane coordinate system.

[0061] Step S20, filtering the lane trajectory points according to the coordinates of the lane trajectory points to obtain filtered lane trajectory points;

[0062] It should be noted that the lane trajectory point data obtained by the sensor may be affected by factors such as noise, occlusion, and illumination changes, so these points need to be filtered to remove those points that do not conform to the lane line characteristics or significantly deviate from the lane trajectory. In addition, when a vehicle may travel in a direction opposite to or significantly deviates from the expected direction for a long time, long-distance reverse trajectory points will be generated. Long-distance reverse trajectory points usually do not occur in normal lane driving, so long-distance reverse trajectory points need to be filtered. Lane trajectory point filtering can be done by setting thresholds for parameters such as coordinate point position, direction, and curvature to remove points that exceed the threshold, or by screening coordinate points according to the geometric characteristics of the lane line (such as parallelism and continuity) to remove those trajectory points that do not conform to the geometric characteristics of the lane line.

[0063] Step S30, calculating the projection distance from the vehicle to the lane according to the coordinates of the filtered lane trajectory points and the vehicle coordinates;

[0064] It should be noted that the filtered lane trajectory points can be fitted by polynomial fitting, least squares method, etc. to obtain the expression of the lane line. According to the vehicle coordinates and the expression of the lane line, the projection point of the vehicle perpendicular to the lane line at the current position is calculated, and then the distance between the vehicle coordinates and the projection point is calculated, that is, the projection distance from the vehicle to the lane.

[0065] Furthermore, based on the coordinates of the lane trajectory points and the vehicle, the relative position of the vehicle to the lane can be determined by analyzing the vector relationship of the coordinate points. According to the different positions of the vehicle relative to the lane, the projection points of the vehicle on the lane are different. According to the different projection point positions, the distance between the vehicle coordinates and the projection point, that is, the projection distance from the vehicle to the lane, is calculated using the corresponding method.

[0066] Step S40: determining a target lane that meets a preset binding condition based on the projection distance, and binding the vehicle to the target lane.

[0067] It should be noted that in order to ensure that the vehicle can be accurately identified and bound to the target lane, the width of the lane and the actual position of the vehicle must be considered. Since the lane has a certain width, direct binding may not be accurate when the vehicle is far away from the lane. Therefore, a projection distance threshold needs to be set. Only when the projection distance between the vehicle and the lane is less than this threshold, it is determined that the vehicle is likely to be in the lane. At the same time, in order to prevent the vehicle from driving in the wrong or significantly deviated direction for a long time, a lane direction deviation threshold can also be set to monitor the vehicle's driving direction and remove data driving in the wrong or significantly deviated direction. When the projection distance meets the projection distance threshold requirements and the lane direction is within the lane direction deviation threshold range, the vehicle is determined to be in the lane and bound to the lane.

[0068] This embodiment provides a lane binding method, which enhances the adaptability to complex road environments and reduces the possibility of lane binding misjudgment by obtaining the coordinates of lane trajectory points and filtering abnormal lane trajectory points that may appear during regular driving. The projection distance from the vehicle to the lane is calculated to accurately reflect the relative position relationship between the vehicle and the lane. Based on the projection distance and the preset binding conditions, the target lane can be dynamically selected according to real-time data and bound to the vehicle. Accurate lane calculation helps to improve the quality of the intelligent driving data set, thereby improving the accuracy of intelligent driving decisions.

[0069] In a feasible implementation manner, the lane coordinates include the starting point coordinates of the lane line and the ending point coordinates of the lane line, and step S20 may include steps S201 to S203:

[0070] Step S201, traversing the lane trajectory points to obtain two adjacent lane trajectory points;

[0071] Step S202: Calculate the offset information of the pairwise adjacent lane trajectory points according to the coordinates of the pairwise adjacent lane trajectory points.

[0072] Step S203: Filter the lane trajectory points according to the offset information and a preset offset threshold to obtain the filtered lane trajectory points.

[0073] It should be noted that, referring to Figure 2 , for a certain lane lane1, which includes several lane trajectory points, they can be respectively denoted as: point1, point2, point3, …… pointN. Slide the pairwise adjacent lane trajectory points window by window in turn. For example, take the first point from the lane trajectory points and denote it as point1, then take the next point and denote it as point2. At this time, point1 and point2 are a pair of adjacent lane trajectory points. Repeat the above process until all lane trajectory points are traversed. The offset information can quantify the positional relationship between adjacent lane trajectory points, including the straight-line distance, the amount of direction change, or other parameters that can reflect the difference between adjacent points. According to the actual characteristics of the lane line and the requirements of the intelligent driving calculation effect and accuracy, set one or more offset thresholds in advance. Traverse each pair of adjacent lane trajectory points and their corresponding offset information, and compare the offset information with the preset offset threshold. If the offset information exceeds the preset threshold, it is considered that at least one of the points in this pair of adjacent points is an abnormal point and needs to be filtered out. For example, when the offset information is set as the straight-line distance and the straight-line distance exceeds the preset maximum distance threshold, one or both of the lane trajectory points in this pair of adjacent lane trajectory points can be removed. Referring to Figure 3 , when the offset information is the amount of direction change, when the vehicle travels in a direction opposite to or significantly deviated from the expected direction for a long time, long-distance reverse trajectory points may be generated. For example Figure 3 the points 3 and 4 in . By filtering through the amount of direction change, long-distance reverse trajectory points can be filtered out, that is, one or both of the lane trajectory points in this pair of adjacent lane trajectory points can be removed. Among them, the preset maximum angle thresholds can be set as angle1 and angle2. When angle1 < offset angle diff_angle < angle2, retain the lane trajectory points corresponding to this offset angle. angle1 can take values angle2 can take values

[0074] The preset maximum angle thresholds angle1 and angle2 can be set according to the requirements of the intelligent driving calculation effect and accuracy for long-distance reverse trajectory points.

[0075] In this implementation, by calculating the offset information between adjacent lane trajectory points and filtering them in combination with a preset offset threshold, the filtered lane trajectory points more accurately reflect the actual position and shape of the lane line, reduce the sensitivity to individual abnormal points in the lane trajectory, retain the key features of the lane line, reduce the amount of calculation for subsequent lane binding, improve the processing efficiency of lane binding, and help ensure that the vehicle can make driving decisions in a timely and accurate manner.

[0076] In a feasible implementation, step S202 may include steps S2021 to S2023:

[0077] Step S2021, calculating the lateral offset and longitudinal offset of the two adjacent lane trajectory points according to the coordinates of the two adjacent lane trajectory points;

[0078] Step S2022, calculating an offset angle according to the lateral offset and the longitudinal offset;

[0079] Step S2023: Obtain the offset information of the pairwise adjacent lane trajectory points according to the offset angle.

[0080] It should be noted that, refer to Figure 2 , two adjacent lane trajectory points are point1(x1,y1) and point2(x2,y2). The lateral offset (diff_x) can be obtained by calculating the difference between the x coordinates of the two points, that is, diff_x = x2-x1. The longitudinal offset (diff_y) can be obtained by calculating the difference between the y coordinates of the two points, that is, diff_y = y2-y1. The inverse tangent function (arctan2) is used to calculate the angle curr_angle between two adjacent lane trajectory points, that is, curr_angle = atan2(diff_y,diff_x).

[0081] For the first point point1 of lane1, since there is no previous point to calculate the angle difference with point1, the offset angle diff_angle is defined as 0. For each non-first point on lane1, it is necessary to calculate the difference between the current point's curr_angle and the previous point's curr_angle to obtain the offset angle diff_angle. Since the angle difference diff_angle may be any real number, it needs to be normalized to the range of [-π,π]. For example, when the absolute value of diff_angle is greater than π, it is adjusted to the range of [-π,π] by adding or subtracting integer multiples of 2π.

[0082] In this embodiment, by calculating the lateral offset and longitudinal offset of each pair of adjacent lane trajectory points, as well as calculating the offset angle, the lane trajectory information can be processed and updated in real time, and the directional change of the lane trajectory line can be quantified. The calculated offset information can be used as input data for subsequent lane binding, thereby improving the accuracy of lane binding.

[0083] In a feasible implementation, step S30 may include steps S301 to S303:

[0084] Step S301, traversing the filtered lane trajectory points to obtain the filtered lane trajectory points that are adjacent to each other;

[0085] Step S302, calculating the projection distance from the vehicle to the lane trajectory points adjacent to each other after filtering according to the coordinates of the lane trajectory points adjacent to each other after filtering and the vehicle coordinates, to obtain a plurality of projection distances;

[0086] Step S303, comparing the multiple projection distances, and obtaining the minimum projection distance as the projection distance from the vehicle to the lane.

[0087] It should be noted that based on the filtered lane trajectory points, pairs of adjacent trajectory points are identified. Lane segments are formed by pairs of adjacent trajectory points, and the angle between the vehicle and the adjacent trajectory points can be calculated through vector operations. The size and positive and negative of the angle can be used to determine whether the vehicle is inside the lane segment or outside the adjacent trajectory points.

[0088] In order to calculate the projection distance, it is first necessary to determine the projection point of the vehicle on the lane. The projection point is the closest point of the vehicle on the lane along the direction perpendicular to the lane. The projection point is different depending on the position of the vehicle relative to the lane. If the vehicle is located inside the lane segment, the projection point of the vehicle relative to the lane is a point on the lane segment closest to the vehicle. In this case, the projection distance is the vertical distance from the vehicle to the lane segment. The projection distance can be obtained by calculating the relationship between the vehicle and the direction vector of the lane segment. If the vehicle is located outside of two adjacent trajectory points, the projection point of the vehicle relative to the lane corresponds to one of the trajectory points, and the projection distance is the distance from the vehicle to one of the trajectory points.

[0089] By calculating the projection distance between the vehicle and the adjacent trajectory points that form the lane segment, multiple projection distance values ​​are obtained. In order to determine the shortest distance from the vehicle to the entire lane, it is necessary to compare these projection distance values ​​and find the minimum value of all projection distances. The minimum projection distance value is used as the projection distance from the vehicle to the lane, which will be used as the data basis for subsequent lane binding decisions.

[0090] In this implementation, by traversing the filtered lane trajectory points and calculating the projection distance from the vehicle to each pair of adjacent trajectory points, the spatial relationship between the vehicle and the lane can be accurately evaluated. By comparing multiple projection distances and selecting the minimum value, the closest point from the vehicle to the entire lane is determined, which helps to improve the accuracy of lane binding.

[0091] In a feasible implementation, step S302 may include steps S3021 to S3023:

[0092] Step S3021, calculating the vectors between the vehicle and the pairwise adjacent lane trajectory points after filtering according to the coordinates of the pairwise adjacent lane trajectory points after filtering and the vehicle coordinates;

[0093] Step S3022, calculating the cosine value of the angle between the vehicle and the filtered lane trajectory points adjacent to each other according to the vector;

[0094] Step S3023, calculating the projection distance from the vehicle to the lane line according to the cosine value of the angle, the coordinates of the filtered lane trajectory points that are adjacent to each other, and the vehicle coordinates.

[0095] It should be noted that for each pair of adjacent lane trajectory points, the system calculates the vectors from the vehicle coordinates to the two trajectory points. Specifically, the vector from the vehicle to the first trajectory point and the vector from the vehicle to the second trajectory point are calculated, as well as the vectors between the two trajectory points, including the first vector from the first trajectory point to the vehicle coordinates, the lane trajectory vector from the first trajectory point to the second trajectory point, and the second vector from the second trajectory point to the vehicle coordinates.

[0096] After obtaining the vectors, calculate the cosine value of the angle between the first vector and the lane trajectory vector, and the cosine value of the angle between the second vector and the lane trajectory vector. The cosine value of the angle can reflect the direction relationship between the two vectors. Assume that the first trajectory point is point1(x1,y1), the second trajectory point is point2(x2,y2), and the vehicle coordinates are agent(p1,p2). When the cosine value of the angle between the first vector and the lane trajectory vector is less than zero, the projection distance is calculated as follows:

[0097]

[0098] When the cosine value of the angle between the first vector and the lane trajectory vector is greater than or equal to zero, the projection distance is calculated as follows:

[0099]

[0100] Wherein, cos_angle1 is the cosine value of the angle between the first vector and the lane trajectory vector.

[0101] When the cosine value of the angle between the second vector and the lane trajectory vector is less than zero, the projection distance is calculated as follows:

[0102]

[0103] When the cosine value of the angle between the second vector and the lane trajectory vector is greater than or equal to zero, the projection distance is calculated as follows:

[0104]

[0105] Wherein, cos_angle1 is the cosine value of the angle between the first vector and the lane trajectory vector.

[0106] In this implementation, the projection distance from the vehicle to the lane can be accurately calculated by combining the cosine value of the angle with the adjacent lane trajectory points and the vehicle coordinates. As a quantitative indicator, the projection distance can intuitively reflect the relative position relationship between the vehicle and the lane, thereby improving the accuracy of the relative position calculation between the vehicle and the lane, providing accurate data support for lane binding, and helping to improve the accuracy of lane binding.

[0107] In a feasible implementation manner, after filtering, the lane trajectory points adjacent to each other include a first trajectory point and a second trajectory point, and step S3021 may include steps S30211 to S30214:

[0108] Step S30211, calculating a first vector from the first trajectory point to the vehicle coordinates according to the first trajectory point and the vehicle coordinates;

[0109] Step S30212, calculating a second vector from the second trajectory point to the vehicle coordinates according to the second trajectory point and the vehicle coordinates;

[0110] Step S30213, calculating a lane trajectory vector from the first trajectory point to the second trajectory point according to the first trajectory point and the second trajectory point;

[0111] Step S30214: obtaining vectors of the vehicle and the lane trajectory points adjacent to each other after filtering according to the first vector, the second vector and the lane trajectory vector.

[0112] It should be noted that, refer to Figure 2, after filtering, the adjacent lane trajectory points are the first trajectory point1(x1,y1) and the second trajectory point2(x2,y2), and the vehicle coordinates are marked as agent(p1,p2). The first vector from the first trajectory point to the vehicle coordinates is (v1_x,v1_y)=(p1–x1,p2–y1), and the lane trajectory vector from the first trajectory point to the second trajectory point is (v2_x,v2_y)=(x2–x1,y2–y1).

[0113] The second vector from the second trajectory point to the vehicle coordinates is (v3_x, v3_y) = (p1-x2, p2-y2).

[0114] In this implementation, by calculating the vectors of the first trajectory point, the second trajectory point and the vehicle coordinates, the relative position relationship between the vehicle and the lane trajectory point can be reflected, thereby reducing the complexity of the lane binding calculation and improving the accuracy of the lane binding.

[0115] In a feasible implementation, step S40 may include steps S401 to S403:

[0116] Step S401, comparing the minimum projection distance with a preset distance threshold to obtain a comparison result;

[0117] Step S402: if the comparison result is that the minimum projection distance is less than the preset distance threshold, then obtaining the lane trajectory point corresponding to the minimum projection distance;

[0118] Step S403: determining a target lane according to the lane trajectory point corresponding to the minimum projection distance, and binding the vehicle to the target lane.

[0119] It should be noted that due to the certain width of the lane, some vehicles cannot be truly bound to the lane. Even if they are bound to the lane, it is meaningless if the vehicle is far away from the lane. Therefore, a distance threshold needs to be set. Only when the minimum projection distance is less than the distance threshold, the lane trajectory point corresponding to the minimum projection distance is determined, and the lane to which the lane trajectory point belongs is the lane bound to the vehicle. Therefore, the lane trajectory point corresponding to the minimum projection distance is obtained, the target lane is determined based on the lane trajectory point, and the vehicle is bound to the target lane. Otherwise, it is determined that the vehicle has no lane to be bound, and the vehicle binding can be defined as a free lane.

[0120] In this embodiment, by comparing the minimum projection distance with the preset distance threshold, it is possible to accurately determine whether the proximity between the vehicle and the lane has reached the standard that allows the vehicle to be considered to be traveling in the lane, effectively reducing the possibility of vehicle misbinding and improving the accuracy of lane binding.

[0121] The present application also provides a lane binding device, please refer to Figure 4 , the lane binding device comprises:

[0122] An acquisition module 10, for acquiring the coordinates of the lane trajectory points and the vehicle coordinates;

[0123] A trajectory point filtering module 20, configured to filter the lane trajectory points according to the coordinates of the lane trajectory points to obtain filtered lane trajectory points;

[0124] A projection distance calculation module 30, for calculating the projection distance from the vehicle to the lane according to the coordinates of the filtered lane trajectory points and the vehicle coordinates;

[0125] The lane binding module 40 is used to determine a target lane that meets a preset binding condition based on the projection distance, and bind the vehicle to the target lane.

[0126] The lane binding device provided in the embodiment of the present application adopts the lane binding method in the above embodiment to solve the technical problem of lane binding. Compared with the prior art, the beneficial effects of the lane binding device provided in the embodiment of the present application are the same as the beneficial effects of the lane binding method provided in the above embodiment, and the other technical features in the lane binding device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0127] The present application provides a lane binding device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the lane binding method in the above-mentioned embodiment one.

[0128] Reference below Figure 5 , which shows a schematic diagram of the structure of a lane binding device suitable for implementing the embodiment of the present application. The lane binding device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The lane binding device shown is merely an example and should not bring any limitation to the functionality and scope of use of the embodiments of the present application.

[0129] like Figure 5As shown, the lane binding device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the lane binding device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the lane binding device to communicate wirelessly or wired with other devices to exchange data. Although the lane binding device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0130] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0131] The lane binding device provided by the present application adopts the lane binding method in the above embodiment to solve the technical problem of lane binding. Compared with the prior art, the beneficial effects of the lane binding device provided by the present application are the same as the beneficial effects of the lane binding method provided by the above embodiment, and the other technical features in the lane binding device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0132] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0133] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0134] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the lane binding method in the above-mentioned embodiment.

[0135] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0136] The computer-readable storage medium may be included in the lane binding device; or may exist independently without being assembled into the lane binding device.

[0137] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the lane binding device, the lane binding device: obtains the coordinates of the lane trajectory points and the vehicle coordinates; filters the lane trajectory points according to the coordinates of the lane trajectory points to obtain filtered lane trajectory points; calculates the projection distance from the vehicle to the lane according to the coordinates of the filtered lane trajectory points and the vehicle coordinates; determines the target lane that meets the preset binding conditions based on the projection distance, and binds the vehicle to the target lane.

[0138] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0139] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0140] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0141] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above lane binding method, and can solve the technical problem of lane binding. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the lane binding method provided in the above embodiment, and will not be repeated here.

[0142] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

Claims

1. A lane binding method, characterized in that: The lane binding method comprises: Get the coordinates of lane trajectory points and vehicle coordinates; filtering the lane trajectory points according to the coordinates of the lane trajectory points to obtain filtered lane trajectory points; Calculating a projection distance from the vehicle to the lane based on the coordinates of the filtered lane trajectory points and the vehicle coordinates; A target lane that meets a preset binding condition is determined based on the projection distance, and the vehicle is bound to the target lane.

2. The method according to claim 1, characterized in that The step of filtering the lane trajectory points according to the coordinates of the lane trajectory points to obtain filtered lane trajectory points comprises: Traversing the lane trajectory points to obtain pairwise adjacent lane trajectory points; Calculating offset information of the pairwise adjacent lane trajectory points according to the coordinates of the pairwise adjacent lane trajectory points; The lane trajectory points are filtered according to the offset information and a preset offset threshold to obtain filtered lane trajectory points.

3. The method according to claim 2, characterized in that The step of calculating the offset information of the pairwise adjacent lane trajectory points according to the coordinates of the pairwise adjacent lane trajectory points comprises: Calculating the lateral offset and the longitudinal offset of the two adjacent lane trajectory points according to the coordinates of the two adjacent lane trajectory points; Calculating an offset angle according to the lateral offset and the longitudinal offset; The offset information of the pairwise adjacent lane trajectory points is obtained according to the offset angle.

4. The method according to claim 1, characterized in that The step of calculating the projection distance from the vehicle to the lane according to the filtered coordinates of the lane trajectory points and the vehicle coordinates comprises: Traversing the filtered lane trajectory points to obtain the filtered lane trajectory points that are adjacent to each other; Calculating the projection distance from the vehicle to the lane trajectory points adjacent to each other after filtering according to the coordinates of the lane trajectory points adjacent to each other after filtering and the vehicle coordinates, to obtain a plurality of projection distances; The plurality of projection distances are compared, and a minimum projection distance is obtained as the projection distance from the vehicle to the lane.

5. The method according to claim 2, characterized in that The step of calculating the projection distance from the vehicle to the pairwise adjacent lane trajectory points after filtering according to the coordinates of the pairwise adjacent lane trajectory points after filtering and the vehicle coordinates comprises: Calculating vectors between the vehicle and the pairwise adjacent lane trajectory points after filtering according to the coordinates of the pairwise adjacent lane trajectory points after filtering and the vehicle coordinates; Calculating the cosine value of the angle between the vehicle and the filtered lane trajectory points adjacent to each other according to the vector; The projection distance from the vehicle to the lane line is calculated according to the cosine value of the angle, the coordinates of the lane trajectory points adjacent to each other after filtering, and the vehicle coordinates.

6. The method according to claim 5, characterized in that The filtered lane trajectory points adjacent to each other include a first trajectory point and a second trajectory point, and the step of calculating the vectors between the vehicle and the filtered lane trajectory points adjacent to each other according to the coordinates of the filtered lane trajectory points adjacent to each other and the vehicle coordinates includes: Calculating a first vector from the first trajectory point to the vehicle coordinates according to the first trajectory point and the vehicle coordinates; Calculating a second vector from the second trajectory point to the vehicle coordinates according to the second trajectory point and the vehicle coordinates; Calculating a lane trajectory vector from the first trajectory point to the second trajectory point according to the first trajectory point and the second trajectory point; According to the first vector, the second vector and the lane trajectory vector, vectors of the vehicle and the lane trajectory points adjacent to each other after filtering are obtained.

7. The method according to claim 4, characterized in that The step of determining a target lane that meets a preset binding condition based on the projection distance and binding the vehicle to the target lane includes: Compare the minimum projection distance with a preset distance threshold to obtain a comparison result; If the comparison result is that the minimum projection distance is less than the preset distance threshold, then obtaining the lane trajectory point corresponding to the minimum projection distance; A target lane is determined according to a lane trajectory point corresponding to the minimum projection distance, and the vehicle is bound to the target lane.

8. A lane binding device, characterized in that: The lane binding device comprises: An acquisition module, used to acquire the coordinates of lane trajectory points and vehicle coordinates; A trajectory point filtering module, used for filtering lane trajectory points according to the coordinates of the lane trajectory points to obtain filtered lane trajectory points; A projection distance calculation module, used to calculate the projection distance from the vehicle to the lane according to the coordinates of the filtered lane trajectory points and the vehicle coordinates; A lane binding module is used to determine a target lane that meets a preset binding condition based on the projection distance, and bind the vehicle to the target lane.

9. A lane binding device, characterized in that: The lane binding device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the lane binding method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the lane binding method according to any one of claims 1 to 7 are implemented.

Images