CN117765497A

CN117765497A - Lane line determination method, lane line determination device, computer equipment, medium and computer product

Info

Publication number: CN117765497A
Application number: CN202311829473.8A
Authority: CN
Inventors: 魏成志; 何煜埕; 潘晓鹏; 朱罗成; 王建州
Original assignee: Jiangsu Aerospace Dawei Technology Co Ltd
Current assignee: Jiangsu Aerospace Dawei Technology Co Ltd
Priority date: 2023-12-27
Filing date: 2023-12-27
Publication date: 2024-03-26

Abstract

The application relates to a lane line determination method, a lane line determination device, a computer device, a medium and a computer product. The method comprises the following steps: determining a first lane line corresponding to a first edge lane in a road section, and acquiring an initial width value between the first edge lane and a second edge lane in the road section; acquiring position information corresponding to each vehicle, determining an initial lane line corresponding to a second edge lane according to the initial width value and the first lane line, judging the position relation between each position information and the first lane line, and judging the position relation between each position information and the initial lane line to obtain a judging result; and carrying out iterative updating on the initial width value and the initial lane line according to the judging result, stopping iterative updating and obtaining a target width value and a target lane line under the condition that the judging result accords with the preset position condition, and determining the lane lines of the road section according to the preset number of lanes and the target width value. The method is simple and high in stability, accuracy can be improved through radar detection information, and cost is reduced.

Description

Lane line determination method, lane line determination device, computer equipment, medium and computer product

Technical Field

The application relates to the technical field of intelligent traffic, in particular to a lane line determining method, a lane line determining device, computer equipment, a medium and a computer product.

Background

In an intelligent traffic system, real-time traffic information of a road can be detected through a radar, and the detected real-time traffic information can be applied to scenes such as speed measurement feedback, curve early warning and traffic flow analysis. In the application process, the road divides the road surface through the lane lines to obtain road surface parameter information, such as the number of lanes and the length of road sections, and the different traffic situation analysis information is corresponding to the different number of lanes and the length of road sections, so that the traffic situation analysis is carried out by determining the lane line information of the road surface and combining the vehicle coordinate information and the speed information of the road, and the information of traffic flow, vehicle queuing and the like in the real-time traffic information can be obtained.

Currently, in a laser radar detection method, an echo signal is received by a laser radar, a road surface and a lane line are distinguished according to echo width information of the echo signal, or reflected light is received by the laser radar, a gray scale is generated according to reflection intensity of the reflected light, invalid information is filtered, and lane line information is obtained. In the image detection method, the region of the lane line can be cut through edge detection, and then the lane line is detected by combining with algorithms such as Hough transformation and the like, so that lane line information is obtained. In the deep learning method, lane characteristics are extracted from original sample data to identify lanes, a large amount of original sample data is trained to obtain a lane line identification model, and lane line information in an actual traffic scene is detected according to the lane line identification model. However, the detection cost of the prior art is high, and the detection effect is unstable and the detection efficiency is low under the influence of factors such as weather environment, traffic environment, lane shape and the like.

Disclosure of Invention

Based on this, it is necessary to provide a lane line determination method, apparatus, computer device, medium and computer product in view of the above technical problems.

In a first aspect, the present application provides a lane line determining method, including:

determining a first lane line corresponding to a first edge lane in a road section, and acquiring an initial width value between the first edge lane and a second edge lane in the road section, wherein the initial width value is in a preset width interval, and the road section comprises lanes with the number of preset lanes;

acquiring position information corresponding to each vehicle, determining an initial lane line corresponding to a second edge lane according to the initial width value and the first lane line, judging the position relation between each position information and the first lane line, and judging the position relation between each position information and the initial lane line to obtain a judging result;

and carrying out iterative updating on the initial width value and the initial lane line according to the judging result, stopping iterative updating and obtaining a target width value and a target lane line under the condition that the judging result accords with the preset position condition, and determining the lane lines of the road section according to the preset number of lanes and the target width value.

In one embodiment, performing iterative update on the initial width value and the initial lane line according to the judgment result, stopping iterative update and obtaining the target width value and the target lane line when the judgment result meets the preset position condition, including:

If the target position information corresponding to the target vehicle is not in the middle of the first lane line and the initial lane line, updating the initial width value to obtain an updated initial width value;

updating the initial lane line according to the updated initial width value and the first lane line to obtain an updated initial lane line;

and judging the position relation between the position information corresponding to each vehicle and the updated initial lane line, stopping iterative updating if each vehicle is positioned between the first lane line and the updated initial lane line, taking the updated initial width value as a target width value, and taking the updated initial lane line as a target lane line.

In one embodiment, after stopping the iterative updating and obtaining the target width value and the target lane line, the method further comprises:

acquiring the initial road section length of a road section;

and iteratively updating the initial road section length until the target vehicle is not in the middle of the first lane line and the target lane line corresponding to the initial road section length, stopping the iterative updating and obtaining the target road section length.

In one embodiment, determining a first lane line corresponding to a first edge lane in a road segment includes:

determining a first straight line and a second straight line in the road section, wherein the first straight line and the second straight line are parallel;

Acquiring a plurality of intersection points of each vehicle and a first straight line to obtain a first intersection point set; acquiring a plurality of intersection points of each vehicle and a second straight line to obtain a second intersection point set;

clustering from a first intersection point set to obtain a first target set, and determining a first edge intersection point corresponding to a first edge lane in the first target set; clustering from a second intersection point set to obtain a second target set, and determining a second edge intersection point corresponding to the first edge lane in the second target set;

a first lane line is determined from the first edge intersection and the second edge intersection.

In one embodiment, clustering from the first set of intersection points to obtain a first set of targets includes:

acquiring an initial set based on the number of preset lanes of the road section;

determining the distance between each intersection point in the first intersection point set and the initial set, and calculating a loss value corresponding to the initial set according to the distance;

and iteratively updating the initial set according to the distance, and stopping iteration and obtaining a first target set when the preset condition is met.

In one embodiment, a first target set is obtained by clustering from a first intersection set, and a first edge intersection corresponding to a first edge lane is determined in the first target set, and the method further includes:

Acquiring the number of vehicles in a road section, and determining a first threshold according to the number of vehicles;

when the number of vehicles is greater than or equal to a first threshold value, clustering the first intersection point set to obtain a first edge intersection point;

the first set of intersections is reset when the number of vehicles is greater than or equal to a second threshold, wherein the second threshold is greater than the first threshold.

In a second aspect, the present application further provides a lane line determining apparatus, including:

the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for determining a first lane line corresponding to a first edge lane in a road section, and acquiring an initial width value between the first edge lane and a second edge lane in the road section, wherein the initial width value is in a preset width interval, and a plurality of vehicles exist in the road section;

the judging module is used for acquiring the position information corresponding to each vehicle, determining an initial lane line corresponding to the second edge lane according to the initial width value and the first lane line, judging the position relation between each position information and the first lane line, and judging the position relation between each position information and the initial lane line to obtain a judging result;

and the updating module is used for carrying out iterative updating on the initial width value and the initial lane line according to the judging result, stopping iterative updating and obtaining the target width value and the target lane line under the condition that the judging result accords with the preset position condition, and determining the first lane line and the target lane line as the lane lines of the road section.

In a third aspect, the present application also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

In a fifth aspect, the present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of:

The lane line determining method, the lane line determining device, the computer equipment, the medium and the computer product are used for determining a first lane line corresponding to a first edge lane in a road section and acquiring an initial width value between the first edge lane and a second edge lane in the road section, wherein the initial width value is in a preset width interval, and the road section comprises lanes with the number of preset lanes; acquiring position information corresponding to each vehicle, determining an initial lane line corresponding to a second edge lane according to the initial width value and the first lane line, judging the position relation between each position information and the first lane line, and judging the position relation between each position information and the initial lane line to obtain a judging result; and carrying out iterative updating on the initial width value and the initial lane line according to the judging result, stopping iterative updating and obtaining a target width value and a target lane line under the condition that the judging result accords with the preset position condition, and determining the lane lines of the road section according to the preset number of lanes and the target width value. The method can determine the positions of the lane lines in the road section according to the first lane line and the target width value by iteratively updating the initial width value, so that the lane line is determined, the method is simple and high in stability, the method can be applied to the radar detection field in the intelligent traffic field, a coordinate system is constructed through the radar, the positions of the lane lines are determined in the coordinate system according to the vehicle coordinate information and the speed information detected by the radar, the accuracy and the efficiency of road section traffic condition analysis are improved, and the cost is reduced.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for a person having ordinary skill in the art.

FIG. 1 is an application environment diagram of a lane line determination method in one embodiment;

FIG. 2 is a flow chart of a lane line determination method according to an embodiment;

FIG. 3 is a flow chart of a lane line determination method according to another embodiment;

FIG. 4 is a block diagram showing the construction of a lane line determining apparatus in one embodiment;

FIG. 5 is an internal block diagram of a computer device as a terminal in one embodiment;

fig. 6 is an internal structural diagram of a computer device as a server in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

The lane line determining method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The terminal 102 determines a first lane line corresponding to a first edge lane in a road section, and acquires an initial width value between the first edge lane and a second edge lane in the road section, wherein the initial width value is in a preset width interval, and the road section comprises lanes with preset number of lanes; acquiring position information corresponding to each vehicle, determining an initial lane line corresponding to a second edge lane according to the initial width value and the first lane line, judging the position relation between each position information and the first lane line, and judging the position relation between each position information and the initial lane line to obtain a judging result; and carrying out iterative updating on the initial width value and the initial lane line according to the judging result, stopping iterative updating and obtaining a target width value and a target lane line under the condition that the judging result accords with the preset position condition, and determining the lane lines of the road section according to the preset number of lanes and the target width value. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.

In an exemplary embodiment, as shown in fig. 2, a lane line determining method is provided, and the method is applied to the terminal 102 in fig. 1 for illustration, and includes the following steps 202 to 206.

Wherein:

step 202, determining a first lane line corresponding to a first edge lane in a road section, and acquiring an initial width value between the first edge lane and a second edge lane in the road section, wherein the initial width value is in a preset width interval, and the road section comprises lanes with preset number of lanes.

The road comprises an ascending lane and a descending lane, the ascending lane and the descending lane are used for describing lanes of different vehicle driving directions in the bidirectional lanes, the road section is a road area with a specific length in the ascending lane or the descending lane, and the road section can be a straight line section or a curve section. The first and second edge lanes refer to lanes at different edge positions of the same road section, for example, the first edge lane may be a rightmost lane of the downlink lane, and the second edge lane may be a leftmost lane of the downlink lane. Lane lines refer to lines in the road, such as solid lines, broken lines, for example, that identify the direction of travel of the vehicle and separate lanes.

In the process of determining the lane line of the road to be detected, taking the downlink lane of the road to be detected as an example, dividing the downlink lane according to the initial road section length to obtain a plurality of road sections, and determining the lane line of each road section to obtain the lane line of the downlink lane of the road to be detected. The millimeter wave radar is used for detecting position information and speed information of vehicles in a road, a detection coordinate system is built by taking the position of the millimeter wave radar as an origin and the radar irradiation direction as a coordinate system longitudinal axis, a lane line expression of a first lane line can be determined in the detection coordinate system according to the position information of the vehicles of the first lane line in the detection coordinate system, and the first lane line can be determined according to the lane line expression. In an actual scenario, the lane width value between the lanes may be 2.8,3,3.25,3.5 and 3.75, etc., the preset number of lanes of the road section is obtained, the initial width value between the first edge lane and the second edge lane may be determined according to the number of lanes and the lane width value, and the distance value between the lane line expression of the first lane line and the lane line expression of the second lane line in the detection coordinate system may be determined, for example, if the initial width value is 2.8 and the lane number is 3, the distance value between the lane line expression of the first lane line and the lane line expression of the second lane line is 2.8×3=8.4.

Step 204, obtaining the position information corresponding to each vehicle, determining an initial lane line corresponding to the second edge lane according to the initial width value and the first lane line, judging the position relation between each position information and the first lane line, and judging the position relation between each position information and the initial lane line to obtain a judging result.

The positional relationship is a positional relationship of a pointing and a straight line, and includes that the vehicle is on a lane line, that the vehicle is above the lane line, and that the vehicle is below the lane line. The judgment result includes that the vehicle is between the first lane line and the second lane line, and the vehicle is not between the first lane line and the second lane line.

As an example, if the road section is a straight road section, the lane line expression of the first lane line is a first lane equation, the inclination angle of the first lane line with respect to the longitudinal axis direction of the detection coordinate system in which the expression of the second lane line can be obtained by translating the first lane equation, the expression of the second lane line being a second lane equation, and the translation value being the lane offset value can be calculated from the inclination angle and the initial width value, as in the foregoing embodiment. If the road section is an arc road section, the first road line and the second road line can be concentric circles with a common center, a first radius corresponding to the first road line is larger than a second radius corresponding to the second road line, the initial width value is a radius difference between the first radius and the second radius, a second road equation can be determined according to the first road equation and the radius difference, and the position of the second road line in the detection coordinate system can be determined according to the second road equation. When a plurality of vehicles move between lanes of the road section, the position point of each vehicle in the detection coordinate system is acquired through the millimeter wave radar, whether the position point of each vehicle is between a first lane equation and a second lane equation or not is judged, namely, whether the vehicle is above the first lane equation, and the vehicle is below the second lane equation or not is judged, for example, whether the position point of each vehicle in the detection coordinate system is above the first lane equation, and whether the vehicle is below the second lane equation or not is judged, and a judgment result is obtained.

And 206, carrying out iterative updating on the initial width value and the initial lane line according to the judging result, stopping iterative updating and obtaining a target width value and a target lane line under the condition that the judging result accords with the preset position condition, and determining the lane lines of the road section according to the preset number of lanes and the target width value.

The preset position condition may be that the vehicle is between a first lane line corresponding to the first edge lane and a target lane line corresponding to the second edge lane.

In an exemplary embodiment, when the determination result does not meet the preset position condition, the initial width value is iteratively updated in the preset width interval, for example, the initial width value is 2.8, the initial width value is updated to 3, the second lane equation is redetermined according to the initial width value, and the positional relationship between each vehicle and the first lane equation and the second lane equation is redetermined until the determination result meets the preset position condition, the initial width value and the second lane equation are fixed, so as to obtain the target width value and the target lane equation, the first lane equation is used as the lane line expression of the first edge lane in the detection coordinate system, the target lane equation is used as the lane line expression of the second edge lane in the detection coordinate system, and the lane equation corresponding to each lane of the road section can be determined according to the first lane equation and the lane width value, so as to determine the lane line of the road section in the detection coordinate system.

In the lane line determining method, a first lane line corresponding to a first edge lane in a road section is determined, and an initial width value between the first edge lane and a second edge lane in the road section is obtained, wherein the initial width value is in a preset width interval, and the road section comprises lanes with the number of preset lanes; acquiring position information corresponding to each vehicle, determining an initial lane line corresponding to a second edge lane according to the initial width value and the first lane line, judging the position relation between each position information and the first lane line, and judging the position relation between each position information and the initial lane line to obtain a judging result; and carrying out iterative updating on the initial width value and the initial lane line according to the judging result, stopping iterative updating and obtaining a target width value and a target lane line under the condition that the judging result accords with the preset position condition, and determining the lane lines of the road section according to the preset number of lanes and the target width value. The method can determine the positions of the lane lines in the road section according to the first lane line and the target width value by iteratively updating the initial width value, so that the lane line is determined, the method is simple and high in stability, the method can be applied to the radar detection field in the intelligent traffic field, a coordinate system is constructed through the radar, the positions of the lane lines are determined in the coordinate system according to the vehicle coordinate information and the speed information detected by the radar, the accuracy and the efficiency of road section traffic condition analysis are improved, and the cost is reduced.

In one embodiment, performing iterative update on the initial width value and the initial lane line according to the judgment result, stopping iterative update and obtaining the target width value and the target lane line when the judgment result meets the preset position condition, including: if the target position information corresponding to the target vehicle is not in the middle of the first lane line and the initial lane line, updating the initial width value to obtain an updated initial width value; updating the initial lane line according to the updated initial width value and the first lane line to obtain an updated initial lane line; and judging the position relation between the position information corresponding to each vehicle and the updated initial lane line, stopping iterative updating if each vehicle is positioned between the first lane line and the updated initial lane line, taking the updated initial width value as a target width value, and taking the updated initial lane line as a target lane line. And in the preset width interval, if the initial width value does not exist, so that each vehicle is positioned between the first lane line and the initial lane line, the first lane line is acquired again, and the target lane line is determined according to the updated first lane line and the initial width value.

Illustratively, as in the previous embodiments, the initial width value is an estimated value of the lane width, and thus, it is necessary to verify the two lane equations determined from the first lane equation and the initial width value. In the verification process, when each lane acquires the position points of a plurality of vehicles in a detection coordinate system when the vehicles move on a road section with the initial road section length, judging the position relation between each position point and each lane equation in the detection coordinate system, when the position points are not between the first lane equation and the second lane equation, verifying that the second lane equation does not pass, and when the lane lines in the actual scene are not matched with the second lane equation in the detection coordinate system, updating the second lane equation by updating the initial width value until each position point is between the first lane equation and the second lane equation, verifying that the second lane equation passes, and the lane lines in the actual scene are matched with the second lane equation in the detection coordinate system. And determining a lane line of the second edge lane according to the verified second lane equation to obtain a target lane line, and taking the target lane line and the first lane line as the lane lines of the road section.

In this embodiment, if the vehicle does not move between the lane equations, there may be an error in the lane equations, and thus, verifying whether the vehicle moves between the lane equations may improve the accuracy of the lane lines and the lane equations.

In one embodiment, after the stopping the iterative updating and obtaining the target width value and the target lane line, the method further includes: acquiring the initial road section length of the road section; and iteratively updating the initial road section length until the target vehicle is not in the middle of the first lane line and the target lane line corresponding to the initial road section length, stopping the iterative updating and obtaining the target road section length.

The initial link length refers to each link length preset when the links are divided.

In an exemplary embodiment, each vehicle moves between a first edge lane and a second edge lane corresponding to the initial road segment length, an update step of the road segment length is set to 1, the initial road segment length may be increased, after the road segment length is increased, if each vehicle continues to move between the first edge lane and the second edge lane, that is, a position point corresponding to each vehicle is between a first lane equation and a target lane equation, the initial road segment length is iteratively updated according to the update step until the position point corresponding to the target vehicle is not between the first lane equation and the target lane equation, and the iterative update of the road segment length is stopped to obtain the target road segment length.

In this embodiment, the accuracy and reliability of the lane equation can be improved by continuously increasing the road length by updating the step length and judging whether the vehicle moves between the lane equation and the quadrangle of the road length.

In one embodiment, determining a first lane line corresponding to a first edge lane in a road segment includes: determining a first straight line and a second straight line in the road section, wherein the first straight line and the second straight line are parallel; acquiring a plurality of intersection points of each vehicle and a first straight line to obtain a first intersection point set; acquiring a plurality of intersection points of each vehicle and a second straight line to obtain a second intersection point set; clustering from a first intersection point set to obtain a first target set, and determining a first edge intersection point corresponding to a first edge lane in the first target set; clustering from a second intersection point set to obtain a second target set, and determining a second edge intersection point corresponding to the first edge lane in the second target set; a first lane line is determined from the first edge intersection and the second edge intersection.

The first straight line may be a stop line of the first road section or a start line of the current road section, and the start line of the current road section is a stop line of the previous road section; the second straight line may be a termination line of the current road segment, and the termination line of the current road segment is a start line of the next road segment. Clustering refers to the automatic grouping of objects or samples in a dataset by their similarity or distance measures, which is used to separate dissimilar data points by finding the inherent structure and pattern within the data, and grouping similar data points into one class.

For example, if the road segment is the first straight road segment of the road in the intersection scene, the first straight line of the first straight road segment is the stop line of the intersection, and if the radar irradiation direction is opposite to the vehicle running direction, the running direction of each vehicle is the negative half-axis direction of the longitudinal axis of the detection coordinate system, and the longitudinal coordinate value PT of each vehicle in the longitudinal axis direction of the detection coordinate system is obtained _j Where j is the vehicle identification, when PT _j At minimum, the vehicle is at the stop line position at the intersection, i.e. PT _j The minimum value of (2) represents the ordinate value of each lane equation at the stop line position. And if the straight line direction corresponding to the second edge lane to the first edge lane is the positive half-axis direction of the transverse axis, acquiring intersection points of each vehicle and the first straight line and the second straight line through the radar when a plurality of vehicles move in the first path section and the number of the vehicles reaches a preset threshold value, and obtaining a first intersection point set and a second intersection point set. Adopting a K-means clustering algorithm to cluster the first intersection point set and the second intersection point set respectively, taking the first intersection point set as an example, adopting different clustering numbers to iteratively cluster the first intersection point set, calculating a loss function corresponding to each clustering number, determining the optimal clustering number of the first intersection point set under different clustering numbers according to the loss function, stopping iteration when the optimal clustering number is equal to the number of lanes, taking the intersection point set obtained by the current clustering as a first target set, wherein the first target set is used for representing the clustering centers of a first straight line corresponding to a plurality of intersection points of a plurality of lane lines, and because of the straight line direction from the second edge lane to the first edge lane The maximum value of the abscissa in the clustering center corresponding to the first straight line is the abscissa of the intersection point of the first straight line and the first lane equation, and further, the abscissa value is the clustering center point, and the abscissa value can be corrected through the offset value, so that the first abscissa value of the intersection point of the first lane equation and the first straight line is obtained. And clustering the second intersection point set on the second straight line to obtain a second target set corresponding to the second intersection point set, and obtaining a second abscissa value of the intersection point of the first lane equation and the second straight line according to the maximum value of the abscissa of the clustering center in the second target set. In the detection coordinate system, a first intersection point of a first intersection point set is determined according to a first abscissa value, a second intersection point of a second intersection point set is determined according to a second abscissa value, an inclination angle of a first lane equation relative to a longitudinal axis is determined according to the first intersection point and the second intersection point, a first lane equation is determined according to the inclination angle, the first intersection point and a linear coordinate equation, and then a first lane line is determined.

If the road section is a first arc road section of a road under an intersection scene, dividing the first arc road section by a first straight line, a second straight line and a third straight line, wherein the first straight line is a stop line of the first arc road section, the second straight line is a stop line of the first arc road section, the third straight line is arranged between the first straight line and the second straight line, the third straight line is parallel to the first straight line and the second straight line and has equal distance, intersection point sets of vehicles and the first straight line, the second straight line and the third straight line are respectively obtained, the first intersection point set, the second intersection point set and the third intersection point set are obtained, the first intersection point set, the second intersection point set, the third intersection point set and the first intersection point, the second intersection point and the third intersection point of a first vehicle equation are clustered, and the first vehicle equation is determined according to the coordinate equation of the first intersection point, the second intersection point, the third intersection point and the circle, and the first vehicle line is further determined.

In the embodiment, the intersection point sets are clustered, so that the coordinate values of the edge lanes can be automatically extracted, and the efficiency and the accuracy of lane line determination are improved. And the intersection points of the vehicles are obtained in real time, the lane equation of the edge lanes can be determined according to the clustering result of the real-time intersection point set, and the lane information can be updated in real time and is suitable for the changes of lanes of different road segments.

In one embodiment, clustering from the first set of intersection points to obtain a first set of targets includes: acquiring an initial set based on the number of preset lanes of the road section; determining the distance between each intersection point in the first intersection point set and the initial set, and calculating a loss value corresponding to the initial set according to the distance; and iteratively updating the initial set according to the distance, and stopping iteration and obtaining a first target set when the preset condition is met. The preset conditions may be iteration times, unchanged cluster centers, error adjustment, minimum and the like, the initial set refers to a set of initial cluster centers determined by first clustering of the first intersection point set, and the first target set refers to a set of target cluster centers determined by completing clustering of the first intersection point set.

For example, when the first intersection point set is clustered, the number of lanes of the road segment is known, the first intersection point set can be clustered according to the number of lanes, a plurality of initial clustering centers can be determined according to the number of lanes to obtain an initial set, and different K values can be adopted for the number of the initial clustering centers when the first intersection point set is clustered. Judging Euclidean distance between each intersection point and each initial clustering center in the initial set, determining a first loss value of the current clustering according to the Euclidean distance of each intersection point, distributing each intersection point to the initial clustering center closest to the initial clustering center according to the Euclidean distance to obtain a first clustering result, re-determining the clustering center according to the first clustering result, determining a second loss value of the current clustering according to the updated clustering center, iteratively updating the clustering center, obtaining a target clustering result when the loss value is smaller than a preset threshold, completing clustering of the first intersection point set if the clustering number of the target clustering results is the same as the number of lanes, and taking the clustering center of the current clustering round number as the target clustering center corresponding to the target set.

In this embodiment, the number of lanes and the characteristics of lanes on different roads are different, and the intersection sets are clustered according to the number of lanes and the loss function, so that the clustering effect can be improved, and the accuracy of the lane lines can be further improved.

In one embodiment, a first target set is obtained by clustering from a first intersection set, and a first edge intersection corresponding to a first edge lane is determined in the first target set, and the method further includes: acquiring the number of vehicles in a road section, and determining a first threshold according to the number of vehicles; when the number of vehicles is greater than or equal to a first threshold value, clustering the first intersection point set to obtain a first edge intersection point; the first set of intersections is reset when the number of vehicles is greater than or equal to a second threshold, wherein the second threshold is greater than the first threshold.

The first threshold is used for representing the minimum value of the number of the intersection points when the first intersection point set is clustered, and the second threshold is used for representing the maximum value of the number of the intersection points in the first intersection point set.

Illustratively, each intersection point coordinate in the first intersection point set is stored in a first array, when the number of intersection point coordinates in the first array is greater than or equal to a multiple of the square number of the number of lanes, namely, the number of intersection points is greater than or equal to a first threshold value, the first intersection point set is clustered to obtain a first edge intersection point, and when the number of intersection point coordinates in the first array is greater than or equal to the maximum storage number of arrays, namely, the number of intersection point coordinates in the first intersection point set is greater than or equal to a second threshold value, the intersection point coordinates of the first intersection point set are cleared and the intersection point coordinates are acquired again.

In this embodiment, the clustering condition of the first intersection point set is determined through the first threshold, so that the clustering effect and the clustering accuracy are improved, and the quantity condition of the second intersection point set is determined through the second threshold, so that resources can be effectively saved, and the stability is improved.

In one exemplary embodiment, as shown in FIG. 3, a lane-line determination method is provided, which includes steps 302 through 318. Wherein:

step 302, determining a first straight line and a second straight line in a road section, wherein the first straight line and the second straight line are parallel; acquiring a plurality of intersection points of each vehicle and a first straight line to obtain a first intersection point set; and obtaining a plurality of intersection points of each vehicle and the second straight line to obtain a second intersection point set.

Illustratively, taking the downlink of an intersection as an example, the position of a vehicle is detected by radar in the downlinkInformation, establishing a radar detection coordinate system with a radar as an origin and a radar irradiation direction as a coordinate system longitudinal axis, wherein a vehicle traveling direction is a negative half-axis direction of the longitudinal axis, a direction from a second edge lane to a first edge lane is a positive half-axis direction of the transverse axis, dividing a downlink lane by an initial link length to obtain a plurality of links, numbering each link, taking a first link as a straight line in the first link, taking a stop line of an intersection as a first straight line of the first link, taking a stop line of the first link as a second straight line, and giving initial coordinate information (LF _ix ，LF _iy ) The number of lanes M of the first road section is set.

Step 304, acquiring the number of vehicles in the road section, and determining a first threshold according to the number of vehicles; and when the number of vehicles is greater than or equal to a first threshold value, acquiring an initial set corresponding to the first intersection point set based on the preset number of lanes of the road section.

The intersection point of the effective running vehicle running and the first road segment parking line is recorded by a radar and stored in an array LPC _j In the method, the intersection point of the first path segment termination line and the first path segment termination line is recorded and stored in an array LPL _j In which j is a number ranging from 0 to the effective number of vehicles, and when j is a multiple of the square of the lane number M, the number of lanes M is counted in each of the arrays LPC _j Sum array LPC _j Executing a K-means clustering algorithm, solving a loss function corresponding to each K value, judging that when the K value at the inflection point of the loss function is equal to the lane number M, judging the current clustering as an effective clustering result, and determining an array LPC _j The transverse coordinate value in the largest class after clustering and array LPL _j Obtaining the intersection point LPC of the first edge lane and the first road segment parking line by the maximum cross coordinate value in the clustered class _valid Coordinates, and an intersection point LPL of the first edge lane and the first road segment ending line _valid Is defined by the coordinates of (a).

Step 306, determining the distance between each intersection point in the first intersection point set and the initial set, and calculating a loss value corresponding to the initial set according to the distance; and iteratively updating the initial set according to the distance, and stopping iteration and obtaining a first target set when the preset condition is met.

Step 308, resetting the first intersection set when the number of vehicles is greater than or equal to a second threshold, wherein the second threshold is greater than the first threshold.

Step 310, clustering from a second intersection point set to obtain a second target set, and determining a second edge intersection point corresponding to the first edge lane in the second target set; a first lane line is determined from the first edge intersection and the second edge intersection.

Illustratively according to LPC _valid To update the abscissa value LF of the initial coordinate information by adding an offset value of two meters to the abscissa value of (2) _ix According to LPC _valid LPL (Low Density polyethylene) _valid Coordinate information can be used to determine the inclination angle of the straight line of the two points relative to the longitudinal axisBased on the inclination angle->Initial coordinate information (LF _ix ，LF _iy ) The lane equation of the first edge lane of the first road section can be obtained, and the lane offset value is obtained according to the lane width, so that the lane equations of all lane lines of the first road section are calculated.

Step 312, obtaining an initial width value between the first edge lane and the second edge lane in the road section, wherein the initial width value is within a preset width interval, and the road section comprises lanes with preset number of lanes.

The method includes the steps that whether the configuration information of a first road segment which is automatically corrected is reasonable is verified, when a vehicle enters the first road segment according to real-time vehicle position information, the relation between a vehicle position point and a first lane line and a last lane line is calculated in real time, whether the position information in the vehicle driving process is in a quadrangle determined by the length of the first lane line, the length of a second lane line and the length of an initial road segment are verified, when the real-time vehicle position information covers M lanes, whether the vehicle position points of all lanes are in the quadrangle is verified, if the vehicle position points are in accordance with position conditions, lane width values are obtained, and if the vehicle position points are not in accordance with the position conditions, the lane width values are updated.

Step 314, obtaining the position information corresponding to each vehicle, determining an initial lane line corresponding to the second edge lane according to the initial width value and the first lane line, judging the position relation between each position information and the first lane line, and judging the position relation between each position information and the initial lane line, if the target position information corresponding to the target vehicle is not in the middle of the first lane line and the initial lane line, updating the initial width value, and obtaining the updated initial width value.

For example, if the position condition is not met, the lane width value is adjusted, the corresponding set of the lane width values is {2.8,3,3.25,3.5,3.75}, the next value in the set is taken, and the lane equation is recalculated.

Step 316, updating the initial lane line according to the updated initial width value and the first lane line to obtain an updated initial lane line; and judging the position relation between the position information corresponding to each vehicle and the updated initial lane line, stopping iterative updating if each vehicle is positioned between the first lane line and the updated initial lane line, taking the updated initial width value as a target width value, and taking the updated initial lane line as a target lane line.

If there is no lane width value in the set corresponding to the lane width value, so that each vehicle is located between the first lane line and the initial lane line, the first lane line is redetermined according to the foregoing steps, an updated first lane line is obtained, and a target lane line is determined according to the updated set corresponding to the first lane line and the lane width value.

Step 318, obtaining an initial road segment length of the road segment; and iteratively updating the initial road section length until the target vehicle is not in the middle of the first lane line and the target lane line corresponding to the initial road section length, stopping the iterative updating and obtaining the target road section length.

The method includes the steps of obtaining the length omega of a current initial road section, adding one to the value omega, wherein the updating step length of omega is 1 meter, judging whether the position condition is met, if the position condition is met, continuing to increase omega, otherwise, outputting the value omega, storing the lane information of the current road section, taking omega as the position of a first road section ending line, configuring the next road section, and finishing the lane line determination of the current road when the number of the road section is equal to the number of the pre-configured road sections.

In this embodiment, a first lane line corresponding to a first edge lane in a road section is determined, and an initial width value between the first edge lane and a second edge lane in the road section is obtained, wherein the initial width value is within a preset width interval, and the road section includes lanes of a preset number of lanes; acquiring position information corresponding to each vehicle, determining an initial lane line corresponding to a second edge lane according to the initial width value and the first lane line, judging the position relation between each position information and the first lane line, and judging the position relation between each position information and the initial lane line to obtain a judging result; and carrying out iterative updating on the initial width value and the initial lane line according to the judging result, stopping iterative updating and obtaining a target width value and a target lane line under the condition that the judging result accords with the preset position condition, and determining the lane lines of the road section according to the preset number of lanes and the target width value. The method can determine the positions of the lane lines in the road section according to the first lane line and the target width value by iteratively updating the initial width value, so that the lane line is determined, the method is simple and high in stability, the method can be applied to the radar detection field in the intelligent traffic field, a coordinate system is constructed through the radar, the positions of the lane lines are determined in the coordinate system according to the vehicle coordinate information and the speed information detected by the radar, the accuracy and the efficiency of road section traffic condition analysis are improved, and the cost is reduced.

It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.

Based on the same inventive concept, the embodiment of the application also provides a lane line determining device for realizing the lane line determining method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the lane line determining device or lane line determining devices provided below may be referred to the limitation of the lane line determining method hereinabove, and will not be repeated here.

In an exemplary embodiment, as shown in fig. 4, there is provided a lane line determining apparatus 400 including: an acquisition module 402, a judgment module 404, and an update module 406, wherein:

an obtaining module 402, configured to determine a first lane line corresponding to a first edge lane in a road segment, and obtain an initial width value between the first edge lane and a second edge lane in the road segment, where the initial width value is within a preset width interval, and a plurality of vehicles exist in the road segment;

the judging module 404 is configured to obtain position information corresponding to each vehicle, determine an initial lane line corresponding to the second edge lane according to the initial width value and the first lane line, judge a position relationship between each position information and the first lane line, and judge a position relationship between each position information and the initial lane line, so as to obtain a judging result;

and the updating module 406 is configured to iteratively update the initial width value and the initial lane line according to the determination result, stop the iterative update and obtain the target width value and the target lane line when the determination result meets the preset position condition, and determine that the first lane line and the target lane line are the lane lines of the road section.

In one embodiment, the updating module 406 is further configured to update the initial width value if there is target location information corresponding to the target vehicle that is not located between the first lane line and the initial lane line, and obtain an updated initial width value; updating the initial lane line according to the updated initial width value and the first lane line to obtain an updated initial lane line; and judging the position relation between the position information corresponding to each vehicle and the updated initial lane line, stopping iterative updating if each vehicle is positioned between the first lane line and the updated initial lane line, taking the updated initial width value as a target width value, and taking the updated initial lane line as a target lane line.

In one embodiment, the updating module 406 is further configured to obtain an initial link length of the link; and iteratively updating the initial road section length until the target vehicle is not in the middle of the first lane line and the target lane line corresponding to the initial road section length, stopping the iterative updating and obtaining the target road section length.

In one embodiment, the obtaining module 402 is further configured to determine a first straight line and a second straight line in the road segment, where the first straight line and the second straight line are parallel; acquiring a plurality of intersection points of each vehicle and a first straight line to obtain a first intersection point set; acquiring a plurality of intersection points of each vehicle and a second straight line to obtain a second intersection point set; clustering from a first intersection point set to obtain a first target set, and determining a first edge intersection point corresponding to a first edge lane in the first target set; clustering from a second intersection point set to obtain a second target set, and determining a second edge intersection point corresponding to the first edge lane in the second target set; a first lane line is determined from the first edge intersection and the second edge intersection.

In one embodiment, the obtaining module 402 is further configured to obtain the initial set based on a preset number of lanes of the road segment; determining the distance between each intersection point in the first intersection point set and the initial set, and calculating a loss value corresponding to the initial set according to the distance; and iteratively updating the initial set according to the distance, and obtaining a first target set when the loss value is smaller than or equal to a preset threshold value.

In one embodiment, the obtaining module 402 is further configured to obtain a number of vehicles in the road segment, and determine the first threshold according to the number of vehicles; when the number of vehicles is greater than or equal to a first threshold value, clustering the first intersection point set to obtain a first edge intersection point; the first set of intersections is reset when the number of vehicles is greater than or equal to a second threshold, wherein the second threshold is greater than the first threshold.

The respective modules in the lane line determination apparatus described above may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one exemplary embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing lane line determination data. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a lane line determination method.

In an exemplary embodiment, a computer device, which may be a terminal, is provided, and an internal structure diagram thereof may be as shown in fig. 6. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a lane line determination method. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

It will be appreciated by persons skilled in the art that the foregoing structures, which are merely block diagrams of partial structures related to the aspects of the present application, are not limiting of the computer device to which the aspects of the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have different arrangements of components.

In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.

It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use, and processing of the related data are required to meet the related regulations.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. A lane line determination method, the method comprising:

Acquiring position information corresponding to each vehicle, determining an initial lane line corresponding to the second edge lane according to the initial width value and the first lane line, judging the position relation between each position information and the first lane line, and judging the position relation between each position information and the initial lane line to obtain a judging result;

and carrying out iterative updating on the initial width value and the initial lane line according to the judging result, stopping iterative updating and obtaining a target width value and a target lane line under the condition that the judging result accords with a preset position condition, and determining the lane lines of the road section according to the preset lane number and the target width value.

2. The method according to claim 1, wherein the iteratively updating the initial width value and the initial lane line according to the determination result, and stopping the iteratively updating and obtaining the target width value and the target lane line if the determination result meets a preset position condition, includes:

and judging the position relation between the position information corresponding to each vehicle and the updated initial lane line, stopping iterative updating if each vehicle is positioned between the first lane line and the updated initial lane line, taking the updated initial width value as the target width value, and taking the updated initial lane line as the target lane line.

3. The method of claim 2, wherein after the stopping the iterative updating and obtaining the target width value and the target lane line, the method further comprises:

acquiring the initial road section length of the road section;

4. The method of claim 1, wherein determining a first lane line corresponding to a first edge lane in the road segment comprises:

Acquiring a plurality of intersection points of each vehicle and the first straight line to obtain a first intersection point set; acquiring a plurality of intersection points of each vehicle and the second straight line to obtain a second intersection point set;

clustering from the first intersection point set to obtain a first target set, and determining a first edge intersection point corresponding to the first edge lane in the first target set; clustering from the second intersection point set to obtain a second target set, and determining a second edge intersection point corresponding to the first edge lane in the second target set;

and determining the first lane line according to the first edge intersection point and the second edge intersection point.

5. The method of claim 4, wherein clustering the first set of points of intersection to obtain a first set of targets comprises:

acquiring an initial set based on the preset number of lanes of the road section;

and iteratively updating the initial set according to the distance, and stopping iteration and obtaining the first target set when a preset condition is met.

6. The method of claim 5, wherein clustering the first set of intersection points to obtain a first target set, and determining a first edge intersection point corresponding to the first edge lane in the first target set, further comprises:

acquiring the number of vehicles in the road section, and determining a first threshold according to the number of vehicles;

when the number of vehicles is greater than or equal to the first threshold value, clustering the first intersection point set to obtain the first edge intersection point;

and resetting the first intersection set when the number of vehicles is greater than or equal to a second threshold, wherein the second threshold is greater than the first threshold.

7. A lane marking determining apparatus, the apparatus comprising:

the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for determining a first lane line corresponding to a first edge lane in a road section and acquiring an initial width value between the first edge lane and a second edge lane in the road section, wherein the initial width value is in a preset width interval, and the road section comprises lanes with the number of preset lanes;

And the updating module is used for carrying out iterative updating on the initial width value and the initial lane line according to the judging result, stopping iterative updating and obtaining a target width value and a target lane line under the condition that the judging result accords with a preset position condition, and determining the lane lines of the road section according to the preset lane number and the target width value.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.