CN115937447A - Lane recognition method, device and equipment in high-precision map - Google Patents
Lane recognition method, device and equipment in high-precision map Download PDFInfo
- Publication number
- CN115937447A CN115937447A CN202211532458.2A CN202211532458A CN115937447A CN 115937447 A CN115937447 A CN 115937447A CN 202211532458 A CN202211532458 A CN 202211532458A CN 115937447 A CN115937447 A CN 115937447A
- Authority
- CN
- China
- Prior art keywords
- lane
- line
- combination
- lane line
- distance threshold
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The application discloses a lane identification method, a lane identification device and lane identification equipment in a high-precision map, and belongs to the technical field of unmanned driving. The method comprises the following steps: generating n line segments according to a plurality of reference points set in each lane line; combining two lane lines of which the average value of the n included angles is smaller than an angle threshold value into a lane line combination, wherein the included angles are formed by line segments with the same number in the two lane lines; screening the lane line combinations with the average value of the n line segment intervals smaller than a second distance threshold, wherein the line segment intervals represent the distances between line segments with the same number in two lane lines; screening lane line combinations with the vertical distance between each reference point on one lane line and the other lane line being greater than a third distance threshold value, wherein the third distance threshold value is smaller than a second distance threshold value; and identifying the screened lane line combination with the minimum line segment spacing as two lane lines of one lane. According to the method and the device, the labor cost of drawing is saved, and the drawing efficiency is improved.
Description
Technical Field
The application relates to the technical field of unmanned driving, in particular to a lane identification method, a lane identification device and lane identification equipment in a high-precision map.
Background
The unmanned system mainly comprises modules of perception, positioning, decision planning, control, high-precision maps, prediction, simulation and the like, wherein the high-precision maps are used for providing important prior knowledge for other modules. For example, a high-precision map can provide anticipation information for an automatic driving system; for another example, lane, road, element information and dynamic traffic data in the high-precision map can be used for assisting high-precision positioning and performing high-precision three-dimensional representation on a road network; as another example, high-precision maps can aid in environmental perception; for another example, semantic information such as traffic lights, speed-limiting boards, road markings and the like in a high-precision map can assist in route planning and decision-making.
When a lane in a high-precision map is drawn, a point cloud map needs to be collected through a collection vehicle and collection equipment such as a related camera, a laser radar, a Global Positioning System (GPS) module, an Inertial Measurement Unit (IMU), a base station and the like, an operator draws a plurality of lane lines in a map editing platform based on the point cloud map, and then selects two lane lines from the plurality of lane lines to form a lane.
When a lane is generated, an operator is required to select two lane lines from a plurality of drawn lane lines to form a lane, and when the number of the lane lines is large, the lane drawing needs high labor cost and affects the drawing efficiency of a high-precision map.
Disclosure of Invention
The application provides a lane identification method, a lane identification device and lane identification equipment in a high-precision map, which are used for solving the problems that when lane lines are manually selected to form lanes, the labor cost is high, and the drawing efficiency of the high-precision map is influenced. The technical scheme is as follows:
in one aspect, a lane recognition method in a high-precision map is provided, and the method includes:
generating n line segments according to a plurality of reference points arranged in each lane line, wherein n is more than or equal to 2, and the distance between the line segments with the same number in different lane lines is less than a first distance threshold;
combining two lane lines of which the average value of n included angles is smaller than an angle threshold value into a lane line combination, wherein the included angles are formed by line segments with the same number in the two lane lines;
screening the lane line combinations with the average value of the n line segment intervals smaller than a second distance threshold, wherein the line segment intervals represent the distances between line segments with the same number in the two lane lines;
screening lane line combinations with the vertical distance between each reference point on one lane line and the other lane line being greater than a third distance threshold value, wherein the third distance threshold value is smaller than the second distance threshold value;
and identifying the screened lane line combination with the minimum line segment spacing as two lane lines of one lane.
In a possible implementation manner, the generating n line segments according to a plurality of reference points set in each lane line includes:
acquiring coordinate information of a plurality of reference points set in each lane line;
selecting n line segments from a plurality of line segments formed by taking the plurality of reference points as end points based on the coordinate information so that the distance between the end points of the line segments with the same number in different lane lines is smaller than the first distance threshold.
In a possible implementation manner, the combining two lane lines of which the average value of the n included angles is smaller than the angle threshold into one lane line combination includes:
for two lane lines traversed each time, acquiring an included angle formed by two line segments corresponding to each number to obtain n included angles;
calculating the average value of the n included angles;
if the average value of the n included angles is smaller than the angle threshold value, the two lane lines form a lane line combination;
and if the average value of the n included angles is larger than or equal to the angle threshold, performing next traversal.
In a possible implementation manner, the screening the lane line combinations where the average value of the n line segment distances is smaller than the second distance threshold includes:
for each traversed lane line combination, calculating the distance between two line segments corresponding to each number to obtain n line segment intervals;
calculating the average value of the n line segment intervals;
if the average value of the n line segment intervals is smaller than the second distance threshold, the lane line combination is reserved, and the next traversal is carried out;
and if the average value of the n line segment intervals is larger than or equal to the second distance threshold, rejecting the lane line combination and performing next traversal.
In a possible implementation manner, the screening a combination of lane lines in which a vertical distance between each reference point on one lane line and another lane line is greater than a third distance threshold includes:
for each traversed lane line combination, calculating the vertical distance between each reference point on one lane line and each line segment of the other lane line;
if all the vertical distances are larger than the third distance threshold, reserving the lane line combination and traversing for the next time;
and if at least one vertical distance is smaller than or equal to the third distance threshold, rejecting the lane line combination and performing next traversal.
In a possible implementation manner, the identifying the screened lane line combination with the smallest line segment spacing as two lane lines of one lane includes:
for each lane line, acquiring a lane line combination containing the lane line
If at least two lane line combinations are screened out, comparing the line segment spacing corresponding to each lane line combination;
and identifying the lane line combination with the minimum line segment spacing as two lane lines of one lane.
In one aspect, a lane recognition method in a high-precision map is provided, and the method includes:
selecting a first line segment and a last line segment in each lane line, wherein each line segment consists of a reference point set in the lane line;
forming a lane line combination by two lane lines of which the average value of two included angles is smaller than an angle threshold value, wherein the included angles are formed by line segments with the same number in the two lane lines;
screening the lane line combination with the average value of the line segment spacing smaller than a second distance threshold, wherein the line segment spacing represents the distance between line segments with the same number in the two lane lines;
screening lane line combinations with the vertical distance between each reference point on one lane line and the other lane line being greater than a third distance threshold value, wherein the third distance threshold value is smaller than the second distance threshold value;
and identifying the screened lane line combination with the minimum line segment spacing as two lane lines of one lane.
In one aspect, there is provided a lane recognition apparatus in a high-precision map, the apparatus including:
the generating module is used for generating n line segments according to a plurality of reference points arranged in each lane line, wherein n is larger than or equal to 2, and the distance between the line segments with the same number in different lane lines is smaller than a first distance threshold;
the combination module is used for combining two lane lines of which the angle average value of n included angles is smaller than an angle threshold value into a lane line combination, and the included angles are formed by line segments with the same number in the two lane lines;
the screening module is used for screening the lane line combinations with the average value of the n line segment distances smaller than a second distance threshold value, wherein the line segment distances represent the distances between line segments with the same number in two lane lines;
the screening module is further configured to screen a lane combination in which a vertical distance between each reference point on one lane line and another lane line is greater than a third distance threshold, and the third distance threshold is smaller than the second distance threshold;
and the identification module is used for identifying the screened lane line combination with the minimum line segment spacing as two lane lines of one lane.
In one aspect, there is provided a lane recognition apparatus in a high-precision map, the apparatus including:
the selection module is used for selecting a first line segment and a last line segment in each lane line, and each line segment consists of a reference point set in the lane line;
the combination module is used for combining two lane lines of which the average value of two included angles is smaller than an angle threshold value into a lane line combination, and the included angles are formed by line segments with the same number in the two lane lines;
the screening module is used for screening the lane line combination of which the average value of the line segment spacing is smaller than a second distance threshold, wherein the line segment spacing represents the distance between line segments with the same number in the two lane lines;
the screening module is further configured to screen a lane combination in which a vertical distance between each reference point on one lane line and another lane line is greater than a third distance threshold, and the third distance threshold is smaller than the second distance threshold;
and the identification module is used for identifying the screened lane line combination with the minimum line segment spacing into two lane lines of one lane.
In one aspect, a computer-readable storage medium having stored therein at least one instruction, which is loaded and executed by a processor, to implement a lane identification method in a high-precision map as described above is provided.
In one aspect, a computer device is provided, which includes a processor and a memory, the memory having stored therein at least one instruction, the instruction being loaded and executed by the processor to implement the lane identification method in a high-precision map as described above.
The technical scheme provided by the application has the beneficial effects that:
firstly, generating n line segments according to a plurality of reference points arranged in each lane line; then two lane lines with the average value of the n included angles smaller than the angle threshold value form a lane line combination; then, screening the lane line combination with the average value of the n line segment intervals smaller than a second distance threshold; screening lane line combinations with the vertical distance between each reference point on one lane line and the other lane line being greater than a third distance threshold value, wherein the third distance threshold value is smaller than the second distance threshold value; and finally, the screened lane line combination with the minimum line segment spacing is identified as two lane lines of one lane, so that the lane can be automatically identified according to the lane lines, the labor cost of drawing is saved, and the drawing efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of a method of lane identification in a high-precision map provided by an embodiment of the present application;
FIG. 2 is a schematic view of a lane line provided by one embodiment of the present application;
FIG. 3 is a flowchart of a method for lane identification in a high-precision map according to an embodiment of the present application;
fig. 4 is a block diagram illustrating a structure of a lane recognition apparatus in a high-precision map according to an embodiment of the present application;
fig. 5 is a block diagram illustrating a structure of a lane recognition device in a high-precision map according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a lane recognition method in a high-precision map, which may be applied to a computer device, according to an embodiment of the present application is shown. The lane recognition method in the high-precision map can comprise the following steps:
After a plurality of drawn lane lines are obtained, a plurality of reference points can be set on each lane line, and the setting rule is as follows: the reference points of the straight line sections of the lane lines are sparse, and the reference points of the bent sections of the lane lines are dense. Specifically, a plurality of reference points may be selected by a worker based on the setting rule, or a plurality of reference points may be selected by a computer device based on the setting rule.
After setting the plurality of reference points, we can generate n line segments based on all or part of the reference points. Specifically, generating n line segments according to a plurality of reference points set in each lane line may include: acquiring coordinate information of a plurality of reference points set in each lane line; from among a plurality of line segments formed with a plurality of reference points as end points, n line segments are selected based on coordinate information so that distances between end points of line segments having the same number among different lane lines are smaller than a first distance threshold.
In this embodiment, a value interval may be set according to an actual service requirement, and the first distance threshold may be selected in the value interval. In one example, the value interval may be set to [1,7] meters, and the first distance threshold may be any value between 1 and 7 meters.
Referring to the two lane lines shown in fig. 2, the dots on the lane lines represent reference points, and each two reference points form a line segment. In this embodiment, n =2 is assumed, and the n selected line segments are the first line segment and the last line segment in the lane line. At this time, the distance between the two end points of the first line segment in the first lane line and the two end points of the first line segment in the second lane line is smaller than a first distance threshold, and the distance between the two end points of the last line segment in the first lane line and the two end points of the last line segment in the second lane line is smaller than the first distance threshold.
It should be noted that the number of the line segment described in this embodiment refers to the number of the line segment in n line segments, not the number in the lane line. For example, if the first line segment and the last line segment in one lane line are selected as n line segments, the number of the first line segment is 1, and the number of the last line segment is 2; and selecting the second line segment and the last line segment in the other lane line as n line segments, wherein the number of the second line segment is 1, and the number of the last line segment is 2.
And 102, combining two lane lines of which the average value of the n included angles is smaller than an angle threshold value into a lane line combination, wherein the included angles are formed by line segments with the same number in the two lane lines.
For a plurality of lane lines, the computer equipment can traverse two lane lines each time, and if the two lane lines meet the condition, the two lane lines form a lane line combination to continue to traverse the next time; and if the two lane lines do not meet the condition, the two lane lines are not combined into a lane line combination, the next traversal is continued, and after the traversal is finished, a plurality of lane line combinations can be obtained.
Specifically, the step of combining two lane lines of which the average value of the n included angles is smaller than the angle threshold value into a lane line combination may include: for two lane lines traversed each time, acquiring an included angle formed by two line segments corresponding to each number to obtain n included angles; calculating the average value of n included angles; if the average value of the n included angles is smaller than the angle threshold value, forming a lane line combination by the two lane lines; and if the average value of the n included angles is larger than or equal to the angle threshold, performing next traversal.
When the included angle is generated, the direction of the lane lines needs to be considered, so that the included angle formed by the lane lines in the same direction is an acute angle, and the included angle formed by the lane lines in the opposite direction is an obtuse angle. Since the two lane lines of a lane must be oriented in the same direction, it is necessary to ensure that the angle threshold is less than 90 °.
In this embodiment, a value interval may be set according to actual service requirements, and an angle threshold may be selected in the value interval. In one example, the span can be set to [0, 30 ° ], and the angle threshold can be any value between 0 and 30 °. I.e. the angle threshold is less than 30 °.
And 103, screening the lane line combination with the average value of the n line segment intervals smaller than a second distance threshold, wherein the line segment intervals represent the distances between line segments with the same number in the two lane lines.
For a plurality of lane line combinations, the computer equipment can traverse one lane line combination each time, if two lane lines in the lane line combination meet the condition, the lane line combination is reserved, and the next traversal is continued; and if the two lane lines in the lane line combination do not meet the condition, removing the lane line combination, continuing to traverse for the next time, and after the traversing is finished, obtaining the number of the lane line combinations which is less than or equal to the number of the lane line combinations obtained in the step 102.
Specifically, screening the lane line combination in which the average value of the n line segment distances is smaller than the second distance threshold may include: for each traversed lane line combination, calculating the distance between two line segments corresponding to each number to obtain n line segment intervals; calculating the average value of the intervals of the n line segments; if the average value of the n line segment intervals is smaller than a second distance threshold, reserving the lane line combination and traversing for the next time; and if the average value of the intervals of the n line segments is greater than or equal to the second distance threshold, removing the lane line combination and traversing for the next time.
Taking n line segments including the first line segment and the last line segment as an example, the line segment spacing can be calculated by the following algorithm:
(1) Determining the vertical distance between a first reference point of one lane line and a first line segment of another lane line as a line segment space;
(2) Determining the vertical distance between the second reference point of one lane line and the first line segment of the other lane line as a line segment space;
(3) Determining the vertical distance between the first reference point of one lane line and the first line segment of the other lane line and the average value of the vertical distances between the second reference point of one lane line and the first line segment of the other lane line as a line segment interval;
(4) Determining the vertical distance between the last reference point of one lane line and the last line segment of the other lane line as a line segment space;
(5) Determining the vertical distance between the penultimate reference point of one lane line and the last line segment of the other lane line as a line segment space;
(6) And determining the vertical distance between the last reference point of one lane line and the last line segment of the other lane line and the average value of the vertical distances between the penultimate reference point of one lane line and the last line segment of the other lane line as a line segment space.
In this embodiment, a maximum value may be set according to actual service requirements, and the selected second distance threshold needs to be smaller than or equal to the maximum value. In one example, a maximum value of 8 meters may be set, and the second distance threshold may be a value less than or equal to 8 meters.
And 104, screening lane line combinations with the vertical distance between each reference point on one lane line and the other lane line being greater than a third distance threshold, wherein the third distance threshold is smaller than the second distance threshold.
For the plurality of lane line combinations screened in step 103, the computer device may continue to traverse one lane line combination at a time, and if two lane lines in the lane line combination satisfy the condition, the lane line combination is reserved and the next traversal is continued; and if the two lane lines in the lane line combination do not meet the condition, rejecting the lane line combination, continuing to traverse for the next time, and after the traversal is finished, obtaining the number of the lane line combinations smaller than or equal to the number of the lane line combinations obtained in the step 103.
Specifically, screening the lane line combination in which the vertical distance between each reference point on one lane line and the other lane line is greater than the third distance threshold may include: for each traversed lane line combination, calculating the vertical distance between each reference point on one lane line and each line segment of the other lane line; if all the vertical distances are larger than the third distance threshold, reserving the lane line combination and traversing for the next time; and if at least one vertical distance is smaller than or equal to the third distance threshold, removing the lane line combination and performing next traversal.
In this embodiment, a minimum value may be set according to an actual service requirement, and the selected third distance threshold needs to be greater than or equal to the maximum value. In one example, a minimum value of 1 meter may be set, and the third distance threshold may be a value greater than or equal to 1 meter.
And 105, identifying the screened lane line combination with the minimum line segment spacing as two lane lines of one lane.
For the plurality of lane line combinations retained after the filtering in step 104, the computer device may select a portion of the lane line combinations as lanes. Wherein one lane line is selected as a boundary of two lanes at most.
Specifically, identifying the combination of the screened lane lines with the smallest line segment distance as two lane lines of one lane may include: if one lane line combination is screened out, identifying the lane line combination as two lane lines of one lane; if at least two lane line combinations are screened out, comparing the line segment spacing corresponding to each lane line combination; and identifying the lane line combination with the minimum line segment spacing as two lane lines of one lane.
In the embodiment, the computer equipment firstly groups the lane lines and then screens the lane line combinations for multiple times, so that the lane lines of the lanes can be automatically identified, and the drawing efficiency of the high-precision map is improved.
In summary, in the lane identification method in the high-precision map provided by the embodiment of the present application, n line segments are generated according to a plurality of reference points set in each lane line; then two lane lines with the average value of the n included angles smaller than the angle threshold value form a lane line combination; then, screening the lane line combination with the average value of the n line segment intervals smaller than a second distance threshold; screening lane line combinations with the vertical distance between each reference point on one lane line and the other lane line being greater than a third distance threshold value, wherein the third distance threshold value is smaller than a second distance threshold value; finally, the selected lane line combination with the minimum line segment spacing is identified as two lane lines of one lane, so that the lane can be automatically identified according to the lane lines, the labor cost of drawing is saved, and the drawing efficiency is improved.
Referring to fig. 3, a flowchart of a method for recognizing a lane in a high-precision map provided by an embodiment of the present application is shown, where the method for recognizing a lane in a high-precision map may be applied to a computer device. The lane recognition method in the high-precision map can comprise the following steps:
After a plurality of drawn lane lines are obtained, a plurality of reference points can be set on each lane line, and the setting rule is as follows: the reference points of the straight line sections of the lane lines are sparse, and the reference points of the bent sections of the lane lines are dense. Specifically, a plurality of reference points may be selected by a worker based on the setting rule, or a plurality of reference points may be selected by a computer device based on the setting rule.
After setting the plurality of reference points, we can generate a plurality of line segments based on the reference points, and select a first line segment and a last line segment from the line segments. The first line segment is composed of a first reference point and a second reference point in one lane line, and the last line segment is composed of a last reference point and a penultimate reference point in one lane line. We can also number two segments in all lane lines, for example, number the first segment in all lane lines as 1 and the last segment in all lane lines as 2.
For a plurality of lane lines, the computer equipment can traverse two lane lines each time, and if the two lane lines meet the condition, the two lane lines form a lane line combination to continue to traverse the next time; and if the two lane lines do not meet the condition, the two lane lines are not combined into a lane line combination, the next traversal is continued, and a plurality of lane line combinations can be obtained after the traversal is finished.
Specifically, combining two lane lines of which the average value of the two included angles is smaller than the angle threshold into a lane line combination may include: for two lane lines traversed each time, acquiring an included angle formed by two line segments corresponding to each number to obtain two included angles; calculating the average value of the two included angles; if the average value of the two included angles is smaller than the angle threshold value, the two lane lines form a lane line combination; and if the average value of the two included angles is larger than or equal to the angle threshold, performing next traversal.
When the included angle is generated, the direction of the lane lines needs to be considered, so that the included angle formed by the lane lines in the same direction is an acute angle, and the included angle formed by the lane lines in the opposite direction is an obtuse angle. Since the two lane lines of a lane must be oriented in the same direction, it is necessary to ensure that the angle threshold is less than 90 °.
In this embodiment, a value interval may be set according to an actual service requirement, and an angle threshold may be selected in the value interval. In one example, the span can be set to [0, 30 ° ], and the angle threshold can be any value between 0 and 30 °. I.e. the angle threshold is less than 30 °.
For a plurality of lane line combinations, the computer equipment can traverse one lane line combination each time, if two lane lines in the lane line combination meet the condition, the lane line combination is reserved, and the next traversal is continued; and if the two lane lines in the lane line combination do not meet the condition, rejecting the lane line combination, and continuing to traverse for the next time, wherein after the traversal is finished, the number of the obtained lane line combinations is less than or equal to the number of the lane line combinations obtained in the step 302.
Specifically, screening the lane line combination in which the average value of the line segment distances is smaller than the second distance threshold may include: for each traversed lane line combination, calculating the distance between two line segments corresponding to each number to obtain the distance between the two line segments; calculating the average value of the distance between the two line segments; if the average value of the distance between the two line segments is smaller than a second distance threshold, reserving the lane line combination and traversing for the next time; and if the average value of the distance between the two line segments is greater than or equal to the second distance threshold, removing the lane line combination and traversing for the next time.
In this embodiment, the line segment distance may be calculated by the following algorithm:
(1) Determining the vertical distance between a first reference point of one lane line and a first line segment of another lane line as a line segment space;
(2) Determining the vertical distance between the second reference point of one lane line and the first line segment of the other lane line as a line segment space;
(3) Determining the vertical distance between the first reference point of one lane line and the first line segment of the other lane line and the average value of the vertical distances between the second reference point of one lane line and the first line segment of the other lane line as a line segment interval;
(4) Determining the vertical distance between the last reference point of one lane line and the last line segment of the other lane line as a line segment space;
(5) Determining the vertical distance between the penultimate reference point of one lane line and the last line segment of the other lane line as a line segment space;
(6) And determining the vertical distance between the last reference point of one lane line and the last line segment of the other lane line and the average value of the vertical distances between the penultimate reference point of one lane line and the last line segment of the other lane line as a line segment space.
In this embodiment, a maximum value may be set according to actual service requirements, and the selected second distance threshold needs to be smaller than or equal to the maximum value. In one example, a maximum value of 8 meters may be set, and the second distance threshold may be a value less than or equal to 8 meters.
And 304, screening lane line combinations with the vertical distance between each reference point on one lane line and the other lane line being greater than a third distance threshold, wherein the third distance threshold is smaller than the second distance threshold.
For a plurality of lane line combinations which are reserved after being screened in the step 303, the computer device may continue to traverse one lane line combination each time, if two lane lines in the lane line combination satisfy the condition, the lane line combination is reserved, and the next traversal is continued; and if the two lane lines in the lane line combination do not meet the condition, rejecting the lane line combination, continuing to traverse for the next time, and after the traversal is finished, obtaining the number of the lane line combinations smaller than or equal to the number of the lane line combinations obtained in the step 303.
Specifically, screening the lane line combinations in which the vertical distance between each reference point on one lane line and the other lane line is greater than the third distance threshold may include: for each traversed lane line combination, calculating the vertical distance between each reference point on one lane line and each line segment of the other lane line; if all the vertical distances are larger than the third distance threshold, reserving the lane line combination and traversing for the next time; and if at least one vertical distance is smaller than or equal to the third distance threshold, removing the lane line combination and traversing for the next time.
In this embodiment, a minimum value may be set according to an actual service requirement, and the selected third distance threshold needs to be greater than or equal to the maximum value. In one example, a minimum value of 1 meter may be set, and the third distance threshold may be a value greater than or equal to 1 meter.
And step 305, identifying the screened lane line combination with the minimum line segment spacing as two lane lines of one lane.
For the plurality of lane line combinations retained after the filtering in step 304, the computer device may select a portion of the lane line combinations as lanes. Wherein one lane line is selected as a boundary of two lanes at most.
Specifically, identifying the combination of the screened lane lines with the smallest line segment distance as two lane lines of one lane may include: if one lane line combination is screened out, identifying the lane line combination as two lane lines of one lane; if at least two lane line combinations are screened out, comparing the line segment spacing corresponding to each lane line combination; and identifying the lane line combination with the minimum line segment spacing as two lane lines of one lane.
In the embodiment, the computer equipment firstly groups the lane lines and then screens the lane line combinations for multiple times, so that the lane lines of the lanes can be automatically identified, and the drawing efficiency of the high-precision map is improved.
In summary, in the lane identification method in the high-precision map provided by the embodiment of the present application, a first line segment and a last line segment in each lane line are selected first; then combining two lane lines of which the average value of the two included angles is smaller than the angle threshold value into a lane line combination; then, screening the lane line combination with the average value of the distance between the two line segments smaller than a second distance threshold; screening lane line combinations with the vertical distance between each reference point on one lane line and the other lane line being greater than a third distance threshold value, wherein the third distance threshold value is smaller than the second distance threshold value; finally, the selected lane line combination with the minimum line segment spacing is identified as two lane lines of one lane, so that the lane can be automatically identified according to the lane lines, the labor cost of drawing is saved, and the drawing efficiency is improved.
Referring to fig. 4, a block diagram of a lane recognition device in a high-precision map according to an embodiment of the present application is shown, where the lane recognition device in the high-precision map can be applied to a computer device. The lane recognition device in the high-precision map may include:
the generating module 410 is configured to generate n line segments according to a plurality of reference points set in each lane line, where n is greater than or equal to 2, and distances between line segments with the same number in different lane lines are smaller than a first distance threshold;
the combination module 420 is used for combining two lane lines of which the angle average value of the n included angles is smaller than an angle threshold value into a lane line combination, wherein the included angles are formed by line segments with the same number in the two lane lines;
the screening module 430 is configured to screen lane line combinations with an average value of n line segment distances smaller than a second distance threshold, where the line segment distance represents a distance between line segments with the same number in two lane lines;
the screening module 430 is further configured to screen lane line combinations in which a vertical distance between each reference point on one lane line and another lane line is greater than a third distance threshold, where the third distance threshold is smaller than the second distance threshold;
and the identifying module 440 is configured to identify the screened lane line combination with the minimum line segment spacing as two lane lines of one lane.
In an optional embodiment, the generating module 410 is further configured to:
acquiring coordinate information of a plurality of reference points set in each lane line;
from among a plurality of line segments formed with a plurality of reference points as end points, n line segments are selected based on coordinate information so that distances between end points of line segments having the same number among different lane lines are smaller than a first distance threshold.
In an alternative embodiment, the combining module 420 is further configured to:
for two lane lines traversed each time, acquiring an included angle formed by two line segments corresponding to each number to obtain n included angles;
calculating the average value of n included angles;
if the average value of the n included angles is smaller than the angle threshold value, combining the two lane lines into a lane line combination;
and if the average value of the n included angles is larger than or equal to the angle threshold, performing next traversal.
In an alternative embodiment, the filtering module 430 is further configured to:
for each traversed lane line combination, calculating the distance between two line segments corresponding to each number to obtain n line segment intervals;
calculating the average value of the intervals of the n line segments;
if the average value of the n line segment intervals is smaller than a second distance threshold, reserving the lane line combination and traversing for the next time;
and if the average value of the intervals of the n line segments is greater than or equal to the second distance threshold, removing the lane line combination and traversing for the next time.
In an optional embodiment, the filtering module 430 is further configured to:
for each traversed lane line combination, calculating the vertical distance between each reference point on one lane line and each line segment of the other lane line;
if all the vertical distances are larger than the third distance threshold, reserving the lane line combination and traversing for the next time;
and if at least one vertical distance is smaller than or equal to the third distance threshold, removing the lane line combination and traversing for the next time.
In an alternative embodiment, the identifying module 440 is further configured to:
if at least two lane line combinations are screened out, comparing the line segment spacing corresponding to each lane line combination;
the lane line combination with the minimum line segment spacing is identified as two lane lines of one lane.
In summary, the lane recognition device in the high-precision map provided in the embodiment of the present application generates n line segments according to a plurality of reference points set in each lane line; then combining two lane lines of which the average value of the n included angles is smaller than the angle threshold value into a lane line combination; then, screening the lane line combinations with the average value of the n line segment distances smaller than a second distance threshold; screening lane line combinations with the vertical distance between each reference point on one lane line and the other lane line being greater than a third distance threshold value, wherein the third distance threshold value is smaller than the second distance threshold value; finally, the selected lane line combination with the minimum line segment spacing is identified as two lane lines of one lane, so that the lane can be automatically identified according to the lane lines, the labor cost of drawing is saved, and the drawing efficiency is improved.
Referring to fig. 5, a block diagram of a lane recognition device in a high-precision map according to an embodiment of the present application is shown, where the lane recognition device in the high-precision map can be applied to a computer device. The lane recognition device in the high-precision map may include:
a selecting module 510, configured to select a first line segment and a last line segment in each lane line, where each line segment is composed of a reference point set in the lane line;
the combination module 520 is used for combining two lane lines of which the angle average value of two included angles is smaller than an angle threshold value into a lane line combination, wherein the included angles are formed by line segments with the same number in the two lane lines;
a screening module 530, configured to screen a lane line combination in which an average value of a line segment interval between two lane lines is smaller than a second distance threshold, where the line segment interval represents a distance between line segments with the same number in the two lane lines;
the screening module 530 is further configured to screen lane line combinations in which a vertical distance between each reference point on one lane line and another lane line is greater than a third distance threshold, where the third distance threshold is smaller than the second distance threshold;
and the identifying module 540 is configured to identify the combination of the screened lane lines with the minimum line segment spacing as two lane lines of one lane.
In an optional embodiment, the combining module 520 is further configured to:
for two lane lines traversed each time, acquiring an included angle formed by two line segments corresponding to each number to obtain two included angles;
calculating the average value of the two included angles;
if the average value of the two included angles is smaller than the angle threshold value, the two lane lines form a lane line combination;
and if the average value of the two included angles is larger than or equal to the angle threshold, performing next traversal.
In an optional embodiment, the screening module 530 is further configured to:
for each traversed lane line combination, calculating the distance between two line segments corresponding to each number to obtain the distance between the two line segments;
calculating the average value of the distance between the two line segments;
if the average value of the distance between the two line segments is smaller than a second distance threshold, reserving the lane line combination and traversing for the next time;
and if the average value of the distance between the two line segments is greater than or equal to the second distance threshold, removing the lane line combination and traversing for the next time.
In an optional embodiment, the screening module 530 is further configured to:
for each traversed lane line combination, calculating the vertical distance between each reference point on one lane line and each line segment of the other lane line;
if all the vertical distances are larger than the third distance threshold, reserving the lane line combination and traversing for the next time;
and if at least one vertical distance is smaller than or equal to the third distance threshold, removing the lane line combination and performing next traversal.
In an alternative embodiment, the identifying module 540 is further configured to:
if at least two lane line combinations are screened out, comparing the line segment spacing corresponding to each lane line combination;
and identifying the lane line combination with the minimum line segment distance as two lane lines of one lane.
In summary, the lane recognition device in the high-precision map provided by the embodiment of the present application selects the first line segment and the last line segment in each lane line; then combining two lane lines of which the average value of the two included angles is smaller than the angle threshold value into a lane line combination; then, screening the lane line combination with the average value of the distance between the two line segments smaller than a second distance threshold; screening lane line combinations with the vertical distance between each reference point on one lane line and the other lane line being greater than a third distance threshold value, wherein the third distance threshold value is smaller than the second distance threshold value; and finally, the screened lane line combination with the minimum line segment spacing is identified as two lane lines of one lane, so that the lane can be automatically identified according to the lane lines, the labor cost of drawing is saved, and the drawing efficiency is improved.
One embodiment of the present application provides a computer-readable storage medium having at least one instruction stored therein, the at least one instruction being loaded and executed by a processor to implement a lane identification method in a high-precision map as described above.
One embodiment of the present application provides a computer device comprising a processor and a memory, wherein the memory stores at least one instruction, and the instruction is loaded and executed by the processor to realize the lane identification method in the high-precision map.
It should be noted that: the lane recognition device in the high-precision map provided in the above embodiment is only exemplified by the division of the above functional modules when performing lane recognition in the high-precision map, and in practical applications, the above functions may be distributed to different functional modules as needed, that is, the internal structure of the lane recognition device in the high-precision map may be divided into different functional modules to complete all or part of the above described functions. In addition, the lane recognition device in the high-precision map provided by the embodiment and the lane recognition method embodiment in the high-precision map belong to the same concept, and the specific implementation process is detailed in the method embodiment and is not described again.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description should not be taken as limiting the embodiments of the present application, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the embodiments of the present application should be included in the scope of the embodiments of the present application.
Claims (10)
1. A method of lane recognition in a high-precision map, the method comprising:
generating n line segments according to a plurality of reference points arranged in each lane line, wherein n is more than or equal to 2, and the distance between line segments with the same number in different lane lines is less than a first distance threshold;
combining two lane lines of which the average value of n included angles is smaller than an angle threshold value into a lane line combination, wherein the included angles are formed by line segments with the same number in the two lane lines;
screening the lane line combinations with the average value of the n line segment intervals smaller than a second distance threshold, wherein the line segment intervals represent the distances between line segments with the same number in the two lane lines;
screening lane line combinations with the vertical distance between each reference point on one lane line and the other lane line being greater than a third distance threshold value, wherein the third distance threshold value is smaller than the second distance threshold value;
and identifying the screened lane line combination with the minimum line segment spacing as two lane lines of one lane.
2. The method for recognizing the lane in the high-precision map according to claim 1, wherein the generating n line segments according to the plurality of reference points set in each lane line comprises:
acquiring coordinate information of a plurality of reference points set in each lane line;
selecting n line segments from a plurality of line segments formed by taking the plurality of reference points as end points based on the coordinate information so that the distance between the end points of the line segments with the same number in different lane lines is smaller than the first distance threshold.
3. The method for recognizing the lane in the high-precision map according to claim 1, wherein the step of combining two lane lines of which the average value of the n included angles is smaller than the angle threshold into a lane line combination comprises:
for two lane lines traversed each time, acquiring an included angle formed by two line segments corresponding to each number to obtain n included angles;
calculating the average value of the n included angles;
if the average value of the n included angles is smaller than the angle threshold value, the two lane lines form a lane line combination;
and if the average value of the n included angles is larger than or equal to the angle threshold, performing next traversal.
4. The method for recognizing the lane in the high-precision map according to claim 1, wherein the screening of the lane line combinations with the average value of the n line segment distances smaller than the second distance threshold comprises:
for each traversed lane line combination, calculating the distance between two line segments corresponding to each number to obtain n line segment intervals;
calculating the average value of the n line segment intervals;
if the average value of the n line segment intervals is smaller than the second distance threshold, the lane line combination is reserved, and the next traversal is carried out;
and if the average value of the n line segment intervals is greater than or equal to the second distance threshold, rejecting the lane line combination and performing next traversal.
5. The method for recognizing the lanes in the high-precision map according to claim 1, wherein the screening of the lane line combinations where the vertical distance between each reference point on one lane line and the other lane line is greater than a third distance threshold comprises:
for each traversed lane line combination, calculating the vertical distance between each reference point on one lane line and each line segment of the other lane line;
if all the vertical distances are larger than the third distance threshold, reserving the lane line combination and traversing for the next time;
and if at least one vertical distance is smaller than or equal to the third distance threshold, rejecting the lane line combination and performing next traversal.
6. The method for recognizing the lane in the high-precision map according to claim 1, wherein the recognizing the combination of the screened lane lines with the smallest line segment distance as two lane lines of one lane comprises:
if at least two lane line combinations are screened out, comparing the line segment spacing corresponding to each lane line combination;
and identifying the lane line combination with the minimum line segment distance as two lane lines of one lane.
7. A method of lane identification in a high-precision map, the method comprising:
selecting a first line segment and a last line segment in each lane line, wherein each line segment consists of a reference point set in the lane line;
forming a lane line combination by two lane lines of which the average value of two included angles is smaller than an angle threshold value, wherein the included angles are formed by line segments with the same number in the two lane lines;
screening the lane line combination with the average value of the line segment spacing smaller than a second distance threshold, wherein the line segment spacing represents the distance between line segments with the same number in the two lane lines;
screening lane line combinations with the vertical distance between each reference point on one lane line and the other lane line being greater than a third distance threshold value, wherein the third distance threshold value is smaller than the second distance threshold value;
and identifying the screened lane line combination with the minimum line segment spacing as two lane lines of one lane.
8. A lane recognition apparatus in a high-precision map, characterized in that the apparatus comprises:
the generating module is used for generating n line segments according to a plurality of reference points arranged in each lane line, wherein n is larger than or equal to 2, and the distance between the line segments with the same number in different lane lines is smaller than a first distance threshold;
the combination module is used for combining two lane lines of which the angle average value of n included angles is smaller than an angle threshold value into a lane line combination, and the included angles are formed by line segments with the same number in the two lane lines;
the screening module is used for screening the lane line combinations with the average value of the n line segment distances smaller than a second distance threshold value, wherein the line segment distances represent the distances between line segments with the same number in two lane lines;
the screening module is further configured to screen a lane combination in which a vertical distance between each reference point on one lane line and another lane line is greater than a third distance threshold, and the third distance threshold is smaller than the second distance threshold;
and the identification module is used for identifying the screened lane line combination with the minimum line segment spacing into two lane lines of one lane.
9. A lane recognition apparatus in a high-precision map, characterized by comprising:
the selection module is used for selecting a first line segment and a last line segment in each lane line, and each line segment consists of a reference point set in the lane line;
the combination module is used for combining two lane lines of which the average value of two included angles is smaller than an angle threshold value into a lane line combination, and the included angles are formed by line segments with the same number in the two lane lines;
the screening module is used for screening the lane line combination of which the average value of the line segment spacing is smaller than a second distance threshold, wherein the line segment spacing represents the distance between line segments with the same number in the two lane lines;
the screening module is further configured to screen a lane combination in which a vertical distance between each reference point on one lane line and another lane line is greater than a third distance threshold, and the third distance threshold is smaller than the second distance threshold;
and the identification module is used for identifying the screened lane line combination with the minimum line segment spacing as two lane lines of one lane.
10. A computer device, characterized in that the computer device comprises a processor and a memory, wherein the memory has at least one instruction stored therein, the instruction being loaded and executed by the processor to implement the lane recognition method in the high precision map according to any one of claims 1 to 6; alternatively, the instructions are loaded and executed by the processor to implement the lane recognition method in the high-precision map of claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211532458.2A CN115937447A (en) | 2022-12-01 | 2022-12-01 | Lane recognition method, device and equipment in high-precision map |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211532458.2A CN115937447A (en) | 2022-12-01 | 2022-12-01 | Lane recognition method, device and equipment in high-precision map |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115937447A true CN115937447A (en) | 2023-04-07 |
Family
ID=86648649
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211532458.2A Pending CN115937447A (en) | 2022-12-01 | 2022-12-01 | Lane recognition method, device and equipment in high-precision map |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115937447A (en) |
-
2022
- 2022-12-01 CN CN202211532458.2A patent/CN115937447A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214248B (en) | Method and device for identifying laser point cloud data of unmanned vehicle | |
| CN111238497B (en) | High-precision map construction method and device | |
| CN108519094B (en) | Local path planning method and cloud processing terminal | |
| CN110163065B (en) | Point cloud data processing method, point cloud data loading method, device and equipment | |
| CN109163730B (en) | High-precision map data gridding management method and device for automatic driving | |
| CN111985662B (en) | Network vehicle-restraining method, device, electronic equipment and storage medium | |
| CN113808400B (en) | Method, device, equipment and medium for displaying traffic flow migration situation | |
| US11341297B2 (en) | Obstacle distribution simulation method, device and terminal based on a probability graph | |
| CN111897906A (en) | Method, device, equipment and storage medium for processing map data | |
| JP2018189457A (en) | Information processing device | |
| CN110264517A (en) | A kind of method and system determining current vehicle position information based on three-dimensional scene images | |
| CN110162589B (en) | Road speed limit value assignment method and device, electronic equipment and computer readable medium | |
| CN114863047A (en) | Intersection virtual line drawing method and device, electronic equipment and computer program product | |
| EP4012342B1 (en) | Data processing method and device | |
| CN112732844B (en) | Method, apparatus, device and medium for automatically associating road object with road | |
| CN112732861A (en) | Road information data acquisition method and device and electronic equipment | |
| CN110174115B (en) | Method and device for automatically generating high-precision positioning map based on perception data | |
| CN111337039B (en) | Map data acquisition method, device and system for congested road section and storage medium | |
| CN115937447A (en) | Lane recognition method, device and equipment in high-precision map | |
| CN113918666A (en) | Map data processing method, device, system and storage medium | |
| CN110795977B (en) | Traffic signal identification method and device, storage medium and electronic equipment | |
| CN116303866B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN111400418A (en) | Lane positioning method and device, vehicle, storage medium and map construction method | |
| CN117115773B (en) | Stop line generation method, apparatus, electronic device, medium, and program product | |
| CN114659535A (en) | Truck return route generation method and device, storage medium and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |