CN114184204A - Method and device for estimating intersection area in high-precision map and intelligent vehicle - Google Patents
Method and device for estimating intersection area in high-precision map and intelligent vehicle Download PDFInfo
- Publication number
- CN114184204A CN114184204A CN202111406633.9A CN202111406633A CN114184204A CN 114184204 A CN114184204 A CN 114184204A CN 202111406633 A CN202111406633 A CN 202111406633A CN 114184204 A CN114184204 A CN 114184204A
- Authority
- CN
- China
- Prior art keywords
- information
- points
- intersection
- point
- information points
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 238000012216 screening Methods 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 9
- 230000009286 beneficial effect Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
Abstract
The embodiment of the invention relates to the technical field of traffic identification, and discloses a method and a device for estimating a crossing region in a high-precision map and an intelligent vehicle, wherein the method comprises the steps of extracting information points at the crossing from the high-precision map, wherein the information points are nodes representing lane lines or lane center lines, and the information included by the information points at least comprises position information of the points and semantic information represented by the points; preprocessing the information points at the intersection; sorting the information points at the intersection; screening the sequenced information points at the intersection, and determining the information points at the edge of the intersection; and connecting the information points at the edge of the intersection according to the sequence to form a concave packet, and estimating the intersection area according to the concave packet. Through the mode, the embodiment of the invention can add the specific information of the lane at the intersection into the calculation of the intersection concave packet, so that the solved intersection concave packet has better effect, and the intersection area can be estimated more accurately.
Description
Technical Field
The embodiment of the invention relates to the technical field of traffic identification, in particular to a method and a device for estimating a intersection region in a high-precision map and an intelligent vehicle.
Background
With the development of the automobile industry technology, the automatic driving technology is applied to more and more automobiles, and great convenience is provided for people when the automobiles are driven. However, the difficulty of the automatic driving technology lies in the identification of obstacles, the judgment of whether the vehicle can pass through the intersection, the passable area and the like, and the current solution generally adopts an external concave packet for solving discrete points at the intersection to identify the passable area.
In the process of implementing the embodiment of the present invention, the inventors of the embodiment of the present invention find that: an algorithm for solving an external concave packet for discrete points exists, but the existing algorithm only takes the discrete points on a lane as common points and does not use specific information of the lane, so that the obtained concave packet has poor effect, and the identification of an intersection region is influenced.
Disclosure of Invention
The embodiment of the invention mainly solves the technical problem of providing a method and a device for estimating an intersection region in a high-precision map and an intelligent vehicle, which can add specific information of a lane at the intersection into calculation of an intersection concave packet, so that the solved intersection concave packet has a better effect, and the intersection region is estimated more accurately.
In order to solve the above technical problem, one technical solution adopted by the embodiments of the present invention is: provided is a method for estimating intersection regions in a high-precision map, the method comprising: extracting information points at the intersection from the high-precision map, wherein the information points are nodes representing lane lines or lane center lines, and the information included in the information points at least comprises position information of the points and semantic information represented by the points; preprocessing the information points at the intersection; sorting the information points at the intersection; screening the sequenced information points at the intersection, and determining the information points at the edge of the intersection; and connecting the information points at the edge of the intersection according to the sequence to form a concave packet, and estimating the intersection area according to the concave packet.
Optionally, the step of screening the sorted information points at the intersection and determining the information points at the intersection edge specifically includes: according to the sorting, forming an included angle by any continuous three information points in sequence, and deleting the information point positioned in the middle of the three information points of which the included angle is smaller than the first angle; sequentially calculating the distance between any two continuous information points according to the sequence, and deleting any one of the two information points of which the distance is smaller than the first distance; according to the sorting, sequentially connecting the information points to form a closed graph, and deleting the information points forming the reentrant corners; according to the sorting, judging whether the distance between the first information point and the last information point is smaller than a second distance, if so, deleting the last information point, and if not, keeping the last information point; and determining the rest information points as the information points of the intersection edge.
Optionally, the step of sequentially forming included angles by the three information points which are arbitrarily continuous according to the sorting, and deleting a middle information point of the three information points of which the included angles are smaller than the first angle specifically includes: selecting a first information point and a second information point to jointly form a first candidate point set according to the sorted information points; judging whether the last information point added into the first candidate point set exists a next information point or not; if not, determining the first candidate point set as a first point set; if so, adding the next information point into the first candidate point set; judging whether an included angle formed by three continuous information points which are added into the first candidate point set finally in the first candidate point set in a counterclockwise manner is larger than a first angle or not; if so, returning to the step of judging whether the last information point added into the first candidate point set exists in the next information point; and if not, deleting the information point positioned in the middle of the three continuous information points, and returning to the judgment of whether the included angle formed by the three continuous information points which are finally added into the first candidate point set in the first candidate point set counterclockwise is larger than a first angle.
Optionally, the step of sequentially calculating the distance between any two consecutive information points according to the sorting, and deleting any one of the two information points whose distance is smaller than the first distance specifically includes: selecting a first information point from the information point with the minimum sequence number to form a second candidate point set according to the first point set; judging whether the last information point added into the second candidate point set exists a next information point or not; if not, determining the second candidate point set as a second point set; if so, adding the next information point into the second candidate point set; calculating the distance between two information points which are added into the second candidate point set at last; judging whether the distance is greater than a first distance; if not, removing the information point positioned at the last of the two information points, and returning to the step of calculating the distance between the two information points added into the second candidate point set at the last; and if so, returning to the step of judging whether the last information point added into the second candidate point set exists in the next information point.
Optionally, the step of sequentially connecting the information points according to the sorting to form a closed graph and deleting the information points forming the reentrant corners specifically includes: sequentially connecting the information points to form a closed graph according to the information points at the edge of the intersection; judging whether the closed graph has a concave angle; if the intersection edge exists, removing the information points forming the reentrant angle, and returning to the information points according to the intersection edge to sequentially connect the information points to form a closed graph; if not, no point is deleted.
Optionally, the step of determining, according to the sorting, whether a distance between a first information point and a last information point is smaller than a second distance, if so, deleting the last information point, and if not, retaining the last information point includes: calculating the distance between the first information point and the last information point in the closed graph according to the closed graph; judging whether the distance is smaller than a second distance; if so, deleting the last information point, and returning to the step of calculating the distance between the first information point and the last information point in the closed graph according to the closed graph; if not, the last information point is reserved.
Optionally, the step of preprocessing the information points at the intersection specifically includes: calculating the distance between two adjacent information points in the same lane line; judging whether the distance is within a first preset range or not; if the distance is smaller than the first preset range, deleting one information point randomly; and if the distance is larger than the first preset range, adding an information point at the middle point of the two adjacent information points.
Optionally, the step of sorting the information points at the intersection specifically includes: calculating a convex hull of the sorted information points; calculating a bounding box of the convex hull according to the convex hull, and determining the center of the bounding box as the center of the intersection; calculating the polar angle of the information point to the center of the intersection; and sorting the information points according to the polar angle by a reverse clock.
In order to solve the above technical problem, another technical solution adopted in the embodiments of the present invention is: there is provided an apparatus for estimating a intersection region in a high-precision map, the apparatus including: the extraction module is used for extracting information points at the intersection from the high-precision map, wherein the information points are nodes representing lane lines or lane center lines, and the information included by the information points at least comprises position information of the points and semantic information represented by the points; the preprocessing module is used for preprocessing the information points at the intersection; the sorting module is used for sorting the information points at the intersection; the first determining module is used for screening the sequenced information points at the intersection and determining the information points at the edge of the intersection; and the connecting module is used for connecting the information points at the edge of the intersection according to the sequence to form a concave packet and estimating the intersection area according to the concave packet.
In order to solve the above technical problem, another technical solution adopted by the embodiment of the present invention is: provided is a smart vehicle including: a vehicle body; an image processor; the image processor is mounted on the vehicle body; a controller mounted to the vehicle body, the controller electrically connected to the image processor, the controller including at least one processor and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of the above.
In order to solve the above technical problem, another technical solution adopted in the embodiments of the present invention is: there is provided a non-transitory computer-readable storage medium having stored thereon computer-executable instructions for causing a server to perform the method of any of the above.
The embodiment of the invention has the beneficial effects that: different from the situation of the prior art, the embodiment of the invention firstly extracts the information points at the intersection from the high-precision map, then preprocesses the information points at the intersection, then sorts the information points at the intersection, then screens the sorted information points at the intersection, determines the information points at the edge of the intersection, finally connects the information points at the edge of the intersection according to the sorting to form the concave packet, and estimates the intersection area according to the concave packet.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
FIG. 1 is a schematic diagram of an application environment of a method for estimating intersection areas in a high-precision map according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for estimating intersection regions in a high-precision map according to an embodiment of the present invention;
fig. 3 is a flowchart of preprocessing information points at the intersection in the method for estimating the intersection region in the high-precision map according to the embodiment of the present invention;
fig. 4 is a flowchart of sorting information points at intersections in the method for estimating intersection regions in a high-precision map according to the embodiment of the present invention;
fig. 5 is a flowchart of screening the sorted information points at the intersection and determining the information points at the intersection edge in the method for estimating the intersection region in the high-precision map according to the embodiment of the present invention;
fig. 6 is a flowchart illustrating that, according to the sorting, included angles are sequentially formed by any three consecutive information points, and a middle information point of the three information points whose included angles are smaller than a first angle is deleted in the method for estimating intersection areas in a high-precision map according to the embodiment of the present invention;
fig. 7 is an example diagram of a process of deleting a middle information point from among three information points having an included angle smaller than a first angle, where the included angle is formed by sequentially forming any three consecutive information points according to the sorting in the method for estimating a intersection region in a high-precision map according to the embodiment of the present invention;
fig. 8 is a flowchart of sequentially calculating the distance between any two consecutive information points according to the sorting in the method for estimating a intersection region in a high-precision map according to the embodiment of the present invention, and deleting any one of the two information points whose distance is smaller than the first distance;
fig. 9 is an example diagram of a process of sequentially calculating the distance between any two consecutive information points according to the sequence and deleting any one of the two information points whose distance is smaller than the first distance in the method for estimating intersection regions in a high-precision map according to the embodiment of the present invention;
fig. 10 is a flowchart of sequentially connecting the information points to form a closed graph according to the sorting in the method for estimating intersection regions in a high-precision map according to the embodiment of the present invention, and deleting the information points forming reentrant corners;
fig. 11 is an example diagram of a flow of sequentially connecting the information points to form a closed graph and deleting the information points forming the reentrant corners according to the sorting in the method for estimating the intersection region in the high-precision map according to the embodiment of the present invention;
fig. 12 is a flowchart illustrating determining whether a distance between a first information point and a last information point is smaller than a second distance according to the sorting in the method for estimating a intersection region in a high-precision map according to the embodiment of the present invention, if so, deleting the last information point, and if not, retaining the last information point;
fig. 13 is a functional block diagram of an estimation apparatus of a intersection region in a high-precision map according to an embodiment of the present invention;
FIG. 14 is a schematic diagram of a smart vehicle according to an embodiment of the present invention.
Detailed Description
In order to facilitate an understanding of the invention, the invention is described in more detail below with reference to the accompanying drawings and specific examples. It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may be present. As used in this specification, the terms "upper," "lower," "inner," "outer," "vertical," "horizontal," and the like are used in the orientation or positional relationship indicated in the drawings for convenience in describing the invention and simplicity in description, and do not indicate or imply that the referenced devices or elements must be in a particular orientation, constructed and operated in a particular orientation, and are not to be considered limiting of the invention. Furthermore, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Furthermore, the technical features mentioned in the different embodiments of the invention described below can be combined with each other as long as they do not conflict with each other.
Referring to fig. 1, fig. 1 is a schematic diagram of an application environment of a method for estimating a road junction area in a high-precision map according to an embodiment of the present invention, where the application environment includes a road junction area 10 and an intelligent vehicle 20, the intelligent vehicle 20 includes a vehicle body 21, an image processor 22 and a controller 23, the image processor 22 is mounted on the vehicle body 21, the controller 23 is mounted on the vehicle body 21, the image processor 22 is electrically connected to the controller 23, and the image processor 22 can receive and store the high-precision map. When the intelligent vehicle 20 travels to the intersection area 10, the image processor 22 can call the high-precision map and transmit the high-precision map information to the controller 23, complete the determination of the intersection concave packet of the intersection area 10 by the controller 23, and estimate the task of the intersection area 10 according to the intersection concave packet.
Fig. 2 is a flowchart illustrating a method for estimating intersection regions in a high-precision map according to an embodiment of the present invention, and as shown in fig. 2, the method includes the following steps:
step S101, extracting information points at the intersection from the high-precision map, wherein the information points are nodes representing lane lines or lane center lines, and the information included in the information points at least comprises position information of the points and semantic information represented by the points;
in the embodiment of the invention, the high-precision map is a discrete high-precision map, the discrete high-precision map is a map expression mode for describing a road structure, and is acquired and manufactured by a special map information acquisition vehicle, wherein the position information is a three-dimensional space coordinate.
Step S102, preprocessing the information points at the intersection;
in some embodiments, referring to fig. 3, the step S102 specifically includes:
step S1021, calculating the distance between two adjacent information points in the same lane line;
step S1022, determining whether the distance is within a first preset range;
step S1023, if the distance is smaller than the first preset range, deleting an information point arbitrarily;
the distance is smaller than the first preset range, which indicates that two information points are too close to each other and are almost overlapped, and the result of the operation performed by using the two information points is almost the same as the result of the operation performed by using only one of the information points, so that one of the information points needs to be deleted in order to reduce the calculation process.
Step S1024, if the distance is larger than the first preset range, adding an information point at the middle point of the two adjacent information points.
The distance is larger than the first preset range, which indicates that the two information points are too far apart, and the jump is too large according to the operation results of the two information points, which is not beneficial to subsequent data analysis.
Step S103, sorting the information points at the intersection;
in some embodiments, referring to fig. 4, the step S103 specifically includes:
step S1031, calculating convex hulls of the sorted information points;
the convex hull is a concept in computing geometry (graphics), and the convex hull of a point set refers to a minimum convex polygon which can satisfy that all points in the point set are on the side of the convex polygon or in the inner part of the convex polygon, namely the convex hull can surround all points in the point set.
Step S1032, calculating a bounding box of the convex hull according to the convex hull, and determining the center of the bounding box as the center of the intersection;
the bounding box of the convex hull is the smallest rectangle that can enclose the convex hull, wherein the smallest rectangle must have one edge that coincides with one edge of the convex hull.
In the algorithm for calculating the minimum area circumscribed rectangle of the point set, the rotating stuck shell algorithm is an important algorithm.
Step S1033, calculating a polar angle of the information point corresponding to the center of the intersection;
and S1034, sorting the information points according to a reverse clock according to the polar angle.
S104, screening the sequenced information points at the intersection, and determining the information points at the edge of the intersection;
in some embodiments, referring to fig. 5, the step S104 specifically includes:
step S1041, forming an included angle by any continuous three information points in sequence according to the sorting, and deleting the information point positioned in the middle of the three information points of which the included angle is smaller than the first angle;
in some embodiments, referring to fig. 6, the step S1041 specifically includes:
step S10411, selecting a first information point and a second information point to form a first candidate point set together according to the sorted information points;
step S10412, determining whether there is a next information point in the last information point added to the first candidate point set;
step S10413, if not, determining the first candidate point set as a first point set;
step S10414, if yes, adding the next information point to the first candidate point set;
step S10415, judging whether an included angle formed by three continuous information points which are finally added into the first candidate point set in the first candidate point set counterclockwise is larger than a first angle;
if so, returning to the step of judging whether the last information point added into the first candidate point set exists in the next information point;
step S10416, if not, deleting the information point located in the middle of the three continuous information points, and returning to the step of determining whether an included angle formed by the three continuous information points, which are added to the first candidate point set in the first candidate point set last, in the counterclockwise direction is greater than a first angle.
To more clearly describe the process of step S1041, please refer to fig. 7, in which the information points shown in fig. 7 are the information points sorted by step S103, and the numbers beside the information points represent the order of the information points, wherein the polar angles of the rays L1, L2 and L3 sequentially increase, and the information points 1 and 2 are selected to form a first candidate point set, at this time, the information point 2 is the last information point added to the first candidate point set, and it is determined whether the information point 2 exists the next information point, as shown in the figure, the next information point of the information point 2 is the information point 3, (assuming that the information points shown in fig. 7 are all the information points, the information point 27 is the last information point, and therefore the information point 27 does not exist the next information point), the information point 3 is added to the first candidate point set, at this time, the information points 3, 2 and 1 are three consecutive information points finally added to the first candidate point set, an included angle formed by the information point 3, the information point 2 and the information point 1 in a counterclockwise direction is ≧ P1P2P3, at this time, the angle P1P2P3 is 180 °, and assuming that the first angle is 80 °, the ≧ P1P2P3 is greater than the first angle, so it is determined whether the information point 3 has the next information point, obviously, the next information point of the information point 3 is the information point 4, the information point 4 is added to the first candidate point set, at this time, the information point 4, the information point 3 and the information point 2 are three consecutive information points to which the first candidate point set is added last, the included angle formed by the information point 4, the information point 3 and the information point 2 in the counterclockwise direction is ≧ P2P3P4, at this time, the angle P2P3P4 is 180 °, the angle P2P3P4 is greater than the first angle, and so on the like in order until the information point 8 is added to the first candidate point set, at this time, the information point 7 and the information point set are three consecutive information points, the included angle formed by the information point 8, the information point 7 and the information point 6 in the counterclockwise direction is ≧ P6P7P8, at this time ≦ P6P7P8 is obviously less than the first angle, at this time, the information point 7 is deleted, then the three consecutive information points added to the first candidate point set finally become the information point 8, the information point 6 and the information point 5, at this time, the included angle formed by the information point 8, the information point 6 and the information point 5 in the counterclockwise direction is ≦ P5P6P8, and the angle P5P6P8 is obviously less than the first angle, then the information point 6 is deleted, then the three consecutive information points added to the first candidate point set finally become the information point 8, the information point 5 and the information point 4, and so on, the information point 5, the information point 4, the information point 3 and the information point 2 are deleted in sequence, at this time, only the information point 8 and the information point 1 are left in the first candidate point set, and whether the information point 8 exists in the next information point is judged, obviously, if the information point 9 is the next information point of the information point 8, the information point 9 is added into the first candidate point set, at this time, three consecutive information points finally added into the first candidate point set become the information point 9, the information point 8 and the information point 1, and so on until all the information points are traversed.
Step S1042, according to the sorting, sequentially calculating the distance between any two continuous information points, and deleting any one of the two information points with the distance smaller than the first distance;
in some embodiments, referring to fig. 8, the step S1042 specifically includes:
step S10421, according to the first point set, starting from the information point with the smallest sequence number, selecting a first information point to form a second candidate point set;
step S10422 of determining whether there is a next information point in the information point added to the second candidate point set last;
step S10423, if not, determining the second candidate point set as a second point set;
step S10424, if yes, adding the next information point into the second candidate point set;
step S10425, calculating a distance between two information points added to the second candidate point set at last;
step S10426, determining whether the distance is greater than a first distance;
step S10427, if not, removing the information point located at the last of the two information points, and returning to the step of calculating the distance between the two information points added to the second candidate point set at the last;
and if so, returning to the step of judging whether the last information point added into the second candidate point set exists in the next information point.
To more clearly describe the process of step S1042, please refer to fig. 9, where the information points shown in fig. 9 are the information points sorted in step S1041, the numbers beside the information points represent the order of the information points, the information points 1 are selected to form a second candidate point set, and it is determined whether the information points 1 have a next information point, obviously, the information points 8 are the next information points of the information points 1, so the information points 8 are added into the second candidate point set, and the distance D between the information points 8 and the information points 1 is calculated8-1Assuming a distance D8-1Judging the distance D as 88-1If it is greater than the first distance, assuming that the first distance is 6, the distance D8-1If the distance is larger than the first distance, adding the information point 8 into the second candidate point set, at this time, the information point finally added into the second candidate point set is the information point 8, judging whether the information point 8 has a next information point, obviously, if the information point 9 is the next information point of the information point 8, adding the information point 9 into the second candidate point set, and calculating the distance D between the information point 9 and the information point 89-8Assuming a distance D9-8Is 5, then the distance D9-8And deleting the information point 9 when the distance is less than the first distance, judging whether the information point 8 exists next information point or not by using the information point added into the second candidate point set as the information point 8, obviously, adding the information point 11 into the second candidate point set when the information point 11 is next information point of the information point 8, and calculating the distance D between the information point 11 and the information point 811-8Assuming a distance D11-8A distance D of 1011-8And if the distance is greater than the first distance, adding the information point 11 into the second candidate point set, wherein the information point which is added into the second candidate point set at last is the information point 11, and so on until all the information points are traversed.
Step S1043, connecting the information points in sequence to form a closed graph according to the sorting, and deleting the information points forming the reentrant corner;
in some embodiments, referring to fig. 10, the step S1043 specifically includes:
step S10431, connecting the information points in sequence to form a closed graph according to the information points at the edge of the intersection;
step S10432, judging whether the closed graph has a reentrant angle;
the reentrant angle is an angle at which the closed graph is recessed inwards, and theoretically, a reentrant angle is certainly present when the reentrant package is solved.
Step S10433, if yes, removing the information points forming the reentrant angle, and returning to the information points according to the intersection edge, and connecting the information points in sequence to form a closed graph;
in step S10434, if not, no point is deleted.
To more clearly describe the process of step S1042, referring to fig. 11, the information points shown in fig. 11 are the information points sorted in step S1042, the numbers near the information points indicate the order of the information points, assuming that only the information points 1, 2, 3, 8, 9, 11 · · 22, 23, 24 · · 100, 101, and 102 remain at the intersection by setting a proper first angle and first distance, the information points are sequentially connected to form a closed graph, and the information points 2, 3, and 8 form a concave angle, the information points 3 need to be deleted, the remaining information points are sequentially connected to form a closed graph, and the information points 1, 2, and 8 form a concave angle, the information points 2 need to be deleted, and then connecting the rest information points in sequence to form a closed graph, wherein no concave angle exists.
Step S1044, according to the sorting, judging whether the distance between the first information point and the last information point is smaller than a second distance, if so, deleting the last information point, otherwise, keeping the last information point;
in some embodiments, referring to fig. 12, the step S1044 specifically includes:
step S10441, calculating a distance between a first information point and a last information point in the closed graph according to the closed graph;
step S10442, determining whether the distance is smaller than a second distance;
step S10443, if yes, deleting the last information point, and returning to the step of calculating the distance between the first information point and the last information point in the closed graph according to the closed graph;
and step S10444, if not, keeping the last information point.
And S1045, determining the remaining information points as the information points of the intersection edge.
And S105, connecting the information points at the edge of the intersection according to the sequence to form a concave packet, and estimating the intersection area according to the concave packet.
The embodiment of the invention has the beneficial effects that: different from the situation of the prior art, the embodiment of the invention firstly extracts the information points at the intersection from the high-precision map, then preprocesses the information points at the intersection, then sorts the information points at the intersection, then screens the sorted information points at the intersection, determines the information points at the edge of the intersection, finally connects the information points at the edge of the intersection according to the sorting to form the concave packet, and estimates the intersection area according to the concave packet.
Referring to fig. 13, fig. 13 shows a functional block diagram of an apparatus 50 for determining a road recess packet according to an embodiment of the present invention, where the apparatus 50 includes: the extraction module 501 is configured to extract information points at the intersection from the high-precision map, where the information points are nodes representing lane lines or lane center lines, and information included in the information points includes at least position information of the points and semantic information represented by the points; the preprocessing module 502 is used for preprocessing the information points at the intersection; the sorting module 503 is configured to sort the information points at the intersection; the first determining module 504 is configured to filter the sorted information points at the intersection, and determine the information points at the intersection edge; the connection module 505 is configured to connect the information points at the intersection edge according to the sequence to form a concave packet, and estimate the intersection region according to the concave packet.
Wherein, the preprocessing module 502 comprises: a first calculating unit 5021, a first judging unit 5022, a first deleting unit 5023 and a first adding unit 5024. The first calculating unit 5021 is used for calculating the distance between two adjacent information points in the same lane line; the first judging unit 5022 is used for judging whether the distance is within a first preset range; the first deleting unit 5023 is configured to delete one information point arbitrarily if the distance is smaller than the first preset range; the first adding unit 5024 is configured to add an information point to the midpoint between the two adjacent information points if the distance is greater than the first preset range.
Wherein, the sorting module 503 comprises: a second calculation unit 5031, a first determination unit 5032, a third calculation unit 5033 and a first ordering unit 5034. Wherein, the second calculating unit 5031 is configured to calculate a convex hull of the sorted information points; the first determining unit 5032 is configured to calculate a bounding box of the convex hull according to the convex hull, and determine that a center of the bounding box is the intersection center; the third calculating unit 5033 is configured to calculate a polar angle of the information point with respect to the intersection center; the first sorting unit 5034 is configured to sort the information points according to the polar angle by a reverse clock.
Wherein the first determining module 504 includes: a second deleting unit 5041, a third deleting unit 5042, a fourth deleting unit 5043, a second judging unit 5044, and a second determining unit 5045, where the second deleting unit 5041 is configured to sequentially form an included angle with any three consecutive information points according to the sorting, and delete a middle information point of the three information points whose included angle is smaller than the first angle; the third deleting unit 5042 is configured to sequentially calculate distances between any two consecutive information points according to the sorting, and delete any one of the two information points whose distances are smaller than the first distance; the fourth deleting unit 5043 is configured to sequentially connect the information points to form a closed graph according to the sorting, and delete the information points forming the reentrant corner; the second determining unit 5044 is configured to determine, according to the sorting, whether a distance between the first information point and the last information point is smaller than a second distance, if yes, delete the last information point, and if not, keep the last information point; the second determining unit 5045 is configured to determine the remaining information points as the information points of the intersection edge.
The second deleting unit 5041 is specifically configured to select, according to the sorted information points, a first information point and a second information point to jointly form a first candidate point set; judging whether the last information point added into the first candidate point set exists a next information point or not; if not, determining the first candidate point set as a first point set; if so, adding the next information point into the first candidate point set; judging whether an included angle formed by three continuous information points which are added into the first candidate point set finally in the first candidate point set in a counterclockwise manner is larger than a first angle or not; if so, returning to the step of judging whether the last information point added into the first candidate point set exists in the next information point; and if not, deleting the information point positioned in the middle of the three continuous information points, and returning to the judgment of whether the included angle formed by the three continuous information points which are finally added into the first candidate point set in the first candidate point set counterclockwise is larger than a first angle.
The third deleting unit 5042 is specifically configured to select, according to the first point set, a first information point from the information point with the smallest sequence number to form a second candidate point set; judging whether the last information point added into the second candidate point set exists a next information point or not; if not, determining the second candidate point set as a second point set; if so, adding the next information point into the second candidate point set; calculating the distance between two information points which are added into the second candidate point set at last; judging whether the distance is greater than a first distance; if not, removing the information point positioned at the last of the two information points, and returning to the step of calculating the distance between the two information points added into the second candidate point set at the last; and if so, returning to the step of judging whether the last information point added into the second candidate point set exists in the next information point.
The fourth deleting unit 5043 is specifically configured to connect the information points in sequence according to the information points at the intersection edge to form a closed graph; judging whether the closed graph has a concave angle; if the intersection edge exists, removing the information points forming the reentrant angle, and returning to the information points according to the intersection edge to sequentially connect the information points to form a closed graph; if not, no point is deleted.
The second determining unit 5044 is specifically configured to calculate, according to the closed graph, a distance between a first information point and a last information point in the closed graph; judging whether the distance is smaller than a second distance; if so, deleting the last information point, and returning to the step of calculating the distance between the first information point and the last information point in the closed graph according to the closed graph; if not, the last information point is reserved.
The embodiment of the invention has the beneficial effects that: different from the situation of the prior art, in the embodiment of the present invention, firstly, the information points at the intersection are extracted from the high-precision map by the extraction module 501, then the information points at the intersection are preprocessed by the preprocessing module 502, then the information points at the intersection are sorted by the sorting module 503, then the sorted information points at the intersection are screened by the first determining module 504, the information points at the edge of the intersection are determined, finally, the information points at the edge of the intersection are connected according to the sorting by the connection module 505 to form the concave packet, and the intersection region is estimated according to the concave packet.
The present invention further provides an embodiment of a smart vehicle 20, please refer to fig. 14, fig. 14 is a schematic diagram of an embodiment of the smart vehicle 20 according to the embodiment of the present invention, and the controller 23 of the smart vehicle 20 includes: at least one processor 231; and a memory 232 communicatively coupled to the at least one processor 231, one of the processors 231 being illustrated in fig. 14. The memory 232 stores instructions executable by the at least one processor 231, and the instructions are executed by the at least one processor 231 to enable the at least one processor 231 to perform the method for estimating the intersection region in the high-precision map described above with reference to fig. 2 to 12, and to perform the apparatus for estimating the intersection region in the high-precision map described above with reference to fig. 13. The processor 231 and the memory 232 may be connected by a bus or other means, and fig. 14 illustrates the connection by a bus as an example.
The memory 232, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the estimation method of the intersection region in the high-precision map in the embodiment of the present application, for example, the respective modules shown in fig. 13. The processor 231 executes various functional applications of the server and data processing by running the nonvolatile software programs, instructions and modules stored in the memory 232, that is, implements the method for estimating the intersection region in the high-precision map of the above-described method embodiment.
The memory 232 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the estimation device of the intersection region in the high-precision map, and the like. Further, the memory 232 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 232 may optionally include memory located remotely from processor 231, which may be connected via a network to an estimation device for the intersection region in the high-precision map. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 232 and, when executed by the one or more processors 231, perform the method of estimating the intersection region in the high precision map of any of the method embodiments described above, e.g., perform the method steps of fig. 2-12 described above, and perform the apparatus of estimating the intersection region in the high precision map described above in fig. 13.
The product can execute the method provided by the embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the methods provided in the embodiments of the present application.
Embodiments of the present application also provide a non-transitory computer-readable storage medium storing computer-executable instructions for execution by one or more processors, for example, to perform the method steps of fig. 2-12 described above and to perform the apparatus for estimating a intersection region in a high-precision map described above with reference to fig. 13.
Embodiments of the present application further provide a computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform a method for estimating a intersection region in a high-precision map in any of the above-described method embodiments, for example, perform the method steps of fig. 2 to 12 described above, and perform an apparatus for estimating an intersection region in a high-precision map described above in fig. 13.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (11)
1. A method for estimating intersection regions in a high-precision map, comprising:
extracting information points at the intersection from the high-precision map, wherein the information points are nodes representing lane lines or lane center lines, and the information included in the information points at least comprises position information of the points and semantic information represented by the points;
preprocessing the information points at the intersection;
sorting the information points at the intersection;
screening the sequenced information points at the intersection, and determining the information points at the edge of the intersection;
and connecting the information points at the edge of the intersection according to the sequence to form a concave packet, and estimating the intersection area according to the concave packet.
2. The method according to claim 1, wherein the step of screening the sorted information points at the intersection and determining the information points at the intersection edge specifically comprises:
according to the sorting, forming an included angle by any continuous three information points in sequence, and deleting the information point positioned in the middle of the three information points of which the included angle is smaller than the first angle;
sequentially calculating the distance between any two continuous information points according to the sequence, and deleting any one of the two information points of which the distance is smaller than the first distance;
according to the sorting, sequentially connecting the information points to form a closed graph, and deleting the information points forming the reentrant corners;
according to the sorting, judging whether the distance between the first information point and the last information point is smaller than a second distance, if so, deleting the last information point, and if not, keeping the last information point;
and determining the rest information points as the information points of the intersection edge.
3. The method according to claim 2, wherein the step of sequentially forming an included angle by any three consecutive information points according to the sorting, and deleting a middle information point of the three information points having the included angle smaller than the first angle specifically includes:
selecting a first information point and a second information point to jointly form a first candidate point set according to the sorted information points;
judging whether the last information point added into the first candidate point set exists a next information point or not;
if not, determining the first candidate point set as a first point set;
if so, adding the next information point into the first candidate point set;
judging whether an included angle formed by three continuous information points which are added into the first candidate point set finally in the first candidate point set in a counterclockwise manner is larger than a first angle or not;
if so, returning to the step of judging whether the last information point added into the first candidate point set exists in the next information point;
and if not, deleting the information point positioned in the middle of the three continuous information points, and returning to the judgment of whether the included angle formed by the three continuous information points which are finally added into the first candidate point set in the first candidate point set counterclockwise is larger than a first angle.
4. The method according to claim 2, wherein said step of calculating, in order according to said ranking, the distance between any two consecutive information points, and deleting any one of the two information points whose distance is smaller than the first distance, specifically comprises:
selecting a first information point from the information point with the minimum sequence number to form a second candidate point set according to the first point set;
judging whether the last information point added into the second candidate point set exists a next information point or not;
if not, determining the second candidate point set as a second point set;
if so, adding the next information point into the second candidate point set;
calculating the distance between two information points which are added into the second candidate point set at last;
judging whether the distance is greater than a first distance;
if not, removing the information point positioned at the last of the two information points, and returning to the step of calculating the distance between the two information points added into the second candidate point set at the last;
and if so, returning to the step of judging whether the last information point added into the second candidate point set exists in the next information point.
5. The method according to claim 2, wherein the step of sequentially connecting the information points to form a closed figure and deleting the information points forming the reentrant corner according to the sorting comprises:
sequentially connecting the information points to form a closed graph according to the information points at the edge of the intersection;
judging whether the closed graph has a concave angle;
if the intersection edge exists, removing the information points forming the reentrant angle, and returning to the information points according to the intersection edge to sequentially connect the information points to form a closed graph;
if not, no point is deleted.
6. The method according to claim 2, wherein the step of determining, according to the sorting, whether a distance between a first information point and a last information point is smaller than a second distance, if so, deleting the last information point, and if not, retaining the last information point specifically includes:
calculating the distance between the first information point and the last information point in the closed graph according to the closed graph;
judging whether the distance is smaller than a second distance;
if so, deleting the last information point, and returning to the step of calculating the distance between the first information point and the last information point in the closed graph according to the closed graph;
if not, the last information point is reserved.
7. The method according to claim 1, wherein the step of preprocessing the information points at the intersection specifically comprises:
calculating the distance between two adjacent information points in the same lane line;
judging whether the distance is within a first preset range or not;
if the distance is smaller than the first preset range, deleting one information point randomly;
and if the distance is larger than the first preset range, adding an information point at the middle point of the two adjacent information points.
8. The method according to claim 1, wherein the step of sorting the information points at the intersection includes:
calculating a convex hull of the sorted information points;
calculating a bounding box of the convex hull according to the convex hull, and determining the center of the bounding box as the center of the intersection;
calculating the polar angle of the information point to the center of the intersection;
and sorting the information points according to the polar angle by a reverse clock.
9. An apparatus for estimating intersection regions in a high-precision map, the apparatus comprising:
the extraction module is used for extracting information points at the intersection from the high-precision map, wherein the information points are nodes representing lane lines or lane center lines, and the information included by the information points at least comprises position information of the points and semantic information represented by the points;
the preprocessing module is used for preprocessing the information points at the intersection;
the sorting module is used for sorting the information points at the intersection;
the first determining module is used for screening the sequenced information points at the intersection and determining the information points at the edge of the intersection;
and the connecting module is used for connecting the information points at the edge of the intersection according to the sequence to form a concave packet and estimating the intersection area according to the concave packet.
10. A smart vehicle, comprising:
a vehicle body;
an image processor; the image processor is mounted on the vehicle body;
a controller mounted to the vehicle body, the controller electrically connected to the image processor, the controller including at least one processor and a memory communicatively coupled to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.
11. A non-transitory computer-readable storage medium storing computer-executable instructions for causing a server to perform the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111406633.9A CN114184204A (en) | 2021-11-24 | 2021-11-24 | Method and device for estimating intersection area in high-precision map and intelligent vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111406633.9A CN114184204A (en) | 2021-11-24 | 2021-11-24 | Method and device for estimating intersection area in high-precision map and intelligent vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114184204A true CN114184204A (en) | 2022-03-15 |
Family
ID=80541469
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111406633.9A Pending CN114184204A (en) | 2021-11-24 | 2021-11-24 | Method and device for estimating intersection area in high-precision map and intelligent vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114184204A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2615185A1 (en) * | 2005-07-22 | 2007-01-25 | Telargo Inc. | Method, device and system for modeling a road network graph |
| KR20070013526A (en) * | 2005-07-26 | 2007-01-31 | 주식회사 현대오토넷 | Apparatus and method for deciding traveling direction of navigation system |
| JP2007086156A (en) * | 2005-09-20 | 2007-04-05 | Zenrin Co Ltd | Map information creating device, method, and program |
| WO2007037126A1 (en) * | 2005-09-29 | 2007-04-05 | Matsushita Electric Industrial Co., Ltd. | Navigation device, navigation method, and vehicle |
| CN102436481A (en) * | 2011-10-21 | 2012-05-02 | 武汉大学 | Automatic identification method for road network structure mode |
| WO2019052998A1 (en) * | 2017-09-12 | 2019-03-21 | Tomtom International B.V. | Methods and systems of providing lane information using a navigation apparatus |
| CN109949389A (en) * | 2019-03-27 | 2019-06-28 | 百度在线网络技术（北京）有限公司 | A kind of crossing method for drafting, device, server and storage medium |
| CN111626206A (en) * | 2020-05-27 | 2020-09-04 | 北京百度网讯科技有限公司 | High-precision map construction method and device, electronic equipment and computer storage medium |
| US20200355515A1 (en) * | 2019-05-07 | 2020-11-12 | Here Global B.V. | Method, apparatus, and computer program product for on-street parking localization |
| US20210108936A1 (en) * | 2019-10-09 | 2021-04-15 | Argo AI, LLC | Methods and systems for topological planning in autonomous driving |
-
2021
- 2021-11-24 CN CN202111406633.9A patent/CN114184204A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2615185A1 (en) * | 2005-07-22 | 2007-01-25 | Telargo Inc. | Method, device and system for modeling a road network graph |
| KR20070013526A (en) * | 2005-07-26 | 2007-01-31 | 주식회사 현대오토넷 | Apparatus and method for deciding traveling direction of navigation system |
| JP2007086156A (en) * | 2005-09-20 | 2007-04-05 | Zenrin Co Ltd | Map information creating device, method, and program |
| WO2007037126A1 (en) * | 2005-09-29 | 2007-04-05 | Matsushita Electric Industrial Co., Ltd. | Navigation device, navigation method, and vehicle |
| CN102436481A (en) * | 2011-10-21 | 2012-05-02 | 武汉大学 | Automatic identification method for road network structure mode |
| WO2019052998A1 (en) * | 2017-09-12 | 2019-03-21 | Tomtom International B.V. | Methods and systems of providing lane information using a navigation apparatus |
| CN109949389A (en) * | 2019-03-27 | 2019-06-28 | 百度在线网络技术（北京）有限公司 | A kind of crossing method for drafting, device, server and storage medium |
| US20200355515A1 (en) * | 2019-05-07 | 2020-11-12 | Here Global B.V. | Method, apparatus, and computer program product for on-street parking localization |
| US20210108936A1 (en) * | 2019-10-09 | 2021-04-15 | Argo AI, LLC | Methods and systems for topological planning in autonomous driving |
| CN111626206A (en) * | 2020-05-27 | 2020-09-04 | 北京百度网讯科技有限公司 | High-precision map construction method and device, electronic equipment and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3505962B1 (en) | Method and apparatus for processing point cloud data | |
| US11709058B2 (en) | Path planning method and device and mobile device | |
| WO2020043041A1 (en) | Method and device for point cloud data partitioning, storage medium, and electronic device | |
| CN108319895B (en) | Method and device for identifying intersection in electronic map | |
| WO2021249071A1 (en) | Lane line detection method, and related apparatus | |
| EP3806064A1 (en) | Method and apparatus for detecting parking space usage condition, electronic device, and storage medium | |
| CN111813101B (en) | Robot path planning method, device, terminal equipment and storage medium | |
| CN111295666A (en) | Lane line detection method, device, control equipment and storage medium | |
| EP3040909A1 (en) | Method of providing an envelope with respect to a cluster | |
| CN111213154A (en) | Lane line detection method, lane line detection equipment, mobile platform and storage medium | |
| CN113989777A (en) | Method, device and equipment for identifying speed limit sign and lane position of high-precision map | |
| CN110490507A (en) | A kind of newly-increased wireline inspection method, device and equipment of logistics network | |
| CN115424245A (en) | Parking space identification method, electronic device and storage medium | |
| CN114092909A (en) | Lane line extraction method and device, vehicle and storage medium | |
| CN112912894A (en) | Road boundary identification method and device | |
| CN115083199A (en) | Parking space information determination method and related equipment thereof | |
| CN114184204A (en) | Method and device for estimating intersection area in high-precision map and intelligent vehicle | |
| CN115457506A (en) | Target detection method, device and storage medium | |
| CN112149471A (en) | Loopback detection method and device based on semantic point cloud | |
| CN109360137A (en) | A kind of car accident appraisal procedure, computer readable storage medium and server | |
| CN110796129A (en) | Text line region detection method and device | |
| CN113963238A (en) | Construction method of multitask perception recognition model and multitask perception recognition method | |
| CN111723866A (en) | Point cloud clustering method and device, unmanned vehicle and readable storage medium | |
| CN114323021A (en) | Method and device for estimating intersection area in high-precision map and intelligent vehicle | |
| CN114155508B (en) | Road change detection method, device, equipment and storage medium |
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 |