CN112685517B - Method and apparatus for identifying diverging/converging regions - Google Patents
Method and apparatus for identifying diverging/converging regions Download PDFInfo
- Publication number
- CN112685517B CN112685517B CN201910990478.6A CN201910990478A CN112685517B CN 112685517 B CN112685517 B CN 112685517B CN 201910990478 A CN201910990478 A CN 201910990478A CN 112685517 B CN112685517 B CN 112685517B
- Authority
- CN
- China
- Prior art keywords
- lane
- lane line
- intersecting
- spatial index
- 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.)
- Active
Links
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention provides a method and equipment for identifying a divergence/confluence area. The method comprises the following steps: establishing a data model according to the received crowdsourcing data; establishing a spatial index of points on the lane line according to the data model; determining an intersecting lane line according to the spatial index of the points on the lane line and a preset sliding window; and determining whether a divergence/confluence area exists or not according to the crossed lane line. The method can determine whether the area corresponding to the lane line is a diverging/converging area or not under the condition that crowdsourcing data only shows that the lane line has an intersection trend, provides a basis for map updating under the condition that the lane line data is incomplete, and improves the identification efficiency compared with the method for identifying through manual experience in the prior art.
Description
Technical Field
The invention relates to unmanned technology, in particular to a method and equipment for identifying a divergence/confluence area.
Background
In recent years, unmanned vehicles are not paid much attention by governments of various countries, the unmanned technology is materialization of understanding, learning and memorizing processes of 'environment perception-decision making and planning-control and execution' in long-term driving practice of human drivers, and the unmanned vehicles are complex intelligent automatic systems with software and hardware combined. In the field of unmanned driving, a high-precision map is used as a service provider of prior environmental information and plays an important role in the processes of high-precision positioning, environment perception assistance, planning and decision making. The high-precision crowdsourcing data source is an important data source for high-precision map updating, and how to identify a divergence/confluence area from crowdsourcing data is a problem to be solved urgently at present.
In the prior art, under the condition that crowdsourcing data only shows that lane lines have an intersection trend, a divergence/confluence area is identified in a manual mode, and then the corresponding lane lines are edited, however, the efficiency is low in the manual identification mode.
Disclosure of Invention
The invention provides a method and equipment for identifying a divergence/confluence area. The method is used for solving the problem that the manual identification method in the prior art is low in efficiency.
In a first aspect, the present invention provides a method for identifying a divergence/confluence area, comprising:
establishing a data model according to the received crowdsourcing data;
establishing a spatial index of points on the lane line according to the data model;
determining an intersecting lane line according to the spatial index of the points on the lane line and a preset sliding window;
and determining whether a diverging/converging area exists or not according to the crossed lane line.
In a second aspect, the present invention provides an apparatus for identifying a divergence/confluence area, comprising:
the establishing module is used for establishing a data model according to the received crowdsourcing data;
the establishing model is also used for establishing a spatial index of points on the lane line according to the data model;
the determining module is used for determining an intersecting lane line according to the spatial index of the points on the lane line and a preset sliding window;
the determining module is further used for determining whether a divergence/confluence area exists according to the crossed lane line.
In a third aspect, the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above-described method of identifying a divergence/convergence region.
In a fourth aspect, the present invention provides a cloud platform, comprising:
the receiving module is used for receiving crowdsourcing data;
the extraction module is used for establishing a data model according to the crowdsourcing data; the data model is used for establishing a data model of a lane line; the system is also used for determining an intersecting lane line according to the spatial index of the points on the lane line and a preset sliding window; the system is also used for determining whether a divergence/confluence area exists according to the crossed lane line;
the sending module is used for sending the result determined by the extracting module to a map data updating device so that the map data updating device updates the map according to the result determined by the extracting module and returns the updated map to the cloud platform;
and the sending module is also used for sending the updated map to an automatic driving vehicle end.
According to the method and the device for identifying the divergence/confluence area, a cloud platform firstly establishes a data model according to crowdsourcing data on the basis of receiving the crowdsourcing data; then, according to the established data model, establishing a spatial index of points on the lane line; and then, determining an intersecting lane line according to the established spatial index of the points on the lane line and a preset sliding window, and finally, determining whether the corresponding area is a diverging/converging area or not according to the determined intersecting lane line. The method can determine whether the area corresponding to the lane line is a diverging/converging area or not under the condition that crowdsourcing data only shows that the lane line has an intersection trend, provides a basis for map updating under the condition that the lane line data is incomplete, and improves the identification efficiency compared with the method for identifying through manual experience in the prior art.
Drawings
Fig. 1 is an optional application scenario diagram of the method for identifying a divergence/confluence area provided by the present invention;
FIG. 2 is a flowchart illustrating a first embodiment of a method for identifying a divergence/convergence zone according to the present invention;
FIG. 3 is a schematic diagram of a data model provided by the present invention;
FIG. 4 is a schematic view of a driving trajectory model provided by the present invention;
FIG. 5 is a first schematic diagram of a relationship between points on a lane line and a driving path model provided by the present invention;
FIG. 6 is a second schematic diagram of a relationship between points on a lane line and a driving path model provided by the present invention;
FIG. 7 is a schematic diagram of the calculation of spatial indices of points on a lane line provided by the present invention;
FIG. 8 is a flowchart illustrating a second embodiment of the method for identifying a divergence/convergence zone provided by the present invention;
FIG. 9 is a schematic diagram of the present invention for determining intersecting lane lines;
FIG. 10 is a schematic diagram of the identification of diverging/converging regions provided by the present invention;
FIG. 11 is a schematic structural diagram of an embodiment of the device for identifying a divergence/confluence area provided by the present invention;
fig. 12 is a schematic diagram of a hardware structure of a cloud platform provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein.
Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the field of unmanned driving, real-time updating of high-precision maps is an important support for safe driving of unmanned vehicles. The high-precision crowdsourcing data source is an important data source for updating a high-precision map, however, lane line information in crowdsourcing data may not be complete, and under such a situation, in the prior art, divergence/confluence areas in crowdsourcing data are mainly identified in a manual mode, and then corresponding lane lines are edited, but the mode of manual identification is low in efficiency, and the precision cannot meet the requirement of the high-precision map.
Based on the above technical problems in the prior art, the present invention provides a method and apparatus for identifying a divergence/confluence area, wherein on the basis of receiving crowdsourcing data, a data model is first established according to the crowdsourcing data; then, according to the established data model, establishing a spatial index of points on the lane line; and then, determining an intersecting lane line according to the established spatial index of the points on the lane line and a preset sliding window, and finally, determining whether the corresponding area is a diverging/converging area or not according to the determined intersecting lane line. Compared with the method for identifying through manual experience in the prior art, the method provided by the invention has high identification efficiency.
Fig. 1 is an optional application scenario diagram of the method for identifying a divergence/confluence area provided by the present invention. The application scenario diagram shown in fig. 1 includes: cloud platform and autopilot car end. The cloud platform and the automatic driving vehicle end can be connected through a wireless communication technology.
The crowdsourcing data collection system is installed on the automatic driving vehicle end and comprises various types of vehicle-mounted sensors, the automatic driving vehicle end can acquire crowdsourcing data through the sensors and send the acquired crowdsourcing data to the cloud platform.
After the cloud platform receives crowdsourcing data sent by the automatic driving vehicle ends, the identification of the divergence/confluence areas can be completed through the steps of modeling the crowdsourcing data, establishing a spatial index, traversing adjacent marked lines through a sliding window and the like, and then the identification results can be sent to each automatic driving vehicle end.
The following describes the technical solutions of the present invention and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
Fig. 2 is a flowchart illustrating a first embodiment of a method for identifying a divergence/confluence area according to the present invention. The method for identifying a divergence/convergence region provided by this embodiment may be executed by the cloud platform shown in fig. 1, and as shown in fig. 2, the method for identifying a divergence/convergence region provided by this embodiment includes:
s201, establishing a data model according to the received crowdsourcing data.
Specifically, the cloud platform receives crowdsourcing data sent by the automatic driving vehicle end, and the crowdsourcing data comprises: the automatic driving vehicle end collects lane line data on the current road and point data contained in each lane line. Since the sensor mounted at the unmanned vehicle end has various forms, in order to improve the generalization capability of the identification method provided by the invention, so that the identification method provided by the invention is oriented to a specific data model rather than a certain data source, the cloud platform needs to model the received crowdsourcing data.
In an implementation manner, the following data model can be established according to crowdsourcing data:
lane model: LBS = { L = { (L) 1 ，L 2 ，……L n },n≥2
Lane line model: l is i ＝{P 1 ，P 2 ，……P n },n≥2
A driving track model: PATH = { P 1 ，P 2 ，……P n },n≥2
Point model: p = { Longitude, latitude, H }
Wherein, the point model is characterized by longitude, latitude and geodetic height, and the vehicle is drivenThe PATH model PATH is composed of point models P on the vehicle running PATH, the order of the point models P in the PATH model PATH is consistent with the vehicle running direction, and the lane line model L i Composed of point models P corresponding to lane lines, lane line model L i The order of the midpoint models P is consistent with the driving direction of the vehicle, and the lane model LBS is composed of a lane line model L i And (4) forming. The number of lane line models in the lane model LBS may be used to represent the adjacency relationship between them. Referring to fig. 3, fig. 3 is a schematic diagram of the lane model LBS including 3 lane line models. In fig. 3, the lane model LBS includes lane line models: l1, L2, L3, wherein L1 and L2 are adjacent lanes, and L2 and L3 are adjacent lanes.
S202, according to the data model, establishing a spatial index of points on the lane line.
Specifically, the following steps may be adopted to establish a spatial index of points on the lane line:
firstly, according to a driving track model, a spatial index of points on a driving track of a vehicle is established.
In the implementation process of the step, firstly, the distance between adjacent point models in the driving track model is determined according to the driving track model; and then, according to the distance between the adjacent point models in the driving track model, establishing a spatial index of points on the driving track of the vehicle.
The following describes the implementation process of this step by taking the following trajectory model shown in fig. 4 as an example:
the driving path model shown in fig. 4 includes P1, P2, … Pn point models, and as shown in fig. 4, first, the distance between each two adjacent point models on the driving path model is calculated and recorded as D1, D2, … Dn-1; then, a spatial index of points on the vehicle travel trajectory is established using the following formula:
therein, index n Representing the spatial index of the nth point on the vehicle running track, and Di representing the model of the ith point on the vehicle running trackAnd the distance between the (i + 1) th point model.
And secondly, establishing a spatial index of points on the lane line according to the spatial index of the points on the vehicle driving track.
In the implementation process of the step, firstly, the point-line distance from a point on a lane line to a line segment formed by every two adjacent point models in a driving track model is calculated; then, determining a corresponding target line segment when the point-line distance is minimum; and finally, establishing the spatial index of the points on the lane line according to the footholds of the points on the lane line on the target line segment and the spatial indexes of the two point models forming the target line segment.
The following describes the implementation process of this step with fig. 5, fig. 6, and fig. 7:
assuming that the relationship between a point PL on the lane line and the traffic track model is shown in fig. 5, first, the point-line distance from the PL to a line segment formed by any two adjacent point models in the traffic track model is calculated, and the calculation method of the point-line distance includes: referring to FIG. 6, if the PL to line segment drop falls within the line segment, the dot to line distance is the PL to perpendicular distance of the line segment, and if the PL to line segment drop falls outside the line segment, the dot to line distance is the PL to the end point of the line segment that is closest to PL.
Then, after obtaining the point-line distance from the PL to a line segment formed by any two adjacent point models in the trajectory model, finding out a target line segment corresponding to the line segment with the minimum point-line distance, wherein the relationship between the PL and the target line segment has two conditions, namely: the PL drop to the target line segment falls within the target line segment as shown in FIG. 7. And the second method comprises the following steps: the PL drop to the target line segment falls outside the target line segment, which indicates that PL is a point outside the model of the trajectory and is discarded. In the first case, the following formula can be used to establish the spatial index of the points on the lane line:
Index PL ＝Index Pn +DL
continuing with FIG. 7, index PL Spatial Index, representing point PL on a lane line Pn Representing the spatial index of a point model Pn on the driving track model, L representing a target line segment, C representing the foot from a point PL to the target line segment, and DL representing a point model Pn and the drop foot C.
And S203, determining the crossed lane line according to the spatial index of the points on the lane line and a preset sliding window.
The purpose of determining the intersecting lane lines is to determine an area in which data of each lane line exists in the vehicle traveling direction, two adjacent lane lines in the area are referred to as intersecting lane lines, and then the diverging/converging area is identified based on the intersecting lane lines in the area.
The relevant parameters of the preset sliding window can be set according to actual conditions, such as: the length of the preset sliding window can be set to 20 meters, and the sliding step length can be set to 1 meter.
And S204, determining whether a divergence/confluence area exists or not according to the crossed lane line.
Specifically, in a real scene, the lane width of the non-divergence/convergence region is constant, and the lane width of the divergence/convergence region is gradually changed, and thus, on the basis of determining the intersecting lane line, whether the divergence/convergence region exists can be identified by whether the lane width is changed.
In the method for identifying a divergence/confluence area provided by this embodiment, on the basis of receiving crowdsourcing data, a cloud platform first establishes a data model according to the crowdsourcing data; then, according to the established data model, establishing a spatial index of points on the lane line; and then, determining an intersecting lane line according to the established spatial index of the points on the lane line and a preset sliding window, and finally, determining whether the corresponding area is a diverging/converging area or not according to the determined intersecting lane line. The method can determine whether the area corresponding to the lane line is a diverging/converging area or not under the condition that crowdsourcing data only shows that the lane line has an intersection trend, provides a basis for map updating under the condition that the lane line data is incomplete, and improves the identification efficiency compared with the method for identifying through manual experience in the prior art.
Fig. 8 is a flowchart illustrating a second embodiment of the method for identifying a divergence/confluence area according to the present invention. As with the foregoing embodiment, the method for identifying a divergence/convergence region provided by this embodiment can be executed by the cloud platform shown in fig. 1, and as shown in fig. 8, the method for identifying a divergence/convergence region provided by this embodiment includes:
s801, establishing a data model according to the received crowdsourcing data.
S802, according to the data model, establishing a spatial index of the points on the lane line.
The implementation manners of S801 to S802 can refer to the above embodiments S201 to S202, and the present invention is not described herein again.
And S803, determining an intersecting marking line in the preset sliding window according to the spatial index of the point on the lane line and the preset sliding window, wherein the intersecting marking line is the intersecting part of the lane line and the preset sliding window.
It should be noted that: the step determines the intersecting marking lines of the adjacent lane line models in the lane model LBS in the preset sliding window. Suppose lane model LBS = { L = { L } 1 ，L 2 ，L 3 And combining adjacent lane line models in the lane models, wherein the adjacent lane line models comprise: g1= { L 1 ，L 2 }，G2＝{L 2 ，L 3 }. Hereinafter, G1= { L = { L = } 1 ，L 2 Explaining the process of determining the intersecting marked lines in the preset sliding window in the step by taking an example:
assuming that the starting point model of L1 is P0, the spatial Index of P0 is denoted as Index0, for example, but not limited to Index0=0 meter, and W is taken as the window length and S is taken as the step length along the vehicle driving direction, the spatial Index range where the nth sliding window is located is:
R＝[Index 0 +n*S，Index 0 +n*S+W]
order to
W1＝Index 0 +n*S
W2＝Index 0 +n*S+W
Calculating an intersecting marking line of L2 and L1 in a preset sliding window by the following method:
if the spatial Index of the n-th and n + 1-th point models on L2 satisfies Index n ≤W1≤Index n+1 If L2 and the preset sliding window have an initial intersection point, the coordinates of the initial intersection point are:
wherein, P x And P x+1 Respectively representing x coordinates of the nth and the (n + 1) th point models on the L2; p y And P y+1 Respectively representing the y coordinates of the nth and the (n + 1) th point models on the L2; p z And P z+1 Respectively representing the z-coordinate of the nth and n +1 th point models on L2.
If no point model on L2 satisfies Index n ≤W1≤Index n+1 Then L2 has no initial intersection with the predetermined sliding window.
If the spatial Index of the n-th and n + 1-th point models on L2 satisfies Index n ≤W2≤Index n+1 If L2 has a termination intersection point with the preset sliding window, the coordinates of the termination intersection point are:
wherein, P x And P x+1 Respectively representing the x coordinates of the nth and the n +1 th point models on the L2; p y And P y+1 Respectively representing the y coordinates of the nth and the (n + 1) th point models on the L2; p z And P z+1 Respectively representing the z-coordinate of the nth and n +1 th point models on L2.
If no point model on L2 satisfies Index n ≤W2≤Index n+1 Then L2 has no termination intersection with the preset sliding window.
Spatial Index if point model on L2 n Satisfy W1. Ltoreq. Index n And if the value is less than or equal to W2, the point model is a point falling in a preset sliding window.
And forming a line by the starting intersection point, the point falling in the preset sliding window and the ending intersection point, wherein the line and the L1 form an intersecting marking line in the preset sliding window.
S804, the starting points of the two crossed marking lines corresponding to the adjacent lane lines are compared to obtain the starting point with the largest space index in the two crossed marking lines.
And S805, comparing the end points of the two intersecting marked lines corresponding to the adjacent lane lines to obtain the end point with the minimum spatial index in the two intersecting marked lines.
S806, determining the crossed lane line according to the starting point with the largest spatial index and the end point with the smallest spatial index.
The following describes the process of S804-S806 by way of example:
assuming that two intersecting marked lines corresponding to adjacent lane lines are respectively M1 and M2, respectively obtaining spatial indexes of a starting point and an end point of M1 and spatial indexes of a starting point and an end point of M2, and recording as follows:
and
if the following relation is satisfied between the data and the data, the data indicates that M1 and M2 have no transverse intersection region, and the data is not subjected to subsequent processing; if the following relation is not satisfied between the M1 and the M2, the existence of the transverse intersection region is indicated, and the subsequent processing process is continued.
In the case of the presence of a transverse intersection region between M1 and M2, this will be
And
a comparison is made to determine the starting point of M1 and M2 where the spatial index is the greatest, will
And
comparing to determine the end point with the minimum spatial index in M1 and M2, as shown in fig. 9, in the schematic diagram of fig. 9, the start point with the maximum spatial index is the start point of M2 and is denoted as P ', the end point with the minimum spatial index is the end point of M1 and is denoted as P ", the foot C from P' to M1 and the foot C from P" to M2 are obtained, and the line segment from the point C to the end point P "on M1 and the line segment from the point P 'to the point C' on M2 form the intersecting lane line.
And S807, calculating the lane distance between the crossed lane lines in each sampling interval along the driving direction of the vehicle according to the crossed lane lines.
And S808, determining whether a divergence/confluence area exists or not according to the lane distance.
Alternatively, if the number of the lane distances having the absolute value larger than the first threshold value is equal to or larger than the second threshold value in each sampling interval in the vehicle traveling direction, it may be determined that the divergence/convergence region exists.
The process of S806-S807 is explained by distance as follows:
referring to fig. 10, a lane distance Δ D between the intersecting lane lines is obtained every Δ X in the vehicle traveling direction from the start point of the intersecting lane line, the number of times that the absolute value is greater than the first threshold value in Δ D is counted, and if the number is greater than or equal to the second threshold value, it is determined that the divergence/convergence region exists.
Alternatively, Δ X may be, for example, 0.1 meter, the first threshold may be, for example, 0.001 meter, and the second threshold may be, for example, 5.
Referring to the above description, since the intersection marked line determined in S803 refers to the intersection marked line of the adjacent lane line model in the lane model within the preset sliding window, correspondingly, the intersection lane line determined in S804-S805 refers to the intersection lane line of the adjacent lane line model, and S806-S807 determine whether the region corresponding to the adjacent lane line model has the divergence/convergence region.
S809, if the lane distance is increased along the vehicle running direction, determining the area corresponding to the crossed lane line as a bifurcation area; and if the lane distance is reduced along the driving direction of the vehicle, determining that the area corresponding to the crossed lane line is a confluence area.
Specifically, when it is determined in S807 that the divergence/convergence region exists, the change of the lane distance Δ D in the vehicle traveling direction is further acquired, and if Δ D in the vehicle traveling direction is increased, the region corresponding to the intersecting lane line is the divergence region, and if Δ D in the vehicle traveling direction is decreased, the region corresponding to the intersecting lane line is the convergence region.
Compared with the identification method through manual experience in the prior art, the identification method of the divergence/confluence area provided by the embodiment has high identification efficiency.
Fig. 11 is a schematic structural diagram of an embodiment of the device for identifying a divergence/confluence area according to the present invention. As shown in fig. 11, the apparatus for identifying a divergence/confluence area according to the present embodiment includes:
an establishing module 1101, configured to establish a data model according to the received crowdsourcing data;
the establishing model 1101 is further configured to establish a spatial index of a point on a lane line according to the data model;
a determining module 1102, configured to determine an intersecting lane line according to the spatial index of the point on the lane line and a preset sliding window;
the determining module 1102 is further configured to determine whether a divergence/confluence area exists according to the intersecting lane line.
Optionally, the data model includes: the lane model comprises a lane model, a lane line model, a driving track model and point models, wherein the driving track model consists of point models on a vehicle driving track, the sequence of the point models in the driving track model is consistent with the driving direction of the vehicle, the lane line model consists of the point models on a lane line, the sequence of the point models in the lane line model is consistent with the driving direction of the vehicle, and the lane model consists of the lane line model.
Optionally, the model 1101 is specifically configured to:
establishing a spatial index of points on the vehicle driving track according to the driving track model;
and establishing a spatial index of the points on the lane line according to the spatial index of the points on the vehicle driving track.
Optionally, the establishing model 1101 is specifically configured to:
determining the distance between adjacent point models in the driving track model according to the driving track model;
and establishing a spatial index of points on the vehicle driving track according to the distance between the adjacent point models in the driving track model.
Optionally, the establishing model 1101 is specifically configured to:
calculating the point-line distance from the point on the lane line to the line segment formed by every two adjacent point models in the driving track model;
determining a corresponding target line segment when the distance between the point lines is minimum;
and establishing a spatial index of the points on the lane line according to the footfalls of the points on the lane line on the target line segment and the spatial indexes of two point models forming the target line segment.
Optionally, the determining module 1102 is specifically configured to:
determining an intersecting marking line in a preset sliding window according to a spatial index of a point on the lane line and the preset sliding window, wherein the intersecting marking line is a part where the lane line intersects with the preset sliding window;
comparing the starting points of two intersecting marking lines corresponding to the adjacent lane lines to obtain the starting point with the largest space index in the two intersecting marking lines;
comparing the end points of the two intersecting marking lines corresponding to the adjacent lane lines to obtain the end point with the minimum spatial index in the two intersecting marking lines;
and determining the crossed lane line according to the starting point with the maximum spatial index and the end point with the minimum spatial index.
Optionally, the determining module 1102 is specifically configured to:
according to the intersecting lane lines, calculating lane distances between the intersecting lane lines in each sampling interval along the driving direction of the vehicle;
and determining whether a divergence/confluence area exists or not according to the lane distance.
Optionally, the determining module 1102 is specifically configured to:
and if the number of the lane distances with the absolute value larger than the first threshold value in each sampling interval in the vehicle driving direction is larger than or equal to a second threshold value, determining that the divergence/convergence region exists.
Optionally, the determining module 1102 is further configured to:
if the lane distance is increased along the vehicle driving direction, determining that the area corresponding to the crossed lane line is a bifurcation area;
and if the lane distance is reduced along the driving direction of the vehicle, determining that the area corresponding to the crossed lane line is a confluence area.
The apparatus for identifying a divergence/confluence area provided in this embodiment can be used to perform the method for identifying a divergence/confluence area described in any of the embodiments above, and its implementation principle and technical effect are similar, and are not described herein again.
Fig. 12 is a schematic diagram of a hardware structure of a cloud platform provided in the present invention. As shown in fig. 12, the cloud platform of the present embodiment may include:
a receiving module 1201, configured to receive crowdsourcing data;
an extracting module 1202, configured to establish a data model according to the crowdsourcing data; the data model is used for establishing a data model of a lane line; the system is also used for determining an intersecting lane line according to the spatial index of the points on the lane line and a preset sliding window; the system is also used for determining whether a divergence/confluence area exists according to the crossed lane line;
a sending module 1203, configured to send the result determined by the extracting module to a map data updating apparatus, so that the map data updating apparatus updates a map according to the result determined by the extracting module, and returns the updated map to the cloud platform;
the sending module 1203 is further configured to issue the updated map to an automatic driving end.
The present invention provides a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the method of identifying a divergence/convergence region described in any one of the above embodiments.
The present invention also provides a program product comprising a computer program stored in a readable storage medium, the computer program being readable from the readable storage medium by at least one processor, the computer program being executable by the at least one processor to cause a cloud platform to implement the method of identifying a diverging/converging region as described in any of the embodiments above.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or in the form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present application may be embodied directly in a hardware processor, or in a combination of the hardware and software modules in the processor.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (11)
1. A method for identifying a divergence/confluence area, comprising:
establishing a data model according to the received crowdsourcing data;
establishing a spatial index of points on the lane line according to the data model;
determining an intersecting lane line according to the spatial index of the points on the lane line and a preset sliding window;
determining whether a divergence/confluence area exists or not according to the crossed lane line;
determining the crossed lane line according to the spatial index of the points on the lane line and a preset sliding window, comprising:
determining an intersecting marking line in a preset sliding window according to a spatial index of a point on the lane line and the preset sliding window, wherein the intersecting marking line is a part where the lane line intersects with the preset sliding window;
comparing the starting points of two intersecting marking lines corresponding to the adjacent lane lines to obtain the starting point with the largest space index in the two intersecting marking lines;
comparing the end points of the two intersecting marking lines corresponding to the adjacent lane lines to obtain the end point with the minimum spatial index in the two intersecting marking lines;
and determining the crossed lane line according to the starting point with the maximum spatial index and the end point with the minimum spatial index.
2. The method of claim 1, wherein the data model comprises: the lane model comprises a lane model, a lane line model, a driving track model and point models, wherein the driving track model consists of point models on a vehicle driving track, the sequence of the point models in the driving track model is consistent with the driving direction of the vehicle, the lane line model consists of the point models on a lane line, the sequence of the point models in the lane line model is consistent with the driving direction of the vehicle, and the lane model consists of the lane line model.
3. The method of claim 2, wherein said building a spatial index of points on a lane line from said data model comprises:
according to the driving track model, establishing a spatial index of points on the driving track of the vehicle;
and establishing a spatial index of the points on the lane line according to the spatial index of the points on the vehicle driving track.
4. The method of claim 3, wherein said building a spatial index of points on the vehicle's travel path from the travel path model comprises:
determining the distance between adjacent point models in the driving track model according to the driving track model;
and establishing a spatial index of points on the vehicle driving track according to the distance between the adjacent point models in the driving track model.
5. The method of claim 4, wherein the building a spatial index of points on the lane-line from a spatial index of points on the vehicle travel track comprises:
calculating the point-line distance from the point on the lane line to the line segment formed by every two adjacent point models in the driving track model;
determining a corresponding target line segment when the distance between the point lines is minimum;
and establishing the spatial index of the points on the lane line according to the footholds of the points on the lane line on the target line segment and the spatial indexes of the two point models forming the target line segment.
6. The method of claim 1, wherein said determining whether a divergence/confluence region exists based on said intersecting lane lines comprises:
according to the intersecting lane lines, calculating lane distances between the intersecting lane lines in each sampling interval along the driving direction of the vehicle;
and determining whether a divergence/confluence area exists according to the lane distance.
7. The method of claim 6, wherein determining whether a divergence/convergence region exists based on the lane distance comprises:
and if the number of the lane distances with the absolute value larger than the first threshold value in each sampling interval in the driving direction of the vehicle is larger than or equal to a second threshold value, determining that the divergence/convergence region exists.
8. The method of any one of claims 6-7, further comprising:
if the lane distance is increased along the vehicle driving direction, determining that the area corresponding to the crossed lane line is a bifurcation area;
and if the lane distance is reduced along the driving direction of the vehicle, determining that the area corresponding to the crossed lane line is a confluence area.
9. An apparatus for identifying a divergence/confluence area, comprising:
the establishing module is used for establishing a data model according to the received crowdsourcing data;
the establishing model is also used for establishing a spatial index of points on the lane line according to the data model;
the determining module is used for determining an intersecting lane line according to the spatial index of the points on the lane line and a preset sliding window;
the determining module is further used for determining whether a divergence/confluence area exists according to the crossed lane line;
the determining module is specifically configured to determine an intersecting marking line in a preset sliding window according to a spatial index of a point on the lane line and the preset sliding window, where the intersecting marking line is a part where the lane line intersects with the preset sliding window;
comparing the starting points of two intersecting marking lines corresponding to the adjacent lane lines to obtain the starting point with the largest space index in the two intersecting marking lines;
comparing the end points of the two intersecting marking lines corresponding to the adjacent lane lines to obtain the end point with the minimum spatial index in the two intersecting marking lines;
and determining the crossed lane line according to the starting point with the maximum spatial index and the end point with the minimum spatial index.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of claims 1 to 8.
11. A cloud platform, comprising:
the receiving module is used for receiving crowdsourcing data;
the extraction module is used for establishing a data model according to the crowdsourcing data; the data model is also used for establishing a space index of points on the lane line according to the data model; the system is also used for determining an intersecting lane line according to the spatial index of the points on the lane line and a preset sliding window; the system is also used for determining whether a divergence/confluence area exists according to the crossed lane line;
the sending module is used for sending the result determined by the extracting module to a map data updating device so that the map data updating device updates the map according to the result determined by the extracting module and returns the updated map to the cloud platform;
the sending module is also used for sending the updated map to an automatic driving vehicle end;
the extraction module is specifically configured to determine an intersecting marking line in a preset sliding window according to a spatial index of a point on the lane line and the preset sliding window, where the intersecting marking line is a part where the lane line intersects with the preset sliding window;
comparing the starting points of two intersecting marking lines corresponding to the adjacent lane lines to obtain the starting point with the largest space index in the two intersecting marking lines;
comparing the end points of the two intersecting marking lines corresponding to the adjacent lane lines to obtain the end point with the minimum spatial index in the two intersecting marking lines;
and determining the crossed lane line according to the starting point with the maximum spatial index and the end point with the minimum spatial index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910990478.6A CN112685517B (en) | 2019-10-17 | 2019-10-17 | Method and apparatus for identifying diverging/converging regions |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910990478.6A CN112685517B (en) | 2019-10-17 | 2019-10-17 | Method and apparatus for identifying diverging/converging regions |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112685517A CN112685517A (en) | 2021-04-20 |
| CN112685517B true CN112685517B (en) | 2023-01-31 |
Family
ID=75444670
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910990478.6A Active CN112685517B (en) | 2019-10-17 | 2019-10-17 | Method and apparatus for identifying diverging/converging regions |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112685517B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113435427B (en) * | 2021-08-27 | 2021-11-09 | 湖北亿咖通科技有限公司 | Method and device for aggregating lane lines |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971521A (en) * | 2014-05-19 | 2014-08-06 | 清华大学 | Method and device for detecting road traffic abnormal events in real time |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012150591A2 (en) * | 2011-05-03 | 2012-11-08 | Alon Atsmon | Automatic content analysis method and system |
| US10488214B2 (en) * | 2017-06-28 | 2019-11-26 | Here Global B.V. | Method, apparatus, and computer program product for dynamic lane guidance |
| CN109059954B (en) * | 2018-06-29 | 2020-09-11 | 广东星舆科技有限公司 | Method and system for supporting high-precision map lane line real-time fusion update |
| CN109214314B (en) * | 2018-08-17 | 2022-03-29 | 宽凳（北京）科技有限公司 | Automatic fusion matching algorithm for lane lines |
-
2019
- 2019-10-17 CN CN201910990478.6A patent/CN112685517B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971521A (en) * | 2014-05-19 | 2014-08-06 | 清华大学 | Method and device for detecting road traffic abnormal events in real time |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112685517A (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110287276B (en) | High-precision map updating method and device and storage medium | |
| CN109520744B (en) | Driving performance testing method and device for automatic driving vehicle | |
| US10403138B2 (en) | Traffic accident warning method and traffic accident warning apparatus | |
| CN109484435B (en) | Train positioning method and device suitable for intelligent rail transit detection system | |
| CN109902899B (en) | Information generation method and device | |
| WO2017010209A1 (en) | Peripheral environment recognition device and computer program product | |
| CN102208035B (en) | Image processing system and position measuring system | |
| RU2742213C1 (en) | Method to control information on lanes, method of traffic control and device for control of information on lanes | |
| CN110749329B (en) | Lane level topology construction method and device based on structured road | |
| US20210403001A1 (en) | Systems and methods for generating lane data using vehicle trajectory sampling | |
| CN102208012A (en) | Scene matching reference data generation system and position measurement system | |
| CN114399916B (en) | Virtual traffic light control reminding method for digital twin smart city traffic | |
| CN113743469B (en) | Automatic driving decision method integrating multi-source data and comprehensive multi-dimensional indexes | |
| CN114518122A (en) | Driving navigation method, driving navigation device, computer equipment, storage medium and computer program product | |
| CN113008260A (en) | Navigation information processing method and device, electronic equipment and storage medium | |
| CN111914691A (en) | Rail transit vehicle positioning method and system | |
| CN110765224A (en) | Processing method of electronic map, vehicle vision repositioning method and vehicle-mounted equipment | |
| CN114926809A (en) | Passable area detection method and device, moving tool and storage medium | |
| US20180208197A1 (en) | Lane keeping assistance system | |
| CN110473405B (en) | Driving state detection method and device, readable storage medium and electronic equipment | |
| CN112685517B (en) | Method and apparatus for identifying diverging/converging regions | |
| CN113178091B (en) | Safe driving area method, device and network equipment | |
| US20210048819A1 (en) | Apparatus and method for determining junction | |
| CN111613052B (en) | Traffic condition determining method and device, electronic equipment and storage medium | |
| CN113392170A (en) | High-precision map data generation method and device and server |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |