CN109916416B - Method, device and equipment for processing and updating lane line data - Google Patents
Method, device and equipment for processing and updating lane line data Download PDFInfo
- Publication number
- CN109916416B CN109916416B CN201910083931.5A CN201910083931A CN109916416B CN 109916416 B CN109916416 B CN 109916416B CN 201910083931 A CN201910083931 A CN 201910083931A CN 109916416 B CN109916416 B CN 109916416B
- Authority
- CN
- China
- Prior art keywords
- curve
- lane line
- lane
- point cloud
- data
- 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
- Image Processing (AREA)
- Image Generation (AREA)
Abstract
The invention discloses a method, a device and equipment for processing and updating lane line data, wherein the method comprises the following steps: acquiring original lane line data for describing a continuous lane, wherein the original lane line data comprises at least one multi-edge line; performing curve fitting on the polygonal lines in the original lane line data to obtain a first curve corresponding to each polygonal line; obtaining a second curve corresponding to the continuous lane according to the first curve corresponding to each multi-edge line; acquiring a target parameter corresponding to the second curve, wherein the target parameter is used for describing the back-to-back degree of the second curve and the original lane line data; and when the target parameter is smaller than a preset shape threshold value, adjusting the first curve, and returning to the step of obtaining a second curve corresponding to the continuous lane according to the first curve corresponding to each polyline. The method and the device can obviously reduce the data volume, reduce the overhead of map differential updating, improve the updating speed and reduce the updating complexity and the error rate.
Description
Technical Field
The invention relates to the field of map data processing, in particular to a method, a device and equipment for processing and updating lane line data.
Background
The precision and timeliness of the high-precision map are important guarantees of automatic driving safety, and lane line data in the high-precision map are used as main references for transverse positioning, driving situation judgment and control decision making in automatic driving, so that the fact that the precision and updating timeliness of the lane line data are guaranteed becomes a significant problem of application of the high-precision map. The lane line data in the high-precision map is stored in a polyline (polyline) form, the lane line data is described by storing each shape point coordinate of the polyline, and the volume of the polyline data is large, so that compression and dynamic updating are not facilitated.
Disclosure of Invention
The invention provides a method, a device and equipment for processing and updating lane line data.
In one aspect, the present invention provides a lane line data processing method, including:
acquiring original lane line data for describing a continuous lane, wherein the original lane line data comprises at least one multi-edge line;
performing curve fitting on the polygonal lines in the original lane line data to obtain a first curve corresponding to each polygonal line;
obtaining a second curve corresponding to the continuous lane according to the first curve corresponding to each multi-edge line;
acquiring a target parameter corresponding to the second curve, wherein the target parameter is used for describing the back-to-back degree of the second curve and the original lane line data;
and when the target parameter is smaller than a preset shape threshold value, adjusting the first curve, and returning to the step of obtaining a second curve corresponding to the continuous lane according to the first curve corresponding to each polyline.
In another aspect, a lane line data updating method is provided, where a continuous lane is described by a second curve in the lane line data, and the method includes:
acquiring point cloud data of a newly added lane line;
acquiring a second curve set corresponding to the lane line point cloud data;
extracting a curve set to be adjusted from the second curve set, wherein the adaptation degree of elements in the curve set to be adjusted and the lane point cloud data is smaller than a preset adaptation threshold value;
and adjusting elements in the curve set to be adjusted to obtain an adjusted curve set, wherein the adaptation degree of the elements in the adjusted curve set and the lane point cloud data is not less than the adaptation threshold value.
In another aspect, a lane line data processing apparatus is provided, the apparatus including:
the system comprises an original lane line number acquisition module, a lane line number acquisition module and a lane line number acquisition module, wherein the original lane line number acquisition module is used for acquiring original lane line data used for describing continuous lanes, and the original lane line data comprises at least one multi-edge line;
the fitting module is used for performing curve fitting on the multiple edges in the original lane line data to obtain a first curve corresponding to each multiple edge;
the second curve acquisition module is used for acquiring a second curve corresponding to the continuous lane according to the first curve corresponding to each multi-edge line;
a target parameter module, configured to obtain a target parameter corresponding to the second curve, where the target parameter is used to describe a degree of a back-off between the second curve and the original lane line data;
and the control module is used for judging whether the target parameter is smaller than a preset shape threshold value or not, if not, adjusting the first curve and acquiring the second curve again.
In another aspect, there is provided a lane line data updating apparatus in which a continuous lane is described by a second curve, the apparatus including:
the point cloud data acquisition module is used for acquiring point cloud data of the newly added lane line;
the second curve set acquisition module is used for acquiring a second curve set corresponding to the point cloud data of the lane line;
the adaptation module is used for extracting a curve set to be adjusted from the second curve set, and the adaptation degrees of elements in the curve set to be adjusted and the lane point cloud data are all smaller than a preset adaptation threshold value;
and the adjusting module is used for adjusting the elements in the curve set to be adjusted to obtain an adjusted curve set, and the adaptation degree of the elements in the adjusted curve set and the lane point cloud data is not less than the adaptation threshold value.
In another aspect, a lane line data processing and updating apparatus is provided, where the apparatus includes a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or a set of instructions, and the at least one instruction, at least one program, a code set, or a set of instructions is loaded by the processor and executes the lane line data processing method and/or the lane line data processing method.
The method, the device and the equipment for processing and updating the lane line data have the following technical effects:
(1) the curve can be updated and modified only by adjusting curve shape points without adding or deleting point data, so that the modification consistency is better;
(2) the curve description does not need to store a large amount of point data, so that the data volume is obviously reduced;
(3) the curve parameters can be updated and adjusted without adding or deleting point data, so that the operation time is reduced, and the speed is increased;
(4) the geometric meaning of the curve is clear, the processing and adjustment of the related data can be automatically carried out, and the manual time is saved;
(5) in the embodiment of the invention, the curve adjustment does not change the topological relation of the original road, and the updated curve does not need to be matched with the original road data, so that an update package can be directly generated, the updating speed is increased, and the updating complexity and the error rate are reduced;
(6) the embodiment of the invention ensures the inheritance of data to a greater extent, minimizes the overhead of differential updating of the map, and meets the requirement of commercial operation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a lane line data processing method provided by the present invention;
FIG. 2(a) is a schematic diagram of a projection of a certain point to a polygonal line provided by the present invention;
FIG. 2(b) is a schematic diagram of a projection of a second curve obtained at a certain point according to an embodiment of the present invention;
FIG. 3 is a flow chart of a lane line data updating method provided by the present invention;
FIG. 4 is a schematic diagram of a three-dimensional laser point cloud provided by the present invention;
FIG. 5(a) is a schematic diagram of polygon update provided by the present invention;
FIG. 5(b) is a schematic diagram of the curve update provided by the present invention;
FIG. 6 is a schematic diagram of a distributed map application scenario provided by the present invention;
FIG. 7 is a flow chart of a method for calculating a degree of adaptation provided by the present invention;
FIG. 8 is a flowchart for calculating the degree of adaptation between the point cloud data of the lane and the second curve according to the present invention;
FIG. 9 is a block diagram of a lane line data processing apparatus according to the present invention;
FIG. 10 is a block diagram of a lane line data update apparatus according to the present invention;
fig. 11 is a structural diagram of a lane line data processing and updating apparatus provided in the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above 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 capable of operation in sequences other than those illustrated or described herein. Furthermore, 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 server 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.
The existing high-precision map lane line data is generally organized according to a polygonal line form, one lane line can be composed of a plurality of polygonal lines, the polygonal lines are composed of position points in a connected mode, the density degree of the position points is closely related to the map precision, and the dense position points cause large data volume of the high-precision map. In addition, dynamic updating of the polygonal lines is complicated, and dynamic modification needs to be performed on specific position points, such as adding position points, deleting position points, changing coordinates of the position points and the like, but the process is difficult to realize fully automatically, and a high-precision map is re-manufactured in an area where data change occurs by comparing the difference between original map data and acquired data; correspondingly, the process of obtaining the differential data packet based on the dynamically updated data is also tedious, and the dynamically updated data needs to be compared with the data before the dynamic update, which is time-consuming and labor-consuming.
In order to solve the technical problems of overlarge data volume and complicated dynamic update of original lane line data, an embodiment of the present invention provides a lane line data processing method, as shown in fig. 1, the method includes:
s101, obtaining original lane line data used for describing continuous lanes, wherein the original lane line data comprises at least one multi-edge line.
Specifically, if a plurality of polygonal lines are included, the plurality of polygonal lines are connected end to form a continuous lane.
The length and definition of the continuous lane can be adaptively changed according to actual conditions, for example, the part of a certain national road in each jurisdiction can be used as a continuous lane, and a certain bridge or a certain tunnel can be used as a continuous lane. The length and definition of the continuous lane can be consistent with those of the existing high-precision map, namely the continuous lane and the multiple side lines forming the continuous lane can be obtained from the existing high-precision map.
S102, performing curve fitting on the polygonal lines in the original lane line data to obtain a first curve corresponding to each polygonal line.
The embodiments of the present invention are not limited to a specific curve form. However, in a preferred embodiment, the fitting result of the polyline may be described by a three-dimensional bezier curve. The three-dimensional Bezier curve can be drawn according to the coordinates of points at four positions, the points at the four positions can be called the shape points of the three-dimensional Bezier curve, and the three-dimensional Bezier curve generates the transformation like stretching of rubber bands along with the regular movement of the shape points.
Obviously, for the three-dimensional bezier curve, only four points are needed for description, and compared with the prior art in which dense position points are needed for description of a multi-segment line, the method for fitting the multi-segment line by using the three-dimensional bezier curve obviously achieves the effect of data compression.
Furthermore, it can be seen from the characteristics of the three-dimensional bezier curve that changing the position of the shape point can easily change the shape of the three-dimensional bezier curve, and if the lane line data is described using the three-dimensional bezier curve, dynamic update of the lane line data is simplified.
S103, obtaining a second curve corresponding to the continuous lane according to the first curve corresponding to each multi-edge line.
Specifically, the polygonal lines are connected end to form original lane line data of the continuous lane, and curves corresponding to the polygonal lines are connected end to form a second curve corresponding to the continuous lane.
S104, acquiring a target parameter corresponding to the second curve, wherein the target parameter is used for describing the back of the second curve and the original lane line data.
In the last step of the embodiment of the present invention, a second curve obtained by connecting three-dimensional segmented third-order bezier curves may be obtained, which is intended to fit a continuous lane through the second curve, and the fitted comprehensive target may be simply summarized as: the number of the first curves used for forming the second curve is small, the fitting error between the second curve and the original lane line data is small, and the correlation derivative value of the joint of the adjacent first curves is small.
The embodiment of the invention does not limit the specific content of the target parameter. However, in a preferred embodiment, in order to more accurately quantify the fitted integrated target, the target parameter may be calculated by using a formula E ═ α data _ fitting + β _ angle _ diff + γ curriculture _ diff + ∈ length, where E represents the target parameter, α, β, γ, and ∈ each have a preset weighting factor, data _ fitting represents a data fitting degree, angle _ diff represents the number of occurrences when the tangential angle jump of the adjacent first curves at the connection exceeds the maximum allowable angle jump, curriculture _ diff represents the number of occurrences when the curvature jump of the adjacent first curves at the connection exceeds the maximum allowable curvature jump, and length is the number of first curves exceeding the maximum allowable length.
And S105, judging whether the target parameter is smaller than a preset shape threshold value.
And S106, if not, adjusting the first curves, and returning to the step of obtaining second curves corresponding to the continuous lanes according to the first curves corresponding to each multi-edge line.
And S107, if so, ending the process.
In a preferred embodiment, the adjustment method of the first curve includes, but is not limited to, merging of adjacent first curves, splitting a certain first curve, disturbing a shape point of a certain first curve, and the like.
In another preferred embodiment, steps S104-S106 may be performed in an iterative manner, including but not limited to using simulated annealing simulation, so that the target parameters corresponding to the second curve may quickly obtain the optimal solution. The simulated annealing algorithm is a method for approximately solving an optimization problem based on Monte Carlo thought design. The simulated annealing is actually a greedy algorithm, but random factors are introduced in the searching process, so that the local optimal solution can be skipped to reach the global optimal solution.
In fact, the embodiment of the present invention discloses a technical solution for describing a continuous lane with an analog curve, by using the analog curve instead of the multi-side line to describe the continuous lane, the data amount of lane line data is reduced, and dynamic update of the lane line data is simplified. After the second curve with the target parameter satisfying the shape threshold is obtained, the second curve can be used for describing a continuous lane and is applied to actual lane line drawing, vehicle navigation based on lane line data and vehicle related decisions.
As shown in fig. 2(a), which shows a schematic diagram of a projection of a certain point to a polygonal line. As can be seen from fig. 2(a), with different sides of the polygonal line as projection references, a certain point may obtain a plurality of projection points, which is caused by the uncertainty of the projection definitions of the points to the polygonal line; fig. 2(b) is a schematic diagram showing a projection of the second curve obtained at a certain point in the embodiment of the present invention. As can be seen from fig. 2(b), the projection of the point on the second curve is uniquely determined. The projection certainty can highlight the significant advantages of the technical scheme of describing the continuous lane by the simulation curve in the embodiment of the invention in practical application, the collection and matching of the lane line related data, the vehicle navigation based on the lane line data and the vehicle related decision may need to be performed with point projection, and accordingly, the advantages of the embodiment of the invention with definite geometric characteristics can be displayed.
Further, in some preferred embodiments, the second curve may be further stored in a high-precision map as a newly added field, so that the high-precision map includes both fine point location information and a fitted curve of consecutive lanes, in the high-precision map, the original lane line data corresponding to each consecutive lane may be stored in a one-to-one correspondence with the second curve corresponding to the consecutive lane, and then dynamic updating of the consecutive lane may be performed according to the correspondence.
On the basis that the above-mentioned embodiment provides a technical solution for describing a continuous lane by using a second curve, an embodiment of the present invention further provides a method for updating lane line data, where the lane line data describes the continuous lane by using the second curve, and an obtaining manner of the second curve may refer to the same embodiment, and is not described again in the embodiment of the present invention. The lane line data updating method is shown in fig. 3, and includes:
s201, point cloud data of the newly added lane lines are obtained.
In a specific embodiment, the point cloud data can be obtained by classifying a new three-dimensional laser point cloud collected by a high-precision collection vehicle. As shown in fig. 4, in the acquired three-dimensional laser point cloud, the reflectivity of the lane line is strong, so that the lane line point cloud data can be extracted according to the reflectivity difference of the midpoints of the three-dimensional laser point cloud and the position communication relationship.
S202, acquiring a second curve set corresponding to the point cloud data of the lane line.
Specifically, the lane line point cloud data may fall into one or more continuous lanes, and each continuous lane corresponds to one second curve, thereby forming a second curve set.
S203, extracting a curve set to be adjusted from the second curve set, wherein the adaptation degree of elements in the curve set to be adjusted and the lane point cloud data is smaller than a preset adaptation threshold value.
In order to extract the curve set to be adjusted from the second curve set, the embodiment of the present invention needs to calculate the degree of adaptation between the point cloud data of the lane and the second curve in the second curve set, and its specific calculation method is described in detail below.
If the adaptation degree of the second curve in the second curve set and the lane point cloud data is larger than the adaptation threshold value, no adjustment is needed, the curve set to be adjusted is empty, and correspondingly, the lane line data does not need to be updated; otherwise, adjustment is needed, and the lane line data is also updated.
And S204, adjusting the elements in the curve set to be adjusted to obtain an adjusted curve set, wherein the adaptation degree of the elements in the adjusted curve set and the lane point cloud data is not less than the adaptation threshold value.
Specifically, the embodiment of the present invention does not limit a specific adjustment strategy, and in a preferred implementation, the curves in the set of curves to be adjusted are all third-order bezier curves, and the shape points of the curves can be dragged to be adjusted according to the characteristics of the third-order bezier curves. Therefore, in the preset adjusting range, the purpose of adjusting the elements in the curve set to be adjusted can be achieved by adjusting the shape points. Specifically, let the third-order bezier curve have a total of four shape points C0(x0,y0,z0),C1(x1,y1,z1),C2(x2,y2,z2),C3(x3,y3,z3) A variation range can be given to each shape point, and the position of the shape point is varied within the variation range to adjust the third-order Bezier curve.
Further, if the curves in the curve set to be adjusted are end-to-end connected, the end-to-end connected curves can be adjusted together until the adaptation degree of each section of curve meets the requirement.
As can be seen from the above description, the method provided in the embodiment of the present invention can achieve the purpose of updating data by adjusting the curve control point, and is significantly more convenient and faster than the way of storing lane line data in the multi-edge line in the prior art. As shown in fig. 5(a), which shows a schematic diagram of polygon updating that requires modification of specific shape points to change the shape of the polygon in a manner of increasing or decreasing the shape points, as shown in fig. 5(b), which shows a schematic diagram of curve updating in an embodiment of the present invention that can adjust the shape without changing the number of shape points, which is obviously more convenient.
Specifically, the adjusted curve set is updated data, in a feasible implementation scenario, a difference calculation may be performed according to the adjusted curve set and the curve set to be adjusted to obtain an update package, and the update package may be applied to a distributed map application scenario. Specifically, the update package includes the identifier of the road corresponding to the adjusted curve and the parameter value of the adjusted curve, and obviously, compared with the prior art, the data volume of the update package can be significantly reduced.
As shown in fig. 6, a distributed mapping application scenario is illustrated. The application scene comprises a high-precision map acquisition vehicle, a map data processing center and a vehicle cloud platform. In the application scene, the high-precision map collecting vehicle can transmit the collected high-precision point cloud data to the map data processing center, the map data processing center processes and updates the map data and generates an update package, and the generated update package is transmitted to the vehicle cloud platform so as to update the vehicle lane line map data of the vehicle cloud platform. The vehicle cloud platform provided by the embodiment of the invention can be used for supporting automatic driving or vehicle-related decision making. Besides, the application scene can further comprise a vehicle production platform, and the vehicle cloud platform updates the lane line data in the relevant vehicle by transmitting the update package to the vehicle production platform.
In another distributed map application scenario, the map data processing center may communicate with various feasible terminals and issue update packages to the terminals in a manner of dynamically issuing software service installation packages.
In addition, the lane line data processing and updating method provided by the embodiment of the invention can be suitable for updating the current L3-level automatic driving high-speed automatic driving map and the ADAS high-level automatic driving assistance map. The high-precision maps provided in the current market are static maps, and are not updated by large-scale automation means. The method provided by the embodiment of the invention can greatly improve the automation level, form an updated commercial solution of the automatic driving map and improve a high-precision map product and an automatic driving system solution.
The embodiment of the present invention does not limit the specific content of the adaptation degree. However, in a preferred embodiment, in order to quantify the degree of adaptation more accurately, an embodiment of the present invention provides a method for calculating the degree of adaptation of lane point cloud data to a second curve, where the second curve is a three-dimensional curve in a spatial coordinate system, and the method includes, as shown in fig. 7:
and S10, obtaining lane point cloud data in a preset range around the second curve.
S20, constructing a first coordinate system, a second coordinate system and a third coordinate system according to the second curve, wherein the first coordinate system is used for describing the change of the point moving along the advancing direction of the second curve in the X direction in a space rectangular coordinate system, the second coordinate system is used for describing the change of the point moving along the advancing direction of the second curve in the Y direction in the space rectangular coordinate system, and the third coordinate system is used for describing the change of the point moving along the advancing direction of the second curve in the Z direction in the space rectangular coordinate system.
S30, calculating a first projection curve, a second projection curve and a third projection curve of the second curve, wherein the first projection curve is the projection of the second curve in the first coordinate system, the second projection curve is the projection of the second curve in the second coordinate system, and the third projection curve is the projection of the second curve in the third coordinate system.
S40, drawing a first discrete point cloud in the first coordinate system, drawing a second discrete point cloud in the second coordinate system and drawing a third discrete point cloud in the third coordinate system according to the lane point cloud data.
S50, calculating the adaptation degree of the lane point cloud data and the second curve according to the first position relation, the second position relation and the third position relation; the first position relation is the position relation between a first projection curve and a first discrete point cloud in a first coordinate system, the second position relation is the position relation between a second projection curve and the first discrete point cloud in a second coordinate system, and the third position relation is the position relation between a third projection curve and a third discrete point cloud in a third coordinate system.
In the embodiment of the invention, the extending direction of the second curve is used as the adaptive entry point, the adaptive degree of the lane point cloud data and the second curve is calculated by calculating the relation between the space position of the second curve and the space position of the lane point cloud along the extending direction of the second curve, and the three spatial directions are considered in the calculation process of the adaptive degree, so that the adaptive degree evaluation result of the second curve and the lane point cloud can be scientifically and accurately obtained.
The embodiment of the present invention does not limit the specific method for calculating the degree of adaptation between the lane point cloud data and the second curve according to the first position relationship, the second position relationship, and the third position relationship, and in a preferred implementation, the following method is adopted to calculate the degree of adaptation between the lane point cloud data and the second curve, and the method, as shown in fig. 8, includes:
s501, obtaining a first adaptation degree according to the first position relation, obtaining a second adaptation degree according to the second position relation, and obtaining a third adaptation degree according to the third position relation.
In the embodiment of the invention, the adaptation degrees correspond to the position relations one by one, namely the adaptation degrees can be uniquely determined through the position relations, the calculation methods of the first adaptation degree, the second adaptation degree and the third adaptation degree can be the same, and the adaptation degrees in the embodiment of the invention can be calculated through formulasWhere Fitting is the adaptation, N1、N2Respectively representing the number of points located at the upper part of the curve and the number of points located at the lower part of the curve.
S502, calculating the adaptation degree of the lane point cloud data and a second curve according to the first adaptation degree, the second adaptation degree and the third adaptation degree.
In the embodiment of the present invention, a specific method for calculating the adaptation degree of the lane point cloud data and the second curve according to the first adaptation degree, the second adaptation degree and the third adaptation degree is not limited, and in a preferred embodiment, the adaptation degree of the lane point cloud data and the second curve may be calculated according to a formula Fitting1、Fitting2、Fitting3And respectively representing the adaptation degree, the first adaptation degree, the second adaptation degree and the third adaptation degree of the lane point cloud data and the second curve.
The embodiment of the invention provides a lane line data processing and updating method, aiming at describing a lane line by fitting a curve instead of a polyline. Compared with the prior art, the method has the following remarkable advantages:
(1) the curve can be updated and modified only by adjusting curve shape points without adding or deleting point data, so that the modification consistency is better;
(2) the curve description does not need to store a large amount of point data, so that the data volume is obviously reduced;
(3) the curve parameters can be updated and adjusted without adding or deleting point data, so that the operation time is reduced, and the speed is increased;
(4) the geometric meaning of the curve is clear, the processing and adjustment of the related data can be automatically carried out, and the manual time is saved;
(5) in the embodiment of the invention, the curve adjustment does not change the topological relation of the original road, and the updated curve does not need to be matched with the original road data, so that an update package can be directly generated, the updating speed is increased, and the updating complexity and the error rate are reduced;
(6) the embodiment of the invention ensures the inheritance of data to a greater extent, minimizes the overhead of differential updating of the map, and meets the requirement of commercial operation.
Further, an embodiment of the present invention provides a lane line data processing apparatus, as shown in fig. 9, the apparatus includes:
an original lane line number obtaining module 301, configured to obtain original lane line data used for describing a continuous lane, where the original lane line data includes at least one polyline;
a fitting module 302, configured to perform curve fitting on the polygon lines in the original lane line data to obtain a first curve corresponding to each polygon line;
a second curve obtaining module 303, configured to obtain a second curve corresponding to the continuous lane according to the first curve corresponding to each polyline;
a target parameter module 304, configured to obtain a target parameter corresponding to the second curve, where the target parameter is used to describe a degree of a back-off between the second curve and the original lane line data;
the control module 305 determines whether the target parameter is smaller than a preset shape threshold, and if not, adjusts the first curve and re-acquires the second curve.
The embodiment of the invention discloses a lane line data processing device and a lane line data processing method based on the same inventive concept.
Further, an embodiment of the present invention provides a lane line data updating apparatus, where a continuous lane is described by a second curve in the lane line data, as shown in fig. 10, the apparatus includes:
a point cloud data obtaining module 401, configured to obtain point cloud data of a newly added lane line;
a second curve set obtaining module 402, configured to obtain a second curve set corresponding to the point cloud data of the lane line;
an adaptation module 403, configured to extract a curve set to be adjusted from the second curve set, where adaptation degrees of elements in the curve set to be adjusted and the lane point cloud data are all smaller than a preset adaptation threshold;
an adjusting module 404, configured to adjust elements in the curve set to be adjusted to obtain an adjusted curve set, where a degree of adaptation between the elements in the adjusted curve set and the lane point cloud data is not less than the adaptation threshold.
The embodiment of the invention discloses a lane line data updating device and a lane line data updating method based on the same inventive concept.
The embodiment of the present invention further provides a lane line data processing and updating device, where the device includes a processor and a memory, where the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, at least one program, a code set, or an instruction set is loaded by the processor and executes the lane line data processing method described in the embodiment, and/or the lane line data processing method described in the embodiment.
Specifically, the embodiment of the present invention discloses a structure diagram of a lane line data processing and updating device, as shown in fig. 11, the device 1200 includes a Central Processing Unit (CPU)1201, a system memory 1204 including a Random Access Memory (RAM)1202 and a Read Only Memory (ROM)1203, and a system bus 1205 connecting the system memory 1204 and the central processing unit 1201. The device 1200 also includes a basic input/output system (I/O system) 1206 to facilitate transfer of information between devices within the computer, and a mass storage device 1207 for storing an operating system 1213, application programs 1214, and other program modules 1215.
The basic input/output system 1206 includes a display 1208 for displaying information and an input device 1209, such as a mouse, keyboard, etc., for a user to input information. Wherein the display 1208 and input device 1209 are connected to the central processing unit 1201 through an input-output controller 1210 coupled to the system bus 1205. The basic input/output system 1206 may also include an input/output controller 1210 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, input-output controller 1210 also provides output to a display screen, a printer, or other type of output device.
The mass storage device 1207 is connected to the central processing unit 1201 through a mass storage controller (not shown) connected to the system bus 1205. The mass storage device 1207 and its associated computer-readable media provide non-volatile storage for the device 1200. That is, the mass storage device 1207 may include a computer-readable medium (not shown) such as a hard disk or CD-ROM drive.
Without loss of generality, the computer-readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that the computer storage media is not limited to the foregoing. The system memory 1204 and mass storage device 1207 described above may be collectively referred to as memory.
The device 1200 may also operate as a remote computer connected to a network via a network, such as the internet, in accordance with various embodiments of the invention. That is, the device 1200 may be connected to the network 1212 through a network interface unit 1211 coupled to the system bus 1205, or the network interface unit 1211 may be used to connect to other types of networks or remote computer systems (not shown).
The memory also includes one or more programs stored in the memory and configured to be executed by one or more processors. The one or more programs include instructions for executing the lane line data processing method described in the above embodiments, and/or the lane line data processing method described in the embodiments.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the device and server embodiments, since they are substantially similar to the method embodiments, the description is simple, and the relevant points can be referred to the partial description of the method embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (11)
1. A lane line data processing method, characterized by comprising:
acquiring original lane line data for describing a continuous lane, wherein the original lane line data comprises at least one multi-edge line;
performing curve fitting on the polygonal lines in the original lane line data to obtain a first curve corresponding to each polygonal line;
obtaining a second curve corresponding to the continuous lane according to the first curve corresponding to each multi-edge line;
acquiring a target parameter corresponding to the second curve, wherein the target parameter is used for describing the back-off degree of the second curve and the original lane line data, and the target parameter is determined according to the data fitting degree, the occurrence frequency of the condition that the tangential angle jump of the adjacent first curve at the joint exceeds the maximum allowable angle jump, the occurrence frequency of the condition that the curvature jump of the adjacent first curve at the joint exceeds the maximum allowable curvature jump, and the number of the first curves exceeding the allowable maximum length;
and when the target parameter is smaller than a preset shape threshold value, adjusting the first curve, and returning to the step of obtaining a second curve corresponding to the continuous lane according to the first curve corresponding to each polyline.
2. The method of claim 1, further comprising:
the first curve is a three-dimensional Bezier curve;
the adjusting the first curve includes:
adjacent first curves merge, and a first curve splits and/or perturbs the shape point of a first curve.
3. The method of claim 1, wherein:
calculating the target parameter by the formula E ═ α × data _ setting + β × angle _ diff + γ × current _ diff + ∈ length, where E denotes the target parameter, α, β, γ, and ∈ are all preset weighting coefficients, data _ setting denotes a data fitting degree, angle _ diff denotes the number of occurrences of a case where a tangential angle jump of adjacent first curves at a connection exceeds a maximum allowable angle jump, current _ diff denotes the number of occurrences of a case where a curvature jump of adjacent first curves at a connection exceeds a maximum allowable curvature jump, and length is the number of first curves exceeding an allowable maximum length.
4. A lane line data updating method in which a continuous lane is described by a second curve obtained by the lane line data processing method according to claim 1, the method comprising:
acquiring point cloud data of a newly added lane line;
acquiring a second curve set corresponding to the lane line point cloud data;
extracting a curve set to be adjusted from the second curve set, wherein the adaptation degree of elements in the curve set to be adjusted and the lane point cloud data is smaller than a preset adaptation threshold value;
and adjusting elements in the curve set to be adjusted to obtain an adjusted curve set, wherein the adaptation degree of the elements in the adjusted curve set and the lane point cloud data is not less than the adaptation threshold value.
5. The method of claim 4, wherein:
the second curves in the curve set to be adjusted are all third-order Bezier curves;
the adjusting the elements in the curve set to be adjusted to obtain the adjusted curve set includes:
the shape of the third-order bezier curve is adjusted by changing the shape point of the third-order bezier curve within the variation range of the shape point of the third-order bezier curve.
6. The method of claim 4, wherein the extracting the set of curves to be adjusted from the second set of curves comprises: calculating the adaptation degree of the lane point cloud data and a second curve in the second curve set; the adaptation degree of the lane-calculating point cloud data and the second curve in the second curve set comprises the following steps:
acquiring lane point cloud data in a preset range around the second curve;
constructing a first coordinate system, a second coordinate system and a third coordinate system according to the second curve, wherein the first coordinate system is used for describing the change of the point moving along the advancing direction of the second curve in the X direction in a space rectangular coordinate system, the second coordinate system is used for describing the change of the point moving along the advancing direction of the second curve in the Y direction in the space rectangular coordinate system, and the third coordinate system is used for describing the change of the point moving along the advancing direction of the second curve in the Z direction in the space rectangular coordinate system;
calculating a first projection curve, a second projection curve and a third projection curve of the second curve, wherein the first projection curve is a projection of the second curve in the first coordinate system, the second projection curve is a projection of the second curve in the second coordinate system, and the third projection curve is a projection of the second curve in the third coordinate system;
drawing a first discrete point cloud in the first coordinate system, a second discrete point cloud in the second coordinate system and a third discrete point cloud in the third coordinate system according to the lane point cloud data;
calculating the adaptation degree of the lane point cloud data and the second curve according to the first position relation, the second position relation and the third position relation; the first position relation is the position relation between a first projection curve and a first discrete point cloud in a first coordinate system, the second position relation is the position relation between a second projection curve and the first discrete point cloud in a second coordinate system, and the third position relation is the position relation between a third projection curve and a third discrete point cloud in a third coordinate system.
7. The method of claim 6, wherein calculating the degree of adaptation of the lane point cloud data to the second curve according to the first position relationship, the second position relationship and the third position relationship comprises:
obtaining a first adaptation degree according to the first position relation, obtaining a second adaptation degree according to the second position relation, and obtaining a third adaptation degree according to the third position relation;
and calculating the adaptation degree of the lane point cloud data and the second curve according to the first adaptation degree, the second adaptation degree and the third adaptation degree.
8. A lane line data processing apparatus, characterized in that the apparatus comprises:
the system comprises an original lane line number acquisition module, a lane line number acquisition module and a lane line number acquisition module, wherein the original lane line number acquisition module is used for acquiring original lane line data used for describing continuous lanes, and the original lane line data comprises at least one multi-edge line;
the fitting module is used for performing curve fitting on the multiple edges in the original lane line data to obtain a first curve corresponding to each multiple edge;
the second curve acquisition module is used for acquiring a second curve corresponding to the continuous lane according to the first curve corresponding to each multi-edge line;
a target parameter module, configured to obtain a target parameter corresponding to the second curve, where the target parameter is used to describe a degree of a back-off between the second curve and the original lane line data, and the target parameter is determined according to a data fitting degree, a number of occurrences of a case where a tangent angle jump of an adjacent first curve at a connection exceeds a maximum allowable angle jump, a number of occurrences of a case where a curvature jump of an adjacent first curve at a connection exceeds a maximum allowable curvature jump, and a number of first curves exceeding an allowable maximum length;
and the control module is used for judging whether the target parameter is smaller than a preset shape threshold value or not, if not, adjusting the first curve and acquiring the second curve again.
9. A lane line data updating apparatus in which a continuous lane is described by a second curve obtained by the lane line data processing method according to claim 1, the apparatus comprising:
the point cloud data acquisition module is used for acquiring point cloud data of the newly added lane line;
the second curve set acquisition module is used for acquiring a second curve set corresponding to the point cloud data of the lane line;
the adaptation module is used for extracting a curve set to be adjusted from the second curve set, and the adaptation degrees of elements in the curve set to be adjusted and the lane point cloud data are all smaller than a preset adaptation threshold value;
and the adjusting module is used for adjusting the elements in the curve set to be adjusted to obtain an adjusted curve set, and the adaptation degree of the elements in the adjusted curve set and the lane point cloud data is not less than the adaptation threshold value.
10. A lane line data processing and updating apparatus, comprising a processor and a memory, wherein the memory has stored therein at least one instruction, at least one program, set of codes, or set of instructions, which is loaded by the processor and executes the lane line data processing method according to any one of claims 1 to 3, and/or the lane line data updating method according to any one of claims 4 to 7.
11. A computer storage medium, wherein instructions in the computer-readable storage medium are used for executing the lane line data processing method according to any one of claims 1 to 3, and/or the lane line data updating method according to any one of claims 4 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910083931.5A CN109916416B (en) | 2019-01-29 | 2019-01-29 | Method, device and equipment for processing and updating lane line data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910083931.5A CN109916416B (en) | 2019-01-29 | 2019-01-29 | Method, device and equipment for processing and updating lane line data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109916416A CN109916416A (en) | 2019-06-21 |
CN109916416B true CN109916416B (en) | 2022-04-01 |
Family
ID=66961058
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910083931.5A Active CN109916416B (en) | 2019-01-29 | 2019-01-29 | Method, device and equipment for processing and updating lane line data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109916416B (en) |
Families Citing this family (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110717141B (en) * | 2019-09-22 | 2023-08-04 | 武汉中海庭数据技术有限公司 | Lane line optimization method, device and storage medium |
CN112560558B (en) * | 2019-09-26 | 2023-04-18 | 阿里巴巴集团控股有限公司 | Lane line correction method and device and electronic equipment |
CN110887494A (en) * | 2019-11-29 | 2020-03-17 | 腾讯科技(深圳)有限公司 | Vehicle positioning method and device |
CN113375680B (en) * | 2020-03-10 | 2024-03-29 | 阿里巴巴集团控股有限公司 | Method, device and equipment for merging line elements in electronic map |
CN111460073B (en) * | 2020-04-01 | 2023-10-20 | 北京百度网讯科技有限公司 | Lane line detection method, device, equipment and storage medium |
CN112052499B (en) * | 2020-09-02 | 2024-03-12 | 浙江数智交院科技股份有限公司 | Modeling method and device for illumination tube, electronic equipment and storage medium |
CN112050821B (en) * | 2020-09-11 | 2021-08-20 | 湖北亿咖通科技有限公司 | Lane line polymerization method |
CN112215952B (en) * | 2020-10-26 | 2021-08-13 | 湖北亿咖通科技有限公司 | Curve drawing method, computer storage medium and electronic device |
CN112232330B (en) * | 2020-12-17 | 2021-02-23 | 中智行科技有限公司 | Lane connecting line generation method and device, electronic equipment and storage medium |
CN112734927B (en) * | 2021-03-31 | 2021-06-25 | 湖北亿咖通科技有限公司 | Method and device for simplifying high-precision map lane line and computer storage medium |
CN113607159B (en) * | 2021-08-09 | 2024-04-12 | 智道网联科技(北京)有限公司 | Optimization method, device and equipment for high-precision map lane line |
CN113626903B (en) * | 2021-08-18 | 2024-03-12 | 北京赛目科技股份有限公司 | Road curve setting method and device, electronic equipment and storage medium |
CN114413927B (en) * | 2022-01-20 | 2024-02-13 | 智道网联科技(北京)有限公司 | Lane line fitting method, electronic device and storage medium |
CN114435402B (en) * | 2022-02-16 | 2024-05-31 | 智道网联科技(北京)有限公司 | Lane line smoothing method and device and electronic equipment |
CN117495989B (en) * | 2023-12-29 | 2024-04-19 | 腾讯科技(深圳)有限公司 | Data processing method, device, equipment and readable storage medium |
CN117539970B (en) * | 2024-01-09 | 2024-07-12 | 腾讯科技(深圳)有限公司 | Lane data compression method, lane data compression device, computer equipment and storage medium |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016045144A (en) * | 2014-08-26 | 2016-04-04 | アルパイン株式会社 | Traveling lane detection device and driving support system |
CN105404844B (en) * | 2014-09-12 | 2019-05-31 | 广州汽车集团股份有限公司 | A kind of Method for Road Boundary Detection based on multi-line laser radar |
CN105260699B (en) * | 2015-09-10 | 2018-06-26 | 百度在线网络技术(北京)有限公司 | A kind of processing method and processing device of lane line data |
CN105488498B (en) * | 2016-01-15 | 2019-07-30 | 武汉中海庭数据技术有限公司 | A kind of lane sideline extraction method and system based on laser point cloud |
CN106127113A (en) * | 2016-06-15 | 2016-11-16 | 北京联合大学 | A kind of road track line detecting method based on three-dimensional laser radar |
CN108345822B (en) * | 2017-01-22 | 2022-02-01 | 腾讯科技(深圳)有限公司 | Point cloud data processing method and device |
CN107704801B (en) * | 2017-08-18 | 2021-08-06 | 电子科技大学 | Curve lane line detection method based on segmented straight line and segmented Bezier curve |
CN108256446B (en) * | 2017-12-29 | 2020-12-11 | 百度在线网络技术(北京)有限公司 | Method, device and equipment for determining lane line in road |
CN109033176B (en) * | 2018-06-25 | 2024-02-27 | 腾讯科技(北京)有限公司 | Road curvature determination method, device, storage medium and computer equipment |
-
2019
- 2019-01-29 CN CN201910083931.5A patent/CN109916416B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN109916416A (en) | 2019-06-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109916416B (en) | Method, device and equipment for processing and updating lane line data | |
US9959670B2 (en) | Method for rendering terrain | |
CN112734641A (en) | Training method and device of target detection model, computer equipment and medium | |
CN110378175B (en) | Method and device for recognizing road edge | |
CN101377851A (en) | System and method for computing a minimum distance from point cloud to point cloud | |
US20100049477A1 (en) | Civil engineering simulation using quadtree data structures | |
US20230042968A1 (en) | High-definition map creation method and device, and electronic device | |
CN105074797A (en) | Map difference data distribution device, map difference data distribution method, and vehicle navigation device | |
JP2014174705A (en) | Multi-agent simulation system and multi-agent simulation method | |
CN112328880A (en) | Geographical region clustering method and device, storage medium and electronic equipment | |
CN111046117A (en) | Method, system, device and medium for displaying route travelling position on map in real time | |
CN110544159A (en) | map information processing method and device, readable storage medium and electronic equipment | |
CN108205565A (en) | Electronic map element vacuates method, apparatus and terminal | |
CN107615183A (en) | In Model Predictive Control application program relative to best performance values premium properties system and method | |
CN117146796A (en) | Data processing method, device, equipment and computer readable storage medium | |
CN108599976B (en) | Network quality evaluation model construction method and device and computer equipment | |
CN114863300A (en) | Shortest path generation method and device | |
CN113986866A (en) | Processing method, device, equipment and medium for large-scale point cloud data | |
CN103582042A (en) | Method and equipment for determining adjacent cells | |
CN117830330A (en) | Road point cloud segmentation method, device, equipment and storage medium | |
CN115096313B (en) | Data processing method and device for regional obstacle avoidance | |
CN113865611B (en) | Data processing method, device, equipment and storage medium | |
CN118094968B (en) | Dynamic river basin dividing method and system based on DEM data | |
CN113535747B (en) | Map updating method and device, electronic equipment and readable storage medium | |
US20240248916A1 (en) | Map Data Updating Method, Apparatus and Electronic Device |
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 |