A lane recognition data merging method and system

Abstract

The application provides a lane recognition data merging method and system, which comprises the following steps: collecting lane recognition data through a vehicle-mounted camera; dividing the lane recognition data on one side of a road Link into equal parts; obtaining a group of lane recognition data closest to the longitudinal offset of each segmented center as a reference; projecting the lane point with an angle difference less than a first preset value with the lane direction angle of the reference to the lane point of the reference, and merging the corresponding lane recognition data to the reference to obtain a lane recognition set; sorting the transverse offset of each element in the lane recognition set by size, and numbering the sorted elements; when the transverse offset distance of adjacent numbered elements is less than a second preset value, deleting the lane recognition data corresponding to the adjacent elements; and merging all segmented lane recognition data by traversing the lane recognition data on both sides of the road Link. Through the scheme, the integrity and accuracy of the lane recognition data can be ensured, and errors in map drawing can be avoided.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of map making, and particularly relates to a lane recognition data merging method and system. BACKGROUND

[0002] In making or updating a map, real scene collection of road lane information is usually needed to improve the accuracy of map making. Generally, road surface images are collected by a vehicle-mounted camera, and lane lines and their positions can be recognized by computer vision processing technology, so as to construct lane lines of a road surface. However, due to the limited field of view of a commonly used vehicle-mounted camera, the observable lanes at the same position can be limited, for example, the vehicle-mounted camera can at most collect the current lane and the left and right lanes of the current lane, and if the number of parallel lanes of a road is greater than three or the vehicle does not travel on the middle lane, the vehicle-mounted camera cannot collect complete road lane information at this position, which can lead to errors in road mapping. SUMMARY

[0003] Therefore, the embodiments of the present application provide a lane recognition data merging method and system to solve the problem of inaccurate lane recognition at the same position and errors in map making.

[0004] In a first aspect of the embodiments of the present application, a lane recognition data merging method is provided, comprising:

[0005] The lane recognition data is collected by a vehicle-mounted camera, the lane recognition data on one side of a road Link is equally divided, a group of lane recognition data with the smallest longitudinal offset distance from the center of each segment is obtained as a reference, the lane point of lane recognition data with an angle difference of lane line direction angle less than a first preset value from the reference is projected to the lane point of the reference, and the corresponding lane recognition data is merged to the reference to obtain a lane line recognition set;

[0006] The transverse offset distances of each element in the lane line recognition set are sorted in size, and the sorted elements are numbered, and when the transverse offset distances of adjacent numbered elements are less than a second preset value, the lane recognition data corresponding to the adjacent elements is deleted;

[0007] The longitudinal offset of the lane point is the distance from the vertical intersection point of the straight line where the lane point is located and the road Link to the starting point of the Link, and the transverse offset of the element is the distance from the lane point to the road Link.

[0008] All the segmented lane recognition data is merged by traversing the lane recognition data on both sides of the road Link.

[0009] In a second aspect of the embodiments of the present application, a system for merging lane recognition data is provided, comprising:

[0010] The segmented merging module is configured to collect lane recognition data by the vehicle-mounted camera, divide the lane recognition data on one side of the road Link equally, obtain a group of lane recognition data closest to the center of each segment in longitudinal deviation as a reference, project the lane point of the lane line recognition data with an angle difference of the lane line direction angle from the reference less than a first preset value to the lane point of the reference, and merge the corresponding lane recognition data to the reference to obtain a lane line recognition set;

[0011] The deleting module is configured to sort the lateral deviation of each element in the lane line recognition set by size, number the sorted elements, and delete the lane recognition data corresponding to adjacent elements when the lateral deviation distance of adjacent numbered elements is less than a second preset value.

[0012] Wherein, the longitudinal deviation of the lane point is the distance from the vertical intersection point of the straight line where the lane point is located and the start point of the Link to the Link, and the lateral deviation of the element is the distance from the lane point to the Link.

[0013] The comprehensive processing module is configured to traverse the lane recognition data of each segment on both sides of the road Link and merge all the lane recognition data of the segments.

[0014] In a third aspect of the embodiments of the present application, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable by the processor, and the processor implements the steps of the method according to the first aspect of the embodiments of the present application when executing the computer program.

[0015] In a fourth aspect of the embodiments of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program is executable by a processor to implement the steps of the method according to the first aspect of the embodiments of the present application.

[0016] In the embodiments of the present application, based on the user driving data of the same road segment, the lane recognition data on both sides of the road is processed by merging and deleting, the complete lane information can be retained, and the redundant data can be removed, so that the complete road information collection based on the vehicle-mounted camera is realized, the integrity and accuracy of the lane recognition at the same position are ensured, and the mapping error is avoided. At the same time, the cost of map making is reduced, and the map updating is facilitated. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0018] Figure 1 A flowchart of a lane recognition data merging method provided by an embodiment of the present application is shown in FIG. 1.

[0019] Figure 2 Another flowchart of a lane recognition data merging method provided by an embodiment of the present application is shown in FIG. 2.

[0020] Figure 3 A structure diagram of a system for lane recognition data merging provided by an embodiment of the present application is shown in FIG. 3.

[0021] Figure 4 A structure diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 4. DETAILED DESCRIPTION

[0022] In order to make the objectives, features, and advantages of the present application more apparent and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the embodiments described below are only some of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort fall within the scope of the present application.

[0023] It should be understood that the terms “comprise” and other similar terms in the specification or claims of the present application and the above-described drawings mean to cover the inclusions without exclusivity, such as a process, method, or system, device comprising a series of steps or units, which is not limited to the listed steps or units. In addition, “first” and “second” are used to distinguish different objects, and are not used to describe a specific order.

[0024] Referring to Figure 1 The flowchart of the lane recognition data merging method provided by the embodiment of the present application includes:

[0025] S101, collecting lane recognition data through a vehicle-mounted camera, dividing the lane recognition data on one side of a road Link equally, obtaining a group of lane recognition data closest to the center of each segment in the longitudinal direction as a reference, projecting the lane point of the lane line recognition data with an angle difference of the lane line direction angle from the reference less than a first preset value to the lane point of the reference, and merging the corresponding lane recognition data to the reference to obtain a lane line recognition set;

[0026] The vehicle-mounted camera is an intelligent camera for vehicles, which can not only collect road surface images, but also perform lane line recognition in combination with image processing recognition technology, including the lane line position, shape, color, and type of the lane where the vehicle is located and the lanes on both sides.

[0027] The lane recognition data is lane data collected by the intelligent camera for each moment, and is generally obtained by recognizing the lane image collected at the moment. The intelligent camera can collect lane recognition data at a predetermined time interval or distance, and each collection of lane recognition data is regarded as a set of lane recognition data. Each set of lane recognition data can include lane lines, lane line direction angles, lane line points, etc.

[0028] Specifically, the lane recognition data can be divided into lane recognition data and lane edge data. The lane recognition data includes recognized lane edges (i.e., lane lines), lane line direction angles, extended intersection points, and longitudinal offsets. The lane edge data includes lane line points, transverse offsets, and lane types.

[0029] The lane line point is a point on the lane line, and the line connecting the lane line point and the extended intersection point is perpendicular to the lane Link, and the extended intersection point is located on the Link (the extended intersection point is the foot point of the lane line point on the Link). The lane line point can be regarded as the foot point of the lane line recognition data collection position on each lane line. The lane line direction angle is the direction angle of the lane line on which the lane line point is located.

[0030] The road Link represents a road in a road network, and the lane recognition data on both sides of the road Link is collected by the vehicle-mounted camera. One side of the lane recognition data is selected, and the lane recognition data is equally divided based on the road Link. Each section of the divided lane recognition data is regarded as a data set, and each section of the data set forms a total set of lane recognition data on one side of the road Link.

[0031] In the segmented data set, a set of lane recognition data closest to the center of each segment is obtained, and the lane recognition data is taken as a reference. Other sets of lane recognition data are searched in the current set, and when the lane line direction angle in the other set of lane recognition data is less than the first preset value, the lane line point in the other set of lane recognition data is projected to the lane line point of the reference, and the corresponding lane recognition data is merged into the reference, that is, the other set of lane recognition data is fused into the reference.

[0032] Optionally, if the angle difference between the lane line point and the reference point is greater than the first preset value, the lane line point corresponding lane recognition data is not merged.

[0033] S102, the transverse offsets of each element in the lane line recognition set are sorted by size, and the sorted elements are numbered. When the transverse offset distance of adjacent numbered elements is less than a second preset value, the lane recognition data corresponding to the adjacent elements is deleted.

[0034] For each element in the lane recognition set, it contains the information of extended intersection point, lateral offset, longitudinal offset, direction angle, etc. The lateral offset of the element is represented by the lateral offset of the lane point.

[0035] The longitudinal offset of the lane point is the distance from the vertical intersection point of the straight line where the lane point is located and the Link to the starting point of the Link. The lateral offset of the element is the distance from the lane point to the Link.

[0036] In one embodiment, as shown in FIG. 1, the Link is composed of point strings S, N and E, R0, R1 and R2 represent lane points, and C represents an extended intersection point. Figure 2

[0037] It should be understood that during the working process of the intelligent camera for vehicles, a rectangular coordinate system is established with the instantaneous measurement center point of the vehicle as the coordinate origin, the driving direction of the vehicle as the X-axis, and the straight line perpendicular to the X-axis at the measurement center point of the vehicle as the Y-axis. The lane points are the intersection points of the Y-axis and the recognized lane in the coordinate system of the intelligent camera according to the lane lines seen in front of the vehicle in real time, such as R0, R1 and R2.

[0038] The longitudinal offset distance of the lane recognition data (or lane points R0, R1 and R2) is the length of the SN line segment plus the length of the NC line segment. The lateral offset distance of the lane point R0 in the lane recognition data is the length of the line segment C to R0, i.e. the distance from R0 to the Link. The lateral offset distance of the lane point R1 is the length of the line segment C to R1. The lateral offset distance of the lane point R2 is the length of the line segment C to R2.

[0039] S103, traverse each segmented lane recognition data on both sides of the Link, and merge all the segmented lane recognition data.

[0040] The segmented lane recognition data on both sides of the Link is processed respectively, the recognition data belonging to the same lane line is deleted, and the recognition data of different lane lines is retained, so as to realize the fusion of the lane recognition data of the Link.

[0041] For example, for the lane recognition data set A on the left side of the Link:

[0042] Step S1, group the elements in set A according to the equal longitudinal offset distance, and the grouping distance is E meters, to obtain a grouped set F of lane recognition data;

[0043] Step S2, take a group of lane recognition data G from the grouped set F, and the group number is N. In set G, find an element L with the closest longitudinal offset to (N+0.5)*E.

[0044] ​Step S3, from the set G, take out a lane recognition data K, if the angle difference between the azimuth angle of K and the azimuth angle of L is less than or equal to the threshold value M, modify all the lane line point positions of K to the projection point positions of the lane line point straight line of L, otherwise take new lane recognition data;

[0045] Step S4, combine all the lane line recognition data of K into the lane line recognition set R of L;

[0046] Step S5, when the set G is traversed, calculate the lateral offset of each element in R, sort each element in R according to the lateral offset from small to large, and set the serial number V starting from 0;

[0047] Step S6, take out the element T0 corresponding to the serial number V and the element T1 corresponding to V+1 in R, if the difference between the lateral offsets of T0 and T1 is less than or equal to the threshold value S, delete T1 in R, otherwise set V=V+1 and continue to judge;

[0048] Step S7, when V+1 is the serial number of the last element in R, take L as the lane merging result of the group, otherwise, jump to S6 and continue to judge the elements.

[0049] Step S8, traverse the set F to obtain the lane recognition data merging result on the Link side and exit.

[0050] In the embodiment, no special surveying and mapping equipment is needed, and 0.5-meter-level lane data acquisition can be realized by using the ordinary mass-produced ADAS single present solution and inertial navigation positioning equipment. By collecting, sorting and analyzing the driving data of users on the same section, the latest complete road lane information and geometric data of the section can be obtained. Not only the accuracy of the lane recognition data can be ensured, but also the cost of road mapping can be reduced (no need for high-precision acquisition of car field collection and no need for high-precision acquisition equipment), and the speed of road map updating can be improved.

[0051] It should be understood that the serial numbers of the steps in the above embodiment do not mean the order of execution, and the execution order of the processes should be determined according to their functions and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0052] Figure 3 A structure schematic diagram of a system for lane recognition data merging provided by the embodiment of the present application is provided, and the system comprises:

[0053] The segmentation and merging module 310 is configured to collect lane recognition data by the vehicle-mounted camera, divide the lane recognition data on one side of the road Link equidistantly, obtain a group of lane recognition data closest to the center of each segment in the longitudinal direction as a reference, project the lane point of the lane recognition data with an angle difference of the lane direction angle from the reference less than a first preset value to the lane point of the reference, and merge the corresponding lane recognition data to the reference to obtain a lane recognition set.

[0054] The lane recognition data includes lane recognition data and lane line recognition data, the lane recognition data includes recognized lane line, lane direction angle, extended intersection point and longitudinal offset, the lane line recognition data includes lane line point, transverse offset and lane line type, and the extended intersection point is a vertical intersection point of the lane line point and the road Link.

[0055] Optionally, when the angle difference of the lane line point and the reference point in the direction angle is greater than the first preset value, the lane recognition data corresponding to the lane line point is reserved without being subjected to the merging processing.

[0056] The deletion module 320 is configured to sort the transverse offsets of each element in the lane recognition set in size, number the sorted elements, and delete the lane recognition data corresponding to adjacent elements when the transverse offset distance of adjacent numbered elements is less than a second preset value.

[0057] The longitudinal offset of the lane line point is the distance from the vertical intersection point of the straight line where the lane line point is located and the road Link to the starting point of the Link, and the transverse offset of the element is the distance from the lane line point to the road Link.

[0058] The comprehensive processing module 330 is configured to traverse the lane recognition data of each segment on both sides of the road Link and merge all the lane recognition data of the segments.

[0059] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and the module described above can refer to the corresponding process in the foregoing method embodiments, which will not be described herein.

[0060] Figure 4 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. The electronic device is used for merging lane recognition data. As shown in Figure 4 The electronic device 4 of this embodiment includes a memory 410, a processor 420 and a system bus 430, the memory 410 includes a program 4101 stored thereon which can be run, those skilled in the art can understand that, Figure 4 The electronic device structure shown in

[0061] The following will be described in combination withFigure 4 The various components of the electronic device are described in detail as follows:

[0062] The memory 410 can be used to store software programs and modules, and the processor 420 executes various function applications and data processing of the electronic device by running the software programs and modules stored in the memory 410. The memory 410 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), etc.; and the data storage area can store data (such as cache data) created according to the use of the electronic device, etc. In addition, the memory 410 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state memory device.

[0063] The executable program 4101 containing the network request method in the memory 410 can be divided into one or more modules / units, which are stored in the memory 410 and executed by the processor 420 to perform lane line data fusion, etc. The one or more modules / units can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program 4101 in the electronic device 4. For example, the computer program 4101 can be divided into function modules such as segment merging module, deletion module, and comprehensive processing module.

[0064] The processor 420 is the control center of the electronic device, connects all parts of the electronic device through various interfaces and lines, executes the software programs and / or modules stored in the memory 410, and calls the data stored in the memory 410, to perform various functions and process data of the electronic device, thereby monitoring the overall state of the electronic device. Optionally, the processor 420 can include one or more processing units; preferably, the processor 420 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor can also not be integrated into the processor 420.

[0065] The system bus 430 is used to connect the internal functional components of the computer, and can transmit data information, address information and control information. The system bus 430 can be, for example, a PCI bus, an ISA bus, a CAN bus, etc. The instructions of the processor 420 are transmitted to the memory 410 through the bus, and the memory 410 feeds back data to the processor 420. The system bus 430 is responsible for the interaction of data and instructions between the processor 420 and the memory 410. Of course, the system bus 430 can also access other devices, such as network interfaces, display devices, etc.

[0066] In the embodiments of the present application, the executable programs executed by the processor 420 included in the electronic device include:

[0067] The lane recognition data of the road Link is equally divided, and the lane recognition data closest to the longitudinal offset of the center of each segment is obtained as a reference. The lane point of the lane line recognition data with an angle difference less than a first preset value from the reference is projected to the lane point of the reference, and the corresponding lane recognition data is merged to obtain a lane line recognition set.

[0068] The lateral offsets of each element in the lane line recognition set are sorted in size, and the sorted elements are numbered. When the lateral offset distance of adjacent numbered elements is less than a second preset value, the lane recognition data corresponding to the adjacent elements is deleted.

[0069] The longitudinal offset of the lane point is the distance from the vertical intersection point of the straight line where the lane point is located and the starting point of the Link to the Link, and the lateral offset of the element is the distance from the lane point to the Link.

[0070] The lane recognition data of each segment on both sides of the road Link is traversed, and all the lane recognition data of the segments is merged.

[0071] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and module described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0072] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0073] The above-described embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced by equivalent replacements; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A lane identification data merging method, characterized by, The method comprises the following steps: Collect lane recognition data through a vehicle-mounted camera, divide the lane recognition data on one side of a road Link equidistantly, obtain a group of lane recognition data closest to the longitudinal offset of each segment center as a reference, project the lane point of the lane line recognition data with an angle difference of the lane line direction angle with the reference less than a first preset value to the lane point of the reference, and merge the corresponding lane recognition data to the reference to obtain a lane line recognition set; The lane recognition data comprises lane recognition data and lane line recognition data, the lane recognition data comprises recognized lane lines, lane line direction angles, extended intersection points, and longitudinal offsets, and the lane line recognition data comprises lane line points, transverse offsets, and lane line types; The extended intersection point is a vertical intersection point of the lane line point and the road Link; Sort the transverse offsets of each element in the lane line recognition set by size, number the sorted elements, and delete the lane recognition data corresponding to adjacent elements when the transverse offset distance of adjacent numbered elements is less than a second preset value; The longitudinal offset of the lane line point is the distance from the vertical intersection point of the straight line where the lane line point is located and the road Link to the starting point of the Link, and the transverse offset of the element is the distance from the lane line point to the road Link; Iterate through the lane recognition data of each segment on both sides of the road Link, and merge all the lane recognition data of the segments.

2. The method of claim 1, wherein, The lane line point of the lane line recognition data with an angle difference of the lane line direction angle with the reference less than a first preset value is projected to the lane point of the reference, and the corresponding lane recognition data is merged to the reference to obtain a lane line recognition set, which comprises the following steps: When the angle difference of the lane line point and the reference point direction angle is greater than the first preset value, the lane recognition data corresponding to the lane line point is retained without merging processing.

3. A system for lane identification data merging, characterized by, The method comprises the following steps: The segment merging module is configured to collect lane recognition data through a vehicle-mounted camera, divide the lane recognition data on one side of a road Link equidistantly, obtain a group of lane recognition data closest to the longitudinal offset of each segment center as a reference, project the lane point of the lane line recognition data with an angle difference of the lane line direction angle with the reference less than a first preset value to the lane point of the reference, and merge the corresponding lane recognition data to the reference to obtain a lane line recognition set; The lane recognition data comprises lane recognition data and lane line recognition data, the lane recognition data comprises recognized lane lines, lane line direction angles, extended intersection points, and longitudinal offsets, and the lane line recognition data comprises lane line points, transverse offsets, and lane line types; The extended intersection point is a vertical intersection point of the lane line point and the road Link; The deleting module is configured to sort the transverse offsets of each element in the lane line recognition set by size, number the sorted elements, and delete the lane recognition data corresponding to adjacent elements when the transverse offset distance of adjacent numbered elements is less than a second preset value; The longitudinal offset of the lane line point is the distance from the vertical intersection point of the straight line where the lane line point is located and the road Link to the starting point of the Link, and the transverse offset of the element is the distance from the lane line point to the road Link; The comprehensive processing module is configured to iterate through the lane recognition data of each segment on both sides of the road Link, and merge all the lane recognition data of the segments.

4. The system of claim 3, wherein, The lane point of the lane line recognition data with the angle difference of the lane line direction angle with the reference being less than a first preset value is projected to the lane point of the reference, and the corresponding lane recognition data is merged to the reference to obtain a lane line recognition set. When the angle difference of the lane point and the reference point direction angle is greater than the first preset value, the lane recognition data corresponding to the lane point is retained without merging processing.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the lane recognition data merging method according to any one of claims 1 to 2.

6. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 5. The computer program is executed to implement the steps of the lane recognition data merging method according to any one of claims 1 to 2.

Images