CN113408407B - Electronic map lane line correction method, electronic map lane line correction equipment and computer readable storage medium - Google Patents
Electronic map lane line correction method, electronic map lane line correction equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN113408407B CN113408407B CN202110673855.0A CN202110673855A CN113408407B CN 113408407 B CN113408407 B CN 113408407B CN 202110673855 A CN202110673855 A CN 202110673855A CN 113408407 B CN113408407 B CN 113408407B
- Authority
- CN
- China
- Prior art keywords
- point
- determining
- lane line
- line
- preset area
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Abstract
The present disclosure provides a lane line correction method, apparatus, and computer-readable storage medium for an electronic map. The technical scheme provided by the disclosure includes: the method comprises the steps of obtaining a target image comprising a lane line, carrying out lane line central line identification processing on the target image by using a machine learning model, determining a reference line, wherein the reference line comprises a plurality of reference points, determining a correction point in a preset area corresponding to each reference point in the target image, and correcting the reference point to the correction point, wherein the energy of the correction point is higher than that of the reference point. Because the higher the energy in the preset area is, the closer the point is to the center line of the lane line, the reference line after the correction is closer to the center line of the lane line, so that the accuracy of the position of the lane line in the electronic map is improved.
Description
The application is a divisional application with the application number of CN201811286291.X, the application date of 2018, 10 month and 31 days, and the invention name of electronic map lane line correction method, device and computer readable storage medium.
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to a lane line correction method and device for an electronic map and a computer readable storage medium.
Background
When the electronic map is generated, image information of a lane is required to be acquired, lane lines in the image information are marked manually, and machine learning is performed through a large number of manually marked lane lines, namely, the large number of manually marked lane lines are used as samples to train a neural network model, so that the trained neural network model can identify the lane lines.
However, the manually marked lane lines may not be accurate, that is, the samples used to train the neural network model may not be accurate, resulting in the trained neural network model not being able to accurately identify the lane lines, and thus resulting in inaccurate positions of the lane lines in the electronic map.
Disclosure of Invention
The embodiment of the disclosure provides a lane line correction method, a lane line correction device and a lane line correction computer readable storage medium for improving the accuracy of the position of a lane line in an electronic map.
In a first aspect, an embodiment of the present disclosure provides a lane line correction method for an electronic map, including:
acquiring a target image comprising a lane line;
carrying out center line identification processing of a lane line on the target image by using a machine learning model, and determining a reference line, wherein the reference line comprises a plurality of reference points;
and determining a correction point in a preset area corresponding to each reference point in the target image, and correcting the reference point to the correction point, wherein the energy of the correction point is higher than that of the reference point.
In a second aspect, an embodiment of the present disclosure provides an electronic map lane line correction apparatus, including:
the acquisition module is used for acquiring a target image comprising a lane line;
the first determining module is used for carrying out center line identification processing on the lane lines of the target image by utilizing a machine learning model, and determining a reference line, wherein the reference line comprises a plurality of reference points;
the second determining module is used for determining a correction point in a preset area corresponding to each reference point in the target image, wherein the energy of the correction point is higher than that of the reference point;
and the correction module is used for correcting the reference point to the correction point.
In a third aspect, an embodiment of the present disclosure provides an electronic device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of the first aspects.
In a fourth aspect, embodiments of the present disclosure provide a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the method according to any one of the first aspects.
In a fifth aspect, embodiments of the present disclosure provide a computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of the first aspects.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
Fig. 1 is a schematic diagram of an application scenario provided in an embodiment of the present disclosure;
FIG. 2 is a schematic illustration of an image provided by an embodiment of the present disclosure;
fig. 3 is a flowchart of a lane line correction method of an electronic map according to an embodiment of the disclosure;
FIG. 4 is a schematic illustration of another image provided by an embodiment of the present disclosure;
FIG. 5 is a flowchart of a lane line correction method for an electronic map according to another embodiment of the present disclosure;
FIG. 6 is a schematic illustration of another image provided by an embodiment of the present disclosure;
FIG. 7 is a flowchart of a lane line correction method for an electronic map according to another embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of an electronic map lane line correction device according to an embodiment of the present disclosure;
fig. 9 is a schematic structural diagram of an electronic map lane line correction apparatus according to an embodiment of the present disclosure.
Specific embodiments of the present disclosure have been shown by way of the above drawings and will be described in more detail below. These drawings and the written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the disclosed concepts to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
The lane line correction method of the electronic map provided by the disclosure can be applied to the application scene shown in fig. 1. As shown in fig. 1, before an electronic map, such as a high-precision road map, is generated, information about a lane needs to be collected, and one implementation is that: the vehicle 11 is provided with a camera, which may be a camera, and a detection device, which may be a radar and/or laser detection device in particular. During the running process of the vehicle 11, the camera acquires image information of the lane in real time, and meanwhile, the radar and/or laser detection equipment detects the three-dimensional point cloud of the lane in real time. For example, the image information of the lane collected by the camera includes a speed limit plate 12 beside the lane and a lane line 13 in the lane, and the radar and/or laser detection device may also detect a three-dimensional point cloud corresponding to the speed limit plate 12 and the lane line 13. When the device for generating the high-precision road map, such as a computer, a server, a terminal device and the like, acquires the image information of the lane acquired by the camera and the three-dimensional point cloud of the lane detected by the radar and/or the laser detection device, the speed limit information of the lane can be determined according to the speed limit plate 12 in the image information acquired by the camera, the position information of the lane line 13 can be determined according to the three-dimensional point cloud of the lane line 13 detected by the radar and/or the laser detection device, and further, the high-precision road map corresponding to the lane can be generated according to the speed limit information of the lane and the position information of the lane line 13. The present embodiment is not limited to the generation of the high-precision road map corresponding to the lane based on the speed limit information of the lane and the position information of the lane line 13, but may be performed based on more lane information.
In an actual lane, a lane line is an area having a certain width, for example, 15cm, in the lane, and may be a solid line area or a dotted line area, for example, as shown in fig. 2, in the image 21 collected by the camera, the lane line corresponds to each area 22, and when a high-precision road map is generated, it is necessary to use the positional information of the center line of the lane line as the positional information of the lane line, that is, it is necessary to determine the positional information of the center line of the lane line, for example, the positional information of the center line 23 of the area 22. Because the position information of the lane lines in a large number of lanes needs to be determined when the high-precision road map is generated, in order to improve the generation efficiency, usually, the center lines of the lane lines in the image are manually marked, the center lines of the lane lines which are manually marked are taken as samples, and a neural network model is trained in a machine learning mode, so that the trained neural network model can identify the center lines of the lane lines. When a large amount of image information of the lane lines is acquired, the center line of the lane lines is identified by the trained neural network model. However, since the center line of the manually marked lane line may not be accurate, that is, the center line of the manually marked lane line may deviate from the real center line of the lane line, so that the trained neural network model is inaccurate, the center line of the lane line identified by the neural network model deviates from the real center line of the lane line more, and finally, the generated high-precision road map is not accurate enough. In order to solve the problem, the embodiment of the present disclosure provides a lane line correction method for an electronic map, and the method is described below with reference to specific embodiments.
The following describes the technical solutions of the present disclosure and how the technical solutions of the present disclosure solve the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present disclosure will be described below with reference to the accompanying drawings.
Fig. 3 is a flowchart of a lane line correction method of an electronic map according to an embodiment of the disclosure. Aiming at the technical problems in the prior art, the embodiment of the disclosure provides a lane line correction method of an electronic map, which comprises the following specific steps:
Optionally, the acquiring the target image including the lane line includes: acquiring a three-dimensional point cloud of a lane comprising the lane line, which is detected by detection equipment; converting the three-dimensional point cloud into a two-dimensional point cloud; and determining the target image according to the two-dimensional point cloud. The detection device comprises at least one of the following: radar, laser detection device.
For example, an apparatus for generating a high-precision road map, such as a server, may acquire a three-dimensional point cloud of a lane line 13 detected by a detection apparatus in a vehicle 11 as shown in fig. 1, for example, the vehicle 11 transmits the three-dimensional point cloud of the lane line 13 detected by the detection apparatus to the server in real time, the server further converts the three-dimensional point cloud into a two-dimensional point cloud and fuses the two-dimensional point cloud into a base map, which is recorded as a target image in which the lane line 13 occupies a certain area.
Optionally, the determining a reference line according to the area occupied by the lane line in the target image includes: and determining the reference line by adopting machine learning according to the area occupied by the lane line in the target image.
As shown in fig. 4, 41 represents the target image, 42 represents the area occupied by the lane line in the target image 41, and is only schematically illustrated herein, and the shape of the area 42 occupied by the lane line in the target image 41 is not limited, and in some embodiments, the area 42 occupied by the lane line may be irregularly shaped. The center line of the lane line can be determined by machine learning from the region 42 occupied by the lane line in the target image 41, and the center line of the lane line determined by machine learning is referred to herein as a reference line, such as the reference line 43 shown in fig. 4. Since the center line of the lane line determined using machine learning is not the true center line of the lane line, the reference line 43 may deviate from the true center line of the lane line, i.e., the center line of the region 42. It will be appreciated that the line is made up of a myriad of points and that the reference line 43 is made up of a myriad of reference points, i.e. the points on the reference line 43 are reference points. As shown in fig. 4, 44, 45, 46 each represent an arbitrary reference point on the reference line 43.
Taking the reference point 44 as an example, a preset area is determined around the reference point 44, where the size of the preset area may be preset, optionally, the preset area includes at least a part of the upper edge and a part of the lower edge of the lane line, as shown in fig. 4, the preset area 47 is not limited to the position of the reference point 44 in the preset area 47, further, the preset area 47 is converted into an energy map, where the brightness of different positions in the energy map is different, the higher the brightness is, the higher the energy is, optionally, the brightness of the area occupied by the lane line in the energy map is higher than the brightness of the other parts, that is, in the preset area 47, the brightness of the area 48 where the preset area 47 and the area 42 overlap is higher than the brightness of the rest of the preset area 47. In addition, the brightness is different at different positions inside the region 48, alternatively, the brightness is highest at the position where the center line 49 of the region 48 is located, and the brightness is lower at the position closer to the upper and lower edge portions of the region 42 inside the region 48, that is, the brightness gradually decreases from the center line 49 of the region 48 in the direction indicated by the arrow. Thus, the point on the center line 49 of the region 48 is the brightest point, i.e., the highest-energy point, in the preset region 47.
Similarly, the brightest point in the preset area around other reference points, such as reference point 45 or reference point 46, on reference line 43 may be determined, and the detailed process will not be repeated here.
And 304, correcting each reference point in the plurality of reference points to the point with highest energy in a preset area around the reference point.
As shown in fig. 4, the point on the center line 49 of the area 48 is the brightest point in the preset area 47, and the brightest point in the preset area 47 may be the point on the center line of the lane line, or the brightest point in the preset area 47 may be the point close to the center line of the lane line. And the reference point 44 is a point on the reference line 43, the reference line 43 being used to identify the center line of the lane line, but the reference line 43 being offset from the center line of the lane line, that is, the reference point 44 being offset from the center line of the lane line. After the brightest point in the preset area 47 is determined, the reference point 44 may be corrected to the brightest point in the preset area 47, that is, the reference point 44 may be corrected to any one point on the center line 49 of the area 48 such that the reference point 44 falls on the center line of the lane line or such that the reference point 44 is close to the center line of the lane line.
According to the embodiment of the disclosure, the reference line for marking the center line of the lane line is determined through the area occupied by the lane line in the target image, the reference line may deviate from the real center line of the lane line, the point with the highest energy in the preset area is determined according to the energy distribution of the preset area around each reference point on the reference line, and the point with the highest energy in the preset area is the point on the center line of the lane line or the point with the highest energy in the preset area is the point close to the center line of the lane line, so that each reference point in the plurality of reference points is corrected to the point with the highest energy in the preset area around the reference point, the reference line is enabled to be closer to the center line of the lane line, and the accuracy of the position of the lane line in the electronic map can be improved when the electronic map is generated according to the position information of the reference line.
Fig. 5 is a flowchart of a lane line correction method of an electronic map according to another embodiment of the disclosure. On the basis of the above embodiment, the lane line correction method for the electronic map specifically includes the following steps:
Step 501 is consistent with the implementation and principles of step 301 and will not be described in detail herein.
Step 502 is consistent with the implementation and principles of step 302 and will not be described in detail herein.
As shown in fig. 6, when the preset area 47 around the reference point 44 is determined on the basis of fig. 4, the preset area 47 centered on the reference point 44 may be determined with the reference point 44 as the center, that is, the reference point 44 is the center of the preset area 47.
The method for determining the brightest point in the preset area 47 according to the energy distribution of the preset area 47 is consistent with the method described in the above embodiment, and will not be described here again.
For example, the reference point 44 is corrected to any point on the center line 49 of the region 48 such that the reference point 44 falls on the center line of the lane line, or such that the reference point 44 is close to the center line of the lane line. Similarly, other reference points on the reference line, such as reference point 45 or reference point 46, are corrected to the centerline of the lane line or to a position close to the centerline of the lane line.
According to the embodiment of the disclosure, the reference line for marking the center line of the lane line is determined through the area occupied by the lane line in the target image, the reference line may deviate from the real center line of the lane line, the point with the highest energy in the preset area is determined according to the energy distribution of the preset area around each reference point on the reference line, and the point with the highest energy in the preset area is the point on the center line of the lane line or the point with the highest energy in the preset area is the point close to the center line of the lane line, so that each reference point in the plurality of reference points is corrected to the point with the highest energy in the preset area around the reference point, the reference line is enabled to be closer to the center line of the lane line, and the accuracy of the position of the lane line in the electronic map can be improved when the electronic map is generated according to the position information of the reference line.
Fig. 7 is a flowchart of a lane line correction method of an electronic map according to another embodiment of the disclosure. On the basis of the above embodiment, the lane line correction method for the electronic map specifically includes the following steps:
Step 701 is consistent with the implementation and principles of step 301 and will not be described in detail herein.
Step 702 is consistent with the implementation and principles of step 302 and will not be described in detail herein.
Step 703 is consistent with the implementation and principles of step 503 and will not be described in detail herein.
As shown in fig. 6, the point on the center line 49 of the area 48 is the brightest point in the preset area 47, and further, the brightest point on the center line 49 of the area 48 closest to the reference point 44 can be determined based on the position information of the reference point 44 and the position information of the point on the center line 49 of the area 48, it is understood that the brightest point on the center line 49 of the area 48 closest to the reference point 44 is the intersection 60 passing through the reference point 44 in the vertical direction with the center line 49.
For example, reference point 44 is corrected to the brightest point 60 closest to reference point 44 on centerline 49 of region 48.
According to the embodiment of the disclosure, the reference line for marking the center line of the lane line is determined through the area occupied by the lane line in the target image, the reference line may deviate from the real center line of the lane line, the point with the highest energy in the preset area is determined according to the energy distribution of the preset area around each reference point on the reference line, and the point with the highest energy in the preset area is the point on the center line of the lane line or the point with the highest energy in the preset area is the point close to the center line of the lane line, so that each reference point in the plurality of reference points is corrected to the point with the highest energy in the preset area around the reference point, the reference line is enabled to be closer to the center line of the lane line, and the accuracy of the position of the lane line in the electronic map can be improved when the electronic map is generated according to the position information of the reference line.
Fig. 8 is a schematic structural diagram of an electronic map lane line correction device according to an embodiment of the disclosure. The electronic map lane line correction apparatus provided in the embodiment of the present disclosure may execute the processing flow provided in the embodiment of the method for lane line correction of an electronic map, as shown in fig. 8, the electronic map lane line correction apparatus 80 includes: an acquisition module 81, a first determination module 82, a second determination module 83, and a correction module 84; wherein, the acquisition module 81 is used for acquiring a target image comprising a lane line; the first determining module 82 is configured to determine a reference line according to an area occupied by the lane line in the target image, where the reference line is used to identify a center line of the lane line, and the reference line includes a plurality of reference points; the second determining module 83 is configured to determine a point with highest energy in a preset area around each of the plurality of reference points according to an energy distribution of the preset area; the correction module 84 is configured to correct each reference point of the plurality of reference points to a point with highest energy in a preset area around the reference point.
Optionally, the second determining module 83 is specifically configured to: determining energy distribution of a preset area around each reference point by taking each reference point in the plurality of reference points as a center; determining the brightest point in the preset area according to the energy distribution of the preset area around the reference point; the correction module 84 is specifically configured to: and correcting each reference point in the plurality of reference points to the brightest point in a preset area around the reference point.
Optionally, the second determining module 83 is specifically configured to: determining the brightest point closest to the reference point in the preset area according to the position information of the reference point and the energy distribution of the preset area around the reference point; the correction module 84 is specifically configured to: and correcting each reference point in the plurality of reference points to the brightest point closest to the reference point in a preset area around the reference point.
Optionally, the first determining module 82 is specifically configured to: and determining the reference line by adopting machine learning according to the area occupied by the lane line in the target image.
Optionally, the obtaining module 81 is specifically configured to: acquiring a three-dimensional point cloud of a lane comprising the lane line, which is detected by detection equipment; converting the three-dimensional point cloud into a two-dimensional point cloud; and determining the target image according to the two-dimensional point cloud.
Optionally, the detection device includes at least one of: radar, laser detection device.
The lane line correction device for an electronic map shown in fig. 8 may be used to implement the technical solution of the above method embodiment, and its implementation principle and technical effects are similar, and will not be described herein again.
Fig. 9 is a schematic structural diagram of an electronic map lane line correction apparatus according to an embodiment of the present disclosure. The electronic map lane line correction apparatus provided in the embodiment of the present disclosure may execute the processing flow provided in the embodiment of the electronic map lane line correction method, as shown in fig. 9, the electronic map lane line correction apparatus 90 includes: memory 91, processor 92, computer programs and communication interface 93; wherein the computer program is stored in the memory 91 and configured to be executed by the processor 92: acquiring a target image comprising a lane line; determining a reference line according to the area occupied by the lane line in the target image, wherein the reference line is used for marking the central line of the lane line and comprises a plurality of reference points; determining the point with highest energy in a preset area according to the energy distribution of the preset area around each reference point in the plurality of reference points; and correcting each reference point in the plurality of reference points to a point with highest energy in a preset area around the reference point.
Optionally, the processor 92 is specifically configured to, when determining a point with highest energy in the preset area according to the energy distribution of the preset area around each of the plurality of reference points: determining energy distribution of a preset area around each reference point by taking each reference point in the plurality of reference points as a center; determining the brightest point in the preset area according to the energy distribution of the preset area around the reference point; the processor 92 is specifically configured to, when correcting each of the plurality of reference points to a point with highest energy in a preset area around the reference point: and correcting each reference point in the plurality of reference points to the brightest point in a preset area around the reference point.
Optionally, the processor 92 is specifically configured to, when determining the brightest point in the preset area according to the energy distribution of the preset area around the reference point: determining the brightest point closest to the reference point in the preset area according to the position information of the reference point and the energy distribution of the preset area around the reference point; the processor 92 is specifically configured to, when correcting each of the plurality of reference points to a brightest point in a preset area around the reference point: and correcting each reference point in the plurality of reference points to the brightest point closest to the reference point in a preset area around the reference point.
Optionally, the processor 92 is specifically configured to, when determining the reference line according to the area occupied by the lane line in the target image: and determining the reference line by adopting machine learning according to the area occupied by the lane line in the target image.
Optionally, the processor 92 is specifically configured to, when acquiring the target image including the lane line: acquiring a three-dimensional point cloud of a lane comprising the lane line, which is detected by detection equipment; converting the three-dimensional point cloud into a two-dimensional point cloud; and determining the target image according to the two-dimensional point cloud. In some embodiments, the processor 92 may receive the three-dimensional point cloud transmitted by the detection device through the communication interface 93.
Optionally, the detection device includes at least one of: radar, laser detection device.
The lane line correction apparatus for an electronic map shown in the embodiment of fig. 9 may be used to implement the technical solution of the embodiment of the method, and its implementation principle and technical effects are similar, and are not repeated here.
In addition, the present embodiment also provides a computer-readable storage medium having stored thereon a computer program that is executed by a processor to implement the electronic map lane line correction method described in the above embodiment.
In the several embodiments provided in the present disclosure, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in hardware plus software functional units.
The integrated units implemented in the form of software functional units described above may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform part of the steps of the methods described in the embodiments of the disclosure. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to perform all or part of the functions described above. The specific working process of the above-described device may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present disclosure, and not for limiting the same; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present disclosure.
Claims (16)
1. A lane line correction method of an electronic map comprises the following steps:
acquiring a target image comprising a lane line;
carrying out center line identification processing of a lane line on the target image by using a machine learning model, and determining a reference line, wherein the reference line comprises a plurality of reference points;
determining a preset area corresponding to each reference point in the target image; determining the energy distribution of the preset area; and determining a correction point in the preset area according to the energy distribution of the preset area, and correcting the reference point to the correction point, wherein the energy of the correction point is higher than that of the reference point.
2. The method of claim 1, wherein determining the correction point within the preset zone according to the energy distribution of the preset zone comprises:
determining the point with the highest energy in the preset area;
and if the energy corresponding to the point with the highest energy is higher than the energy of the reference point, determining the point with the highest energy as the correction point.
3. The method of claim 2, wherein determining the point of highest energy within the preset area comprises:
determining at least one candidate point in the preset area, wherein the candidate point is the point with the highest brightness in the preset area;
and determining a candidate point closest to the reference point from the at least one candidate point as the point with the highest energy.
4. A method according to any one of claims 1-3, wherein the predetermined area is centered on the reference point.
5. The method of claim 4, wherein the predetermined area comprises a portion of a first edge and a portion of a second edge of the lane line, the first edge and the second edge being edges along a length extension of the lane line.
6. The method of any of claims 1-3, 5, wherein the acquiring a target image comprising a lane line comprises:
acquiring a three-dimensional point cloud of a lane comprising the lane line, which is detected by detection equipment;
converting the three-dimensional point cloud into a two-dimensional point cloud;
and determining the target image according to the two-dimensional point cloud.
7. The method of claim 6, wherein the detection device comprises at least one of:
radar, laser detection device.
8. An electronic map lane line correction apparatus, comprising:
the acquisition module is used for acquiring a target image comprising a lane line;
the first determining module is used for carrying out center line identification processing on the lane lines of the target image by utilizing a machine learning model, and determining a reference line, wherein the reference line comprises a plurality of reference points;
the second determining module is used for determining a preset area corresponding to each reference point in the target image; determining the energy distribution of the preset area; according to the energy distribution of the preset area, a correction point is determined in the preset area, and the energy of the correction point is higher than that of the reference point;
and the correction module is used for correcting the reference point to the correction point.
9. The apparatus of claim 8, wherein the second determining module is specifically configured to:
determining the point with the highest energy in the preset area;
and if the energy corresponding to the point with the highest energy is higher than the energy of the reference point, determining the point with the highest energy as the correction point.
10. The apparatus of claim 9, wherein the second determining module is specifically configured to:
determining at least one candidate point in the preset area, wherein the candidate point is the point with the highest brightness in the preset area;
and determining a candidate point closest to the reference point from the at least one candidate point as the point with the highest energy.
11. The apparatus of any of claims 8-10, wherein the predetermined area is centered on the reference point.
12. The apparatus of claim 11, wherein the predetermined area comprises a portion of a first edge and a portion of a second edge of the lane line, the first edge and the second edge being edges along a length extension of the lane line.
13. The apparatus according to any one of claims 8-10, 12, wherein the acquisition module is specifically configured to:
acquiring a three-dimensional point cloud of a lane comprising the lane line, which is detected by detection equipment;
converting the three-dimensional point cloud into a two-dimensional point cloud;
and determining the target image according to the two-dimensional point cloud.
14. The apparatus of claim 13, wherein the detection device comprises at least one of:
radar, laser detection device.
15. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.
16. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110673855.0A CN113408407B (en) | 2018-10-31 | 2018-10-31 | Electronic map lane line correction method, electronic map lane line correction equipment and computer readable storage medium |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811286291.XA CN109636820B (en) | 2018-10-31 | 2018-10-31 | Electronic map lane line correction method, device and computer readable storage medium |
| CN202110673855.0A CN113408407B (en) | 2018-10-31 | 2018-10-31 | Electronic map lane line correction method, electronic map lane line correction equipment and computer readable storage medium |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811286291.XA Division CN109636820B (en) | 2018-10-31 | 2018-10-31 | Electronic map lane line correction method, device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113408407A CN113408407A (en) | 2021-09-17 |
| CN113408407B true CN113408407B (en) | 2023-06-23 |
Family
ID=66067023
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110673855.0A Active CN113408407B (en) | 2018-10-31 | 2018-10-31 | Electronic map lane line correction method, electronic map lane line correction equipment and computer readable storage medium |
| CN201811286291.XA Active CN109636820B (en) | 2018-10-31 | 2018-10-31 | Electronic map lane line correction method, device and computer readable storage medium |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811286291.XA Active CN109636820B (en) | 2018-10-31 | 2018-10-31 | Electronic map lane line correction method, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN113408407B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110120084A (en) * | 2019-05-23 | 2019-08-13 | 广东星舆科技有限公司 | A method of generating lane line and road surface |
| CN110530398B (en) * | 2019-08-30 | 2021-02-02 | 北京三快在线科技有限公司 | Method and device for detecting precision of electronic map |
| CN110539306B (en) * | 2019-09-06 | 2021-06-22 | 广东利元亨智能装备股份有限公司 | Workpiece bonding method and device |
| CN113160396B (en) * | 2020-01-23 | 2024-03-29 | 宝马股份公司 | Method for establishing map model, method for generating real-time map and map system |
| CN114705180B (en) * | 2022-06-06 | 2023-03-24 | 中汽创智科技有限公司 | Data correction method, device and equipment for high-precision map and storage medium |
| CN114724379A (en) * | 2022-06-08 | 2022-07-08 | 中汽创智科技有限公司 | Data processing method, device, equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102314599A (en) * | 2011-10-11 | 2012-01-11 | 东华大学 | Identification and deviation-detection method for lane |
Family Cites Families (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4374211B2 (en) * | 2002-08-27 | 2009-12-02 | クラリオン株式会社 | Lane marker position detection method, lane marker position detection device, and lane departure warning device |
| JP2007104171A (en) * | 2005-10-03 | 2007-04-19 | Omron Corp | Front monitoring device |
| JP2007128141A (en) * | 2005-11-01 | 2007-05-24 | Hitachi Software Eng Co Ltd | System and method for determining road lane number in road image |
| JP5733196B2 (en) * | 2011-12-22 | 2015-06-10 | アイシン・エィ・ダブリュ株式会社 | Lane guidance display system, method and program |
| JP5792678B2 (en) * | 2012-06-01 | 2015-10-14 | 株式会社日本自動車部品総合研究所 | Lane boundary detection device and program |
| CN103605977B (en) * | 2013-11-05 | 2017-01-18 | 奇瑞汽车股份有限公司 | Extracting method of lane line and device thereof |
| CN103903019B (en) * | 2014-04-11 | 2017-12-15 | 北京工业大学 | A kind of automatic generation method of multilane track of vehicle space-time diagram |
| US9721471B2 (en) * | 2014-12-16 | 2017-08-01 | Here Global B.V. | Learning lanes from radar data |
| 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 |
| CN106570446B (en) * | 2015-10-12 | 2019-02-01 | 腾讯科技（深圳）有限公司 | The method and apparatus of lane line drawing |
| CN105426861B (en) * | 2015-12-02 | 2019-05-21 | 百度在线网络技术（北京）有限公司 | Lane line determines method and device |
| US10102434B2 (en) * | 2015-12-22 | 2018-10-16 | Omnivision Technologies, Inc. | Lane detection system and method |
| CN105528588B (en) * | 2015-12-31 | 2019-04-23 | 百度在线网络技术（北京）有限公司 | A kind of Lane detection method and device |
| CN105957182B (en) * | 2016-04-21 | 2018-08-03 | 深圳市元征科技股份有限公司 | A kind of method and device of rectilinear direction that correcting instruction vehicle traveling |
| TWI609807B (en) * | 2016-05-17 | 2018-01-01 | 緯創資通股份有限公司 | Image evaluation method and electronic apparatus thereof |
| CN106559658B (en) * | 2016-12-02 | 2017-08-04 | 郑州捷安高科股份有限公司 | Multi-channel projection fusion band color balance Control Scheme method |
| US10762776B2 (en) * | 2016-12-21 | 2020-09-01 | Here Global B.V. | Method, apparatus, and computer program product for determining vehicle lane speed patterns based on received probe data |
| CN106740841B (en) * | 2017-02-14 | 2018-07-10 | 驭势科技（北京）有限公司 | Method for detecting lane lines, device and mobile unit based on dynamic control |
| CN107066986A (en) * | 2017-04-21 | 2017-08-18 | 哈尔滨工业大学 | A kind of lane line based on monocular vision and preceding object object detecting method |
| CN107341453B (en) * | 2017-06-20 | 2019-12-20 | 北京建筑大学 | Lane line extraction method and device |
| CN108470159B (en) * | 2018-03-09 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Lane line data processing method and device, computer device and storage medium |
-
2018
- 2018-10-31 CN CN202110673855.0A patent/CN113408407B/en active Active
- 2018-10-31 CN CN201811286291.XA patent/CN109636820B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102314599A (en) * | 2011-10-11 | 2012-01-11 | 东华大学 | Identification and deviation-detection method for lane |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109636820A (en) | 2019-04-16 |
| CN109636820B (en) | 2021-07-06 |
| CN113408407A (en) | 2021-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113408407B (en) | Electronic map lane line correction method, electronic map lane line correction equipment and computer readable storage medium | |
| CN109584706B (en) | Electronic map lane line processing method, device and computer readable storage medium | |
| EP3505869B1 (en) | Method, apparatus, and computer readable storage medium for updating electronic map | |
| CN100458359C (en) | Small-displacement measuring system in long-distance plane | |
| CN109141444B (en) | positioning method, positioning device, storage medium and mobile equipment | |
| CN104090970A (en) | Interest point showing method and device | |
| CN112307810B (en) | Visual positioning effect self-checking method and vehicle-mounted terminal | |
| CN110148099B (en) | Projection relation correction method and device, electronic equipment and computer readable medium | |
| US20150117753A1 (en) | Computing device and method for debugging computerized numerical control machine | |
| CN105809658A (en) | Method and apparatus for setting region of interest | |
| CN109781163B (en) | Calibration parameter validity checking method, device, equipment and storage medium | |
| EP3843036B1 (en) | Sample labeling method and device, and damage category identification method and device | |
| CN103399015A (en) | Pathological section scanner and method and device for measuring locating precision of slide glass platform | |
| CN112146848B (en) | Method and device for determining distortion parameter of camera | |
| CN112735253B (en) | Traffic light automatic labeling method and computer equipment | |
| CN111160360B (en) | Image recognition method, device and system | |
| CN104750879A (en) | Electronic map labelling, claiming and error-correcting method and processing equipment | |
| CN109190674B (en) | Training data generation method and device | |
| CN110633620A (en) | Pointer instrument scale identification method and electronic equipment | |
| CN113255578B (en) | Traffic identification recognition method and device, electronic equipment and storage medium | |
| CN108297795A (en) | A kind of lane recognition system of electric vehicle | |
| CN113503880A (en) | Vehicle positioning method and device | |
| CN110539748B (en) | Congestion car following system and terminal based on look-around | |
| CN111639593A (en) | Lane line label processing method and device | |
| CN207931598U (en) | A kind of lane recognition system of electric vehicle |
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 |