CN109636820A - Electronic map lane line modification method, equipment and computer readable storage medium - Google Patents
Electronic map lane line modification method, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN109636820A CN109636820A CN201811286291.XA CN201811286291A CN109636820A CN 109636820 A CN109636820 A CN 109636820A CN 201811286291 A CN201811286291 A CN 201811286291A CN 109636820 A CN109636820 A CN 109636820A
- Authority
- CN
- China
- Prior art keywords
- point
- reference point
- predeterminable area
- line
- lane line
- 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.)
- Granted
Links
- 238000002715 modification method Methods 0.000 title claims abstract description 22
- 238000000034 method Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 11
- 238000010801 machine learning Methods 0.000 claims description 10
- 239000004744 fabric Substances 0.000 claims description 5
- 241000208340 Araliaceae Species 0.000 claims description 4
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 4
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 4
- 235000008434 ginseng Nutrition 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 11
- 238000003062 neural network model Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000001755 vocal effect Effects 0.000 description 1
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 using two or more images, e.g. averaging or 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the present invention provides a kind of electronic map lane line modification method, equipment and computer readable storage medium.The embodiment of the present invention passes through region shared by lane line described in target image, determine the reference line for identifying the center line of lane line, the reference line may deviate from the true center line of the lane line, further with the Energy distribution of the predeterminable area around each reference point on the reference line, determine the highest point of energy in the predeterminable area, since the highest point of energy is point on the center line of lane line in the predeterminable area, or, the highest point of energy is close to the point of the center line of the lane line in the predeterminable area, therefore, each reference point in multiple reference points is adapted on the highest point of energy in the predeterminable area around the reference point, it may make the reference line closer to the center line of lane line, when generating electronic map according to the location information of the reference line, the accurate of the position of lane line in the electronic map can be improved Degree.
Description
Technical field
The present embodiments relate to field of computer technology more particularly to a kind of electronic map lane line modification method, set
Standby and computer readable storage medium.
Background technique
Currently when generating electronic map, need to acquire the image information in lane, and by manually in the image information
Lane line be labeled, machine learning is carried out by a large amount of lane line that manually marks out, i.e., it is big by what is manually marked out
The lane line of amount is as sample training neural network model so that trained neural network model can identify lane line.
But the lane line manually marked out may not precisely, that is to say, that for training the sample of neural network model
It originally may be not accurately, lane line can not accurately to be identified so as to cause trained neural network model, so as to cause electricity
The position of lane line is not accurate in sub- map.
Summary of the invention
The embodiment of the present invention provides a kind of electronic map lane line modification method, equipment and computer readable storage medium,
To improve the accuracy of the position of lane line in electronic map.
In a first aspect, the embodiment of the present invention provides a kind of electronic map lane line modification method, comprising:
Obtain the target image including lane line;
According to region shared by lane line described in the target image, reference line is determined, the reference line is for identifying
The center line of the lane line, the reference line include multiple reference points;
According to the Energy distribution of the predeterminable area around reference point each in the multiple reference point, the preset areas is determined
The highest point of energy in domain;
Each reference point in the multiple reference point is adapted in the predeterminable area around the reference point energy most
On high point.
Second aspect, the embodiment of the present invention provide a kind of electronic map lane line correcting device, comprising:
Module is obtained, for obtaining the target image including lane line;
First determining module determines reference line for region shared by the lane line according to the target image, institute
Reference line is stated for identifying the center line of the lane line, the reference line includes multiple reference points;
Second determining module, for according to the energy of the predeterminable area around reference point each in the multiple reference point point
Cloth determines the highest point of energy in the predeterminable area;
Correction module, it is default around the reference point for each reference point in the multiple reference point to be adapted to
In region on the highest point of energy.
The third aspect, the embodiment of the present invention provide a kind of electronic map lane line corrective, comprising:
Memory;
Processor;And
Computer program;
Wherein, the computer program stores in the memory, and is configured as being executed by the processor following
Operation:
Obtain the target image including lane line;
According to region shared by lane line described in the target image, reference line is determined, the reference line is for identifying
The center line of the lane line, the reference line include multiple reference points;
According to the Energy distribution of the predeterminable area around reference point each in the multiple reference point, the preset areas is determined
The highest point of energy in domain;
Each reference point in the multiple reference point is adapted in the predeterminable area around the reference point energy most
On high point.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, are stored thereon with computer program,
The computer program is executed by processor to realize method described in first aspect.
Electronic map lane line modification method, equipment and computer readable storage medium provided in an embodiment of the present invention lead to
Region shared by lane line described in target image is crossed, determines the reference line for identifying the center line of lane line, the reference line
The true center line of the lane line may be deviated from, further with the predeterminable area around each reference point on the reference line
Energy distribution determines the highest point of energy in the predeterminable area, since the highest point of energy is lane line in the predeterminable area
Point on center line, alternatively, the highest point of energy is close to the point of the center line of the lane line in the predeterminable area, therefore,
Each reference point in multiple reference points is adapted on the highest point of energy in the predeterminable area around the reference point, may make
This can be improved when generating electronic map according to the location information of the reference line in the center line of the reference line closer to lane line
The accuracy of the position of lane line in electronic map.
Detailed description of the invention
Fig. 1 is a kind of schematic diagram of application scenarios provided in an embodiment of the present invention;
Fig. 2 is a kind of schematic diagram of image provided in an embodiment of the present invention;
Fig. 3 is electronic map lane line modification method flow chart provided in an embodiment of the present invention;
Fig. 4 is the schematic diagram of another image provided in an embodiment of the present invention;
Fig. 5 be another embodiment of the present invention provides electronic map lane line modification method flow chart;
Fig. 6 is the schematic diagram of another image provided in an embodiment of the present invention;
Fig. 7 be another embodiment of the present invention provides electronic map lane line modification method flow chart;
Fig. 8 is the structural schematic diagram of electronic map lane line correcting device provided in an embodiment of the present invention;
Fig. 9 is the structural schematic diagram of electronic map lane line corrective provided in an embodiment of the present invention.
Through the above attached drawings, it has been shown that the specific embodiment of the disclosure will be hereinafter described in more detail.These attached drawings
It is not intended to limit the scope of this disclosure concept by any means with verbal description, but is by referring to specific embodiments
Those skilled in the art illustrate the concept of the disclosure.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
Electronic map lane line modification method provided by the invention, can be adapted for application scenarios shown in FIG. 1.Such as Fig. 1
It is shown, before generating electronic map such as high-precision road-map, need to acquire the relevant information in lane, a kind of implementation
It is: is provided with capture apparatus and detecting devices in vehicle 11, which can be camera, which specifically can be
Radar and/or laser detection equipment.For vehicle 11 during traveling, camera acquires the image information in lane, while thunder in real time
It reaches and/or the three-dimensional point cloud in laser detection equipment real-time detection lane.For example, the image information in the lane of camera acquisition includes
Limit also can be detected in the lane line 13 in speed limitation board 12 and the lane beside the lane, radar and/or laser detection equipment
Fast board 12 and the corresponding three-dimensional point cloud of lane line 13.For generate the equipment of high-precision road-map for example computer, server,
Terminal device etc. gets the image information in the lane of camera acquisition and radar and/or laser detection equipment detect
When the three-dimensional point cloud in lane, the speed-limiting messages in the lane can be determined according to the speed limitation board 12 in the image information that camera acquires,
According to the three-dimensional point cloud for the lane line 13 that the radar and/or laser detection equipment detect, the location information of the lane line 13 is determined,
Further, according to the location information of the speed-limiting messages in the lane and the lane line 13, the corresponding high-precision road in the lane is generated
Map.It only schematically illustrates herein, is not limited to the location information of the speed-limiting messages and the lane line 13 according to the lane, generate
The corresponding high-precision road-map in the lane can also generate the corresponding high-precision in the lane according to more lane informations
Road-map.
In practical lane, lane line is the region with one fixed width such as 15cm in lane, which can be with
It is solid line region, is also possible to dashed region, by taking dashed region as an example, as shown in Fig. 2, in camera acquired image 21, vehicle
It is that region 22 one by one is needed when generating high-precision road-map with the position of the lane line center line that diatom is corresponding
Confidence ceases the location information as the lane line, that is to say, that, it is thus necessary to determine that the location information of the lane line center line, such as area
The location information of the center line 23 in domain 22.Due to when generating high-precision road-map, it is thus necessary to determine that lane line in a large amount of lanes
Location information, in order to improve formation efficiency, usually by manually marking the center line of the lane line in image, manually to mark
The center line of lane line out is sample, the training neural network model by the way of machine learning, so that the trained mind
The center line of lane line can be identified through network model.When getting the image information of a large amount of lane line, trained by this
Neural network model identification lane line center line.But the center line of the lane line due to manually marking out may be not
Precisely, that is to say, that the center line of the lane line manually marked out may deviate the true center line of the lane line, to lead
Cause the neural network model trained not accurate, the center line for the lane line for causing the neural network model to identify deviates more from
It is not accurate enough to eventually lead to the high-precision road-map generated for the true center line of the lane line.In order to solve this problem, originally
Application embodiment provides a kind of electronic map lane line modification method, is situated between below with reference to specific embodiment to this method
It continues.
How to be solved with technical solution of the specifically embodiment to technical solution of the present invention and the application below above-mentioned
Technical problem is described in detail.These specific embodiments can be combined with each other below, for the same or similar concept
Or process may repeat no more in certain embodiments.Below in conjunction with attached drawing, the embodiment of the present invention is described.
Fig. 3 is electronic map lane line modification method flow chart provided in an embodiment of the present invention.The embodiment of the present invention is directed to
The technical problem as above of the prior art provides electronic map lane line modification method, and specific step is as follows for this method:
Step 301 obtains the target image including lane line.
Optionally, described to obtain the target image including lane line, comprising: what acquisition detecting devices detected includes described
The three-dimensional point cloud in the lane of lane line;The three-dimensional point cloud is converted into two-dimensional points cloud;According to the two-dimensional points cloud, determine described in
Target image.The detecting devices includes following at least one: radar, laser detection equipment.
For example, the equipment such as server for generating high-precision road-map can obtain in vehicle 11 as shown in Figure 1
The three-dimensional point cloud for the lane line 13 that detecting devices detects, for example, the lane line 13 that vehicle 11 detects the detecting devices
Three-dimensional point cloud is sent to the server in real time, which is further converted to two-dimensional points cloud for three-dimensional point cloud, and by the two dimension
Point cloud is fused to base map, the base map is denoted as target image herein, lane line 13 occupies certain region in the target image.
Region shared by step 302, the lane line according to the target image determines reference line, the reference line
For identifying the center line of the lane line, the reference line includes multiple reference points.
Optionally, region shared by the lane line according to the target image, determines reference line, comprising: root
The reference line is determined using machine learning according to region shared by lane line described in the target image.
As shown in figure 4,41 indicate the target image, 42 indicate target images 41 in lane line shared by region, herein
It only schematically illustrates, does not limit the shape in region 42 shared by lane line in the target image 41, in some embodiments,
Region 42 shared by lane line may be irregular shape.According to region 42 shared by lane line in target image 41, use
Machine learning, it may be determined that go out the center line of lane line, be herein denoted as the center line for the lane line determined using machine learning
Reference line, such as reference line shown in Fig. 4 43.Since the center line for the lane line determined using machine learning is not the lane
The true center line of line, so reference line 43 may deviate the true center line of the lane line i.e. center line in region 42.It can
To understand, line is made of numerous point, and similarly, reference line 43 is made of numerous reference point, that is to say, that reference
Point on line 43 is reference point.As shown in figure 4,44,45,46 respectively indicate any reference point on the reference line 43.
Step 303, according to the Energy distribution of the predeterminable area around reference point each in the multiple reference point, determine institute
State the highest point of energy in predeterminable area.
By taking reference point 44 as an example, a predeterminable area is determined around reference point 44, the size of the predeterminable area can be with
Be it is preset, optionally, which includes at least the portion upper edge and lower peripheral edge of lane line, as shown in Figure 4
Predeterminable area 47 does not limit position of the reference point 44 in the predeterminable area 47 herein and is further converted to predeterminable area 47
Energy diagram, the brightness of different location is different in the energy diagram, and brightness is higher, and expression energy is higher, optionally, the energy diagram
The brightness of the brightness ratio other parts in region shared by middle lane line is high, that is to say, that in predeterminable area 47, predeterminable area 47
The brightness for the brightness ratio in region 48 47 rest part of predeterminable area being overlapped with region 42 is high.In addition, inside region 48 not
Also different with the brightness of position, optionally, the brightness highest of 49 position of center line in region 48, the inside of region 48 is closer
Brightness in 42 lower edges part of region is lower, that is to say, that along shown in arrow since the center line 49 in region 48
Direction, brightness are gradually lowered.Therefore, the point on the center line 49 in region 48 is point most bright in predeterminable area 47 i.e. energy highest
Point.
Similarly, the preset areas on reference line 43 around other reference points such as reference point 45 or reference point 46 can be determined
Most bright point in domain, details are not described herein again for detailed process.
Step 304, the predeterminable area being adapted to each reference point in the multiple reference point around the reference point
On the middle highest point of energy.
As shown in figure 4, the point on the center line 49 in region 48 is point most bright in predeterminable area 47, in the predeterminable area 47
Most bright point can be the point on the center line of lane line, alternatively, point most bright in the predeterminable area 47 is close to the lane
The point of the center line of line.And reference point 44 is a point on reference line 43, reference line 43 is used to identify the center line of lane line,
But reference line 43 deviates from the center line of lane line, that is to say, that reference point 44 deviates from the center line of lane line.It is determining
In predeterminable area 47 after most bright point, reference point 44 can be adapted on point most bright in the predeterminable area 47, that is to say, that
Reference point 44 can be adapted on any one point on the center line 49 in region 48, so that reference point 44 is fallen in lane line
On heart line, or make reference point 44 close to the center line of lane line.
The embodiment of the present invention is determined by region shared by lane line described in target image for identifying in lane line
The reference line of heart line, the reference line may deviate from the true center line of the lane line, further with each on the reference line
The Energy distribution of predeterminable area around reference point determines the highest point of energy in the predeterminable area, due in the predeterminable area
The highest point of energy is the point on the center line of lane line, alternatively, the highest point of energy is close to the vehicle in the predeterminable area
The point of the center line of diatom, therefore, the predeterminable area each reference point in multiple reference points being adapted to around the reference point
On the middle highest point of energy, it may make the reference line closer to the center line of lane line, according to the location information of the reference line
When generating electronic map, the accuracy of the position of lane line in the electronic map can be improved.
Fig. 5 be another embodiment of the present invention provides electronic map lane line modification method flow chart.In above-described embodiment
On the basis of, the electronic map lane line modification method specifically comprises the following steps:
Step 501 obtains the target image including lane line.
Step 501 is consistent with the implementation of step 301 and principle, and details are not described herein again.
Region shared by step 502, the lane line according to the target image determines reference line, the reference line
For identifying the center line of the lane line, the reference line includes multiple reference points.
Step 502 is consistent with the implementation of step 302 and principle, and details are not described herein again.
Step 503, centered on each reference point in the multiple reference point, determine default around the reference point
The Energy distribution in region.
As shown in fig. 6, on the basis of fig. 4, it, can be by reference point when determining the predeterminable area 47 around reference point 44
Centered on 44, the predeterminable area 47 centered on reference point 44 is determined, that is to say, that reference point 44 is in predeterminable area 47
The heart.
Step 504, according to the Energy distribution of the predeterminable area around the reference point, determine most bright in the predeterminable area
Point.
According to the Energy distribution of predeterminable area 47, method and above-described embodiment institute of point most bright in predeterminable area 47 are determined
The method stated is consistent, and details are not described herein again.
Step 505, the predeterminable area being adapted to each reference point in the multiple reference point around the reference point
In on most bright point.
For example, reference point 44 is adapted on any one point on the center line 49 in region 48, so that reference point 44 is fallen in
On the center line of lane line, or make reference point 44 close to the center line of lane line.Similarly, by other ginsengs on reference line
Examination point such as reference point 45 or reference point 46 are adapted on the center line of lane line, or are adapted to the center close to lane line
The position of line.
The embodiment of the present invention is determined by region shared by lane line described in target image for identifying in lane line
The reference line of heart line, the reference line may deviate from the true center line of the lane line, further with each on the reference line
The Energy distribution of predeterminable area around reference point determines the highest point of energy in the predeterminable area, due in the predeterminable area
The highest point of energy is the point on the center line of lane line, alternatively, the highest point of energy is close to the vehicle in the predeterminable area
The point of the center line of diatom, therefore, the predeterminable area each reference point in multiple reference points being adapted to around the reference point
On the middle highest point of energy, it may make the reference line closer to the center line of lane line, according to the location information of the reference line
When generating electronic map, the accuracy of the position of lane line in the electronic map can be improved.
Fig. 7 be another embodiment of the present invention provides electronic map lane line modification method flow chart.In above-described embodiment
On the basis of, the electronic map lane line modification method specifically comprises the following steps:
Step 701 obtains the target image including lane line.
Step 701 is consistent with the implementation of step 301 and principle, and details are not described herein again.
Region shared by step 702, the lane line according to the target image determines reference line, the reference line
For identifying the center line of the lane line, the reference line includes multiple reference points.
Step 702 is consistent with the implementation of step 302 and principle, and details are not described herein again.
Step 703, centered on each reference point in the multiple reference point, determine default around the reference point
The Energy distribution in region.
Step 703 is consistent with the implementation of step 503 and principle, and details are not described herein again.
Step 704 is divided according to the energy of the predeterminable area around the location information of the reference point and the reference point
Cloth determines the most bright point that reference point described in distance is nearest in the predeterminable area.
As shown in fig. 6, the point on the center line 49 in region 48 is point most bright in predeterminable area 47, further, according to ginseng
The location information of the location information of examination point 44 and the point on the center line 49 in region 48, it may be determined that go out on the center line 49 in region 48
The nearest most bright point of distance reference point 44, it will be understood that nearest most bright of distance reference point 44 on the center line 49 in region 48
Point be by 44 vertical direction of reference point and the intersection point 60 of center line 49.
Step 705, the predeterminable area being adapted to each reference point in the multiple reference point around the reference point
On the middle most bright point nearest apart from the reference point.
For example, reference point 44 will be adapted to the most bright point 60 that distance reference point 44 is nearest on the center line 49 in region 48
On.
The embodiment of the present invention is determined by region shared by lane line described in target image for identifying in lane line
The reference line of heart line, the reference line may deviate from the true center line of the lane line, further with each on the reference line
The Energy distribution of predeterminable area around reference point determines the highest point of energy in the predeterminable area, due in the predeterminable area
The highest point of energy is the point on the center line of lane line, alternatively, the highest point of energy is close to the vehicle in the predeterminable area
The point of the center line of diatom, therefore, the predeterminable area each reference point in multiple reference points being adapted to around the reference point
On the middle highest point of energy, it may make the reference line closer to the center line of lane line, according to the location information of the reference line
When generating electronic map, the accuracy of the position of lane line in the electronic map can be improved.
Fig. 8 is the structural schematic diagram of electronic map lane line correcting device provided in an embodiment of the present invention.The present invention is implemented
The electronic map lane line correcting device that example provides can execute the processing of electronic map lane line modification method embodiment offer
Process, as shown in figure 8, electronic map lane line correcting device 80 includes: to obtain module 81, the first determining module 82, second really
Cover half block 83 and correction module 84;Wherein, module 81 is obtained for obtaining the target image including lane line;First determining module
82, for region shared by the lane line according to the target image, determine reference line, the reference line is for identifying institute
The center line of lane line is stated, the reference line includes multiple reference points;Second determining module 83 is used for according to the multiple reference
The Energy distribution of predeterminable area in point around each reference point determines the highest point of energy in the predeterminable area;Correct mould
Block 84 is used to each reference point in the multiple reference point being adapted in the predeterminable area around the reference point energy most
On high point.
Optionally, the second determining module 83 is specifically used for: centered on each reference point in the multiple reference point, really
The Energy distribution of predeterminable area around the fixed reference point;According to the Energy distribution of the predeterminable area around the reference point,
Determine point most bright in the predeterminable area;Correction module 84 is specifically used for: by each reference point in the multiple reference point
It is adapted on point most bright in the predeterminable area around the reference point.
Optionally, the second determining module 83 is specifically used for: according to the location information of the reference point and the reference point
The Energy distribution of the predeterminable area of surrounding determines the most bright point that reference point described in distance is nearest in the predeterminable area;Amendment
Module 84 is specifically used for: each reference point in the multiple reference point is adapted in the predeterminable area around the reference point
On the most bright point nearest apart from the reference point.
Optionally, the first determining module 82 is specifically used for: according to region shared by lane line described in the target image,
Using machine learning, the reference line is determined.
Optionally, it obtains module 81 to be specifically used for: obtaining the lane including the lane line that detecting devices detects
Three-dimensional point cloud;The three-dimensional point cloud is converted into two-dimensional points cloud;According to the two-dimensional points cloud, the target image is determined.
Optionally, the detecting devices includes following at least one: radar, laser detection equipment.
The electronic map lane line correcting device of embodiment illustrated in fig. 8 can be used for executing the technical side of above method embodiment
Case, it is similar that the realization principle and technical effect are similar, and details are not described herein again.
Fig. 9 is the structural schematic diagram of electronic map lane line corrective provided in an embodiment of the present invention.The present invention is implemented
The electronic map lane line corrective that example provides can execute the processing of electronic map lane line modification method embodiment offer
Process, as shown in figure 9, electronic map lane line corrective 90 includes: memory 91, processor 92, computer program and leads to
Communication interface 93;Wherein, computer program is stored in memory 91, and is configured as executing following operation by processor 92: being obtained
Take the target image including lane line;According to region shared by lane line described in the target image, reference line is determined, it is described
Reference line is used to identify the center line of the lane line, and the reference line includes multiple reference points;According to the multiple reference point
In predeterminable area around each reference point Energy distribution, determine the highest point of energy in the predeterminable area;It will be described more
Each reference point in a reference point is adapted on the highest point of energy in the predeterminable area around the reference point.
Optionally, processor 92 is according to the energy of the predeterminable area around reference point each in the multiple reference point point
Cloth is specifically used for when determining energy highest in the predeterminable area: being with each reference point in the multiple reference point
Center determines the Energy distribution of the predeterminable area around the reference point;According to the energy of the predeterminable area around the reference point
Amount distribution, determines point most bright in the predeterminable area;Processor 92 is repaired by each reference point in the multiple reference point
When just into the predeterminable area around the reference point on the highest point of energy, it is specifically used for: will be in the multiple reference point
Each reference point is adapted on point most bright in the predeterminable area around the reference point.
Optionally, processor 92 determines described default in the Energy distribution according to the predeterminable area around the reference point
In region when most bright point, it is specifically used for: according to the preset areas around the location information of the reference point and the reference point
The Energy distribution in domain determines the most bright point that reference point described in distance is nearest in the predeterminable area;Processor 92 will be will be described
It is specific to use when each reference point in multiple reference points is adapted on point most bright in the predeterminable area around the reference point
In: each reference point in the multiple reference point is adapted in the predeterminable area around the reference point described in distance and is referred to
On the nearest most bright point of point.
Optionally, the region shared by the lane line according to the target image of processor 92, when determining reference line,
It is specifically used for: the reference line is determined using machine learning according to region shared by lane line described in the target image.
Optionally, processor 92 is specifically used for when obtaining includes the target image of lane line: obtaining detecting devices detection
The three-dimensional point cloud in the lane including the lane line arrived;The three-dimensional point cloud is converted into two-dimensional points cloud;According to the two dimension
Point cloud, determines the target image.In some embodiments, processor 92 can receive the detecting devices by communication interface 93
The three-dimensional point cloud sent.
Optionally, the detecting devices includes following at least one: radar, laser detection equipment.
The electronic map lane line corrective of embodiment illustrated in fig. 9 can be used for executing the technical side of above method embodiment
Case, it is similar that the realization principle and technical effect are similar, and details are not described herein again.
In addition, the present embodiment also provides a kind of computer readable storage medium, it is stored thereon with computer program, the meter
Calculation machine program is executed by processor to realize electronic map lane line modification method described in above-described embodiment.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or logical of device or unit
Letter connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
It is each that equipment (can be personal computer, server or the network equipment etc.) or processor (processor) execute the present invention
The part steps of embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-
OnlyMemory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. is various can
To store the medium of program code.
Those skilled in the art can be understood that, for convenience and simplicity of description, only with above-mentioned each functional module
Division progress for example, in practical application, can according to need and above-mentioned function distribution is complete by different functional modules
At the internal structure of device being divided into different functional modules, to complete all or part of the functions described above.On
The specific work process for stating the device of description, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (13)
1. a kind of electronic map lane line modification method characterized by comprising
Obtain the target image including lane line;
According to region shared by lane line described in the target image, determine that reference line, the reference line are described for identifying
The center line of lane line, the reference line include multiple reference points;
According to the Energy distribution of the predeterminable area around reference point each in the multiple reference point, determine in the predeterminable area
The highest point of energy;
It is highest that each reference point in the multiple reference point is adapted to energy in the predeterminable area around the reference point
Point on.
2. the method according to claim 1, wherein described according to reference point week each in the multiple reference point
The Energy distribution of the predeterminable area enclosed determines the highest point of energy in the predeterminable area, comprising:
Centered on each reference point in the multiple reference point, the energy point of the predeterminable area around the reference point is determined
Cloth;
According to the Energy distribution of the predeterminable area around the reference point, point most bright in the predeterminable area is determined;
Each reference point by the multiple reference point is adapted in the predeterminable area around the reference point energy most
On high point, comprising:
Each reference point in the multiple reference point is adapted on point most bright in the predeterminable area around the reference point.
3. according to the method described in claim 2, it is characterized in that, the energy according to the predeterminable area around the reference point
Amount distribution, determines point most bright in the predeterminable area, comprising:
According to the Energy distribution of the predeterminable area around the location information of the reference point and the reference point, determine described pre-
If the nearest most bright point of reference point described in distance in region;
Each reference point by the multiple reference point is adapted to most bright in the predeterminable area around the reference point
Point on, comprising:
Each reference point in the multiple reference point is adapted to ginseng described in distance in the predeterminable area around the reference point
On the nearest most bright point of examination point.
4. method according to claim 1-3, which is characterized in that the vehicle according to the target image
Region shared by diatom, determines reference line, comprising:
The reference line is determined using machine learning according to region shared by lane line described in the target image.
5. the method according to claim 1, wherein described obtain the target image including lane line, comprising:
Obtain the three-dimensional point cloud in the lane including the lane line that detecting devices detects;
The three-dimensional point cloud is converted into two-dimensional points cloud;
According to the two-dimensional points cloud, the target image is determined.
6. according to the method described in claim 5, it is characterized in that, the detecting devices includes following at least one:
Radar, laser detection equipment.
7. a kind of electronic map lane line corrective characterized by comprising
Memory;
Processor;And
Computer program;
Wherein, the computer program stores in the memory, and is configured as executing following operation by the processor:
Obtain the target image including lane line;
According to region shared by lane line described in the target image, determine that reference line, the reference line are described for identifying
The center line of lane line, the reference line include multiple reference points;
According to the Energy distribution of the predeterminable area around reference point each in the multiple reference point, determine in the predeterminable area
The highest point of energy;
It is highest that each reference point in the multiple reference point is adapted to energy in the predeterminable area around the reference point
Point on.
8. electronic map lane line corrective according to claim 7, which is characterized in that the processor is according to institute
The Energy distribution for stating the predeterminable area in multiple reference points around each reference point determines that energy is highest in the predeterminable area
When point, it is specifically used for:
Centered on each reference point in the multiple reference point, the energy point of the predeterminable area around the reference point is determined
Cloth;
According to the Energy distribution of the predeterminable area around the reference point, point most bright in the predeterminable area is determined;
The processor is in the predeterminable area being adapted to each reference point in the multiple reference point around the reference point
When on the middle highest point of energy, it is specifically used for:
Each reference point in the multiple reference point is adapted on point most bright in the predeterminable area around the reference point.
9. electronic map lane line corrective according to claim 8, which is characterized in that the processor is according to institute
The Energy distribution for stating the predeterminable area around reference point is specifically used for when determining point most bright in the predeterminable area:
According to the Energy distribution of the predeterminable area around the location information of the reference point and the reference point, determine described pre-
If the nearest most bright point of reference point described in distance in region;
The processor is in the predeterminable area being adapted to each reference point in the multiple reference point around the reference point
In on most bright point when, be specifically used for:
Each reference point in the multiple reference point is adapted to ginseng described in distance in the predeterminable area around the reference point
On the nearest most bright point of examination point.
10. according to the described in any item electronic map lane line correctives of claim 7-9, which is characterized in that the processing
Device region shared by the lane line according to the target image, when determining reference line, is specifically used for:
The reference line is determined using machine learning according to region shared by lane line described in the target image.
11. electronic map lane line corrective according to claim 7, which is characterized in that the processor is obtaining
When target image including lane line, it is specifically used for:
Obtain the three-dimensional point cloud in the lane including the lane line that detecting devices detects;
The three-dimensional point cloud is converted into two-dimensional points cloud;
According to the two-dimensional points cloud, the target image is determined.
12. electronic map lane line corrective according to claim 11, which is characterized in that the detecting devices includes
It is following at least one:
Radar, laser detection equipment.
13. a kind of computer readable storage medium, which is characterized in that be stored thereon with computer program, the computer program
It is executed by processor to realize as the method according to claim 1 to 6.
Priority Applications (2)
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 |
CN201811286291.XA CN109636820B (en) | 2018-10-31 | 2018-10-31 | Electronic map lane line correction method, device and computer readable storage medium |
Applications Claiming Priority (1)
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 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110673855.0A Division 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 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109636820A true CN109636820A (en) | 2019-04-16 |
CN109636820B CN109636820B (en) | 2021-07-06 |
Family
ID=66067023
Family Applications (2)
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 |
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 |
Family Applications After (1)
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 |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN109636820B (en) |
Cited By (4)
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 |
CN110530398A (en) * | 2019-08-30 | 2019-12-03 | 北京三快在线科技有限公司 | A kind of method and device of electronic map accuracy detection |
CN110539306A (en) * | 2019-09-06 | 2019-12-06 | 广东利元亨智能装备股份有限公司 | Workpiece bonding method and device |
CN113160396A (en) * | 2020-01-23 | 2021-07-23 | 宝马股份公司 | Method for establishing map model, method for generating real-time map and map system |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114387583A (en) * | 2022-01-14 | 2022-04-22 | 广州小鹏自动驾驶科技有限公司 | Method and device for processing lane line |
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 (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103605977A (en) * | 2013-11-05 | 2014-02-26 | 奇瑞汽车股份有限公司 | Extracting method of lane line and device thereof |
US20150169966A1 (en) * | 2012-06-01 | 2015-06-18 | Denso Corporation | Apparatus for detecting boundary line of vehicle lane and method thereof |
CN105528588A (en) * | 2015-12-31 | 2016-04-27 | 百度在线网络技术(北京)有限公司 | Lane line recognition method and device |
CN106570446A (en) * | 2015-10-12 | 2017-04-19 | 腾讯科技(深圳)有限公司 | Lane line extraction method and device |
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 |
CN107341453A (en) * | 2017-06-20 | 2017-11-10 | 北京建筑大学 | A kind of lane line extracting method and device |
CN108470159A (en) * | 2018-03-09 | 2018-08-31 | 腾讯科技(深圳)有限公司 | Lane line data processing method, device, computer equipment and storage medium |
Family Cites Families (15)
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 |
CN102314599A (en) * | 2011-10-11 | 2012-01-11 | 东华大学 | Identification and deviation-detection method for lane |
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 |
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 |
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 |
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 |
-
2018
- 2018-10-31 CN CN201811286291.XA patent/CN109636820B/en active Active
- 2018-10-31 CN CN202110673855.0A patent/CN113408407B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150169966A1 (en) * | 2012-06-01 | 2015-06-18 | Denso Corporation | Apparatus for detecting boundary line of vehicle lane and method thereof |
CN103605977A (en) * | 2013-11-05 | 2014-02-26 | 奇瑞汽车股份有限公司 | Extracting method of lane line and device thereof |
CN106570446A (en) * | 2015-10-12 | 2017-04-19 | 腾讯科技(深圳)有限公司 | Lane line extraction method and device |
CN105528588A (en) * | 2015-12-31 | 2016-04-27 | 百度在线网络技术(北京)有限公司 | Lane line recognition method and device |
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 |
CN107341453A (en) * | 2017-06-20 | 2017-11-10 | 北京建筑大学 | A kind of lane line extracting method and device |
CN108470159A (en) * | 2018-03-09 | 2018-08-31 | 腾讯科技(深圳)有限公司 | Lane line data processing method, device, computer equipment and storage medium |
Non-Patent Citations (2)
Title |
---|
JIANZHUANG WANG ETAL.: "Model-Based Lane Detection and Lane Following for Intelligent Vehicles", 《2010 SECOND INTERNATIONAL CONFERENCE ON INTELLIGENT HUMAN-MACHINE SYSTEMS AND CYBERNETICS》 * |
刘振超等: "水平亮度微分在车道线检测中的使用", 《仪表技术》 * |
Cited By (5)
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 |
CN110530398A (en) * | 2019-08-30 | 2019-12-03 | 北京三快在线科技有限公司 | A kind of method and device of electronic map accuracy detection |
CN110539306A (en) * | 2019-09-06 | 2019-12-06 | 广东利元亨智能装备股份有限公司 | Workpiece bonding method and device |
CN113160396A (en) * | 2020-01-23 | 2021-07-23 | 宝马股份公司 | Method for establishing map model, method for generating real-time map and map system |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN113408407A (en) | 2021-09-17 |
CN113408407B (en) | 2023-06-23 |
CN109636820B (en) | 2021-07-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109636820A (en) | Electronic map lane line modification method, equipment and computer readable storage medium | |
CN108694882B (en) | Method, device and equipment for labeling map | |
CN105512646B (en) | A kind of data processing method, device and terminal | |
CN110458112B (en) | Vehicle detection method and device, computer equipment and readable storage medium | |
CN109993780A (en) | A kind of three-dimensional high-precision ground drawing generating method and device | |
CN106707293A (en) | Obstacle recognition method and device for vehicles | |
CN109271861B (en) | Multi-scale fusion point cloud traffic signboard automatic extraction method | |
CN109931939A (en) | Localization method, device, equipment and the computer readable storage medium of vehicle | |
CN110892760B (en) | Positioning terminal equipment based on deep learning | |
CN110298370A (en) | Network model training method, device and object pose determine method, apparatus | |
US20220414910A1 (en) | Scene contour recognition method and apparatus, computer-readable medium, and electronic device | |
CN113255578B (en) | Traffic identification recognition method and device, electronic equipment and storage medium | |
CN109492688B (en) | Weld joint tracking method and device and computer readable storage medium | |
EP4027299A8 (en) | Method and apparatus for generating depth map, and storage medium | |
CN110222641B (en) | Method and apparatus for recognizing image | |
CN110751040B (en) | Three-dimensional object detection method and device, electronic equipment and storage medium | |
CN114004882A (en) | Two-dimensional map generation method and device, terminal equipment and storage medium | |
JP2013064733A (en) | Columnar object extraction method, columnar object extraction program and columnar object extraction device | |
CN110807431A (en) | Object positioning method and device, electronic equipment and storage medium | |
CN104423142B (en) | Calibration data collection method and system for optical proximity correction model | |
CN106980851A (en) | A kind of localization method and device of data matrix DM codes | |
CN112183381A (en) | Method and device for detecting driving area of vehicle | |
KR20200076628A (en) | Location measuring method of mobile device, location measuring device and electronic device | |
CN106909916A (en) | A kind of method based on cell phone platform quick detection with identification pavement zebra stripes | |
CN113448340B (en) | Unmanned aerial vehicle path planning method and device, unmanned aerial vehicle and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |