CN109858374A - Arrow class graticule extraction method and device in high-precision cartography - Google Patents
Arrow class graticule extraction method and device in high-precision cartography Download PDFInfo
- Publication number
- CN109858374A CN109858374A CN201811650011.9A CN201811650011A CN109858374A CN 109858374 A CN109858374 A CN 109858374A CN 201811650011 A CN201811650011 A CN 201811650011A CN 109858374 A CN109858374 A CN 109858374A
- Authority
- CN
- China
- Prior art keywords
- arrow
- point
- point cloud
- target
- cloud
- 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
Landscapes
- Image Analysis (AREA)
Abstract
The embodiment of the present invention provides arrow class graticule extraction method and device in high-precision cartography, use three dimensional point cloud as input, it is end-to-end to automatically extract arrow target form point, arrow form point is effectively extracted using the method that image key points return, guarantees that arrow extraction accuracy meets high-precision cartography demand；Point of use cloud semantic segmentation obtains high-level semantic relation scene understanding, boosting algorithm robustness；The precision and high-precision map automated production efficiency of arrow category line drawing can be effectively improved, artificial mark workload is reduced.
Description
Technical field
The present embodiments relate to high-precision map manufacture technology fields, more particularly, to a kind of high-precision map system
Arrow class graticule extraction method and device in work.
Background technique
The invention of automobile changes the trip mode of the mankind, it effectively pushes commodity and people with its convenience and rapidity
The flowing of member, plays an important role to the development of economy and society.With the continuous development of production technology, new production method subtracts
The production of units time for having lacked automobile, the unit price of automobile is reduced, so that automobile becomes a kind of mass product.By
2010, there are about the various automobiles that sum is 1,000,000,000 in the whole world, and this number is still growing at top speed.However, along with vapour
The increase of vehicle ownership, traffic safety problem are more prominent.In Chinese annual generation 50 Wan Yuqi of traffic accident, traffic accident is dead
Dying number is more than 100,000 people, every year because the economic loss of traffic accident initiation is up to tens billion of members.
Currently, every country has carried out the research of automatic driving vehicle in succession, but it is constrained to the development of technology, machine
Replace the mankind to complete vehicle drive completely and also needs a period of time.The intelligent vehicle of this life often uses DAS (Driver Assistant System)
Guarantee the safety of driver.Such as can have been seen in high-end vehicle automatic parking auxiliary system, brake assist system,
Reversing aid system, driving auxiliary system, lane keep auxiliary system etc..Wherein the key technology of lane holding auxiliary system is
The detection of roadmarking can calculate the positional relationship of vehicle and roadmarking by it, and then can remind driver's vehicle
Driving status, can effectively relieving fatigue drive or human negligence and the route deviation problem that generates, increase safety.
High-precision map is one of unmanned core technology, and accurately map to unmanned vehicle positioning, navigation and controls, and
Safety is most important.High-precision map includes a large amount of driving auxiliary informations, wherein most importantly three-dimensional characterization accurate to road network
(centimetre class precision).For example, the geometry on road surface, the position of road traffic marking, the point cloud model etc. of peripheral path environment.
Wherein, road traffic marking is to be drawn by mark in various lines, arrow, text, object marking, protuberant guide post and profile on road surface
The traffic safety facilities that mark etc. is constituted, its effect are control and guidance traffic.
Summary of the invention
The present invention provides a kind of high-precision cartography for overcoming the above problem or at least being partially solved the above problem
Middle arrow class graticule extraction method and device.
In a first aspect, the embodiment of the present invention provides arrow class graticule extraction method in a kind of high-precision cartography,
Include:
The three dimensional point cloud of road scene in ground high-precision figure production is obtained, and based on the point cloud semantic segmentation trained
Model obtains constituting the target point cloud of arrow target；
Arrow image is generated based on the target point cloud rectangular projection, arrow is obtained based on the key point regression model trained
The image coordinate of arrow form point in head image, and rectangular projection inverse transformation is carried out to the arrow-shaped point, it obtains arrow form point and exists
Point cloud coordinate in target point cloud extracts arrow target based on described cloud coordinate.
Preferably, obtaining the three dimensional point cloud of road scene in cartography, specifically include:
The three dimensional point cloud of road scene is obtained based on scanning laser radar:
P={ pk=(xk, yk, zk, ik), 1≤k≤n }
In formula, pkFor a single point, (xk, yk, zk) it is point coordinate, ikFor intensity, k is serial number a little, and n is number a little.
Preferably, and obtaining the target point cloud of composition arrow target based on the point cloud semantic segmentation model trained
Before, further includes:
Mark the arrow form point of arrow target in the three dimensional point cloud of road scene；
It only include the target point cloud of arrow target based on arrow form point interception；
Rectangular projection is carried out to the target point cloud and generates arrow image, the point cloud coordinate of target point cloud is converted into arrow
The image coordinate of image.
Preferably, after carrying out rectangular projection generation arrow image to the target point cloud, further includes:
Arrow form point coordinate is converted into image coordinate as the corresponding markup information of rectangular projection, makes training set；
Thermodynamic chart regression training is carried out based on convolutional neural networks CNN model, is obtained for extracting arrow in arrow image
The key point regression model of form point image coordinate.
Preferably, after marking the arrow form point of arrow target in the three dimensional point cloud, further includes:
Based on the arrow form point making point cloud semantic segmentation data set of mark arrow target, it is based on described cloud semantic segmentation
Data set carries out deep learning training, obtains a cloud semantic segmentation model.
Preferably, marking the arrow form point of arrow target in the three dimensional point cloud, specifically include:
Based on an arrow form point for cloud interactive mode annotation tool mark arrow target, the mark of each arrow form point is believed
Breath is Lc={ (xj, yj, zj), 1≤j≤m }, wherein c is mark classification, (xj, yj, zj) it is mark coordinate, j is form point serial number,
M is form point number.
Preferably, being specifically included based on arrow form point interception only comprising the target point cloud of arrow target:
Arrow form point based on mark constitutes minimum external cube, will be described with the center of the external cube of minimum
Flare factor of the minimum external cube in ± X, ± Y and ± Z-direction expansion, ± X, ± Y and ± Z-direction be respectively α, β and
γ；
Based on the cube intercept point cloud after expansion, target point cloud is obtained.
Second aspect, the embodiment of the present invention provide arrow class graticule automatic extracting device in a kind of high-precision cartography,
Include:
First module, for obtaining the three dimensional point cloud of road scene in cartography, and based on the point cloud trained
Semantic segmentation model obtains constituting the target point cloud of arrow target；
Second module, for generating arrow image based on the target point cloud rectangular projection, based on the key point trained
Regression model obtains the image coordinate of arrow form point in arrow image, and carries out rectangular projection inverse transformation to the arrow-shaped point,
Point cloud coordinate of the arrow form point in target point cloud is obtained, arrow target is extracted based on described cloud coordinate.
The third aspect, the embodiment of the present invention provides a kind of electronic equipment, including memory, processor and is stored in memory
Computer program that is upper and can running on a processor, is realized when the processor executes described program as first aspect provides
Method the step of.
Fourth aspect, the embodiment of the present invention provide a kind of non-transient computer readable storage medium, are stored thereon with calculating
Machine program is realized as provided by first aspect when the computer program is executed by processor the step of method.
The embodiment of the present invention proposes arrow class graticule extraction method and device in high-precision cartography, uses three
It ties up point cloud data and is used as input, it is end-to-end to automatically extract arrow target form point, it is effectively mentioned using the method that image key points return
Arrow form point is taken, guarantees that arrow extraction accuracy meets high-precision cartography demand；Point of use cloud semantic segmentation obtains high-level language
Adopted relationship scene understanding, boosting algorithm robustness；Precision and the high-precision map that arrow category line drawing can be effectively improved are automatic
Change producing efficiency, reduces artificial mark workload.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is according to arrow class graticule extraction method schematic diagram in the high-precision cartography of the embodiment of the present invention；
Fig. 2 is according to arrow class graticule extraction method detailed process in the high-precision cartography of the embodiment of the present invention
Schematic diagram；
Fig. 3 is according to arrow class graticule automatic extracting device schematic diagram in the high-precision cartography of the embodiment of the present invention；
Fig. 4 is the entity structure schematic diagram according to the electronic equipment of the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
In road safety assessment and emulation field, vehicle-mounted laser point cloud measuring system, which has been obtained, to be widely applied.Base
In the outdoor scene scene of 360 ° of distant view photographs production, so that road environment visualization is truer, and road color laser point cloud number
According to matching fusion, then create measuring for road visible environment.Among these, the extraction of graticule facilitates in road
Textures, analysis and safety evaluation are carried out in scalable 360 ° of outdoor scenes.However, current point cloud data format is different, mostly
Number needs to rely on expensive measuring devices, set about designing from the design of equipment it is enough get parms, which increase problems
Complexity.Roadmarking data are quickly and effectively extracted from the routine data of cloud, are become instantly urgently to be resolved and are asked
Topic.
Therefore various embodiments of the present invention provide arrow class graticule extraction method and dress in a kind of high-precision cartography
It sets, the precision and high-precision map automated production efficiency of arrow category line drawing can be effectively improved.Multiple realities will be passed through below
It applies example and carries out expansion explanation and introduction.
Fig. 1 is arrow class graticule extraction method in a kind of high-precision cartography provided in an embodiment of the present invention, packet
It includes:
S1, the three dimensional point cloud for obtaining road scene in high-precision cartography, and based on the point Yun Yuyi trained
Parted pattern obtains constituting the target point cloud of arrow target；
S2, arrow image is generated based on the target point cloud rectangular projection, is obtained based on the key point regression model trained
The image coordinate of arrow form point into arrow image, and rectangular projection inverse transformation is carried out to the arrow-shaped point, obtain arrow-shaped
Point cloud coordinate of the point in target point cloud extracts arrow target based on described cloud coordinate.
In the present embodiment, use three dimensional point cloud as input, it is end-to-end to automatically extract arrow target form point, use
The method that image key points return effectively extracts arrow form point, guarantees that arrow extraction accuracy meets high-precision cartography demand；Make
High-level semantic relation scene understanding, boosting algorithm robustness are obtained with cloud semantic segmentation；Arrow class graticule can be effectively improved
The precision of extraction and high-precision map automated production efficiency reduce artificial mark workload.
On the basis of the above embodiments, the three dimensional point cloud for obtaining road scene in cartography, specifically includes:
The three dimensional point cloud of road scene is obtained based on scanning laser radar:
P={ pk=(xk, yk, zk, ik), 1≤k≤n }
In formula, pkFor a single point, (xk, yk, zk) it is point coordinate, ikFor intensity, k is serial number a little, and n is number a little.
In the present embodiment, the means mentioned by three-dimensional laser scanning technique as link characteristic information, it can be straight
It connects and carries out quickly reverse three dimensional data collection and model reconstruction from material object, so that it is real completely, accurately to rebuild scanning
Object and it is quickly obtained original surveying and mapping data.Coordinate information, color rgb value and the roadmarking distribution spy of the road data point of acquisition
Link characteristic information automation is extracted in sign, position etc., identification is of great significance.
On the basis of the various embodiments described above, as shown in Fig. 2, and obtaining structure based on the point cloud semantic segmentation model trained
Before the target point cloud of arrow target, further includes:
Mark the arrow form point of arrow target in the three dimensional point cloud of road scene；
It only include the target point cloud of arrow target based on arrow form point interception；
Rectangular projection is carried out to the target point cloud and generates arrow image, the point cloud coordinate of target point cloud is converted into arrow
The image coordinate of image.
On the basis of the various embodiments described above, after carrying out rectangular projection generation arrow image to the target point cloud, also wrap
It includes:
Arrow form point coordinate is converted into image coordinate as the corresponding markup information of rectangular projection, makes training set；
Thermodynamic chart regression training is carried out based on convolutional neural networks CNN model, is obtained for extracting arrow in arrow image
The key point regression model of form point image coordinate.
On the basis of the various embodiments described above, after the arrow form point for marking arrow target in the three dimensional point cloud, also
Include:
Based on the arrow form point making point cloud semantic segmentation data set of mark arrow target, it is based on described cloud semantic segmentation
Data set carries out deep learning training, obtains a cloud semantic segmentation model.
On the basis of the various embodiments described above, the arrow form point of arrow target in the three dimensional point cloud is marked, specifically
Include:
Based on an arrow form point for cloud interactive mode annotation tool mark arrow target, the mark of each arrow form point is believed
Breath is Lc={ (xj, yj, zj), 1≤j≤m }, wherein c is mark classification, (xj, yj, zj) it is mark coordinate, j is form point serial number,
M is form point number.
It only include the target point cloud of arrow target based on the arrow form point interception on the basis of the various embodiments described above,
It specifically includes:
Arrow form point based on mark constitutes minimum external cube, will be described with the center of the external cube of minimum
Flare factor of the minimum external cube in ± X, ± Y and ± Z-direction expansion, ± X, ± Y and ± Z-direction be respectively α, β and
γ；
Based on the cube intercept point cloud after expansion, target point cloud is obtained.Three-dimensional point is intercepted by the cube after expansion
Cloud data obtain target point cloud.
The present embodiment also provides arrow class graticule automatic extracting device in a kind of high-precision cartography, is based on above-mentioned each reality
Arrow class graticule extraction method in the high-precision cartography in example is applied, as shown in figure 3, including the first module 30 and second
Module 40, in which:
First module 30 obtains the three dimensional point cloud of road scene in cartography, and based on the point Yun Yuyi trained
Parted pattern obtains constituting the target point cloud of arrow target；
Second module 40 is based on the target point cloud rectangular projection and generates arrow image, is returned based on the key point trained
Model obtains the image coordinate of arrow form point in arrow image, and carries out rectangular projection inverse transformation to the arrow-shaped point, obtains
Point cloud coordinate of the arrow form point in target point cloud extracts arrow target based on described cloud coordinate.
Fig. 4 is the entity structure schematic diagram of electronic equipment provided in an embodiment of the present invention, as shown in figure 4, the electronic equipment
It may include: processor (processor) 810,820, memory communication interface (Communications Interface)
(memory) 830 and communication bus 840, wherein processor 810, communication interface 820, memory 830 pass through communication bus 840
Complete mutual communication.Processor 810 can call the meter that is stored on memory 830 and can run on processor 810
Calculation machine program, to execute arrow class graticule extraction method in the high-precision cartography that the various embodiments described above provide, such as
Include:
S1, the three dimensional point cloud for obtaining road scene in cartography, and based on the point cloud semantic segmentation mould trained
Type obtains constituting the target point cloud of arrow target；
S2, arrow image is generated based on the target point cloud rectangular projection, is obtained based on the key point regression model trained
The image coordinate of arrow form point into arrow image, and rectangular projection inverse transformation is carried out to the arrow-shaped point, obtain arrow-shaped
Point cloud coordinate of the point in target point cloud extracts arrow target based on described cloud coordinate.
In addition, the logical order in above-mentioned memory 830 can be realized by way of SFU software functional unit and conduct
Independent product when selling or using, can store in a computer readable storage medium.Based on this understanding, originally
The technical solution of the inventive embodiments substantially part of the part that contributes to existing technology or the technical solution in other words
It can be embodied in the form of software products, which is stored in a storage medium, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes the present invention respectively
The all or part of the steps of a embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory
(ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk
Etc. the various media that can store program code.
The embodiment of the present invention also provides a kind of non-transient computer readable storage medium, is stored thereon with computer program,
The computer program is implemented to carry out arrow class in the high-precision cartography of the various embodiments described above offer when being executed by processor
Graticule extraction method, for example,
S1, the three dimensional point cloud for obtaining road scene in cartography, and based on the point cloud semantic segmentation mould trained
Type obtains constituting the target point cloud of arrow target；
S2, arrow image is generated based on the target point cloud rectangular projection, is obtained based on the key point regression model trained
The image coordinate of arrow form point into arrow image, and rectangular projection inverse transformation is carried out to the arrow-shaped point, obtain arrow-shaped
Point cloud coordinate of the point in target point cloud extracts arrow target based on described cloud coordinate.
The embodiment of the present invention also provides the present embodiment and discloses a kind of computer program product, the computer program product packet
The computer program being stored in non-transient computer readable storage medium is included, the computer program includes program instruction, when
Described program instruction is when being computer-executed, computer be able to carry out as in above-mentioned high-precision cartography arrow class graticule from
Dynamic extracting method, for example,
S1, the three dimensional point cloud for obtaining road scene in cartography, and based on the point cloud semantic segmentation mould trained
Type obtains constituting the target point cloud of arrow target；
S2, arrow image is generated based on the target point cloud rectangular projection, is obtained based on the key point regression model trained
The image coordinate of arrow form point into arrow image, and rectangular projection inverse transformation is carried out to the arrow-shaped point, obtain arrow-shaped
Point cloud coordinate of the point in target point cloud extracts arrow target based on described cloud coordinate.
In conclusion arrow class graticule extraction method and dress in high-precision cartography provided in an embodiment of the present invention
It sets, uses three dimensional point cloud as input, end-to-end to automatically extract arrow target form point, the side returned using image key points
Method effectively extracts arrow form point, guarantees that arrow extraction accuracy meets high-precision cartography demand；Point of use cloud semantic segmentation obtains
High-level semantic relation scene understanding, boosting algorithm robustness；The precision of arrow category line drawing and high-precision can be effectively improved
Map automated production efficiency reduces artificial mark workload.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. arrow class graticule extraction method in a kind of high-precision cartography characterized by comprising
The three dimensional point cloud of road scene in high-precision cartography is obtained, and based on the point cloud semantic segmentation model trained
Obtain constituting the target point cloud of arrow target；
Arrow image is generated based on the target point cloud rectangular projection, arrow plot is obtained based on the key point regression model trained
The image coordinate of arrow form point as in, and rectangular projection inverse transformation is carried out to the arrow-shaped point, arrow form point is obtained in target
Point cloud coordinate in point cloud extracts arrow target based on described cloud coordinate.
2. arrow class graticule extraction method in high-precision cartography according to claim 1, which is characterized in that obtain
The three dimensional point cloud for taking road scene in cartography, specifically includes:
The three dimensional point cloud of road scene is obtained based on scanning laser radar:
P={ pk=(xk, yk, zk, ik), 1≤k≤n }
In formula, pkFor a single point, (xk, yk, zk) it is point coordinate, ikFor intensity, k is serial number a little, and n is number a little.
3. arrow class graticule extraction method in high-precision cartography according to claim 1, which is characterized in that simultaneously
Before obtaining the target point cloud of composition arrow target based on the point cloud semantic segmentation model trained, further includes:
Mark the arrow form point of arrow target in the three dimensional point cloud of road scene；
It only include the target point cloud of arrow target based on arrow form point interception；
Rectangular projection is carried out to the target point cloud and generates arrow image, the point cloud coordinate of target point cloud is converted into arrow image
Image coordinate.
4. arrow class graticule extraction method in high-precision cartography according to claim 3, which is characterized in that right
After the target point cloud carries out rectangular projection generation arrow image, further includes:
Arrow form point coordinate is converted into image coordinate as the corresponding markup information of rectangular projection, makes training set；
Thermodynamic chart regression training is carried out based on convolutional neural networks CNN model, is obtained for extracting arrow form point in arrow image
The key point regression model of image coordinate.
5. arrow class graticule extraction method in high-precision cartography according to claim 3, which is characterized in that mark
After the arrow form point for infusing arrow target in the three dimensional point cloud, further includes:
Based on the arrow form point making point cloud semantic segmentation data set of mark arrow target, it is based on described cloud semantic segmentation data
Collection carries out deep learning training, obtains a cloud semantic segmentation model.
6. arrow class graticule extraction method in high-precision cartography according to claim 3, which is characterized in that mark
The arrow form point for infusing arrow target in the three dimensional point cloud, specifically includes:
Based on an arrow form point for cloud interactive mode annotation tool mark arrow target, the markup information to each arrow form point is
Lc={ (xj, yj, zj), 1≤j≤m }, wherein c is mark classification, (xj, yj, zj) it is mark coordinate, j is form point serial number, and m is
Form point number.
7. arrow class graticule extraction method in high-precision cartography according to claim 3, which is characterized in that base
In the target point cloud that arrow form point interception only includes arrow target, specifically include:
Arrow form point based on mark constitutes minimum external cube, with the center of the external cube of minimum by the minimum
External cube is expanded in ± X, ± Y and ± Z-direction, and the flare factor in ± X, ± Y and ± Z-direction is respectively α, β and γ；
Based on the cube intercept point cloud after expansion, target point cloud is obtained.
8. arrow class graticule automatic extracting device in a kind of high-precision cartography characterized by comprising
First module, for obtaining the three dimensional point cloud of road scene in cartography, and based on the point Yun Yuyi trained
Parted pattern obtains constituting the target point cloud of arrow target；
Second module is returned for generating arrow image based on the target point cloud rectangular projection based on the key point trained
Model obtains the image coordinate of arrow form point in arrow image, and carries out rectangular projection inverse transformation to the arrow-shaped point, obtains
Point cloud coordinate of the arrow form point in target point cloud extracts arrow target based on described cloud coordinate.
9. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor realizes method as described in any one of claim 1 to 7 when executing described program
The step of.
10. a kind of non-transient computer readable storage medium, is stored thereon with computer program, which is characterized in that the calculating
The step of machine program realizes method as described in any one of claim 1 to 7 when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811650011.9A CN109858374B (en) | 2018-12-31 | 2018-12-31 | Automatic extraction method and device for arrow mark lines in high-precision map making |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811650011.9A CN109858374B (en) | 2018-12-31 | 2018-12-31 | Automatic extraction method and device for arrow mark lines in high-precision map making |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109858374A true CN109858374A (en) | 2019-06-07 |
| CN109858374B CN109858374B (en) | 2021-08-17 |
Family
ID=66893568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811650011.9A Active CN109858374B (en) | 2018-12-31 | 2018-12-31 | Automatic extraction method and device for arrow mark lines in high-precision map making |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109858374B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192311A (en) * | 2019-12-31 | 2020-05-22 | 武汉中海庭数据技术有限公司 | Automatic extraction method and device for longitudinal deceleration marked line in high-precision map making |
| CN111209826A (en) * | 2019-12-31 | 2020-05-29 | 武汉中海庭数据技术有限公司 | Semi-automatic point cloud extraction method and device for high-precision map guardrail |
| CN111210456A (en) * | 2019-12-31 | 2020-05-29 | 武汉中海庭数据技术有限公司 | High-precision direction arrow extraction method and system based on point cloud |
| CN111652179A (en) * | 2020-06-15 | 2020-09-11 | 东风汽车股份有限公司 | Semantic high-precision map construction and positioning method based on dotted line feature fusion laser |
| CN111932621A (en) * | 2020-08-07 | 2020-11-13 | 武汉中海庭数据技术有限公司 | Method and device for evaluating arrow extraction confidence |
| CN112258519A (en) * | 2020-10-12 | 2021-01-22 | 武汉中海庭数据技术有限公司 | Automatic extraction method and device for way-giving line of road in high-precision map making |
| CN113569652A (en) * | 2021-06-30 | 2021-10-29 | 惠州市德赛西威智能交通技术研究院有限公司 | Method for detecting short obstacles by automatic parking all-round looking camera |
| CN114120349A (en) * | 2022-01-10 | 2022-03-01 | 深圳市菁优智慧教育股份有限公司 | Test paper identification method and system based on deep learning |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103226833A (en) * | 2013-05-08 | 2013-07-31 | 清华大学 | Point cloud data partitioning method based on three-dimensional laser radar |
| US20140233808A1 (en) * | 2013-02-15 | 2014-08-21 | Gordon Peckover | Method of measuring road markings |
| CN105426861A (en) * | 2015-12-02 | 2016-03-23 | 百度在线网络技术（北京）有限公司 | Method and device for determining lane line |
| CN105957145A (en) * | 2016-04-29 | 2016-09-21 | 百度在线网络技术（北京）有限公司 | Road barrier identification method and device |
| US20170039436A1 (en) * | 2015-08-03 | 2017-02-09 | Nokia Technologies Oy | Fusion of RGB Images and Lidar Data for Lane Classification |
| CN107093210A (en) * | 2017-04-20 | 2017-08-25 | 北京图森未来科技有限公司 | A kind of laser point cloud mask method and device |
| CN108090423A (en) * | 2017-12-01 | 2018-05-29 | 上海工程技术大学 | A kind of depth detection method of license plate returned based on thermodynamic chart and key point |
| US20180181817A1 (en) * | 2015-09-10 | 2018-06-28 | Baidu Online Network Technology (Beijing) Co., Ltd. | Vehicular lane line data processing method, apparatus, storage medium, and device |
| CN108319957A (en) * | 2018-02-09 | 2018-07-24 | 深圳市唯特视科技有限公司 | A kind of large-scale point cloud semantic segmentation method based on overtrick figure |
| CN108415032A (en) * | 2018-03-05 | 2018-08-17 | 中山大学 | A kind of point cloud semanteme map constructing method based on deep learning and laser radar |
| 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 |
| CN108564874A (en) * | 2018-05-07 | 2018-09-21 | 腾讯大地通途（北京）科技有限公司 | Method, the method for model training, equipment and the storage medium of surface mark extraction |
| CN109073404A (en) * | 2016-05-02 | 2018-12-21 | 谷歌有限责任公司 | For the system and method based on terrestrial reference and real time image generation navigation direction |
-
2018
- 2018-12-31 CN CN201811650011.9A patent/CN109858374B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140233808A1 (en) * | 2013-02-15 | 2014-08-21 | Gordon Peckover | Method of measuring road markings |
| CN103226833A (en) * | 2013-05-08 | 2013-07-31 | 清华大学 | Point cloud data partitioning method based on three-dimensional laser radar |
| US20170039436A1 (en) * | 2015-08-03 | 2017-02-09 | Nokia Technologies Oy | Fusion of RGB Images and Lidar Data for Lane Classification |
| US20180181817A1 (en) * | 2015-09-10 | 2018-06-28 | Baidu Online Network Technology (Beijing) Co., Ltd. | Vehicular lane line data processing method, apparatus, storage medium, and device |
| CN105426861A (en) * | 2015-12-02 | 2016-03-23 | 百度在线网络技术（北京）有限公司 | Method and device for determining lane line |
| CN105957145A (en) * | 2016-04-29 | 2016-09-21 | 百度在线网络技术（北京）有限公司 | Road barrier identification method and device |
| CN109073404A (en) * | 2016-05-02 | 2018-12-21 | 谷歌有限责任公司 | For the system and method based on terrestrial reference and real time image generation navigation direction |
| CN107093210A (en) * | 2017-04-20 | 2017-08-25 | 北京图森未来科技有限公司 | A kind of laser point cloud mask method and device |
| CN108090423A (en) * | 2017-12-01 | 2018-05-29 | 上海工程技术大学 | A kind of depth detection method of license plate returned based on thermodynamic chart and key point |
| CN108319957A (en) * | 2018-02-09 | 2018-07-24 | 深圳市唯特视科技有限公司 | A kind of large-scale point cloud semantic segmentation method based on overtrick figure |
| CN108415032A (en) * | 2018-03-05 | 2018-08-17 | 中山大学 | A kind of point cloud semanteme map constructing method based on deep learning and laser radar |
| 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 |
| CN108564874A (en) * | 2018-05-07 | 2018-09-21 | 腾讯大地通途（北京）科技有限公司 | Method, the method for model training, equipment and the storage medium of surface mark extraction |
Non-Patent Citations (5)
| Title |
|---|
| LINHUI LI 等: "Dense 3D Semantic SLAM of traffic environment based on stereo vision", 《2018 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV)》 * |
| LYNE P. TCHAPMI, 等: "SEGCloud: Semantic Segmentation of 3D Point Clouds", 《2017 INTERNATIONAL CONFERENCE ON 3D VISION (3DV)》 * |
| 万国伟: "面向建筑物的三维点云生成、增强和重建技术研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
| 陈永辉: "基于激光扫描的三维点云数据处理技术研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
| 高阳 等: "车载激光彩色点云的道路标志线提取方法", 《测绘通报》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111192311B (en) * | 2019-12-31 | 2022-05-17 | 武汉中海庭数据技术有限公司 | Automatic extraction method and device for longitudinal deceleration marked line in high-precision map making |
| CN111209826A (en) * | 2019-12-31 | 2020-05-29 | 武汉中海庭数据技术有限公司 | Semi-automatic point cloud extraction method and device for high-precision map guardrail |
| CN111210456A (en) * | 2019-12-31 | 2020-05-29 | 武汉中海庭数据技术有限公司 | High-precision direction arrow extraction method and system based on point cloud |
| CN111192311A (en) * | 2019-12-31 | 2020-05-22 | 武汉中海庭数据技术有限公司 | Automatic extraction method and device for longitudinal deceleration marked line in high-precision map making |
| CN111210456B (en) * | 2019-12-31 | 2023-03-10 | 武汉中海庭数据技术有限公司 | High-precision direction arrow extraction method and system based on point cloud |
| CN111209826B (en) * | 2019-12-31 | 2022-05-27 | 武汉中海庭数据技术有限公司 | Semi-automatic point cloud extraction method and device for high-precision map guardrail |
| CN111652179A (en) * | 2020-06-15 | 2020-09-11 | 东风汽车股份有限公司 | Semantic high-precision map construction and positioning method based on dotted line feature fusion laser |
| CN111652179B (en) * | 2020-06-15 | 2024-01-09 | 东风汽车股份有限公司 | Semantic high-precision map construction and positioning method based on point-line feature fusion laser |
| CN111932621B (en) * | 2020-08-07 | 2022-06-17 | 武汉中海庭数据技术有限公司 | Method and device for evaluating arrow extraction confidence |
| CN111932621A (en) * | 2020-08-07 | 2020-11-13 | 武汉中海庭数据技术有限公司 | Method and device for evaluating arrow extraction confidence |
| CN112258519A (en) * | 2020-10-12 | 2021-01-22 | 武汉中海庭数据技术有限公司 | Automatic extraction method and device for way-giving line of road in high-precision map making |
| CN112258519B (en) * | 2020-10-12 | 2022-09-20 | 武汉中海庭数据技术有限公司 | Automatic extraction method and device for way-giving line of road in high-precision map making |
| CN113569652A (en) * | 2021-06-30 | 2021-10-29 | 惠州市德赛西威智能交通技术研究院有限公司 | Method for detecting short obstacles by automatic parking all-round looking camera |
| CN114120349A (en) * | 2022-01-10 | 2022-03-01 | 深圳市菁优智慧教育股份有限公司 | Test paper identification method and system based on deep learning |
| CN114120349B (en) * | 2022-01-10 | 2022-05-03 | 深圳市菁优智慧教育股份有限公司 | Test paper identification method and system based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109858374B (en) | 2021-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109858374A (en) | Arrow class graticule extraction method and device in high-precision cartography | |
| US10643378B2 (en) | Method and device for modelling three-dimensional road model, and storage medium | |
| US7881915B2 (en) | System and method for collecting and modeling object simulation data | |
| Essa et al. | Simulated traffic conflicts: do they accurately represent field-measured conflicts? | |
| CN113899384B (en) | Method, device, apparatus, medium, and program for displaying intersection surface of lane-level road | |
| CN111123920A (en) | Method and device for generating automatic driving simulation test scene | |
| CN108470159A (en) | Lane line data processing method, device, computer equipment and storage medium | |
| CN108921200A (en) | Method, apparatus, equipment and medium for classifying to Driving Scene data | |
| CN113009506B (en) | Virtual-real combined real-time laser radar data generation method, system and equipment | |
| CN109993064B (en) | Method for extracting connection path between road network nodes in picture | |
| CN110345951A (en) | A kind of ADAS accurately map generalization method and device | |
| CN116529784A (en) | Method and system for adding lidar data | |
| CN113358125B (en) | Navigation method and system based on environment target detection and environment target map | |
| JP2022522385A (en) | Road sign recognition methods, map generation methods, and related products | |
| CN104281746A (en) | Method for generating traffic safety road characteristic graphs on basis of point-cloud | |
| CN109101743A (en) | A kind of construction method of high-precision road net model | |
| CN110363771A (en) | A kind of isolation guardrail form point extracting method and device based on three dimensional point cloud | |
| CN113792061A (en) | Map data updating method and device and electronic equipment | |
| CN112801236A (en) | Image recognition model migration method, device, equipment and storage medium | |
| CN104613970B (en) | The data creation method and client of a kind of analogue navigation | |
| CN106931988A (en) | Show the true three-dimensional navigation method and system of guideboard | |
| CN112529116B (en) | Scene element fusion processing method, device and equipment and computer storage medium | |
| CN114987495A (en) | Man-machine hybrid decision-making method for highly automatic driving | |
| Zhang | Traffic Sign Detection Based on YOLO v3 | |
| Zhao et al. | Point Cloud Automatic Annotation Framework for Autonomous Driving |
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 |