CN108573272A - Track approximating method - Google Patents
Track approximating method Download PDFInfo
- Publication number
- CN108573272A CN108573272A CN201711346608.XA CN201711346608A CN108573272A CN 108573272 A CN108573272 A CN 108573272A CN 201711346608 A CN201711346608 A CN 201711346608A CN 108573272 A CN108573272 A CN 108573272A
- Authority
- CN
- China
- Prior art keywords
- track
- coordinate
- peripheral
- model
- coordinate set
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000003068 static effect Effects 0.000 claims abstract description 21
- 230000002093 peripheral effect Effects 0.000 claims description 85
- 230000008859 change Effects 0.000 claims description 15
- 238000013461 design Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- VIKNJXKGJWUCNN-XGXHKTLJSA-N norethisterone Chemical compound O=C1CC[C@@H]2[C@H]3CC[C@](C)([C@](CC4)(O)C#C)[C@@H]4[C@@H]3CCC2=C1 VIKNJXKGJWUCNN-XGXHKTLJSA-N 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention relates to a kind of track approximating methods, including:Coordinate of at least one static object in roadside relative to the position of vehicle is acquired in real time using trailer-mounted radar sensor;Based on at least first part of the first coordinate set track periphery model is established, and track periphery model is verified or update based on at least second part of the first coordinate set, to form the second coordinate set;And lane line is fitted based on the second coordinate set.This method can more accurately calculate lane boundary information, be travelled in lane boundary always to help to control vehicle, this improves the safety of driving, meanwhile, also improve the usage experience of user.
Description
Technical field
The present invention relates to auxiliary driving technology fields, more specifically to a kind of track approximating method.
Background technology
In the prior art, automatic Pilot and auxiliary driving product are largely view-based access control model sensors to carry out letter to track
Breath acquisition and model definition, to realize the functionality of automatic Pilot or auxiliary driving.But these methods have great limitation
Property, in the actual environment, lane line complexity is various, cuts in and out, merely using visual information come determine track can give drive automatically
It sails and brings uncertainty.
Invention content
The purpose of the present invention is to provide a kind of track approximating methods that can overcome above-mentioned prior art shortcoming.
To achieve the above object, it is as follows to provide a kind of technical solution by the present invention:
A kind of track approximating method, including:A), at least one static state in roadside is acquired in real time using trailer-mounted radar sensor
Coordinate of the target relative to the position of vehicle, to form original coordinates set;B), at least first based on the first coordinate set
Point establish track periphery model, and boxing outside track is verified or update based on at least second part of the first coordinate set
Type, to form the second coordinate set;Wherein, the first coordinate set is converted through coordinate system by original coordinates set and is formed, and second sits
Mark set includes the corresponding track peripheral point of track periphery model, and first part is different from second part;And c), based on the
Two coordinate sets are fitted lane line.
Preferably, coordinate system, which is converted, includes:Obtain vehicle first time to during the second time velocity information and side
To information;Velocity information and directional information are converted into vehicle body change in location information and vehicle body angle change information;And with vehicle
The parameter that body change in location information and vehicle body angle change information are converted as coordinate system.
Preferably, static object includes:The trees in road roadside;The guardrail in road roadside;Or the sensing target of road stationary road-side.
Preferably, step b) is specifically included:B1), it is based on the peripheral model of first preset track periphery point design first;
B2 at least one set of coordinate for meeting the first peripheral model), is extracted from the first coordinate set, to form first group of track periphery
Point;B3), it is based on preset the second peripheral model of track periphery point design of second batch;B4 symbol), is extracted from the first coordinate set
At least one set of coordinate for closing the second peripheral model, to form second group of track peripheral point;B5 first group of track peripheral point), is assessed
With second group of track peripheral point respectively relative to being excluded in the first coordinate set outside first group of track peripheral point and second group of track
The deviation of rest part after enclosing a little;And b6), by first group of track peripheral point and second group of track peripheral point relative to
Smaller the first peripheral model corresponding to that of the deviation of rest part or the second peripheral model are determined as track periphery model.
Preferably, step c) includes:C1), lane line is fitted using least square method;Wherein, lane line
It is expressed as cubic equation of the y-axis coordinate of lane boundary point relative to x-axis coordinate;C2), based on the cost function for making cubic equation
Partial derivative be 0, calculate the coefficient of cubic equation.
Invention additionally discloses a kind of tracks to be fitted system, including:Trailer-mounted radar sensor, for acquiring road roadside extremely in real time
Few coordinate of the static object relative to the position of vehicle, to form original coordinates set;Peripheral model computing unit, with vehicle
Set sensor is coupled, for establishing track periphery model based on at least first part of the first coordinate set, and based on the
Track periphery model is verified or updated at least second part of one coordinate set, to form the second coordinate set;Wherein, first
Coordinate set is converted through coordinate system by original coordinates set and is formed, and the second coordinate set includes the corresponding vehicle of track periphery model
Road peripheral point, first part are different from second part;And edge fitting unit, it is coupled, uses with peripheral model computing unit
In being fitted lane line based on the second coordinate set.
The track approximating method and system that various embodiments of the present invention provide, acquire in real time by using High Accuracy Radar
The static object coordinate in roadside, can more accurately calculate lane boundary information, be travelled always to help to control vehicle
In in lane boundary, this improves the safety of driving, meanwhile, also improve the usage experience of user.
Description of the drawings
Fig. 1 shows the flow diagram for the track approximating method that first embodiment of the invention provides.
Fig. 2 shows the modular structure schematic diagrams that the track that second embodiment of the invention provides is fitted system.
Specific implementation mode
Detail is proposed in the following description, in order to provide thorough understanding of the present invention.However, the technology of this field
Personnel will clearly know, can implement the embodiment of the present invention without these details.In the present invention, it can carry out
Specific numeric reference, such as " first element ", " second device " etc..But be understood not to must for specific number reference
Its literal sequence must be submitted to, but should be understood that " first element " is different from " second element ".
Detail proposed by the invention is exemplary, and detail can change, but still fall into the present invention
Spirit and scope within.Term " coupling ", which is defined to indicate that, is directly connected to component or via another component and in succession
It is connected to component.
Below by way of the preferred embodiment for the mthods, systems and devices for being described with reference to be adapted for carrying out the present invention.Though
Right each embodiment be described for single combine of element, however, it is understood that the present invention include all of disclosed element can
It can combination.Therefore, if one embodiment includes element A, B and C, and second embodiment includes element B and D, then of the invention
Other residue combinations of A, B, C or D should be believed to comprise, even if not disclosing clearly.
As shown in Figure 1, first embodiment of the invention provides a kind of track approximating method comprising following steps are rapid.
Step S10, at least one static object in roadside is acquired in real time relative to vehicle using trailer-mounted radar sensor
The coordinate of position.
Specifically, trailer-mounted radar sensor may include ultrasonic radar and millimetre-wave radar.The static mesh in road roadside
Mark can be the trees on road side;Guardrail;Or other static targets for sensing.
In this step, using ultrasonic radar and millimetre-wave radar in real time, constantly acquisition roadside static object
Coordinate, this coordinate are coordinate of the static object relative to moving vehicle.In other words, the origin of coordinate system is located on vehicle body.Through
Acquisition in real time obtains original coordinates set.
Step S11, it based on at least first part of the first coordinate set to establish track periphery model, and is sat based on first
At least second part of set is marked to verify or update track periphery model, to form the second coordinate set.
It should be understood that the foundation of track periphery model needs multigroup coordinate, for example, first from history gathered data group of seat
Mark and second group of coordinate from current gathered data.Since first group of coordinate and second group of coordinate are acquired respectively at different time
And obtain, due to the movement of vehicle, vehicle is in different positions, that is, first group of coordinate and second group of coordinate are respectively relied on
Coordinate origin be different.
Before establishing track periphery coordinate using multigroup coordinate, different coordinates can be converted so that first
Group coordinate and second group of coordinate are under identical coordinate system.Specifically, coordinate system, which is converted, may include:Vehicle is obtained to exist
At the first time to the velocity information and directional information during the second time;Velocity information and directional information are converted into vehicle body position
Change information and vehicle body angle change information;In turn, using vehicle body change in location information and vehicle body angle change information as coordinate
The parameter of system's conversion is carried out the specific coordinate system that executes and is converted.
As an example, setting (xs,ys) it is coordinate of the static object in the historical juncture relative to moving vehicle, (xt,yt) it is same
Coordinate of one static object at current time relative to moving vehicle, α are in the historical juncture to (such as 1 second during current time
Duration) vehicle body angle change, (tx, ty) be the change in location of vehicle body in the meantime.Coordinate system conversion using following formula come
It carries out.
Wherein, coordinate system is converted to optional sub-step.It is alternatively possible to select to acquiring obtained static object in real time
Relative coordinate date be based respectively on current vehicle location and vehicle body angle is modified, makeover process can be in step slo
It carries out.
After carrying out above-mentioned coordinate system conversion to original coordinates set, the first coordinate set, the first coordinate set can be formed
In each coordinate points all under identical coordinate system.
In step S11, first part is extracted from the first coordinate set initially to establish track periphery model (work
For default models), then second part is extracted to verify the track periphery model from the first coordinate set.Specifically, if tested
Card finds the track periphery model closing to reality, then can be by the corresponding track peripheral point of track periphery model for being fitted
Lane line;If track periphery model deviates practical, Selection utilization second part replaces former track periphery model.Make
For a kind of specific example, step S11 is executed as follows.
Step (1) is based on the peripheral model (default peripheral model) of first preset track periphery point design first.
Step (2), extraction meets at least one set of coordinate of the first peripheral model from the first coordinate set, to form first
Group track peripheral point.Wherein, those of the first peripheral model coordinate that meets for extracting from the first coordinate set is defined as first
The first part of coordinate set
Step (3) is based on preset the second peripheral model of track periphery point design of second batch.
Step (4), extraction meets at least one set of coordinate of the second peripheral model from the first coordinate set, to form second
Group track peripheral point.Wherein, those of the second peripheral model coordinate that meets for extracting from the first coordinate set is defined as first
The second part of coordinate set.Since the second peripheral model is different from the first peripheral model, second part also will differ from first
Part.
Step (5), first group of track peripheral point of assessment and second group of track peripheral point are respectively relative to the first coordinate set
The middle deviation for excluding the rest part after first group of track peripheral point and second group of track peripheral point.
Step (6), by first group of track peripheral point and second group of track peripheral point relative to the deviation of rest part more
The first peripheral model or the second peripheral model corresponding to that small are determined as track periphery model.Specifically, if first group
Track peripheral point is smaller relative to the rest part deviation, then is considered as second group of track peripheral point and is able to verify that the first outer boxing
Type is track periphery model to the first peripheral model of acquiescence;Conversely, using the second peripheral model replace default models as
Track periphery model.The corresponding track peripheral point of the track periphery model forms the second coordinate set.
As another example, step S11 can be executed as follows again.
Step A, it is based on the peripheral model of first preset track periphery point design first.Step B, the first coordinate set is determined
Whether the first coordinate in conjunction, which meets the first peripheral model, is added the first coordinate if met and corresponds to the first outer boxing
The track peripheral point of type.Step C, step B is repeated, until the quantity of track peripheral point reaches peripheral point threshold value.
Wherein, the first coordinate is any coordinate in the first coordinate set.First preset track peripheral point can be with base
In the first coordinate set (for example, according to coordinate corresponding to the strongest signal of radar echo signal in certain time period) next life
At (for example, the confirmation of empirical data or user to a certain static object) can also being arranged by other means.
If first preset track peripheral point comes from the first coordinate set, first preset track peripheral point adds
Upper the first coordinate that (the track peripheral point of the first peripheral model) is added every time, is defined as the first of the first coordinate set together
Part.If first preset track peripheral point is not originate from the first coordinate set, it will be added (the first peripheral model every time
Track peripheral point) the first coordinate be defined as the first part of the first coordinate set.
Further include following steps rapid D, E, F, G after above step A, B, C.
Step D, it is based on preset the second peripheral model of track periphery point design of second batch.Step E, the first coordinate set is determined
Whether the second coordinate in conjunction, which meets the second peripheral model, is added the second coordinate if met and corresponds to the second outer boxing
The track peripheral point of type.Step F, step E is repeated, until the quantity of track peripheral point reaches peripheral point threshold value.
Wherein, the second coordinate is any coordinate in the first coordinate set.Similarly, the preset track peripheral point of second batch
It can be generated, can also be generated by other means based on the first coordinate set.
If the preset track peripheral point of second batch comes from the first coordinate set, the preset track peripheral point of second batch adds
Upper the second coordinate that (the track peripheral point of the second peripheral model) is added every time, is defined as the second of the first coordinate set together
Part.If the preset track peripheral point of second batch is not originate from the first coordinate set, it will be added (the second peripheral model every time
Track peripheral point) the second coordinate be defined as the second part of the first coordinate set.
Step G, the first peripheral model and the second peripheral model respectively deviation relative to the first coordinate set are assessed.It is more excellent
Selection of land, for its remaining part after excluding first group of track peripheral point and second group of track peripheral point in the first coordinate set
Point, respectively calculate the deviation of the first peripheral model and the second peripheral model relative to the rest part.
According to further embodiment of this invention, a preset track periphery point set can be set up in advance, is therefrom carried every time
It takes the preset track peripheral point of a batch independently to carry out the calculating of peripheral model, multiple and different outer boxings can be formed in this way
Type.It is appreciated that by establishing multiple and different peripheral models, it can preferably go out and the first coordinate set is closest to (or deviation
It is minimum) that peripheral model be used as " track periphery model " described in the embodiment of the present invention.With the track periphery model
Corresponding track peripheral point then forms " the second coordinate set " described in the embodiment of the present invention.
For the close degree of determination or above-mentioned deviation, corresponding (multiple) the track peripheries of each peripheral model can be sought
Point and the variance that the rest part after first group of track peripheral point and second group of track peripheral point is excluded in the first coordinate set,
Variance yields is smaller, indicates closer.
Alternatively, in above-mentioned sub-step B, if a certain coordinate in the first coordinate set meets the first periphery
Model can indicate that the degree of reiability of the first peripheral model increases by 1, and if it meets the second peripheral model, by second
The degree of reiability of peripheral model increases by 1.In this manner it is achieved that after traversing the first coordinate set, reliability can determine
Measure that highest peripheral model.
Step S12, lane line is fitted based on the second coordinate set.
In step S12, first, according to each coordinate point data in the second coordinate set, using least square method come
It is fitted lane line.Wherein, lane line is usually 2, the left margin and right margin in track, it is preferable that left margin
Cubic equation of the y-axis coordinate of lane boundary point relative to x-axis coordinate can be expressed as with right margin.
It should be understood that the point on lane line is different from track peripheral point, this is because track peripheral point corresponds to roadside
The relative coordinate of static object, and these static objects are usually in the outside of practical lane line, but roadside static object with
Spacing between practical lane line is floated or fixed usually in smaller range.By using this spacing pair
Coordinate points in two coordinate sets are coordinately transformed, and can fit lane line.
Further, the partial derivative based on the cost function for making lane boundary point cubic equation is 0, can calculate cube
The coefficient of journey.As an example, lane line is expressed as y=c0+c1x+c2x2+c3x3。
In the fitting of least square method, carried out using following formula.
Wherein,For above-mentioned cubic equation, m is the quantity of the coordinate points in the second coordinate set, and i is the number of coordinate points.
By making functional valueWith actual coordinate data yiVariance δi 2The sum of for minimum, can determine four in cubic equation
A parameter c0, c1, c2, c3。
Before being fitted, the second coordinate set can also be screened or is filtered, with filter out wherein with its
His larger coordinate points of coordinate points deviation, or the higher coordinate points of confidence level are therefrom filtered out to be fitted, to improve vehicle
The accuracy of road boundary line.
According to one embodiment of the invention, a kind of storage medium is provided, computer executable instructions are stored thereon with, these meters
Calculation machine executable instruction when executed by the processor, it is quasi- the track that first embodiment above provides can be executed by sequence appropriate
Each step of conjunction method.
As shown in Fig. 2, second embodiment of the invention provides a kind of track fitting system comprising ultrasonic radar 201, milli
Metre wave radar 202, peripheral model computing unit 210 and edge fitting unit 220.
Specifically, ultrasonic radar 201 and millimetre-wave radar 202 acquire in real time the static object in road roadside relative to
The coordinate of the position of (mobile status) vehicle obtains original coordinates set.
Peripheral model computing unit 210 couples respectively with two radars, at least first based on the first coordinate set
Point establish track periphery model, and boxing outside track is verified or update based on at least second part of the first coordinate set
Type, to obtain the second coordinate set.First coordinate set is by original coordinates set through coordinate system conversion (conversion to same coordinate system
Under) formed, the second coordinate set includes the corresponding track peripheral point of track periphery model.In foundation, verification or update track
In peripheral model, carried out using the method in above-mentioned first embodiment.
Edge fitting unit 220 is coupled with peripheral model computing unit 210, and vehicle is fitted based on the second coordinate set
Road boundary line.In fit procedure, edge fitting unit 220 can specifically use least square fitting, can also use and draw
The method well known in the prior art such as Ge Lang interpolation methods, Newton iteration method carries out.
In some embodiments of the invention, at least part of above system can be used that communication network is connected one group
Distributed computing devices are realized, or, realized based on " cloud ".In such systems, multiple computing devices co-operate, with logical
It crosses and provides service using its shared resource.As an example, edge fitting unit 220, peripheral model computing unit 210 are set to
High in the clouds, and its result of calculation is fed back into vehicle end.
Reality based on " cloud " nows provide one or more advantages, including:Open, flexibility and scalability, can in
Heart management, reliability, scalability, computing resource is optimized, with polymerization and analyze across multiple users information ability,
It is attached and is used for multiple movements or data network operator the ability of network connectivty across multiple geographic areas.
It can be predicted that according to the above-mentioned the first embodiment or the second embodiment of the present invention, track approximating method and/or it is
System can be applied in Vehicular automatic driving system, DAS (Driver Assistant System) and traveling navigation system, to which vehicle can be controlled
Ground is travelled on always in be fitted lane line, or indicates to the user that the track of suggestion traveling, this automatic Pilot system
System, DAS (Driver Assistant System) can improve the safety of user's driving.Navigation system can provide the user with more preferably usage experience.
Above description is not lain in and is limited the scope of the invention only in the preferred embodiment of the present invention.Ability
Field technique personnel may make various modifications design, the thought without departing from the present invention and subsidiary claim.
Claims (12)
1. a kind of track approximating method, including:
A), seat of at least one static object in roadside relative to the position of vehicle is acquired in real time using trailer-mounted radar sensor
Mark, to form original coordinates set;
B) track periphery model, is established based on at least first part of the first coordinate set, and is based on first coordinate set
Track periphery model is verified or updated at least second part closed, to form the second coordinate set;Wherein, described first
Coordinate set is converted through coordinate system by the original coordinates set and is formed, and second coordinate set includes boxing outside the track
Track peripheral point corresponding to type, the first part are different from the second part;And
C) lane line, is fitted based on second coordinate set.
2. according to the method described in claim 1, it is characterized in that, coordinate system conversion includes:
Vehicle is obtained in first time to the velocity information and directional information during the second time;
The velocity information and the directional information are converted into vehicle body change in location information and vehicle body angle change information;And
The parameter converted using the vehicle body change in location information and the vehicle body angle change information as the coordinate system.
3. according to the method described in claim 1, it is characterized in that, the static object includes:
The trees in road roadside;
The guardrail in road roadside;Or
The sensing target of road stationary road-side.
4. according to the method described in claim 1, it is characterized in that, the step b) is specifically included:
B1), it is based on the peripheral model of first preset track periphery point design first;
B2 at least one set of coordinate for meeting the described first peripheral model), is extracted from first coordinate set, to form first
Group track peripheral point;
B3), it is based on preset the second peripheral model of track periphery point design of second batch;
B4 at least one set of coordinate for meeting the described second peripheral model), is extracted from first coordinate set, to form second
Group track peripheral point;
B5 first group of track peripheral point and second group of track peripheral point), are assessed respectively relative to first coordinate
The deviation of the rest part after first group of track peripheral point and second group of track peripheral point is excluded in set;And
B6), by first group of track peripheral point and second group of track peripheral point relative to the inclined of the rest part
Smaller the described first peripheral model corresponding to that of difference or the second peripheral model are determined as track periphery model.
5. according to the method described in claim 1, it is characterized in that, the step c) includes:
C1 the lane line), is fitted using least square method;Wherein, the lane line is expressed as lane boundary
Cubic equation of the y-axis coordinate of point relative to x-axis coordinate;
C2 the partial derivative), based on the cost function for making the cubic equation is 0, calculates the coefficient of the cubic equation.
6. the method according to any one of claims 1 to 5, it is characterized in that, the radar sensor includes:
Ultrasonic radar;And
Millimetre-wave radar.
7. a kind of storage medium is stored thereon with computer executable instructions, the computer executable instructions are by processor
When execution, the step of executing method as described in any one of above claim 1-6.
8. a kind of track is fitted system, including:
Trailer-mounted radar sensor, for acquiring coordinate of at least one static object in road roadside relative to the position of vehicle in real time,
To form original coordinates set;
Peripheral model computing unit, is coupled with the onboard sensor, at least first based on the first coordinate set
Point establish track periphery model, and the track is verified or update based on at least second part of first coordinate set
Peripheral model, to form the second coordinate set;Wherein, first coordinate set is turned by the original coordinates set through coordinate system
It changes to be formed, second coordinate set includes the corresponding track peripheral point of track periphery model, and the first part is not
It is same as the second part;And
Edge fitting unit is coupled with the peripheral model computing unit, for being fitted based on second coordinate set
Lane line.
9. system according to claim 8, which is characterized in that the radar sensor includes:
Ultrasonic radar;And
Millimetre-wave radar.
10. a kind of Vehicular automatic driving system, including Driving control unit, wherein the Driving control unit control vehicle by
According to being travelled in the obtained lane line of track approximating method described in any one of claim 1-8.
11. a kind of DAS (Driver Assistant System), including auxiliary drive unit, the auxiliary drives unit control vehicle and is wanted according to right
Seek traveling in the obtained lane line of track approximating method described in any one of 1-8.
12. a kind of auto-navigation system, the navigation system indicates vehicle according to the vehicle described in any one of claim 1-8
Traveling in the obtained lane line of road approximating method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711346608.XA CN108573272B (en) | 2017-12-15 | 2017-12-15 | Lane fitting method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711346608.XA CN108573272B (en) | 2017-12-15 | 2017-12-15 | Lane fitting method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108573272A true CN108573272A (en) | 2018-09-25 |
CN108573272B CN108573272B (en) | 2021-10-29 |
Family
ID=63575933
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711346608.XA Active CN108573272B (en) | 2017-12-15 | 2017-12-15 | Lane fitting method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108573272B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110502797A (en) * | 2019-07-24 | 2019-11-26 | 同济大学 | A kind of lane acquisition modeling and method based on GNSS |
CN110969837A (en) * | 2018-09-30 | 2020-04-07 | 长城汽车股份有限公司 | Road information fusion system and method for automatic driving vehicle |
CN110962856A (en) * | 2018-09-30 | 2020-04-07 | 长城汽车股份有限公司 | Method and device for determining area of vehicle where environmental target is located |
CN111267862A (en) * | 2020-01-13 | 2020-06-12 | 清华大学 | Method and system for constructing virtual lane line depending on following target |
CN111316128A (en) * | 2018-12-28 | 2020-06-19 | 深圳市大疆创新科技有限公司 | Continuous obstacle detection method, device, system and storage medium |
CN114578690A (en) * | 2022-01-26 | 2022-06-03 | 西北工业大学 | Intelligent automobile autonomous combined control method based on multiple sensors |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103150786A (en) * | 2013-04-09 | 2013-06-12 | 北京理工大学 | Non-contact type unmanned vehicle driving state measuring system and measuring method |
CN103745018A (en) * | 2014-02-11 | 2014-04-23 | 天津市星际空间地理信息工程有限公司 | Multi-platform point cloud data fusion method |
CN104240536A (en) * | 2013-06-20 | 2014-12-24 | 福特全球技术公司 | Lane monitoring method with electronic horizon |
CN105404844A (en) * | 2014-09-12 | 2016-03-16 | 广州汽车集团股份有限公司 | Road boundary detection method based on multi-line laser radar |
CN106096525A (en) * | 2016-06-06 | 2016-11-09 | 重庆邮电大学 | A kind of compound lane recognition system and method |
US20170139420A1 (en) * | 2014-07-16 | 2017-05-18 | Ford Global Technologies, Llc | Automotive drone deployment system |
CN106842231A (en) * | 2016-11-08 | 2017-06-13 | 长安大学 | A kind of road edge identification and tracking |
CN106846392A (en) * | 2016-12-12 | 2017-06-13 | 国网北京市电力公司 | The method and apparatus of three-dimensional modeling |
CN106991389A (en) * | 2017-03-29 | 2017-07-28 | 蔚来汽车有限公司 | The apparatus and method for determining road edge |
US20170241794A1 (en) * | 2016-02-18 | 2017-08-24 | Electronics And Telecommunications Research Institute | Method and apparatus for predicting vehicle route |
-
2017
- 2017-12-15 CN CN201711346608.XA patent/CN108573272B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103150786A (en) * | 2013-04-09 | 2013-06-12 | 北京理工大学 | Non-contact type unmanned vehicle driving state measuring system and measuring method |
CN104240536A (en) * | 2013-06-20 | 2014-12-24 | 福特全球技术公司 | Lane monitoring method with electronic horizon |
CN103745018A (en) * | 2014-02-11 | 2014-04-23 | 天津市星际空间地理信息工程有限公司 | Multi-platform point cloud data fusion method |
US20170139420A1 (en) * | 2014-07-16 | 2017-05-18 | Ford Global Technologies, Llc | Automotive drone deployment system |
CN105404844A (en) * | 2014-09-12 | 2016-03-16 | 广州汽车集团股份有限公司 | Road boundary detection method based on multi-line laser radar |
US20170241794A1 (en) * | 2016-02-18 | 2017-08-24 | Electronics And Telecommunications Research Institute | Method and apparatus for predicting vehicle route |
CN106096525A (en) * | 2016-06-06 | 2016-11-09 | 重庆邮电大学 | A kind of compound lane recognition system and method |
CN106842231A (en) * | 2016-11-08 | 2017-06-13 | 长安大学 | A kind of road edge identification and tracking |
CN106846392A (en) * | 2016-12-12 | 2017-06-13 | 国网北京市电力公司 | The method and apparatus of three-dimensional modeling |
CN106991389A (en) * | 2017-03-29 | 2017-07-28 | 蔚来汽车有限公司 | The apparatus and method for determining road edge |
Non-Patent Citations (3)
Title |
---|
FLORIAN JANDA ET AL.: ""Road Boundary Detection for Run-off Road Prevention based on the Fusion of Video and Radar"", 《2013 IEEE INTELLIGENT VEHICLES SYMPOSIUM (IV)》 * |
刘波等: ""基于改进最小二乘法拟合的车道线检测"", 《信息技术》 * |
朱峰: ""基于模型驱动的车线偏离警告系统"", 《计算机系统应用》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110969837A (en) * | 2018-09-30 | 2020-04-07 | 长城汽车股份有限公司 | Road information fusion system and method for automatic driving vehicle |
CN110962856A (en) * | 2018-09-30 | 2020-04-07 | 长城汽车股份有限公司 | Method and device for determining area of vehicle where environmental target is located |
CN110969837B (en) * | 2018-09-30 | 2022-03-25 | 毫末智行科技有限公司 | Road information fusion system and method for automatic driving vehicle |
CN111316128A (en) * | 2018-12-28 | 2020-06-19 | 深圳市大疆创新科技有限公司 | Continuous obstacle detection method, device, system and storage medium |
WO2020133217A1 (en) * | 2018-12-28 | 2020-07-02 | 深圳市大疆创新科技有限公司 | Continuous obstacle detection method, device and system, and storage medium |
CN110502797A (en) * | 2019-07-24 | 2019-11-26 | 同济大学 | A kind of lane acquisition modeling and method based on GNSS |
CN110502797B (en) * | 2019-07-24 | 2021-06-04 | 同济大学 | Lane acquisition modeling system and method based on GNSS |
CN111267862A (en) * | 2020-01-13 | 2020-06-12 | 清华大学 | Method and system for constructing virtual lane line depending on following target |
CN111267862B (en) * | 2020-01-13 | 2021-04-02 | 清华大学 | Method and system for constructing virtual lane line depending on following target |
CN114578690A (en) * | 2022-01-26 | 2022-06-03 | 西北工业大学 | Intelligent automobile autonomous combined control method based on multiple sensors |
Also Published As
Publication number | Publication date |
---|---|
CN108573272B (en) | 2021-10-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108573272A (en) | Track approximating method | |
US11242144B2 (en) | Aerial vehicle smart landing | |
US10871783B2 (en) | Advanced path prediction | |
US10031526B1 (en) | Vision-based driving scenario generator for autonomous driving simulation | |
JP7367183B2 (en) | Occupancy prediction neural network | |
CN110377025A (en) | Sensor aggregation framework for automatic driving vehicle | |
WO2018221453A1 (en) | Output device, control method, program, and storage medium | |
CN109489675A (en) | The path planning based on cost for automatic driving vehicle | |
CN110146909A (en) | A kind of location data processing method | |
CN108387241A (en) | Update the method and system of the positioning map of automatic driving vehicle | |
CN109491376A (en) | The decision and planning declined based on Dynamic Programming and gradient for automatic driving vehicle | |
CN110239562A (en) | The real-time perception adjustment based on surrounding vehicles behavior of automatic driving vehicle is adjusted with driving | |
CN108139225A (en) | Determine the layout information of motor vehicle | |
WO2018154579A1 (en) | Method of navigating an unmanned vehicle and system thereof | |
CN108628298A (en) | Control type planning for automatic driving vehicle and control system | |
JP2022022287A (en) | Map making device, method for control, program, and storage medium | |
CN104677361A (en) | Comprehensive positioning method | |
KR20200133184A (en) | Navigation device for self-driving vehicle | |
CN109901193A (en) | The light of short distance barrier reaches arrangement for detecting and its method | |
CN110271553A (en) | Method and apparatus for steadily positioning vehicle | |
CN211427151U (en) | Automatic guide system applied to unmanned freight vehicle in closed field | |
CN111337027B (en) | Ship follow-up operation auxiliary driving method and system | |
CN109901589B (en) | Mobile robot control method and device | |
CN113885496A (en) | Intelligent driving simulation sensor model and intelligent driving simulation method | |
WO2001013138A1 (en) | Method and device at flying vehicle for detecting a collision risk |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200730 Address after: Susong Road West and Shenzhen Road North, Hefei Economic and Technological Development Zone, Anhui Province Applicant after: Weilai (Anhui) Holding Co., Ltd Address before: Room 502, Minsheng Bank Building, 12 Cecil Harcourt Road, central, Hongkong, China Applicant before: NIO NEXTEV Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |