CN106991389A - The apparatus and method for determining road edge - Google Patents
The apparatus and method for determining road edge Download PDFInfo
- Publication number
- CN106991389A CN106991389A CN201710196345.2A CN201710196345A CN106991389A CN 106991389 A CN106991389 A CN 106991389A CN 201710196345 A CN201710196345 A CN 201710196345A CN 106991389 A CN106991389 A CN 106991389A
- Authority
- CN
- China
- Prior art keywords
- road
- road edge
- vehicle
- curve
- static target
- 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 19
- 230000003068 static effect Effects 0.000 claims abstract description 63
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000012887 quadratic function Methods 0.000 claims description 22
- 230000001419 dependent effect Effects 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 description 20
- 238000003384 imaging method Methods 0.000 description 12
- 238000002955 isolation Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012886 linear function Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000011088 calibration curve Methods 0.000 description 1
- 238000012888 cubic function Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
Classifications
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of apparatus and method for determining road edge, belongs to intelligent automobile technical field.A kind of device for determining road edge, it includes:Radar detedtor on vehicle, the static target where it can at least detect vehicle beside the road edge of road;And processing component, it is configured as:Receive static target that the radar detedtor detected and extract the arrangement information of relative road substantially regularly arranged static target, so as to obtain road edge information based on the arrangement information.Apparatus and method of the present invention is highly suitable to be applied in unstructured road obtaining road edge information, and can also relatively accurately obtain road edge information at a distance.
Description
Technical field
The invention belongs to intelligent automobile technical field, it is related to the static target beside based on road edge and determines road edge
Apparatus and method.
Background technology
Automatic Pilot(Driven comprising auxiliary)It is the important directions of intelligent automobile development, and is more and more opened in vehicle
Begin application automated driving system to realize the Function for Automatic Pilot of vehicle.Normally, automated driving system can need momentarily true
The wheeled region of vehicle is determined, it is determined that during wheeled region, an important aspect is it needs to be determined that going out current line
Sail the road edge of road.
At present, typically by imaging sensor in automated driving system(Camera for example on vehicle)Adopted
The image including lane line of collection determines road edge, wherein, road edge is based on the car in the image gathered in real time
The image procossing of diatom is determined.There is at least one aspect of problems with this technology for determining road edge:
In a first aspect, be necessarily dependent upon the lane line in track, for lane line is fuzzy, lane line excalation or lane line are complete
Complete non-existent road, is difficult to determine road edge, or the road edge determined is significantly to deviate real roads side
Edge;
Second aspect, the technology of this determination road edge realized based on imaging sensor, but in actual applications,
The information content that imaging sensor is carried on close-up images and remote image difference.Usually, with regard on image two
For the actual physics distance represented between individual pixel, the neighbouring distance of image sensor lens central point is than shot boundary area more
It is small, so, the problem of easily bringing to remote Lane detection ability, that is, at a distance(Relative to vehicle)Road
The determination or detection on roadside edge are inaccurate.
The content of the invention
At least one aspect or other technologies the problem present invention of the technical problem to be solved in the present invention provide following technology
Scheme.
It is an aspect of this invention to provide that providing a kind of device for determining road edge, it includes:
Radar detedtor on vehicle, the static mesh where it can at least detect vehicle beside the road edge of road
Mark;With
Processing component, it is configured as:Receive static target that the radar detedtor detected and to extract relative road big
The arrangement information of regularly arranged static target is caused, so as to obtain road edge information based on the arrangement information.
According to another aspect of the present invention, there is provided a kind of method for determining road edge, it is characterised in that including step:
(a)Static target where detecting vehicle beside the road edge of road;And
(b)The arrangement information of relative road substantially regularly arranged static target is extracted, and is obtained based on the arrangement information
Obtain road edge information.
According to the further aspect of the present invention there is provided a kind of vehicle, automated driving system, the automated driving system are provided with
In be provided with the device of any of the above-described described determination road edge.
It will become apparent according to the features above of the following description and drawings present invention and operation.
Brief description of the drawings
From described further below with reference to accompanying drawing, it will make the above and other purpose and advantage of the present invention more complete
It is clear, wherein, same or analogous key element, which is adopted, to be indicated by the same numeral.
Fig. 1 is the structural representation of the device of the determination road edge according to one embodiment of the invention.
Fig. 2 is the device of embodiment illustrated in fig. 1 it is determined that application scenarios schematic diagram during road edge.
Fig. 3 is the flow chart of the method for the determination road edge according to one embodiment of the invention.
Embodiment
The present invention is more fully described now with reference to accompanying drawing, shown in the drawings of the exemplary embodiment of the present invention.
But, the present invention can be realized according to many different forms, and be not construed as being limited to embodiments set forth here.
On the contrary, thesing embodiments are provided so that the disclosure becomes thorough and complete, and the design of the present invention is entirely delivered to this area
Technical staff.In accompanying drawing, identical label refers to identical element or part, therefore, will omit description of them.
Some block diagrams shown in accompanying drawing are functional entitys, not necessarily must be with physically or logically independent entity phase
Correspondence.These functional entitys can be realized using software form, or in one or more hardware modules or integrated circuit
These functional entitys are realized, or realize in heterogeneous networks and/or processor device and/or microcontroller device these functions
Entity.
Fig. 1 show the structural representation of the device of the determination road edge according to one embodiment of the invention, and Fig. 2 is shown
The device of embodiment illustrated in fig. 1 is it is determined that application scenarios schematic diagram during road edge.Below in conjunction with Fig. 1 and Fig. 2 to the present invention
The device and its operation principle of embodiment are illustrated.
As shown in figure 1, determining the device of road edge(Hereinafter referred to as " determining device ")It is to be installed in vehicle 100
On, the particular type of vehicle 100 is not restricted, relative to the determining device, and vehicle 100 is host's car of the determining device
.The determining device can apply in the automated driving system that vehicle 100 is installed.
Using Fig. 2 to illustrate, vehicle 100 is travelled on road 900, and road 900 has corresponding road edge
901a and 901b, wherein, 901a is left road edge, and 901b is right road edge, in the application scenarios, road edge 901a
Do not specifically identify out by lane line with 901b, or in one section of road 900 of the example and in the absence of phase
The lane line answered identifies road edge.The both sides of road 900 exists various static(It is static with respect to road)Object, it is to determine
The target of device detection, therefore, also referred to as " static target ";Illustratively, it is static beside the left road edge 901a of road 900
Target is illustrated, for example, tree 801, electric pole 802, isolation honest 803(There is shown with three isolation honest 803a, 803b and 803c)
Deng, it will be appreciated that the static target beside road edge is not limited to the kind of object of above example, for example, can also be grid
Column, direction board vertical rod etc.,
Determining device mainly includes the radar detedtor 110 being arranged on vehicle 100, and it can at least detect the institute of vehicle 100
The static target of at least one side in the road both sides of road 900.In one embodiment, radar detedtor 110 is millimeter wave
Radar, it is arranged on the front end of vehicle 100, can be on road plane with the various things in front of 90 ° of detection angle range detections
Static target beside body, including road edge 901a for example as shown in Figure 2.Radar detedtor 110 launches one in detection
The electromagnetic wave of standing wave length simultaneously receives the reflection from objects in front, therefore, it can detect the position of various objects, particularly pair
In remote(Such as more than 40 meters)Object, can relatively accurately be detected as closer object(Relative to image
For sensor 120), therefore, its relative image sensor 120 has preferably remote detection characteristic.
It is pointed out that vehicle coordinate system can be pre-defined in determining device, i.e. XY coordinate-systems, wherein, with
The barycenter of vehicle 100 is round dot O, and X-axis is defined as the front vertical direction of vehicle 100, and X-coordinate is defined as the barycenter of relative vehicle
Distance deviation in vertical direction, Y-axis is defined as the horizontal direction of vehicle 100, and Y-coordinate is defined as relatively described vehicle
The deviation of the distance of barycenter in the horizontal direction.Radar detedtor 110 is detecting various objects(Including stationary object)When, certain
The coordinate of one object(X, Y)Substantially determined, wherein, X-coordinate represents the matter of the object and vehicle 100 under vehicle coordinate system
The deviation of the distance of the heart in vertical direction(Deviation i.e. in X-axis), Y-coordinate represents the object and vehicle under vehicle coordinate system
The deviation of the distance of 100 barycenter in the horizontal direction(Deviation i.e. in Y-axis).
Wherein, millimetre-wave radar be configured can the speed based on Doppler effect and host vehicle from the various things of detection
Static target, namely the actionless object of relative road edge 901 are determined in body.Therefore, millimetre-wave radar can be substantially real
When export the relevant information of static target(For example, the coordinate under vehicle coordinate system).
Have relative cost low when radar detedtor 110 is using millimetre-wave radar and can accurately detect remote(Such as 40
It is more than rice)Static target advantage, it is understood, however, that radar detedtor 110 is not limited to as millimetre-wave radar, such as
It can also be laser radar, and laser radar relatively more detects various static targets exactly(Including remote static mesh
Mark), still, relatively expensive, the data-handling capacity to subsequent process hardware 130 requires higher.
Continue as shown in figure 1, determining device also includes processing component 130, it is also provided with vehicle 100, specifically it can
To be realized by the processing unit in the automated driving system on vehicle 100, can also independently it be set with respect to automated driving system
Processor is put to realize.Processing component 130 can handle the algorithmic code that wherein stores and perform from automated driving system or
The instruction of vehicle, known to the particular hardware implementation of processing component 130, will not be described in detail herein.
The static target relevant information that processing component 130 can mainly be transmitted to radar detedtor 110 carries out data
Handle to obtain road edge curve, it is configured as:Receive the static target that is detected of radar detedtor 110 and extract phase
To the arrangement information of road substantially regularly arranged static target, so as to obtain road edge information based on the arrangement information.Its
In, road edge information can specifically show as road edge calibration curve information.Below to obtain the left road edge shown in Fig. 2
901a road edge curve illustrates the concrete operating principle of processing component 130.
In one embodiment, the static target quantity that radar detedtor 110 is transmitted after single pass detection may
Tens this orders of magnitude can be reached, therefore, corresponding screening unit 131 are provided with processing component 130, it is from can
More than at least three static targets are filtered out as with reference to mesh from numerous static targets that radar detedtor 110 is transmitted
Mark.As shown in Fig. 2 there are substantially regularly arranged trees from relative road 900 can be filtered out from many static targets
901st, electric pole 902, isolation honest 903 as left road edge 901a reference object, for not being relatively left road edge
The static targets such as other trees, the electrical bar of 901a irregular alignments, can not be selected as reference object or be filtered.
Applicant have observed that, because the both sides of road 900 can typically have relative road 900 substantially regularly arranged thing
Body, such as trees 901 and electric pole 902;When it is determined that whether relative a certain static target road 900 be substantially regularly arranged,
Can the current yaw velocity based on vehicle 100(Such as can from the steering of vehicle 100 gather in part and obtain
Take)To obtain predicting driving trace, the prediction driving trace is generally corresponding to current road curve, therefore, it can big
Cause to determine its static target whether with respect to road 900 based on whether relative static target prediction driving trace be substantially regularly arranged
It is substantially regularly arranged, so as to filter out respective stationary target as reference object.It should be appreciated that " substantially rule is arranged
" substantially " static target of the both sides of reflection road 900 is not necessarily neat with respect to road in strict accordance with a certain rule in row "
Arrangement, for example, there is tolerance on the several meters of orders of magnitude etc. on the marshalling degree of relative road.
As shown in Fig. 2 regularly arranged trees 801, electric pole 802, hard shoulder 803 beside left road edge 901a etc.
It is substantially regularly arranged to be screened unit 131 and be determined as relative prediction driving trace, therefore, by least three in them
As reference object, for example, more than three trees 801 of selection as reference object or selection hard shoulder 803a, 803b and
803c is as reference object or selects multiple trees 801 and an electric pole 802 and a hard shoulder 803a as with reference to mesh
Mark.The quantity of reference object is more, is subsequently more conducive to accurately obtaining road edge curve.
In one embodiment, aim curve fitting unit 132 is provided with processing component 130, it is configured as at least to
Three or three carry out curve fitting to obtain corresponding reference object arrangement song above by reference to target under vehicle coordinate system
Line.In particular it is required that obtained reference object alignment curve is defined with quadratic function in advance, i.e., following functional relation
(1):
Y=C2×X2 + C1×X + C0’ (1)
Wherein, X is independent variable, and it corresponds to the X-coordinate under vehicle coordinate system, and the X-coordinate is defined as relatively described vehicle
Barycenter distance deviation in vertical direction;Y is dependent variable, and it corresponds to the Y-coordinate under vehicle coordinate system, the Y
Coordinate definition is the deviation of the distance of the barycenter of relatively described vehicle in the horizontal direction;C2For secondary term coefficient, C1For first order
Coefficient, C0' it is constant term.
Further, the coordinate of multiple reference objects is substituted into quadratic function relation formula(1), calculate quadratic function relation formula
(1)In secondary term coefficient C2, Monomial coefficient C1With constant term C0' value, so as to obtain relational expression(1), namely determine
Reference object alignment curve.
In another embodiment, the current yaw velocity of the vehicle can also be also based on to calculate current vehicle
Radius of turn, so as to calculate relational expression(1)In secondary term coefficient C2, now quadratic function relation formula(1)It is reduced to
Linear function relational expression, based on the coordinate of multiple reference objects, can further calculate Monomial coefficient C1And constant term
C0' value, so as to obtain relational expression(1), namely reference object alignment curve is determined.
In one embodiment, road edge estimation unit 133 is provided with processing component 130, it is used to be based on reference to mesh
Mark alignment curve estimation obtains road edge curve.In one embodiment, the road edge estimation unit 133 is by with lower section
Formula obtains corresponding road edge curve:From quadratic function relation formula(1)Obtain following quadratic function relation formula(2)It is used as road
Edge curve:
Y=C2×X2 + C1×X + C0(2)
Wherein, C0For constant term, C0=C0'+D, D is distance of the road edge with respect to static target substantially regularly arranged beside it
Constant, for example, estimating corresponding static target beside left road edge 901a in advance(Trees 801, electric pole 802, isolation
Honest 803 etc.)Relatively left road edge 901a distance constant D, usually, trees 801, electric pole 802, isolation honest 803 are relative
The distance of road edge 901 is respectively present corresponding specification regulation, can be estimated based on these settings and obtain distance constant D
(Specific such as 0.5m)
So, quadratic function relation formula(2)It is determined, namely road edge curve is determined.
Although it should be noted that above example is that reference object alignment curve and road are determined with quadratic function relation formula
Roadside is along curve, it will be appreciated that be also based on the functional relation of more high order(Such as cubic function relational expression, biquadratic function
Relational expression)To determine reference object alignment curve and road edge curve, certainly, functional relation number of times is higher, required
The number of reference object is also more.
The determining device of above example can determine road edge information based on the static target of road both sides, completely
Realized independent of lane line, also therefore, be highly suitable to be applied for unstructured road(Such as lane line is fuzzy, lane line
The road for disappearing or lacking)Middle acquisition road edge information;Also, realize, therefore, break away from also not dependent on imaging sensor
The problem of remote road can not obtain corresponding road edge information exactly, can also relatively accurately obtain at a distance
Road side information.
The determining device of above example can apply in the vehicle 100 with automated driving system, automatic Pilot system
The road edge curve that system is provided based on determining device, can not only provide the wheeled region of near-end, and can provide phase
To accurate distal end wheeled region, wherein, the algorithm that wheeled region is determined based on road edge curve is not limitation
Property.
Continue as shown in figure 1, in another embodiment, imaging sensor 120 can also be set in determining device, it is for example
May be mounted at the substantially position of rear view mirror of vehicle interior, imaging sensor 120 be specifically as follows shooting it is first-class, it can be real
When obtain the lane line 901 of road 900(In the case of lane line 901)Lane line image information, certainly,
In practical application, the image information acquired in imaging sensor 120 is not limited to lane line image information, for example, also include front
Vehicle, pedestrian, barrier etc. image information.
In another embodiment, the processing component 130 in determining device also receives above-mentioned lane line image information, also,
Also calculate the road edge curve for obtaining road 900 in real time based on lane line image information;Entered based on lane line image information
Row image procossing simultaneously calculates that to obtain road edge curve be it is known in the art that will not be described in detail herein.Therefore, processing component 130
The two road edge curve that two kinds of mechanism are obtained respectively may can be obtained, processing component 130 can be in base under different scenes
The road edge curve of road 900 is determined in two road edge curve.
Illustratively, under a kind of scene, the lane line of road 900 is present and the side of road 900 is big in the presence of relative road 900
Regularly arranged static target is caused, based on above two mechanism or two road edge curve, for closely road, its road
Roadside can use along curve and calculate obtained road edge curve based on lane line image information, for remote road, its
Road edge curve, which uses to calculate based on the static target, obtains road edge curve, so, overcomes based on track line chart
As information calculates obtained road edge curve the problem of remote section is inaccurate.
Illustratively, under another scene, the lane line of road 900 is present by part way missing or unclear, road 900
In the presence of relative road 900 substantially regularly arranged static target, for the lane line missing in the road or unsharp road
Section, its road edge curve, which can use to calculate based on the static target, obtains road edge curve.So as to overcome based on figure
The problem of can not being obtained in some sections as sensor 120 or can not accurately obtain road edge curve.
Fig. 3 show the flow chart of the method for the determination road edge according to one embodiment of the invention.With reference to Fig. 1 to Fig. 3,
The method for illustrating the determination road edge of the embodiment of the present invention.
First, step S310, the static target where detection vehicle beside the road edge of road.
Step S310 can be realized in the radar detedtor 110 of such as millimetre-wave radar.Pass through radar detedtor 110
Detect at least one side in the road both sides of the place road 900 of vehicle 100(Such as left road edge 901a sides)Static mesh
Mark, especially for remote(Such as 40 meters with first-class)Object, can relatively accurately be examined as closer object
Survey.Millimetre-wave radar is configured that static target can be determined from the various objects of detection based on Doppler effect, namely relatively
The actionless object of road edge 901, such as including tree 801, electric pole 802, isolation honest 803.Therefore, millimetre-wave radar energy
Enough relevant informations for exporting static target essentially in real time(For example, the coordinate under vehicle coordinate system).
Further, step S320, reference object is filtered out from static target.
Realized in screening unit 131 in processing component 130 main step S320, in the step, from radar detection
More than at least three static targets are filtered out as reference object in numerous static targets that device 110 is transmitted.Screening
Principle is arranged with the whether relative substantially regulation of road 900 of the static target, and specifically, road 900 can travel rail to predict
Mark is corresponded to, and the prediction driving trace can the current yaw velocity based on vehicle 100(For example can be from vehicle 100
Gather and obtain in the parts such as steering)To obtain, based on the regularly arranged trees 801 beside left road edge 901a, electricity
It is substantially regularly arranged that line bar 802, hard shoulder 803 etc., which are determined as relative prediction driving trace, so as to be screened and be
Reference object.The quantity of reference object is more, is subsequently more conducive to accurately obtaining road edge curve.
Further, step S330, carries out curve fitting to reference object and obtains reference object alignment curve.
Step S330 is main to be realized in the aim curve fitting unit 132 of processing component 130.In one embodiment,
Obtained reference object alignment curve is needed to be defined in advance with quadratic function, i.e., following functional relation(1):
Y=C2×X2 + C1×X + C0’ (1)
Wherein, X is independent variable, and it corresponds to the X-coordinate under vehicle coordinate system, and the X-coordinate is defined as relatively described vehicle
Barycenter distance deviation in vertical direction;Y is dependent variable, and it corresponds to the Y-coordinate under vehicle coordinate system, the Y
Coordinate definition is the deviation of the distance of the barycenter of relatively described vehicle in the horizontal direction;C2For secondary term coefficient, C1For first order
Coefficient, C0' it is constant term.
Further, by the coordinate of multiple reference objects(For example trees 801, electric pole 802, hard shoulder 803 are in vehicle coordinate
Coordinate under embodying)Substitute into quadratic function relation formula(1), calculate quadratic function relation formula(1)In secondary term coefficient C2, one
Secondary term coefficient C1With constant term C0' value, so as to obtain relational expression(1), namely reference object alignment curve is determined.
In another embodiment, the current yaw velocity of the vehicle can also be also based on to calculate current vehicle
Radius of turn, so as to calculate relational expression(1)In secondary term coefficient C2, now quadratic function relation formula(1)It is reduced to
Linear function relational expression, based on the coordinate of multiple reference objects, can further calculate Monomial coefficient C1And constant term
C0' value, so as to obtain relational expression(1), namely reference object alignment curve is determined.
Further, step S340, road edge curve is obtained based on the estimation of reference object alignment curve.
Step S330 is main to be realized in the road edge estimation unit 133 of processing component 130.In one embodiment,
Corresponding road edge curve is obtained in the following manner:From quadratic function relation formula(1)Obtain following quadratic function relation formula
(2)It is used as road edge curve:
Y=C2×X2 + C1×X + C0(2)
Wherein, C0For constant term, C0=C0'+D, D is distance of the road edge with respect to static target substantially regularly arranged beside it
Constant, for example, estimating corresponding static target beside left road edge 901a in advance(Trees 801, electric pole 802, isolation
Honest 803 etc.)Relatively left road edge 901a distance constant D, usually, trees 801, electric pole 802, isolation honest 803 are relative
The distance of road edge 901 is respectively present corresponding specification regulation, can be estimated based on these settings and obtain distance constant D
(Specific such as 0.5m)
So, quadratic function relation formula(2)It is determined, namely road edge curve is determined.
The method of the determination road edge of figure 3 above illustrated embodiment is both independent of lane line, also not dependent on image
Sensor is realized, is highly suitable to be applied for unstructured road(Such as lane line is fuzzy, the road of track heading line off or missing
Road)Middle acquisition road edge information, and road edge information can also be relatively accurately obtained at a distance.
Herein, both term " closely " and " remote " are the effective detections for being generally based on radar detedtor respectively
The effective detection range of distance and imaging sensor comes corresponding, usually, and the effective detection range of radar detedtor is relative to scheme
As the effective detection range of sensor is farther;Therefore, by less than or equal to the effective detection range of imaging sensor apart from model
Enclose and be defined as " closely ", " long distance of the application will be defined as beyond the distance range of the effective detection range of imaging sensor
From ".It is to be understood that, fixed distance value is not based between " closely " and " remote " to divide, for example, different shaped
Number the effective detection range of imaging sensor may be also different, also for example have, with the development of image sensor technologies, at this
The effective detection range of the imaging sensor newly emerged in large numbers after the applying date may also be farther.
The apparatus and method that example above primarily illustrates the determination road edge of the present invention.Although only to some of them originally
The embodiment of invention is described, but those of ordinary skill in the art are it is to be appreciated that the present invention can be without departing from it
Implement in spirit and scope in many other forms.Therefore, the example that is shown and embodiment be considered as it is schematical and
Nonrestrictive, in the case where not departing from the spirit and scope of the present invention as defined in appended claims, the present invention can
Various modifications and replacement can be covered.
Claims (17)
1. a kind of device for determining road edge, it is characterised in that including:
Radar detedtor on vehicle, the static mesh where it can at least detect vehicle beside the road edge of road
Mark;With
Processing component, it is configured as:Receive static target that the radar detedtor detected and to extract relative road big
The arrangement information of regularly arranged static target is caused, so as to obtain road edge information based on the arrangement information.
2. device as claimed in claim 1, it is characterised in that the processing component includes:
Screening unit, its be used for from the static target to filter out three or more than three relatively described roads substantially regular
The static target of arrangement is used as reference object;
Aim curve fitting unit, it is used for three or three reference objects described above march under vehicle coordinate system
Line is fitted to obtain corresponding reference object alignment curve;And
Road edge estimation unit, it is used to obtain the first road edge curve based on reference object alignment curve estimation.
3. device as claimed in claim 2, it is characterised in that the screening unit is configured as:Working as based on the vehicle
Preceding yaw velocity calculates the prediction driving trace for obtaining vehicle, is based further on the whether relatively described prediction of the static target
Driving trace is substantially regularly arranged to filter out respective stationary target as reference object.
4. device as claimed in claim 2, it is characterised in that the reference object alignment curve is following quadratic function relation
Formula(1):
Y=C2×X2 + C1×X + C0’ (1)
Wherein, X is independent variable, and it corresponds to the X-coordinate under the vehicle coordinate system, and the X-coordinate is defined as relatively described
The deviation of the distance of the barycenter of vehicle in vertical direction;Y is dependent variable, and it corresponds to the Y under the vehicle coordinate system
Coordinate, the Y-coordinate is defined as the deviation of the distance of the barycenter of relatively described vehicle in the horizontal direction;C2For secondary term coefficient, C1
For Monomial coefficient, C0' it is constant term;
Wherein, the coordinate information based on reference object under the vehicle coordinate system, calculates quadratic function relation formula(1)In
Secondary term coefficient C2, Monomial coefficient C1With constant term C0’;
Wherein, the current yaw velocity of the vehicle calculates the radius of turn of Current vehicle, so as to draw described secondary
Term coefficient C2;
Further, the road edge estimation unit is additionally configured to:From the quadratic function relation formula(1)Obtain following secondary
Functional relation(2)It is used as the first road edge curve:
Y=C2×X2 + C1×X + C0(2)
Wherein, C0For constant term, C0= C0'+D, D be road edge with respect to static target substantially regularly arranged beside it away from
From constant.
5. device as claimed in claim 1 or 2, it is characterised in that the radar detedtor is millimetre-wave radar.
6. device as claimed in claim 2, it is characterised in that described device also includes:Image on the vehicle
Sensor, it is used for the lane line image information for obtaining the road;
Wherein, the processing component is additionally configured to:Calculated based on the lane line image information and obtain the second of the road
Road edge curve, and the road of the road is determined based on the first road edge curve and the second road edge curve
Roadside is along curve.
7. device as claimed in claim 6, it is characterised in that the processing component is additionally configured to:The closely road of road
Roadside uses first of roadside along curve using the road edge curve of the second road edge curve, remote road
Along curve.
8. device as claimed in claim 6, it is characterised in that the processing component is additionally configured to:In the car of the road
Diatom is lacked or unsharp section is used as its road edge curve using the first road edge curve.
9. a kind of method for determining road edge, it is characterised in that including step:
(a)Static target where detecting vehicle beside the road edge of road;And
(b)The arrangement information of relative road substantially regularly arranged static target is extracted, and is obtained based on the arrangement information
Obtain road edge information.
10. method as claimed in claim 9, it is characterised in that the step(b)Including sub-step:
(b1)From in the static target filter out three or more than three relatively described roads it is substantially regularly arranged described in
Static target is used as reference object;
(b2)Three or three reference objects described above are carried out curve fitting under vehicle coordinate system corresponding to obtain
Reference object alignment curve;And
(b3)First road edge curve is obtained based on reference object alignment curve estimation.
11. method as claimed in claim 10, it is characterised in that the sub-step(b1)In, based on the current of the vehicle
Yaw velocity calculates the prediction driving trace for obtaining vehicle, is based further on the whether relatively described prediction row of the static target
Sail that track is substantially regularly arranged to filter out respective stationary target as reference object.
12. method as claimed in claim 10, it is characterised in that the step(b2)In, the reference object alignment curve
For following quadratic function relation formula(1):
Y=C2×X2 + C1×X + C0’ (1)
Wherein, X is independent variable, and it corresponds to the X-coordinate under the vehicle coordinate system, and the X-coordinate is defined as relatively described
The deviation of the distance of the barycenter of vehicle in vertical direction;Y is dependent variable, and it corresponds to the Y under the vehicle coordinate system
Coordinate, the Y-coordinate is defined as the deviation of the distance of the barycenter of relatively described vehicle in the horizontal direction;C2For secondary term coefficient, C1
For Monomial coefficient, C0' it is constant term;
Wherein, the coordinate information based on reference object under the vehicle coordinate system, calculates quadratic function relation formula(1)In
Secondary term coefficient C2, Monomial coefficient C1With constant term C0’;
Wherein, the radius of turn of Current vehicle is calculated based on the current yaw velocity of the vehicle, so as to draw described
Secondary term coefficient C2;
The step(b3)In, from the quadratic function relation formula(1)Obtain following quadratic function relation formula(2)It is used as first
Roadside is along curve:
Y=C2×X2 + C1×X + C0(2)
Wherein, C0For constant term, C0= C0'+D, D be road edge with respect to static target substantially regularly arranged beside it away from
From constant.
13. method as claimed in claim 9, it is characterised in that also including step:
Obtain the lane line image information of the road;
The the second road edge curve for obtaining the road is calculated based on the lane line image information;And
The road edge curve of the road is determined based on the first road edge curve and the second road edge curve.
14. method as claimed in claim 13, it is characterised in that it is determined that the road road edge curve the step of
In, closely the road edge curve of road uses the second road edge curve, the road edge curve of remote road
Using the first road edge curve.
15. method as claimed in claim 14, it is characterised in that it is determined that the road road edge curve the step of
In, its road edge is used as using the first road edge curve in the lane line missing of the road or unsharp section
Curve.
16. a kind of automated driving system for vehicle, it includes the determination road as any one of claim 1 to 8
The device at edge.
17. a kind of vehicle, is provided with automated driving system, it is characterised in that set in the automated driving system just like right
It is required that the device of the determination road edge any one of 1-8.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710196345.2A CN106991389B (en) | 2017-03-29 | 2017-03-29 | Device and method for determining road edge |
PCT/CN2018/075130 WO2018177026A1 (en) | 2017-03-29 | 2018-02-02 | Device and method for determining road edge |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710196345.2A CN106991389B (en) | 2017-03-29 | 2017-03-29 | Device and method for determining road edge |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106991389A true CN106991389A (en) | 2017-07-28 |
CN106991389B CN106991389B (en) | 2021-04-27 |
Family
ID=59412995
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710196345.2A Active CN106991389B (en) | 2017-03-29 | 2017-03-29 | Device and method for determining road edge |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106991389B (en) |
WO (1) | WO2018177026A1 (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108573272A (en) * | 2017-12-15 | 2018-09-25 | 蔚来汽车有限公司 | Track approximating method |
CN108572642A (en) * | 2017-12-15 | 2018-09-25 | 蔚来汽车有限公司 | A kind of automated driving system and its crosswise joint method |
WO2018177026A1 (en) * | 2017-03-29 | 2018-10-04 | 蔚来汽车有限公司 | Device and method for determining road edge |
CN108693517A (en) * | 2018-05-22 | 2018-10-23 | 森思泰克河北科技有限公司 | Vehicle positioning method, device and radar |
CN109254289A (en) * | 2018-11-01 | 2019-01-22 | 百度在线网络技术(北京)有限公司 | The detection method and detection device of road guard |
CN109895694A (en) * | 2017-12-08 | 2019-06-18 | 郑州宇通客车股份有限公司 | A kind of lane departure warning method, device and vehicle |
CN110174113A (en) * | 2019-04-28 | 2019-08-27 | 福瑞泰克智能系统有限公司 | A kind of localization method, device and the terminal in vehicle driving lane |
CN110244696A (en) * | 2019-06-24 | 2019-09-17 | 北京经纬恒润科技有限公司 | Vehicle body crosswise joint method and electronic control unit ECU |
CN110320504A (en) * | 2019-07-29 | 2019-10-11 | 浙江大学 | A kind of unstructured road detection method based on laser radar point cloud statistics geometrical model |
CN110736981A (en) * | 2018-07-19 | 2020-01-31 | 德尔福技术有限责任公司 | Radar-based tracking of slow moving objects |
CN111198370A (en) * | 2020-01-02 | 2020-05-26 | 北京百度网讯科技有限公司 | Millimeter wave radar background detection method and device, electronic equipment and storage medium |
CN111289980A (en) * | 2020-03-06 | 2020-06-16 | 成都纳雷科技有限公司 | Roadside stationary object detection method and system based on vehicle-mounted millimeter wave radar |
CN112597839A (en) * | 2020-12-14 | 2021-04-02 | 上海宏景智驾信息科技有限公司 | Road boundary detection method based on vehicle-mounted millimeter wave radar |
CN112949489A (en) * | 2021-03-01 | 2021-06-11 | 成都安智杰科技有限公司 | Road boundary identification method and device, electronic equipment and storage medium |
WO2022183369A1 (en) * | 2021-03-02 | 2022-09-09 | 华为技术有限公司 | Target detection method and apparatus |
CN118212232A (en) * | 2024-05-20 | 2024-06-18 | 安徽蔚来智驾科技有限公司 | Linear element detection method, intelligent device and computer readable storage medium |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112132109A (en) * | 2020-10-10 | 2020-12-25 | 北京百度网讯科技有限公司 | Lane line processing and lane positioning method, device, equipment and storage medium |
CN113762011B (en) * | 2020-11-25 | 2024-06-21 | 北京京东乾石科技有限公司 | Method, device, equipment and storage medium for detecting curbstone |
CN113525368A (en) * | 2021-06-23 | 2021-10-22 | 清华大学 | Lane keeping emergency control strategy and safety control method and device for vehicle |
CN113879312B (en) * | 2021-11-01 | 2023-02-28 | 无锡威孚高科技集团股份有限公司 | Forward target selection method and device based on multi-sensor fusion and storage medium |
CN114067120B (en) * | 2022-01-17 | 2022-09-20 | 腾讯科技(深圳)有限公司 | Augmented reality-based navigation paving method, device and computer readable medium |
CN114475614A (en) * | 2022-03-21 | 2022-05-13 | 中国第一汽车股份有限公司 | Method, device, medium and equipment for screening dangerous targets |
CN114872712B (en) * | 2022-06-29 | 2022-10-18 | 小米汽车科技有限公司 | Static vehicle detection method, device, equipment, vehicle and storage medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6728392B1 (en) * | 2001-01-30 | 2004-04-27 | Navigation Technologies Corp. | Shape comparison using a rotational variation metric and applications thereof |
CN101210825A (en) * | 2006-12-27 | 2008-07-02 | 爱信艾达株式会社 | Map information generating systems |
CN102275587A (en) * | 2011-06-07 | 2011-12-14 | 长安大学 | Rear vehicle collision danger monitoring device and monitoring method thereof |
CN104002809A (en) * | 2014-05-28 | 2014-08-27 | 长安大学 | Vehicle fork road segment detection device and detection method |
US20140306844A1 (en) * | 2013-04-11 | 2014-10-16 | Mando Corporation | Lane estimation apparatus and method |
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 |
CN105711588A (en) * | 2016-01-20 | 2016-06-29 | 奇瑞汽车股份有限公司 | Lane keeping assist system and lane keeping assist method |
CN106326850A (en) * | 2016-08-18 | 2017-01-11 | 宁波傲视智绘光电科技有限公司 | Fast lane line detection method |
CN106476689A (en) * | 2015-08-27 | 2017-03-08 | 长城汽车股份有限公司 | A kind of road limit for width alert device and method for vehicle |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106463064B (en) * | 2014-06-19 | 2020-06-26 | 日立汽车系统株式会社 | Object recognition device and vehicle travel control device using same |
CN105922991B (en) * | 2016-05-27 | 2018-08-17 | 广州大学 | Based on the lane departure warning method and system for generating virtual lane line |
CN106991389B (en) * | 2017-03-29 | 2021-04-27 | 蔚来(安徽)控股有限公司 | Device and method for determining road edge |
-
2017
- 2017-03-29 CN CN201710196345.2A patent/CN106991389B/en active Active
-
2018
- 2018-02-02 WO PCT/CN2018/075130 patent/WO2018177026A1/en active Application Filing
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6728392B1 (en) * | 2001-01-30 | 2004-04-27 | Navigation Technologies Corp. | Shape comparison using a rotational variation metric and applications thereof |
CN101210825A (en) * | 2006-12-27 | 2008-07-02 | 爱信艾达株式会社 | Map information generating systems |
CN102275587A (en) * | 2011-06-07 | 2011-12-14 | 长安大学 | Rear vehicle collision danger monitoring device and monitoring method thereof |
US20140306844A1 (en) * | 2013-04-11 | 2014-10-16 | Mando Corporation | Lane estimation apparatus and method |
CN104002809A (en) * | 2014-05-28 | 2014-08-27 | 长安大学 | Vehicle fork road segment detection device and detection method |
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 |
CN106476689A (en) * | 2015-08-27 | 2017-03-08 | 长城汽车股份有限公司 | A kind of road limit for width alert device and method for vehicle |
CN105711588A (en) * | 2016-01-20 | 2016-06-29 | 奇瑞汽车股份有限公司 | Lane keeping assist system and lane keeping assist method |
CN106326850A (en) * | 2016-08-18 | 2017-01-11 | 宁波傲视智绘光电科技有限公司 | Fast lane line detection method |
Non-Patent Citations (3)
Title |
---|
DAS S ET AL.: "Use of Salient Features for the Design of a Multistage Framework to Extract Ros From High-Resolution Multispectral Satellit Images", 《IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTS SENSING》 * |
曹旭光: "非结构化道路识别及拟合算法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
林桂潮 等: "改进随机样本一致性算法的弯曲果园道路检测", 《农业工程学报》 * |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018177026A1 (en) * | 2017-03-29 | 2018-10-04 | 蔚来汽车有限公司 | Device and method for determining road edge |
CN109895694A (en) * | 2017-12-08 | 2019-06-18 | 郑州宇通客车股份有限公司 | A kind of lane departure warning method, device and vehicle |
CN109895694B (en) * | 2017-12-08 | 2020-10-20 | 郑州宇通客车股份有限公司 | Lane departure early warning method and device and vehicle |
CN108572642A (en) * | 2017-12-15 | 2018-09-25 | 蔚来汽车有限公司 | A kind of automated driving system and its crosswise joint method |
CN108573272A (en) * | 2017-12-15 | 2018-09-25 | 蔚来汽车有限公司 | Track approximating method |
CN108573272B (en) * | 2017-12-15 | 2021-10-29 | 蔚来(安徽)控股有限公司 | Lane fitting method |
CN108693517B (en) * | 2018-05-22 | 2020-10-09 | 森思泰克河北科技有限公司 | Vehicle positioning method and device and radar |
CN108693517A (en) * | 2018-05-22 | 2018-10-23 | 森思泰克河北科技有限公司 | Vehicle positioning method, device and radar |
CN110736981B (en) * | 2018-07-19 | 2023-12-05 | 德尔福技术有限责任公司 | Radar-based tracking of slowly moving objects |
CN110736981A (en) * | 2018-07-19 | 2020-01-31 | 德尔福技术有限责任公司 | Radar-based tracking of slow moving objects |
CN109254289A (en) * | 2018-11-01 | 2019-01-22 | 百度在线网络技术(北京)有限公司 | The detection method and detection device of road guard |
CN110174113A (en) * | 2019-04-28 | 2019-08-27 | 福瑞泰克智能系统有限公司 | A kind of localization method, device and the terminal in vehicle driving lane |
CN110244696A (en) * | 2019-06-24 | 2019-09-17 | 北京经纬恒润科技有限公司 | Vehicle body crosswise joint method and electronic control unit ECU |
CN110320504B (en) * | 2019-07-29 | 2021-05-18 | 浙江大学 | Unstructured road detection method based on laser radar point cloud statistical geometric model |
CN110320504A (en) * | 2019-07-29 | 2019-10-11 | 浙江大学 | A kind of unstructured road detection method based on laser radar point cloud statistics geometrical model |
CN111198370A (en) * | 2020-01-02 | 2020-05-26 | 北京百度网讯科技有限公司 | Millimeter wave radar background detection method and device, electronic equipment and storage medium |
CN111289980A (en) * | 2020-03-06 | 2020-06-16 | 成都纳雷科技有限公司 | Roadside stationary object detection method and system based on vehicle-mounted millimeter wave radar |
CN111289980B (en) * | 2020-03-06 | 2022-03-08 | 成都纳雷科技有限公司 | Roadside stationary object detection method and system based on vehicle-mounted millimeter wave radar |
CN112597839A (en) * | 2020-12-14 | 2021-04-02 | 上海宏景智驾信息科技有限公司 | Road boundary detection method based on vehicle-mounted millimeter wave radar |
CN112597839B (en) * | 2020-12-14 | 2022-07-08 | 上海宏景智驾信息科技有限公司 | Road boundary detection method based on vehicle-mounted millimeter wave radar |
CN112949489A (en) * | 2021-03-01 | 2021-06-11 | 成都安智杰科技有限公司 | Road boundary identification method and device, electronic equipment and storage medium |
CN112949489B (en) * | 2021-03-01 | 2023-05-12 | 成都安智杰科技有限公司 | Road boundary identification method and device, electronic equipment and storage medium |
WO2022183369A1 (en) * | 2021-03-02 | 2022-09-09 | 华为技术有限公司 | Target detection method and apparatus |
CN118212232A (en) * | 2024-05-20 | 2024-06-18 | 安徽蔚来智驾科技有限公司 | Linear element detection method, intelligent device and computer readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2018177026A1 (en) | 2018-10-04 |
CN106991389B (en) | 2021-04-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106991389A (en) | The apparatus and method for determining road edge | |
CN104793202B (en) | The object emerging system of more radar imagery sensors | |
US9083856B2 (en) | Vehicle speed measurement method and system utilizing a single image capturing unit | |
CN106772435B (en) | A kind of unmanned plane barrier-avoiding method and device | |
US9607220B1 (en) | Image-based vehicle speed estimation | |
CN109791598A (en) | The image processing method of land mark and land mark detection system for identification | |
CN112562405A (en) | Radar video intelligent fusion and early warning method and system | |
US20140313347A1 (en) | Traffic camera calibration update utilizing scene analysis | |
KR101822373B1 (en) | Apparatus and method for detecting object | |
CN106203381B (en) | Obstacle detection method and device in a kind of driving | |
CN111316128A (en) | Continuous obstacle detection method, device, system and storage medium | |
CN103176185A (en) | Method and system for detecting road barrier | |
CN110379168A (en) | A kind of vehicular traffic information acquisition method based on Mask R-CNN | |
CN113505638B (en) | Method and device for monitoring traffic flow and computer readable storage medium | |
CN110110678A (en) | Determination method and apparatus, storage medium and the electronic device of road boundary | |
CN113093128A (en) | Method and device for calibrating millimeter wave radar, electronic equipment and road side equipment | |
CN115018879A (en) | Target detection method, computer-readable storage medium, and driving apparatus | |
CN110426714B (en) | Obstacle identification method | |
EP3467545A1 (en) | Object classification | |
CN112447060A (en) | Method and device for recognizing lane and computing equipment | |
KR101878427B1 (en) | Traffic radar device, traffic management server, traffic management system, and method of tracking object move traces | |
CN112037536A (en) | Vehicle speed measuring method and device based on video feature recognition | |
CN115542338B (en) | Laser radar data learning method based on point cloud spatial distribution mapping | |
CN115856908A (en) | Vehicle speed measurement method and system based on three-dimensional laser radar | |
CN113183982A (en) | Method and device for generating driving route of vehicle and automatic driving vehicle |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200731 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 |