CN108896994A - A kind of automatic driving vehicle localization method and equipment - Google Patents
A kind of automatic driving vehicle localization method and equipment Download PDFInfo
- Publication number
- CN108896994A CN108896994A CN201810447923.XA CN201810447923A CN108896994A CN 108896994 A CN108896994 A CN 108896994A CN 201810447923 A CN201810447923 A CN 201810447923A CN 108896994 A CN108896994 A CN 108896994A
- Authority
- CN
- China
- Prior art keywords
- information
- vehicle
- trailer
- radar
- data
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/867—Combination of radar systems with cameras
Abstract
The present invention relates to a kind of automatic driving vehicle localization methods to include the following steps suitable for executing in calculating equipment：Vehicle vision information is obtained, the vehicle vision information derives from vehicle-mounted vidicon, including barrier visual information, curb visual information, lane line visual information and signal lamp visual information；Trailer-mounted radar information is obtained, the trailer-mounted radar information derives from trailer-mounted radar, including relative vehicle radar information and barrier radar information；The vehicle vision information and the trailer-mounted radar information are fused in vehicular map information according to default registration relationship, generate vehicle location information.Automatic driving vehicle localization method provided by the invention is mutually merged by the visual information for obtaining video camera with the radar information that trailer-mounted radar obtains, and can obtain the more accurate location information of this vehicle without the information that global position system provides and then guiding vehicle accurately travels safely.
Description
Technical field
The present invention relates to unmanned technical fields, more particularly to a kind of automatic driving vehicle localization method and equipment.
Background technique
The positive accelerated development in recent years of automatic driving vehicle technology, safety, in terms of have very
Big advantage, it is considered to be solve traffic congestion, reduce traffic accident and improve the effective way of environmental pollution.Nearest one
In the section time, with the continuous development of artificial intelligence and intelligent vehicle, unmanned technology is got the attention, and is become not
Carry out the important directions of development of automobile.
However the application scenarios of automatic driving vehicle are carried out under openr environment mostly at present, non-open
Scene under and the time of bad visibility under it is unmanned, be easy to appear deviation, be easy to produce and unfavorable asked to driving safely
Topic.Basic reason is that the positioning provided in the prior art depends on satellite navigation system/inertial navigation system, thus non-
The accurate vehicle body position of vehicle cannot be obtained under open scene or in satellite navigation system/abnormal situation of inertial navigation system work
It sets, automatic driving vehicle also can not just be instructed accurately to travel safely.
Summary of the invention
Based on this, it is necessary at least one problem mentioned above, a kind of automatic driving vehicle localization method is provided,
And corresponding automatic driving vehicle positioning device.
A kind of automatic driving vehicle localization method includes the following steps suitable for executing in calculating equipment：
Obtain vehicle vision information, the vehicle vision information derive from vehicle-mounted vidicon, including barrier visual information,
Curb visual information, lane line visual information and signal lamp visual information；
Trailer-mounted radar information is obtained, the trailer-mounted radar information derives from trailer-mounted radar, including relative vehicle radar information
With barrier radar information；
The vehicle vision information and the trailer-mounted radar information are fused to vehicular map according to default registration relationship to believe
In breath, vehicle location information is generated.
The figure that the vehicle vision information is absorbed on several sequential time points by video camera in one of the embodiments,
As information forms；The trailer-mounted radar information is made of the geography information that trailer-mounted radar acquires on several sequential time points.
Further, described to merge the vehicle vision information and the trailer-mounted radar information according to default registration relationship
Into vehicular map information, generate vehicle location information the step of specifically include：
Angle point data are extracted from described image information；
The track data of the vehicle is calculated according to the angle point data, and according to the default registration relationship and vehicle-mounted thunder
Correction track data is generated up to information；
The correction track data is mapped in the vehicular map information, vehicle location information is generated.
In one of the embodiments, the relative vehicle radar information include vehicle spacing data, direction of traffic data,
Vehicle relative velocity data；The barrier radar information includes range data, bearing data and relative velocity data.
The default registration relationship is that the trailer-mounted radar information and the vehicle vision are believed in one of the embodiments,
With the functional relation between location point in breath.
Further, the functional relation is specially Mr=R*Mc, and wherein Mc is coordinate Mc of the point M under camera coordinates system
(Xc, Yc, Zc), Mr are coordinate Mr (Xr, Yr) of the point M under radar image coordinate.
The vehicular map information includes satellite navigation data in one of the embodiments, the satellite navigation data
By selecting from one of GPS data, BDS data, GLONASS data and GALILEO data.
The automatic driving vehicle localization method further includes being obtained by Inertial Measurement Unit in one of the embodiments,
The step of vehicle inertia information, the vehicle inertia information is for correcting the trailer-mounted radar information.
Invention also provides a kind of vehicle-mounted storage equipment, wherein be stored with a plurality of instruction, described instruction be suitable for by
Reason device is loaded and is executed：
Obtain vehicle vision information, the vehicle vision information derive from vehicle-mounted vidicon, including barrier visual information,
Curb visual information, lane line visual information and signal lamp visual information；
Trailer-mounted radar information is obtained, the trailer-mounted radar information derives from trailer-mounted radar, including relative vehicle radar information
With barrier radar information；
The vehicle vision information and the trailer-mounted radar information are fused to vehicular map according to default registration relationship to believe
In breath, vehicle location information is generated.
Correspondingly, the present invention provides a kind of vehicle mobile terminals, including processor, are adapted for carrying out each instruction；And it deposits
Equipment is stored up, is suitable for storing a plurality of instruction, described instruction is suitable for being loaded and being executed by processor：
Obtain vehicle vision information, the vehicle vision information derive from vehicle-mounted vidicon, including barrier visual information,
Curb visual information, lane line visual information and signal lamp visual information；
Trailer-mounted radar information is obtained, the trailer-mounted radar information derives from trailer-mounted radar, including relative vehicle radar information
With barrier radar information；
The vehicle vision information and the trailer-mounted radar information are fused to vehicular map according to default registration relationship to believe
In breath, vehicle location information is generated.
Automatic driving vehicle localization method provided by the invention passes through the visual information and trailer-mounted radar that obtain video camera
The radar information of acquisition mutually merges, and improves and detects the accurate of other object spaces in addition to this vehicle in particular circumstances
Property, the more accurate location information of this vehicle can be obtained without the information that global position system provides, and pass through the position
Information MAP generates vehicle location information into vehicular map to instruct on-board driving system drive vehicle safety accurately to go
It sails.
Detailed description of the invention
Fig. 1 is the automatic driving vehicle localization method flow chart in one embodiment of the invention；
Fig. 2 is the automatic driving vehicle localization method flow chart in another embodiment of the present invention；
Fig. 3 is the vehicle mobile terminals structural schematic diagram in another embodiment of the present invention.
Specific embodiment
To facilitate the understanding of the present invention, a more comprehensive description of the invention is given in the following sections with reference to the relevant attached drawings.In attached drawing
Give presently preferred embodiments of the present invention.But the invention can be realized in many different forms, however it is not limited to this paper institute
The embodiment of description.On the contrary, purpose of providing these embodiments is keeps the understanding to the disclosure more thorough
Comprehensively.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in specification of the invention
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member
Part is " connected " or when " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " may include being wirelessly connected or wirelessly coupling.It is used herein to arrange
Diction "and/or" includes one or more associated wholes for listing item or any cell and all combinations.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific term), there is meaning identical with the general understanding of those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have in the context of the prior art
The consistent meaning of meaning, and unless idealization or meaning too formal otherwise will not be used by specific definitions as here
To explain.
A kind of automatic driving vehicle localization method is provided in one embodiment of the invention, as shown in Figure 1, being suitable for setting in calculating
Standby middle execution, includes the following steps S100~S300：
S100：Vehicle vision information is obtained, the vehicle vision information derives from vehicle-mounted vidicon, including barrier vision
Information, curb visual information, lane line visual information and signal lamp visual information.
An important component is exactly vehicle-mounted vision camera on automatic driving vehicle, can by the vehicle-mounted vision camera
The visual information namely image information or video information for getting vehicle periphery all objects, when with single picture or one section
Between interval in video stream exist, can learn shape, the color of vehicle periphery object, even motion state and fortune
The information such as dynamic direction.Vehicle-mounted vidicon is usually arranged multiple, is distributed in around automatic driving vehicle according to certain rule, to obtain
Vehicle periphery information as comprehensive as possible.Data accessed by each vehicle-mounted vidicon have to be assigned by each vehicle-mounted vidicon
The position mark given, to supply computing module accurate application.Wherein barrier visual information refers to that automatic driving vehicle nearby occurs
Possibility hinder image or video information, such as pedestrian, animal, other vehicles, the sundries on road surface of object of traveling etc..Road
Along visual information refer to the vehicle got by vehicle-mounted vidicon where road edge label line image or video information, and lane
Line visual information is then the image or video information of the traffic sign line of road where the vehicle that vehicle-mounted vidicon is got, such as
Existing double amber lines, direction line, left-hand bend or right-hand bend index line etc..Signal lamp visual information then includes coming from road
The image or video information of the driving status indicator light of traffic lights or other vehicles, such as traffic lights, front or after
Brake lamp, turn signal of square vehicle etc..
S200：Trailer-mounted radar information is obtained, the trailer-mounted radar information derives from trailer-mounted radar, including relative vehicle radar
Information and barrier radar information.
The visual resolving power of vehicle-mounted vidicon is high, stronger to the sensing capability of the information such as color, shape, but is easy to be visited
From the influence with light intensity etc., this just needs to carry out reinforcement and correction to information accessed by step S100, utilize for ranging
Trailer-mounted radar can be realized this purpose.Radar system is necessarily mounted on automatic driving vehicle, as accurate Driving control
Information collecting device preferentially selects millimetre-wave radar.The trailer-mounted radar information that trailer-mounted radar is got includes relative vehicle radar
Information, relative vehicle radar information refer to the radar information between vehicle and vehicle, using this vehicle as object of reference, radar detection arrive with
Information between surrounding vehicles is preferred, and relative vehicle radar information includes vehicle spacing data, direction of traffic data, vehicle phase
To speed data etc., barrier radar information includes the range data of vehicle and obstacles around the vehicle, bearing data and opposite
Speed data etc..
It is further preferred that automatic driving vehicle localization method further includes obtaining vehicle by Inertial Measurement Unit (IMU)
The step of Inertia information, vehicle inertia information is for correcting above-mentioned trailer-mounted radar information.It is opposed using real-time IMU position data
Than calibration, automatic driving vehicle itself exact position in special screne is derived.
Need to make an explanation, above-mentioned steps S100 and S200 might not according to step S100 formerly and step S200
Posterior sequence, the two are substantially to obtain corresponding information simultaneously on same time point, could so cooperate with and describe nobody
The real time running state for driving vehicle instructs imminent driving status according to the real time running state.In addition, video information
The essence image information set that be the frame image on several continuous time points obtained with certain playback rate namely vehicle vision
Information is absorbed on several sequential time points by video camera and acquired image information forms.Equally, trailer-mounted radar information
And be made of the geography information that trailer-mounted radar absorbs on several sequential time points, which includes physical location, phase
To spacing, even relative velocity between object.
S300：The vehicle vision information and the trailer-mounted radar information are fused to vehicle-mountedly according to default registration relationship
In figure information, vehicle location information is generated.
On the basis of step S100 and step S200 the vehicle vision information got and trailer-mounted radar information, it is also necessary to
The two is merged, trailer-mounted radar information is allowed to come reinforcement and correction vehicle vision information, it is more accurately unmanned to obtain
The location information of vehicle.After getting the accurate location information of vehicle, needs to be fused to and be preloaded in nobody
It drives in the vehicular map information in vehicle memory itself or processor, it is fixed to obtain the vehicle in the vehicular map information
Position information passes through the traveling technological guidance automatic driving vehicle safety essence in unmanned technology further according to vehicle location information
Really advance.In the process, be not necessarily required to the satellite navigation information using the vehicles such as vehicle GPS information, avoid because
Vehicle enters the positions such as the weaker forest of tunnel, mobile communication signal or suburb and can not receive navigation information in time and cause to travel
The problem of deviation, gets rid of dependence of the automatic driving vehicle for satellite navigation information and mobile communications network situation.In addition,
Even believing under night, greasy weather or the undesirable driving conditions of rainy day visual isopter by vehicle vision information and trailer-mounted radar
The mutual reinforcement and correction of breath, can also get and depend merely on satellite navigation or vehicle-mounted vidicon or trailer-mounted radar more than originally
Accurate and safety vehicle location information.
It is, of course, preferable to, it is unpiloted that automatic driving vehicle can be further increased using access satellite navigation data
Safety and accuracy, thus vehicular map information can also include satellite navigation data.Usual mobile communication signal is defended
Star navigation signal covers good area, and there are boundaries with bad area is covered, when vehicle is by chance in the boundary, row
Route line is simultaneously not mutated, and the traveling in latter time interval is still enterprising on the vehicle location information basis of previous interval
Capable, thus access in the previous interval for having satellite navigation data and be capable of providing more accurate vehicle location information, with
The vehicle in latter time interval is more accurately instructed to advance.The satellite navigation data is not limited to common GPS data, may be used also
To be BDS data (Beidou navigation data), GLONASS data (GLONASS navigation data, Russia provide) and GALILEO number
According to one or more of (Galileo navigation data, European Union provide).
Further, as one of them preferred scheme, as shown in Fig. 2, vehicle vision information and trailer-mounted radar are believed
Breath according to preset registration relationship be fused in vehicular map information, generate vehicle location information the step of specifically include S310~
S330：
S310：Angle point data are extracted from image information.
As mentioned above, vehicle vision information is intake and acquired image information on several sequential time points
Composition, includes numerous contents in the visual information image information that vehicle-mounted vidicon is got, such as color, shape, opposite
Distance etc., angle point data are extracted using computer vision technique from image information.Angle point is image important feature, right
The understanding and analysis of image graphics play a very important role.Angle point, can be effective while retaining image graphics important feature
Ground reduce information data volume, can reflection image graphics information as much as possible, improve calculation processing rate, favorably
It is reliably matched in the real-time of image.Preferably, vehicle vision information is acquired using binocular stereo vision scheme, that is, is passed through
3 D stereo video camera obtains, and the vehicle vision information obtained with this solution not only has in the primary images such as color, shape
Hold (shape and color can be reflected by the angle point of different attribute), additionally it is possible to based on SLAM algorithm, to the depth in image
Degree information is handled, and interframe registration Algorithm is added in the plane information in the image with depth information, to improve interframe
The robustness and precision of registration Algorithm are stablized and obtain more accurate vehicle vision information.Use index weight function --- it cuts
Disconnected symbolic measurement body, rebuilds the image depth information of vehicle vision information, which compares common weight
Function can preferably reduce the influence that image depth information is rebuild in camera depth distortion.
S320：The track data of vehicle is calculated according to angle point data, and according to default registration relationship and trailer-mounted radar information
Generate correction track data.
The target that visual sensor is mainly extracted includes：Lane line, the figure of curb, tunnel face, signal lamppost etc. object
Image angle point data, the position of subject matter is calculated according to angle point data, and particular content includes：
1, the R of present frame is solved by previous frame image | (R is spin matrix to t, for determining the posture of two field pictures
Relationship, t are translation vector), i.e., relative to the posture of former frame and displacement.
2, camera coordinate system is transformed into world coordinate system.This conversion method can obtain in related art
It arrives, now briefly makes specific aim explanation：Assuming that the homogeneous coordinates under the world coordinates of spatial point P are (Xw, Yw, Zw, 1)T, and phase
Homogeneous coordinates under machine coordinate are (Xc, Yc, Zc, 1)T, image coordinate is (x, y), and pixel coordinate is (u, v), these coordinates it
Between transformational relation be：
Wherein, under image coordinate system, dx, dy are physical size of the pixel in x-axis and y-axis direction；(u0, v0)
For coordinate of the image center under image coordinate system；F is the focal length of camera lens.Angle point data extraction algorithm is based on deep
It spends the frame of study and is optimized using RANSAC algorithm (a kind of stochastical sampling consistency algorithm based on probability and statistics),
It needs to eliminate wrong characteristic matching point in calculating process, such as eliminates caused by the sludge or dust being deposited on camera lens
Error corner point data.
Angle point data by obtaining multiple continuous same sensation targets can calculate the track data of vehicle.So
And the track data is only provided by vehicle-mounted visual information, it is perfect not enough, need with the mutual reinforcement of trailer-mounted radar information and correction,
It, can be according to acquired matching relationship since there are matching relationships as described below with trailer-mounted radar information for vehicle-mounted visual information
Function is corrected the vehicle-mounted visual information obtained in actual travel scene with trailer-mounted radar information.Default registration relationship is institute
It states in trailer-mounted radar information and the vehicle vision information with the functional relation between location point, namely is able to reflect simultaneously in vehicle
The functional relation of the same target in radar information and vehicle vision information is carried, only such as lane line number in vehicle vision information
According to, be not provided with the lane line of sensor since current trailer-mounted radar can not be found out, the two also just there is no default registration relationship,
Certainly it is not precluded within marker or sensor that setting in lane line can be found out by radar and be absorbed image by vehicle-mounted vidicon, when
There are when such marker or sensor, the default registration relationship above-mentioned for same target is naturally existed also.Functional relation
Specially：Mr=R*Mc；Wherein R is one 2 × 3 matrix, Mc be point M under camera coordinates system coordinate Mc (Xc, Yc,
Zc), Mr is coordinate Mr (Xr, Yr) of the point M under radar image coordinate system.If known coordinate Mr and Mc, so that it may be registrated
Relationship R, and the registration relationship is applied, by the reinforcement of trailer-mounted radar information and correct the correspondence portion in vehicle-mounted visual information
Point.Coordinate Mr and Mc by preparatory test and can be calculated, thus being registrated relationship R is also that can be previously obtained confirmation.
According to trailer-mounted radar information and the track data of registration relationship R available reinforcement and calibration, i.e. correction track
Data, in case being applied in the later period.
S330：High-ranking officers' positive rail data are mapped in vehicular map information, generate vehicle location information.
After obtaining correction track data by step S320, is mapped and be fused in existing vehicular map information, increased
Data content in vehicular map information database, real-time lane line, curb, the tunnel that automatic driving vehicle is got
The data such as mouth, signal lamppost, vehicle spacing, car speed, barrier volume and motion state increase in vehicular map, to
Guiding vehicle driving system generates vehicle location information, guiding vehicle fortune in cartographic information according to the vehicle after the fuse information
It is dynamic.Vehicular map information database has data access compatibility, can realize data by map datum related art
Mapping and expansion.It should be mentioned that vehicular map information refers not only to the ground being loaded in automatic driving vehicle computer system
Diagram data further includes the map datum in other mobile terminals such as mobile phone or laptop and other moving map terminals,
When using the map datum of other mobile terminals, it need to also be provided in automatic driving vehicle localization method and communication of mobile terminal
The step of, since the particular technique content-related technology field personnel of the step can know that therefore not to repeat here.
Present invention simultaneously provides a kind of vehicle-mounted storage equipment, wherein be stored with a plurality of instruction, these instructions be suitable for by
Device is managed to load and execute following method steps S100~S300 in the processor：
S100：Vehicle vision information is obtained, the vehicle vision information derives from vehicle-mounted vidicon, including barrier vision
Information, curb visual information, lane line visual information and signal lamp visual information.
S200：Trailer-mounted radar information is obtained, the trailer-mounted radar information derives from trailer-mounted radar, including relative vehicle radar
Information and barrier radar information.
S300：The vehicle vision information and the trailer-mounted radar information are fused to vehicle-mountedly according to default registration relationship
In figure information, vehicle location information is generated.
The specific implementation process of the above method has elaborated above, and for details, reference can be made to foregoing descriptions.It needs
Bright, storage medium mentioned above can be read-only memory, disk or CD etc..
Correspondingly, the present invention provides a kind of vehicle mobile terminals, including processor, are adapted for carrying out each instruction；And it deposits
Equipment is stored up, is suitable for storing a plurality of instruction, these instructions are suitable for being loaded by processor and executing the following steps：
S100：Vehicle vision information is obtained, the vehicle vision information derives from vehicle-mounted vidicon, including barrier vision
Information, curb visual information, lane line visual information and signal lamp visual information.
S200：Trailer-mounted radar information is obtained, the trailer-mounted radar information derives from trailer-mounted radar, including relative vehicle radar
Information and barrier radar information.
S300：The vehicle vision information and the trailer-mounted radar information are fused to vehicle-mountedly according to default registration relationship
In figure information, vehicle location information is generated.
Vision has been specifically included in the vehicle mobile terminals obtains module, radar module and Fusion Module, as shown in figure 3,
Wherein vision obtains module and derives from vehicle-mounted vidicon, including barrier for obtaining vehicle vision information, the vehicle vision information
Hinder object visual information, curb visual information, lane line visual information and signal lamp visual information.Radar module is vehicle-mounted for obtaining
Radar information, the trailer-mounted radar information derive from trailer-mounted radar, including relative vehicle radar information and barrier radar information.
And Fusion Module is vehicle-mounted for the vehicle vision information and the trailer-mounted radar information to be fused to according to default registration relationship
In cartographic information, vehicle location information is generated.The vehicle mobile terminals are not limited only to be mounted on the end on automatic driving vehicle
End equipment, can be other mobile terminal equipments, and the moveable terminal has and carries out letter with automatic driving vehicle
The interface of docking is ceased, in order to form stand-alone product.
It preferably, further include having extraction unit, correction unit and map unit in Fusion Module, wherein extraction unit
For extracting angle point data from image information, correction unit is used to calculate the track data of vehicle according to angle point data, and
According to registration relationship and trailer-mounted radar information generation correction track data is preset, map unit is mapped for high-ranking officers' positive rail data
Into vehicular map information, vehicle location information is generated.The realization of specific functional mode methodology above step into
It has gone and has elaborated, it can be referring specifically to foregoing description.
Automatic driving vehicle localization method provided by the invention and equipment for ease of understanding, the present invention also provides below
A kind of application example：
Vehicle mobile terminals on automatic driving vehicle include vehicle-mounted vidicon and trailer-mounted radar simultaneously, the two work simultaneously
Make.Go out in tunnel face, vehicle-mounted vidicon intake to indicator light image on tunnel face image, surrounding vehicles image, front and back vehicle,
Road traffic line image, traffic lights image (there may be) etc., trailer-mounted radar detect tunnel face radar data, surrounding vehicle
Indicator light radar data on radar data, fore-aft vehicle, traffic lights radar data etc. on road, vehicle mobile terminals are logical
Cross the phase that the above-mentioned trailer-mounted radar Data correction got also exists in the vehicle-mounted visual information that vehicle-mounted vidicon is got
Vehicle movement with the motion information (information including relative static conditions) of object or characteristic point, after getting reinforcement and correction
Trace information, the map unit in vehicle mobile terminals in Fusion Module again map the vehicle movement trace information after the correction
Into vehicular map information, real-time vehicular map data are become, generate vehicle in the vehicle location information of tunnel face, and nothing
People drives the driving system on vehicle and is advanced according to the vehicle location information guiding vehicle.When vehicle enters in tunnel, on
It states equipment and repeats the above process, constantly obtain new vehicle location information, continuous guiding vehicle is advanced.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
The above is only some embodiments of the invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (10)
1. a kind of automatic driving vehicle localization method, suitable for being executed in calculating equipment, which is characterized in that include the following steps：
Vehicle vision information is obtained, the vehicle vision information derives from vehicle-mounted vidicon, including barrier visual information, curb
Visual information, lane line visual information and signal lamp visual information；
Trailer-mounted radar information is obtained, the trailer-mounted radar information derives from trailer-mounted radar, including relative vehicle radar information and barrier
Hinder object radar information；
The vehicle vision information and the trailer-mounted radar information are fused in vehicular map information according to default registration relationship,
Generate vehicle location information.
2. automatic driving vehicle localization method according to claim 1, which is characterized in that the vehicle vision information is by taking the photograph
The image information composition that camera absorbs on several sequential time points；The trailer-mounted radar information is by trailer-mounted radar in several sequences
The geography information composition acquired on time point.
3. automatic driving vehicle localization method according to claim 2, which is characterized in that described to believe the vehicle vision
Breath and the trailer-mounted radar information are fused in vehicular map information according to default registration relationship, generate the step of vehicle location information
Suddenly it specifically includes：
Angle point data are extracted from described image information；
The track data of the vehicle is calculated according to the angle point data, and is believed according to the default registration relationship and trailer-mounted radar
Breath generates correction track data；
The correction track data is mapped in the vehicular map information, vehicle location information is generated.
4. automatic driving vehicle localization method according to claim 1, which is characterized in that the relative vehicle radar information
Including vehicle spacing data, direction of traffic data, vehicle relative velocity data；The barrier radar information includes apart from number
According to, bearing data and relative velocity data.
5. automatic driving vehicle localization method according to any one of claims 1 to 4, which is characterized in that the default registration
Relationship is in the trailer-mounted radar information and the vehicle vision information with the functional relation between location point.
6. automatic driving vehicle localization method according to claim 5, which is characterized in that the functional relation is specially Mr
=R*Mc, wherein Mc is coordinate Mc (Xc, Yc, Zc) of the point M under camera coordinates system, and Mr is point M under radar image coordinate
Coordinate Mr (Xr, Yr).
7. automatic driving vehicle localization method according to claim 1, which is characterized in that the vehicular map information includes
Satellite navigation data, the satellite navigation data is by selecting from GPS data, BDS data, GLONASS data and GALILEO data
One of.
8. automatic driving vehicle localization method according to claim 1, which is characterized in that the automatic driving vehicle positioning
Method further includes the steps that, by Inertial Measurement Unit acquisition vehicle inertia information, the vehicle inertia information is described for correcting
Trailer-mounted radar information.
9. a kind of vehicle-mounted storage equipment, which is characterized in that be wherein stored with a plurality of instruction, described instruction is suitable for being loaded by processor
And it executes：
Vehicle vision information is obtained, the vehicle vision information derives from vehicle-mounted vidicon, including barrier visual information, curb
Visual information, lane line visual information and signal lamp visual information；
Trailer-mounted radar information is obtained, the trailer-mounted radar information derives from trailer-mounted radar, including relative vehicle radar information and barrier
Hinder object radar information；
The vehicle vision information and the trailer-mounted radar information are fused in vehicular map information according to default registration relationship,
Generate vehicle location information.
10. a kind of vehicle mobile terminals, which is characterized in that including processor, be adapted for carrying out each instruction；And storage equipment, it fits
In storing a plurality of instruction, described instruction is suitable for being loaded and being executed by processor：
Vehicle vision information is obtained, the vehicle vision information derives from vehicle-mounted vidicon, including barrier visual information, curb
Visual information, lane line visual information and signal lamp visual information；
Trailer-mounted radar information is obtained, the trailer-mounted radar information derives from trailer-mounted radar, including relative vehicle radar information and barrier
Hinder object radar information；
The vehicle vision information and the trailer-mounted radar information are fused in vehicular map information according to default registration relationship,
Generate vehicle location information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810447923.XA CN108896994A (en) | 2018-05-11 | 2018-05-11 | A kind of automatic driving vehicle localization method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810447923.XA CN108896994A (en) | 2018-05-11 | 2018-05-11 | A kind of automatic driving vehicle localization method and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108896994A true CN108896994A (en) | 2018-11-27 |
Family
ID=64342678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810447923.XA Pending CN108896994A (en) | 2018-05-11 | 2018-05-11 | A kind of automatic driving vehicle localization method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108896994A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109031304A (en) * | 2018-06-06 | 2018-12-18 | 上海国际汽车城（集团）有限公司 | Vehicle positioning method in view-based access control model and the tunnel of millimetre-wave radar map feature |
| CN109737977A (en) * | 2018-12-10 | 2019-05-10 | 北京百度网讯科技有限公司 | Automatic driving vehicle localization method, device and storage medium |
| CN109901194A (en) * | 2019-03-18 | 2019-06-18 | 爱驰汽车有限公司 | Onboard system, method, equipment and the storage medium of anticollision |
| CN110189366A (en) * | 2019-04-17 | 2019-08-30 | 北京迈格威科技有限公司 | A kind of laser rough registration method, apparatus, mobile terminal and storage medium |
| CN110766024A (en) * | 2019-10-08 | 2020-02-07 | 湖北工业大学 | Visual odometer feature point extraction method based on deep learning and visual odometer |
| CN111223494A (en) * | 2019-12-17 | 2020-06-02 | 深圳市联谛信息无障碍有限责任公司 | Method and device for identifying road surface information and electronic equipment |
| CN111323038A (en) * | 2020-03-27 | 2020-06-23 | 新石器慧通（北京）科技有限公司 | Method and system for positioning unmanned vehicle in tunnel and electronic equipment |
| CN111435565A (en) * | 2018-12-26 | 2020-07-21 | 杭州海康威视数字技术股份有限公司 | Road traffic state detection method, road traffic state detection device, electronic equipment and storage medium |
| CN111551976A (en) * | 2020-05-20 | 2020-08-18 | 四川万网鑫成信息科技有限公司 | Method for automatically completing abnormal positioning by combining various data |
| WO2020186522A1 (en) * | 2019-03-21 | 2020-09-24 | 合刃科技（深圳）有限公司 | Anti-halation vehicle assistant driving system |
| CN112153567A (en) * | 2019-06-28 | 2020-12-29 | 大陆泰密克汽车系统（上海）有限公司 | Method and vehicle for constructing real-time regional electronic map |
| CN113091733A (en) * | 2021-03-15 | 2021-07-09 | 武汉大学 | Real-time positioning device and method based on fusion of millimeter wave radar and IMU |
| CN113093176A (en) * | 2019-12-23 | 2021-07-09 | 北京三快在线科技有限公司 | Linear obstacle detection method, linear obstacle detection device, electronic apparatus, and storage medium |
| CN113390435A (en) * | 2021-05-13 | 2021-09-14 | 中铁二院工程集团有限责任公司 | High-speed railway multi-element auxiliary positioning system |
| CN113408157A (en) * | 2021-08-18 | 2021-09-17 | 北京赛目科技有限公司 | World coordinate and road coordinate conversion method and device of unmanned simulation system |
| CN113551686A (en) * | 2021-08-03 | 2021-10-26 | 上海淞泓智能汽车科技有限公司 | Internet automobile track monitoring method based on high-precision map information fusion |
| CN113706682A (en) * | 2021-08-18 | 2021-11-26 | 北京赛目科技有限公司 | Method and device for three-dimensional rendering of road by unmanned simulation system |
| CN113900070A (en) * | 2021-10-08 | 2022-01-07 | 河北德冠隆电子科技有限公司 | Method, device and system for automatically drawing target data and accurately outputting radar lane |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107161141A (en) * | 2017-03-08 | 2017-09-15 | 深圳市速腾聚创科技有限公司 | Pilotless automobile system and automobile |
| CN107272687A (en) * | 2017-06-29 | 2017-10-20 | 深圳市海梁科技有限公司 | A kind of driving behavior decision system of automatic Pilot public transit vehicle |
| CN107301654A (en) * | 2017-06-12 | 2017-10-27 | 西北工业大学 | A kind of positioning immediately of the high accuracy of multisensor is with building drawing method |
-
2018
- 2018-05-11 CN CN201810447923.XA patent/CN108896994A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107161141A (en) * | 2017-03-08 | 2017-09-15 | 深圳市速腾聚创科技有限公司 | Pilotless automobile system and automobile |
| CN107301654A (en) * | 2017-06-12 | 2017-10-27 | 西北工业大学 | A kind of positioning immediately of the high accuracy of multisensor is with building drawing method |
| CN107272687A (en) * | 2017-06-29 | 2017-10-20 | 深圳市海梁科技有限公司 | A kind of driving behavior decision system of automatic Pilot public transit vehicle |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109031304A (en) * | 2018-06-06 | 2018-12-18 | 上海国际汽车城（集团）有限公司 | Vehicle positioning method in view-based access control model and the tunnel of millimetre-wave radar map feature |
| CN109737977A (en) * | 2018-12-10 | 2019-05-10 | 北京百度网讯科技有限公司 | Automatic driving vehicle localization method, device and storage medium |
| US11619939B2 (en) | 2018-12-10 | 2023-04-04 | Apollo Intelligent Driving Technology (Beijing) Co., Ltd. | Self-driving vehicle positioning method, apparatus and storage medium |
| CN111435565A (en) * | 2018-12-26 | 2020-07-21 | 杭州海康威视数字技术股份有限公司 | Road traffic state detection method, road traffic state detection device, electronic equipment and storage medium |
| CN109901194A (en) * | 2019-03-18 | 2019-06-18 | 爱驰汽车有限公司 | Onboard system, method, equipment and the storage medium of anticollision |
| WO2020186522A1 (en) * | 2019-03-21 | 2020-09-24 | 合刃科技（深圳）有限公司 | Anti-halation vehicle assistant driving system |
| CN110189366A (en) * | 2019-04-17 | 2019-08-30 | 北京迈格威科技有限公司 | A kind of laser rough registration method, apparatus, mobile terminal and storage medium |
| CN110189366B (en) * | 2019-04-17 | 2021-07-06 | 北京迈格威科技有限公司 | Laser coarse registration method and device, mobile terminal and storage medium |
| CN112153567A (en) * | 2019-06-28 | 2020-12-29 | 大陆泰密克汽车系统（上海）有限公司 | Method and vehicle for constructing real-time regional electronic map |
| CN110766024A (en) * | 2019-10-08 | 2020-02-07 | 湖北工业大学 | Visual odometer feature point extraction method based on deep learning and visual odometer |
| CN111223494A (en) * | 2019-12-17 | 2020-06-02 | 深圳市联谛信息无障碍有限责任公司 | Method and device for identifying road surface information and electronic equipment |
| CN113093176A (en) * | 2019-12-23 | 2021-07-09 | 北京三快在线科技有限公司 | Linear obstacle detection method, linear obstacle detection device, electronic apparatus, and storage medium |
| CN111323038B (en) * | 2020-03-27 | 2021-10-26 | 新石器慧通（北京）科技有限公司 | Method and system for positioning unmanned vehicle in tunnel and electronic equipment |
| CN111323038A (en) * | 2020-03-27 | 2020-06-23 | 新石器慧通（北京）科技有限公司 | Method and system for positioning unmanned vehicle in tunnel and electronic equipment |
| CN111551976A (en) * | 2020-05-20 | 2020-08-18 | 四川万网鑫成信息科技有限公司 | Method for automatically completing abnormal positioning by combining various data |
| CN113091733A (en) * | 2021-03-15 | 2021-07-09 | 武汉大学 | Real-time positioning device and method based on fusion of millimeter wave radar and IMU |
| CN113390435A (en) * | 2021-05-13 | 2021-09-14 | 中铁二院工程集团有限责任公司 | High-speed railway multi-element auxiliary positioning system |
| CN113390435B (en) * | 2021-05-13 | 2022-08-26 | 中铁二院工程集团有限责任公司 | High-speed railway multi-element auxiliary positioning system |
| CN113551686A (en) * | 2021-08-03 | 2021-10-26 | 上海淞泓智能汽车科技有限公司 | Internet automobile track monitoring method based on high-precision map information fusion |
| CN113408157A (en) * | 2021-08-18 | 2021-09-17 | 北京赛目科技有限公司 | World coordinate and road coordinate conversion method and device of unmanned simulation system |
| CN113706682A (en) * | 2021-08-18 | 2021-11-26 | 北京赛目科技有限公司 | Method and device for three-dimensional rendering of road by unmanned simulation system |
| CN113706682B (en) * | 2021-08-18 | 2022-05-17 | 北京赛目科技有限公司 | Method and device for three-dimensional rendering of road by unmanned simulation system |
| CN113900070A (en) * | 2021-10-08 | 2022-01-07 | 河北德冠隆电子科技有限公司 | Method, device and system for automatically drawing target data and accurately outputting radar lane |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108896994A (en) | A kind of automatic driving vehicle localization method and equipment | |
| JP7040867B2 (en) | System, method and program | |
| US20210311490A1 (en) | Crowdsourcing a sparse map for autonomous vehicle navigation | |
| JP7432285B2 (en) | Lane mapping and navigation | |
| US10248124B2 (en) | Localizing vehicle navigation using lane measurements | |
| KR102558055B1 (en) | Suboptimal estimation method | |
| Alonso et al. | Accurate global localization using visual odometry and digital maps on urban environments | |
| CN110462343A (en) | The automated graphics for vehicle based on map mark | |
| CN109949439B (en) | Driving live-action information labeling method and device, electronic equipment and medium | |
| CN111046743B (en) | Barrier information labeling method and device, electronic equipment and storage medium | |
| JP2022553491A (en) | Systems and methods for vehicle navigation | |
| CN108628324A (en) | Unmanned vehicle navigation method, device, equipment based on map vector and storage medium | |
| US20190293444A1 (en) | Lane level accuracy using vision of roadway lights and particle filter | |
| Hara et al. | Vehicle localization based on the detection of line segments from multi-camera images | |
| CN112884892B (en) | Unmanned mine car position information processing system and method based on road side device | |
| CN109297502A (en) | Laser projection pointing method and device based on image procossing Yu GPS navigation technology | |
| Jiang et al. | Precise vehicle ego-localization using feature matching of pavement images | |
| CN113390422B (en) | Automobile positioning method and device and computer storage medium | |
| US20230417885A1 (en) | Systems and methods for detecting erroneous lidar data | |
| CN117002527A (en) | Vehicle control method and device, vehicle and storage medium | |
| CN115435802A (en) | Lane level positioning method and system based on 4D imaging radar and vehicle | |
| JP2022169324A (en) | object tracking device | |
| CN116433771A (en) | Visual SLAM positioning method and device, electronic equipment and storable medium | |
| CN116508067A (en) | Processing images to extract information about known objects | |
| Hu et al. | MODEL-BASED CAMERA 3D POSE TRACKING–A SOLUTION OF REGISTRATION PROBLEM FOR ON-ROAD NAVIGATION |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181127 |
|
| RJ01 | Rejection of invention patent application after publication |