CN110414487A - Method and device for identifying lane line - Google Patents
Method and device for identifying lane line Download PDFInfo
- Publication number
- CN110414487A CN110414487A CN201910759230.9A CN201910759230A CN110414487A CN 110414487 A CN110414487 A CN 110414487A CN 201910759230 A CN201910759230 A CN 201910759230A CN 110414487 A CN110414487 A CN 110414487A
- Authority
- CN
- China
- Prior art keywords
- image
- lane line
- vehicle
- vehicle front
- obtains
- 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
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
Abstract
The application discloses method and device for recognizing lane lines, which can acquire a second image shot by an image acquisition device positioned at a preset position in front of a vehicle besides a first image shot by a front-view camera of the vehicle, wherein the first image and the second image form a complete image in front of the vehicle. After the first image and the second image are acquired, the first image and the second image can be identified to obtain a lane line in front of the vehicle. Therefore, in the embodiment of the application, the lane line in front of the vehicle can be determined according to the complete image in front of the vehicle (namely the first image and the second image).
Description
Technical field
This application involves vehicular fields, more particularly to a kind of method and device for identifying lane line.
Background technique
With the development of science and technology, automated driving system is fitted on many vehicles at present or auxiliary drives system
System.Currently, the image that automated driving system or DAS (Driver Assistant System) can be shot in conjunction with the forward sight camera of vehicle, is identified
Lane line on road, to realize that automatic Pilot or auxiliary drive in conjunction with the lane line identified.
But this mode realizing automatic Pilot or auxiliary and driving, there can be vehicle and step on padding machine in the process of moving
The phenomenon that diatom, the effect driven so as to cause automatic Pilot or auxiliary are bad.
Summary of the invention
Technical problems to be solved in this application are traditional modes realizing automatic Pilot or auxiliary and driving, and can be existed
Vehicle steps on the phenomenon that padding machine diatom in the process of moving, and the effect driven so as to cause automatic Pilot or auxiliary is bad, provides
A kind of method and device identifying lane line.
In a first aspect, the embodiment of the present application provides a kind of method for identifying lane line, which comprises
The first image of the forward sight camera shooting of vehicle is obtained, and obtains the predeterminated position for being located at the vehicle front
Image acquisition equipment shooting the second image;Vehicle front described in the first image and second image construction it is complete
Image;
Image recognition is carried out to the first image and second image, obtains the lane line of the vehicle front.
Optionally, it is described to the first image and second image carry out image recognition, obtain the vehicle front
Lane line, comprising:
Image recognition is carried out to the first image and second image respectively, obtains the corresponding vehicle of the first image
Diatom and the corresponding lane line of second image;
The corresponding lane line of the first image and the corresponding lane line of second image are fitted, obtained described
The lane line of vehicle front.
Optionally, the method also includes:
Obtain the third image of the rearview camera shooting of vehicle;
Image recognition is carried out to the third image, obtains the lane line of the rear of vehicle;
The lane line of lane line and the rear of vehicle to the vehicle front is fitted, and obtains global lane line.
Optionally, the method also includes:
First position locating for the vehicle is obtained by the positioning device on the vehicle, and is obtained near first position
Cartographic information;
The relative position between the default object of reference of the vehicle front and the vehicle is determined according to the first image
Information;
According to the cartographic information, the determining relative position between the default object of reference meets aforementioned relative position letter
The second position is determined as the actually located position of the vehicle by the second position of breath.
Optionally, the default object of reference includes following any one or combination:
Lane line, traffic signboard, signal lamp and building.
Optionally, the method also includes:
Obtain the corresponding history lane line in the second position;The history lane line is that the vehicle is passed through in the historical juncture
The lane line being calculated when crossing the second position;
It is described to the first image and second image carry out image recognition, obtain the lane of the vehicle front
Line, comprising:
The first image and second image are identified, and in conjunction with the recognition result and the history lane
Line obtains the lane line of the vehicle front.
Optionally, the predeterminated position of the vehicle front, comprising:
The air-inlet grille of the vehicle front, and/or, the bumper of the vehicle front.
Optionally, described image obtains equipment, comprising:
Fish-eye camera, and/or, visual sensor.
Second aspect, the embodiment of the present application provide a kind of device for identifying lane line, and described device includes:
First acquisition unit, the first image that the forward sight camera for obtaining vehicle is shot, and obtain positioned at described
Second image of the image acquisition equipment shooting of the predeterminated position of vehicle front;The first image and second image construction
The complete image of the vehicle front;
First recognition unit obtains the vehicle for carrying out image recognition to the first image and second image
Lane line in front of.
Optionally, first recognition unit, comprising:
It identifies subelement, for carrying out image recognition to the first image and second image respectively, obtains described
The corresponding lane line of first image and the corresponding lane line of second image;
Be fitted subelement, for the corresponding lane line of the first image and the corresponding lane line of second image into
Row fitting, obtains the lane line of the vehicle front.
Optionally, described device further include:
Second acquisition unit, the third image that the rearview camera for obtaining vehicle is shot;
Second recognition unit obtains the lane line of the rear of vehicle for carrying out image recognition to the third image;
Fitting unit, the lane line for lane line and the rear of vehicle to the vehicle front are fitted, obtain
To global lane line.
Optionally, described device further include:
Third acquiring unit, for obtaining first position locating for the vehicle by the positioning device on the vehicle,
And obtain the cartographic information near first position;
First determination unit, for determining the default object of reference and the vehicle of the vehicle front according to the first image
Relative position information between;
Second determination unit, for according to the cartographic information, the determining relative position between the default object of reference
The second position is determined as the actually located position of the vehicle by the second position for meeting aforementioned relative position information.
Optionally, the default object of reference includes following any one or combination:
Lane line, traffic signboard, signal lamp and building.
Optionally, described device further include:
4th acquiring unit, for obtaining the corresponding history lane line in the second position;The history lane line is institute
State the lane line that vehicle is calculated when the historical juncture passing through the second position;
First recognition unit, is specifically used for:
The first image and second image are identified, and in conjunction with the recognition result and the history lane
Line obtains the lane line of the vehicle front.
Optionally, the predeterminated position of the vehicle front, comprising:
The air-inlet grille of the vehicle front, and/or, the bumper of the vehicle front.
Optionally, described image obtains equipment, comprising:
Fish-eye camera, and/or, visual sensor.Compared with prior art, the embodiment of the present application has the advantage that
In the embodiment of the present application, it is contemplated that in the prior art, can be deposited when due to the shooting of forward sight camera in vehicle proximate
Image forward sight camera in certain shooting blind area, i.e. vehicle front proximal end may be shot less than to affect lane line
The precision of identification.So in the embodiment of the present application, other than the first image of forward sight camera shooting for obtaining vehicle, also
The available predeterminated position positioned at the vehicle front image acquisition equipment shooting the second image, the first image and
Second image forms the complete image of the vehicle front.In other words, in the second image, including vehicle front position forward sight
The corresponding image in shooting blind area of camera.It, can be to the first image and second after getting the first image and the second image
Image is identified, the lane line of the vehicle front is obtained.It can be seen that in the embodiment of the present application, it can be according to described
The complete image (i.e. the first image adds the second image) of vehicle front, determines the lane line of vehicle front, with traditional technology phase
Than can not only determine the lane line of vehicle front distal end, can also determine that the shooting blind area of forward sight camera is corresponding
The lane line of lane line, identified vehicle front is more accurate, to avoid the process driven in automatic Pilot or auxiliary
Middle vehicle steps on the problem of padding machine diatom, improves the effect of automatic Pilot or auxiliary driving.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The some embodiments recorded in application, for those of ordinary skill in the art, without creative efforts,
It is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow diagram of method for identifying lane line provided by the embodiments of the present application;
Fig. 2 is a kind of flow diagram of location determining method provided by the embodiments of the present application;
Fig. 3 is a kind of structural schematic diagram of device for identifying lane line provided by the embodiments of the present application.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only this
Apply for a part of the embodiment, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall in the protection scope of this application.
Present inventor has found that in the prior art, automated driving system or DAS (Driver Assistant System) can after study
With the image for combining the forward sight camera of vehicle to shoot, the lane line on road is identified, thus in conjunction with the lane line identified
Realize that automatic Pilot or auxiliary drive.But this mode realizing automatic Pilot or auxiliary and driving, there can be vehicle and exist
The phenomenon that padding machine diatom is stepped in driving process, the effect driven so as to cause automatic Pilot or auxiliary are bad.Because forward sight is taken the photograph
As that can have certain shooting blind area in vehicle proximate when head shooting, i.e. the image forward sight camera of vehicle front proximal end may be clapped
It takes the photograph less than so as to cause the corresponding lane line in shooting blind area part that cannot recognize that forward sight camera, to affect lane
Line identification precision, further, cause automatic Pilot or auxiliary drive during there are vehicles to step on padding machine diatom
Phenomenon, the effect driven so as to cause automatic Pilot or auxiliary are bad.
To solve the above-mentioned problems, in the embodiment of the present application, in addition to obtaining the first of the forward sight camera shooting of vehicle
Except image, the second image of the image acquisition equipment shooting positioned at the predeterminated position of the vehicle front, institute can also be obtained
It states the first image and second image forms the complete image of the vehicle front.In other words, in the second image, including vehicle
The corresponding image in shooting blind area of front position forward sight camera.It, can be to after getting the first image and the second image
One image and the second image are identified, the lane line of the vehicle front is obtained.It can be seen that in the embodiment of the present application,
The lane line of vehicle front can be determined according to the complete image (i.e. the first image adds the second image) of the vehicle front,
Compared with traditional technology, the lane line of vehicle front distal end can be not only determined, can also determine the bat of forward sight camera
Take the photograph the corresponding lane line in blind area, so the lane line of identified vehicle front is more accurate, thus avoid in automatic Pilot or
Person assists the problem of vehicle steps on padding machine diatom during driving, and improves the effect of automatic Pilot or auxiliary driving.
With reference to the accompanying drawing, the various non-limiting embodiments of the application are described in detail.
Illustrative methods
Referring to Fig. 1, which is a kind of flow diagram of method for identifying lane line provided by the embodiments of the present application.
The method of identification lane line provided by the embodiments of the present application, such as can be realized by the controller on vehicle, it is described
Controller can be the already existing controller of script on vehicle, such as being configured with automatic Pilot or DAS (Driver Assistant System)
Vehicle, the controller can be the controller of automated driving system or DAS (Driver Assistant System).The controller can also be with
The controller being separately configured for identification lane line, the embodiment of the present application are not specifically limited.
The method of identification lane line provided by the embodiments of the present application, such as can be realized by following steps S101-S102.
S101: the first image of the forward sight camera shooting of vehicle is obtained, and obtains and is located at the pre- of the vehicle front
If the second image that the image acquisition equipment of position is shot;Vehicle front described in the first image and second image construction
Complete image.
It should be noted that the forward sight camera of vehicle, is typically placed in the inside of the front windshield of vehicle.This just leads
Cause there can be certain shooting blind area when the shooting of forward sight camera in vehicle proximate, i.e. the image forward sight camera shooting of vehicle front proximal end
Head may shoot less than.
It can be that take vehicle front certain it is understood that the first image that the forward sight camera of vehicle is shot
The image of the road surface in region and vehicle front respective objects such as traffic signboard, signal lamp and building etc..
In the embodiment of the present application, it is handled except forward sight camera on vehicle, it can also be in the predeterminated position of vehicle front
Place's setting image acquisition equipment.The figure of first two equipment acquisition vehicle front is imaged by the image acquisition equipment and aforementioned forward sight
Picture.Wherein, the corresponding image in shooting blind area of forward sight camera can be taken positioned at the image acquisition equipment of predetermined position.
So the first image and the second image may be constructed the complete image of vehicle front.
The embodiment of the present application does not limit the predeterminated position specifically, and as an example, the predeterminated position can be institute
State the air-inlet grille of vehicle front.As another example, the predeterminated position can be the bumper of vehicle front, specifically
Ground, described image obtain any position that equipment can be located on the bumper of the vehicle front.
The embodiment of the present application does not limit described image specifically and obtains equipment, as an example, it is contemplated that fish-eye camera
Shooting angle be 180 degree, so described image obtain equipment can be fish-eye camera.As another example, it is contemplated that
The precision that visual sensor obtains close-up images is relatively high, and the shooting blind area of forward sight camera is generally compared apart from vehicle
Closely, so it can be visual sensor that described image, which obtains equipment,.
It is understood that in practical applications, image acquisition equipment can be only set at the air-inlet grille, such as
Fish-eye camera or visual sensor, without image acquisition equipment, such as fish-eye camera or view are arranged on bumper
Feel sensor;Image acquisition equipment, such as fish-eye camera or visual sensor can also be only set on the bumper,
Without image acquisition equipment, such as fish-eye camera or visual sensor are arranged at air-inlet grille;It can also be both described
Image acquisition equipment, such as fish-eye camera or visual sensor are set at air-inlet grille, and image is set on bumper
Obtain equipment, such as fish-eye camera or visual sensor;The embodiment of the present application is not specifically limited.
S102: image recognition is carried out to the first image and second image, obtains the lane of the vehicle front
Line.
It in the embodiment of the present application, can be to the first image and the second figure after getting the first image and the second image
As being identified, to obtain the lane line of the vehicle front.The embodiment of the present application does not limit specifically to the first image
The specific implementation of image recognition is carried out with second image, as an example, it is contemplated that lane line generally comprises white
Therefore line and yellow line can identify the white line and yellow line in the first image and second image, to obtain described
The lane line of vehicle front.
It as can be seen from the above description, can be according to the complete graph of the vehicle front using the scheme of the embodiment of the present application
As (i.e. the first image adds the second image), determines the lane line of vehicle front, compared with traditional technology, can not only determine
The lane line of vehicle front distal end, can also determine the corresponding lane line in shooting blind area of forward sight camera, so determine
Vehicle front lane line it is more accurate, thus avoid automatic Pilot or auxiliary drive during vehicle step on padding machine road
The problem of line, improves the effect of automatic Pilot or auxiliary driving.
In a kind of implementation of the embodiment of the present application, it is contemplated that the first image and the second image are not same images,
Therefore, in a kind of implementation of the embodiment of the present application, the first image and second image can be carried out respectively
Image recognition obtains the corresponding lane line of the first image and the corresponding lane line of second image, then to first figure
As corresponding lane line and the corresponding lane line of second image are fitted, to obtain the lane of the vehicle front
Line.For example, the white line and yellow line in the white line and yellow line and second image in the first image are identified respectively, and
The white line obtained according to the white line identified in the first image and the second image recognition is fitted afterwards, is obtained complete white
Line lane line;The yellow line obtained according to the yellow line identified in the first image and the second image recognition is fitted, is obtained
Complete yellow line lane line, complete yellow line lane line and complete white line lane line then constitute the lane of the vehicle front
Line.Specifically, vehicle axis system can be constructed, and it is corresponding using image recognition to obtain the first image under vehicle axis system
The corresponding lane line equation of second image under lane line equation and vehicle axis system, lane corresponding to the first image
It, can be to the corresponding lane line equation of the first image and when line and the corresponding lane line of second image are fitted
The corresponding lane line equation of two images is fitted, and obtains the corresponding equation of lane line of the vehicle front.
About the vehicle axis system, it should be noted that can be using the rear shaft center of vehicle point as vehicle coordinate
The origin of system constructs vehicle axis system, the direction of each reference axis about vehicle axis system, can determines according to actual conditions,
Herein without limitation.
It is understood that vehicle is during traveling, coordinate of the rear shaft center's point of vehicle in world coordinate system
It can change, the corresponding equation of lane line of the above-mentioned vehicle front referred to refers to that the lane is being calculated
Corresponding equation in corresponding vehicle axis system at the time of line equation.For example, vehicle shoots the first image and second
It is the t1 moment at the time of image, and controller is calculated lane line according to the first image and the second image and needs the regular hour
(this time is generally shorter, and when the computational efficiency of controller is enough high, which be can be ignored), is calculated lane
It is the t2 moment at the time of line, t1 moment and t2 moment respectively correspond a vehicle axis system, then aforementioned lane line equation is in t2
Lane line equation under moment corresponding vehicle axis system.It will be appreciated that if when the computational efficiency of controller is enough high, it is preceding
Stating lane line equation is the lane line equation under t1 moment corresponding vehicle axis system.When between t1 moment and t2 moment
Time difference can not ignore not-time, and the lane line equation under t1 moment corresponding vehicle axis system can be calculated first,
Then according to the coordinate transformation relation between t1 moment corresponding vehicle axis system and t2 moment corresponding vehicle axis system, will before
State the lane that the lane line equation under t1 moment corresponding vehicle axis system is converted under t2 moment corresponding vehicle axis system
Line equation.
In another implementation of the embodiment of the present application, in order to promote the lane line for the vehicle front being calculated
Precision can also obtain the cartographic information that vehicle is presently near position, and combining cartographic information and the first image and
Two images determine the lane line of vehicle front.Specifically, it can use such as GPS positioning system of the positioning device on vehicle to obtain
Then extract ground so that the position acquisition vehicle according to vehicle is presently in the cartographic information near position in the position of pick-up
Lane line information in figure information, thus according to extracted lane line information and the lane line information being calculated progress
Match, the lane line being calculated is determined according to matching result.For example, when the lane line information extracted from cartographic information and calculating
It, then can be directly corresponding by the lane line information extracted from map when error very little between obtained lane line information
Lane line be determined as the lane line of the vehicle front, or directly using the lane line information being calculated as described in
The lane line of vehicle front.When the mistake between the lane line information extracted in cartographic information and the lane line information being calculated
When difference is very big, then in view of the error between the lane line information extracted in cartographic information and the lane line information being calculated
It greatly may be very because caused by the position error of GPS, so the lane of vehicle front can be recalculated in conjunction with other information
Line.Such as the lane line of vehicle front is determined in conjunction with history lane line described below.
In a kind of implementation of the embodiment of the present application, in order to enable the lane line of identification is more complete, it can also obtain
The third image of the rearview camera shooting of pick-up;Image recognition is carried out to the third image, obtains the rear of vehicle
Lane line;The lane line of lane line and the rear of vehicle to the vehicle front is fitted, and obtains global lane line.
In the embodiment of the present application, the rearview camera for example can be set in a certain position of parking stall, rear-camera
Head can shoot vehicle tail pair road surface image.
It should be noted that identifying to the third image, the specific reality of the lane line of the rear of vehicle is obtained
Existing mode identifies, the implementation for obtaining the corresponding lane line of the first image is similar with to the first image, so close
It is identified in the third image, obtains the specific implementation of the lane line of the rear of vehicle, it can be with reference to above
For identifying to the first image, the description section of the implementation of the corresponding lane line of the first image is obtained, herein
No longer it is described in detail.
In the embodiment of the present application, the lane line to the vehicle front and the lane line of the rear of vehicle are intended
Close, obtain the implementation of global lane line, with to the corresponding lane line of the first image and the corresponding lane line of the second image into
Row fitting, the implementation for obtaining the lane line of the vehicle front is similar, so for the lane line to the vehicle front
It is fitted with the lane line of the rear of vehicle, obtains the implementation of global lane line, it can be with reference to above for the
The corresponding lane line of one image and the corresponding lane line of the second image are fitted, and obtain the reality of the lane line of the vehicle front
The description section of existing mode, and will not be described here in detail.
In the embodiment of the present application, it is contemplated that in practical applications, open automatic Pilot or auxiliary drives function
Vehicle will adjust or plan in real time travelling route according to the position of vehicle itself during driving.So vehicle exists
The location of itself is particularly significant for accurately determining in driving process.Currently, can use the positioning device example on vehicle
Such as GPS positioning system, the location of vehicle is determined.But positioning device has certain position error, in order to enable vehicle
The location of itself is accurately determined in the process of moving, and method provided by the embodiments of the present application can also include shown in Fig. 2
Step S201-S203.Fig. 2 is a kind of flow diagram of location determining method provided by the embodiments of the present application.
S201: first position locating for the vehicle is obtained by the positioning device on the vehicle, and obtains first
Set neighbouring cartographic information.
It should be noted that the positioning device on the vehicle referred in the embodiment of the present application, such as can be on vehicle
GPS positioning system.It is understood that the characterization institute that the first position is positioned by the positioning device on the vehicle
State the position of current vehicle position.
The embodiment of the present application does not limit the specific implementation for obtaining the cartographic information near first position specifically, shows as one kind
Example, can obtain the cartographic information near the first position by internet;Certainly, if map letter has been locally stored in vehicle
Breath then can locally obtain the cartographic information near first position from vehicle.
It should be noted that in the embodiment of the present application, the cartographic information near the first position, it is believed that be packet
Include first position, and the cartographic information including the object near first position.
S202: it is determined according to the first image opposite between the default object of reference of the vehicle front and the vehicle
Location information.
As can be seen from the foregoing, the first image can be road surface and the vehicle front for including vehicle front certain area
The image of respective objects such as traffic signboard, signal lamp and building etc..It, can be in consideration of it, in the embodiment of the present application
First image is analyzed, determines the relative position information between the default object of reference of the vehicle front and the vehicle.
The embodiment of the present application does not limit the default object of reference specifically, the default object of reference for example can for lane line,
At least one of in traffic signboard, signal lamp and building.Wherein, the lane line of the vehicle front can be utilization with
The lane line of vehicle front determined by the method that upper embodiment provides.The traffic signboard of the vehicle front, signal lamp with
And building, it can be and what image recognition obtained is carried out to the first image.
As it was noted above, the corresponding lane line of the vehicle front, can be presented as the lane line in vehicle axis system
In lane line equation, when the default object of reference includes the lane line of the vehicle front, the default object of reference and institute
The relative position information between vehicle is stated, can be the lane line equation itself.When the default object of reference includes the vehicle
In the traffic signboard in front, signal lamp and building at least one of when, the default object of reference and the vehicle it
Between relative position information, can in traffic signboard, signal lamp and building for embodying the vehicle front etc. extremely
The information of relative positional relationship between one item missing and the vehicle, for example including between the default object of reference and the vehicle
Distance and the default object of reference and the vehicle between direction etc..
In the embodiment of the present application, if the default object of reference includes the traffic signboard of the vehicle front, signal lamp
At least one of and in building, then traffic signboard, the letter of the vehicle front can be obtained by the first image recognition
At least one of in signal lamp and building, then the first image can be shot further combined with the forward sight camera
Viewing-angle information determines at least one in traffic signboard, signal lamp and building of the vehicle front etc. and the vehicle
Relative positional relationship between, such as with the distance between the vehicle and the direction between the vehicle etc., from
And in obtaining the traffic signboard, signal lamp and building of the vehicle front etc. at least one of between the vehicle
Relative positional relationship.
S203: according to the cartographic information, the determining relative position between the default object of reference meets aforementioned opposite
The second position is determined as the actually located position of the vehicle by the second position of location information.
Although its error generally exists it is understood that the positioning device on vehicle has certain position error
Decimetre rank, it is especially big to be unlikely to error, therefore, in the cartographic information obtained according to the first position, including the vehicle
Actually located position and aforementioned default object of reference.
It therefore, in the embodiment of the present application, can be in conjunction with the cartographic information, the determining phase between the default object of reference
Meet the second position of aforementioned relative position information to position, and the second position is determined as the location of described vehicle.
It, can since the relative position information between the default object of reference and vehicle is calculated based on the first image
To be considered accurately, and the cartographic information near first position, it is also assumed that being accurately and reliably, therefore, in conjunction with aforementioned
The second position determined by relative position information between cartographic information and default object of reference and vehicle, it is believed that be vehicle reality
The location of border.Facts proved that using the method for S201-S203, positioning of the position error in centimetre rank, with vehicle
Device is compared, and the precision of position determined by the method for S201-S203 is higher.
In another implementation of the embodiment of the present application, it is contemplated that in practical applications, vehicle may be passed through repeatedly
Identical position is crossed, for convenience of describing, by " lane line for the vehicle front that vehicle was once calculated by current location "
Referred to as " history lane line ".In order to promoted the vehicle front being calculated lane line precision, vehicle is presently in if it exists
Position be corresponding with history lane line, then can be determined in conjunction with the history lane line and the first image and the second image
The lane line of vehicle front.Specifically, available vehicle is in the historical juncture by the history vehicle that is calculated when the second position
Diatom, and the first image and the second image are identified, and the lane line of the vehicle front is determined in conjunction with recognition result.Tool
Body, image recognition can be carried out to the first image and the second image, original lane line be obtained, then to history lane line with before
It states original lane line to perform corresponding processing, such as can use Kalman filtering method to history lane line and aforementioned original lane
Line is handled, to obtain the lane line of the vehicle front.
It should be noted that the embodiment of the present application does not limit the aforementioned historical juncture specifically, which can be acquisition
Any moment before at the time of first image and the second image correspond to.
Example devices
The method of identification lane line is provided based on above embodiments, the embodiment of the present application also provides a kind of identification lane lines
Device, introduce the device below in conjunction with attached drawing.
Referring to Fig. 3, which is a kind of structural schematic diagram of device for identifying lane line provided by the embodiments of the present application.It is described
Device 300 can for example specifically include: first acquisition unit 301 and the first recognition unit 302.
First acquisition unit 301, the first image that the forward sight camera for obtaining vehicle is shot, and obtain and be located at institute
State the second image of the image acquisition equipment shooting of the predeterminated position of vehicle front;The first image and the second image structure
At the complete image of the vehicle front.
First recognition unit 302 obtains described for carrying out image recognition to the first image and second image
The lane line of vehicle front.
Optionally, first recognition unit 301, comprising:
It identifies subelement, for carrying out image recognition to the first image and second image respectively, obtains described
The corresponding lane line of first image and the corresponding lane line of second image;
Be fitted subelement, for the corresponding lane line of the first image and the corresponding lane line of second image into
Row fitting, obtains the lane line of the vehicle front.
Optionally, described device 300 further include:
Second acquisition unit, the third image that the rearview camera for obtaining vehicle is shot;
Second recognition unit obtains the lane line of the rear of vehicle for carrying out image recognition to the third image;
Fitting unit, the lane line for lane line and the rear of vehicle to the vehicle front are fitted, obtain
To global lane line.
Optionally, described device 300 further include:
Third acquiring unit, for obtaining first position locating for the vehicle by the positioning device on the vehicle,
And obtain the cartographic information near first position;
First determination unit, for determining the default object of reference and the vehicle of the vehicle front according to the first image
Relative position information between;
Second determination unit, for according to the cartographic information, the determining relative position between the default object of reference
The second position is determined as the actually located position of the vehicle by the second position for meeting aforementioned relative position information.
Optionally, the default object of reference includes following any one or combination:
Lane line, traffic signboard, signal lamp and building.
Optionally, described device 300 further include:
4th acquiring unit, for obtaining the corresponding history lane line in the second position;The history lane line is institute
State the lane line that vehicle is calculated when the historical juncture passing through the second position;
First recognition unit 302, is specifically used for:
The first image and second image are identified, and in conjunction with the recognition result and the history lane
Line obtains the lane line of the vehicle front.
Optionally, the predeterminated position of the vehicle front, comprising:
The air-inlet grille of the vehicle front, and/or, the bumper of the vehicle front.
Optionally, described image obtains equipment, comprising:
Fish-eye camera, and/or, visual sensor.Since described device 300 is the side provided with above method embodiment
The corresponding device of method, the specific implementation of each unit of described device 300 are same design with above method embodiment, because
This, the specific implementation of each unit about described device 300 can refer to the description section of above method embodiment, herein
It repeats no more.
It as can be seen from the above description, can be according to the complete graph of the vehicle front using the scheme of the embodiment of the present application
As (i.e. the first image adds the second image), determines the lane line of vehicle front, compared with traditional technology, can not only determine
The lane line of vehicle front distal end, can also determine the corresponding lane line in shooting blind area of forward sight camera, so determine
Vehicle front lane line it is more accurate, thus avoid automatic Pilot or auxiliary drive during vehicle step on padding machine road
The problem of line, improves the effect of automatic Pilot or auxiliary driving.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the application
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the application, these modifications, purposes or
Person's adaptive change follows the general principle of the application and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the application are by following
Claim is pointed out.
It should be understood that the application is not limited to the precise structure that has been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.Scope of the present application is only limited by the accompanying claims
The foregoing is merely the preferred embodiments of the application, not to limit the application, it is all in spirit herein and
Within principle, any modification, equivalent replacement, improvement and so on be should be included within the scope of protection of this application.
Claims (16)
1. a kind of method for identifying lane line, which is characterized in that the described method includes:
The first image of the forward sight camera shooting of vehicle is obtained, and obtains the figure for being located at the predeterminated position of the vehicle front
The second image as obtaining equipment shooting;The complete graph of vehicle front described in the first image and second image construction
Picture;
Image recognition is carried out to the first image and second image, obtains the lane line of the vehicle front.
2. the method according to claim 1, wherein described carry out the first image with second image
Image recognition obtains the lane line of the vehicle front, comprising:
Image recognition is carried out to the first image and second image respectively, obtains the corresponding lane line of the first image
Lane line corresponding with second image;
The corresponding lane line of the first image and the corresponding lane line of second image are fitted, the vehicle is obtained
The lane line in front.
3. the method according to claim 1, wherein the method also includes:
Obtain the third image of the rearview camera shooting of vehicle;
Image recognition is carried out to the third image, obtains the lane line of the rear of vehicle;
The lane line of lane line and the rear of vehicle to the vehicle front is fitted, and obtains global lane line.
4. the method according to claim 1, wherein the method also includes:
First position locating for the vehicle is obtained by the positioning device on the vehicle, and obtains the ground near first position
Figure information;
The relative position information between the default object of reference of the vehicle front and the vehicle is determined according to the first image;
According to the cartographic information, the determining relative position between the default object of reference meets aforementioned relative position information
The second position is determined as the actually located position of the vehicle by the second position.
5. according to the method described in claim 4, it is characterized in that, the default object of reference includes following any one or group
It closes:
Lane line, traffic signboard, signal lamp and building.
6. according to the method described in claim 4, it is characterized in that, the method also includes:
Obtain the corresponding history lane line in the second position;The history lane line passes through institute in the historical juncture for the vehicle
The lane line being calculated when stating the second position;
It is described to the first image and second image carry out image recognition, obtain the lane line of the vehicle front, wrap
It includes:
The first image and second image are identified, and in conjunction with the recognition result and the history lane line,
Obtain the lane line of the vehicle front.
7. method described in -6 any one according to claim 1, which is characterized in that the predeterminated position of the vehicle front, packet
It includes:
The air-inlet grille of the vehicle front, and/or, the bumper of the vehicle front.
8. method described in -6 any one according to claim 1, which is characterized in that described image obtains equipment, comprising:
Fish-eye camera, and/or, visual sensor.
9. a kind of device for identifying lane line, which is characterized in that described device includes:
First acquisition unit, the first image that the forward sight camera for obtaining vehicle is shot, and obtain and be located at the vehicle
Second image of the image acquisition equipment shooting of the predeterminated position in front;Described in the first image and second image construction
The complete image of vehicle front;
First recognition unit, for carrying out image recognition to the first image and second image, before obtaining the vehicle
The lane line of side.
10. device according to claim 9, which is characterized in that first recognition unit, comprising:
It identifies subelement, for carrying out image recognition to the first image and second image respectively, obtains described first
The corresponding lane line of image and the corresponding lane line of second image;
It is fitted subelement, for intending the corresponding lane line of the first image and the corresponding lane line of second image
It closes, obtains the lane line of the vehicle front.
11. device according to claim 9, which is characterized in that described device further include:
Second acquisition unit, the third image that the rearview camera for obtaining vehicle is shot;
Second recognition unit obtains the lane line of the rear of vehicle for carrying out image recognition to the third image;
Fitting unit, the lane line for lane line and the rear of vehicle to the vehicle front are fitted, and are obtained complete
Office's lane line.
12. device according to claim 9, which is characterized in that described device further include:
Third acquiring unit for obtaining first position locating for the vehicle by the positioning device on the vehicle, and obtains
Take the cartographic information near first position;
First determination unit, for determined according to the first image the vehicle front default object of reference and the vehicle it
Between relative position information;
Second determination unit, for according to the cartographic information, the determining relative position between the default object of reference to meet
The second position is determined as the actually located position of the vehicle by the second position of aforementioned relative position information.
13. device according to claim 12, which is characterized in that the default object of reference include following any one or
Combination:
Lane line, traffic signboard, signal lamp and building.
14. device according to claim 12, which is characterized in that described device further include:
4th acquiring unit, for obtaining the corresponding history lane line in the second position;The history lane line is the vehicle
The lane line that is calculated when the historical juncture passing through the second position;
First recognition unit, is specifically used for:
The first image and second image are identified, and in conjunction with the recognition result and the history lane line,
Obtain the lane line of the vehicle front.
15. according to device described in claim 9-14 any one, which is characterized in that the predeterminated position of the vehicle front,
Include:
The air-inlet grille of the vehicle front, and/or, the bumper of the vehicle front.
16. according to device described in claim 9-14 any one, which is characterized in that described image obtains equipment, comprising:
Fish-eye camera, and/or, visual sensor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910759230.9A CN110414487B (en) | 2019-08-16 | 2019-08-16 | Method and device for identifying lane line |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910759230.9A CN110414487B (en) | 2019-08-16 | 2019-08-16 | Method and device for identifying lane line |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110414487A true CN110414487A (en) | 2019-11-05 |
CN110414487B CN110414487B (en) | 2022-05-13 |
Family
ID=68367499
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910759230.9A Active CN110414487B (en) | 2019-08-16 | 2019-08-16 | Method and device for identifying lane line |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110414487B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117218619A (en) * | 2023-11-07 | 2023-12-12 | 安徽中科星驰自动驾驶技术有限公司 | Lane recognition method and system for automatic driving vehicle |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103991449A (en) * | 2014-06-12 | 2014-08-20 | 北京联合大学 | Vehicle travelling control method and system |
CN105426864A (en) * | 2015-12-04 | 2016-03-23 | 华中科技大学 | Multiple lane line detecting method based on isometric peripheral point matching |
CN108528456A (en) * | 2017-03-03 | 2018-09-14 | 通用汽车环球科技运作有限责任公司 | Lane detection system and method |
CN108765496A (en) * | 2018-05-24 | 2018-11-06 | 河海大学常州校区 | A kind of multiple views automobile looks around DAS (Driver Assistant System) and method |
CN109271857A (en) * | 2018-08-10 | 2019-01-25 | 广州小鹏汽车科技有限公司 | A kind of puppet lane line elimination method and device |
US20190095722A1 (en) * | 2017-09-28 | 2019-03-28 | Samsung Electronics Co., Ltd. | Method and apparatus for identifying driving lane |
CN109816980A (en) * | 2019-02-20 | 2019-05-28 | 东软睿驰汽车技术(沈阳)有限公司 | The method and relevant apparatus in lane locating for a kind of determining vehicle |
-
2019
- 2019-08-16 CN CN201910759230.9A patent/CN110414487B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103991449A (en) * | 2014-06-12 | 2014-08-20 | 北京联合大学 | Vehicle travelling control method and system |
CN105426864A (en) * | 2015-12-04 | 2016-03-23 | 华中科技大学 | Multiple lane line detecting method based on isometric peripheral point matching |
CN108528456A (en) * | 2017-03-03 | 2018-09-14 | 通用汽车环球科技运作有限责任公司 | Lane detection system and method |
US20190095722A1 (en) * | 2017-09-28 | 2019-03-28 | Samsung Electronics Co., Ltd. | Method and apparatus for identifying driving lane |
CN108765496A (en) * | 2018-05-24 | 2018-11-06 | 河海大学常州校区 | A kind of multiple views automobile looks around DAS (Driver Assistant System) and method |
CN109271857A (en) * | 2018-08-10 | 2019-01-25 | 广州小鹏汽车科技有限公司 | A kind of puppet lane line elimination method and device |
CN109816980A (en) * | 2019-02-20 | 2019-05-28 | 东软睿驰汽车技术(沈阳)有限公司 | The method and relevant apparatus in lane locating for a kind of determining vehicle |
Non-Patent Citations (1)
Title |
---|
侯利龙: ""高速公路车道线检测算法研究"", 《中国优秀硕士学位论文全文数据库(电子期刊)》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117218619A (en) * | 2023-11-07 | 2023-12-12 | 安徽中科星驰自动驾驶技术有限公司 | Lane recognition method and system for automatic driving vehicle |
Also Published As
Publication number | Publication date |
---|---|
CN110414487B (en) | 2022-05-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11673605B2 (en) | Vehicular driving assist system | |
JP6380422B2 (en) | Automated driving system | |
CN105946853B (en) | The system and method for long range automatic parking based on Multi-sensor Fusion | |
JP5962850B2 (en) | Signal recognition device | |
WO2012091476A2 (en) | Apparatus and method for displaying a blind spot | |
CN107600067A (en) | A kind of autonomous parking system and method based on more vision inertial navigation fusions | |
CN105678787A (en) | Heavy-duty lorry driving barrier detection and tracking method based on binocular fisheye camera | |
CN104057882A (en) | System For Viewing A Curb In A Front Region On The Basis Of Two Cameras | |
CN206623754U (en) | Lane detection device | |
CN109866684A (en) | Lane departure warning method, system, readable storage medium storing program for executing and computer equipment | |
CN110036426A (en) | Control device and control method | |
US20210179172A1 (en) | Method and apparatus for determining a trailer hitch articulation angle in a motor vehicle | |
CN109211260B (en) | Intelligent vehicle driving path planning method and device and intelligent vehicle | |
CN108528337A (en) | A kind of lubrication groove difference intelligent early-warning system and method for early warning based on video projection | |
US11900696B2 (en) | Method and system for processing a plurality of images so as to detect lanes on a road | |
CN110414487A (en) | Method and device for identifying lane line | |
JP7065585B2 (en) | Vehicle driving control device | |
US20220266824A1 (en) | Road information generation apparatus | |
CN109583432A (en) | A kind of vehicle blind zone intelligent early-warning method based on image recognition | |
CN109736236A (en) | A kind of the semantic information system and construction method of the unmanned sweeper Driving Scene in garden | |
JP5557036B2 (en) | Exit determination device, exit determination program, and exit determination method | |
CN114734989A (en) | Auxiliary parking device and method based on around vision | |
JP2014104840A (en) | On-vehicle image processing system | |
CN109398356A (en) | Lane Keeping System and method | |
CN111753632B (en) | Driving assistance device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |