CN103077371B - The lane recognition method and its device of vehicle - Google Patents
The lane recognition method and its device of vehicle Download PDFInfo
- Publication number
- CN103077371B CN103077371B CN201210306455.7A CN201210306455A CN103077371B CN 103077371 B CN103077371 B CN 103077371B CN 201210306455 A CN201210306455 A CN 201210306455A CN 103077371 B CN103077371 B CN 103077371B
- Authority
- CN
- China
- Prior art keywords
- mrow
- msub
- msubsup
- filter
- time points
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The present invention is the image application multiple filter and the weighted value of each wave filter to being obtained from camera, excludes the misrecognition problem in track, steady implementation LKAS controls.That is the lane recognition method of vehicle of the invention is that implementation step includes：More than two left side local filters are applicable to the left-hand lane information obtained from vehicle image device；More than two right side local filters are applicable to the right-hand lane information obtained from the image device of the vehicle；Calculate the penalty factor of the left side and right-hand lane information；Left-hand lane estimate is obtained using the penalty factor to the result by described two left side local filter filtering above；Right-hand lane estimate is obtained using the penalty factor to the result by described two right side local filter filtering above.
Description
Technical field
The present invention relates to the lane recognition method of vehicle and its device, specifically track keeps accessory system（LKAS：Lane
Keeping Assistance System）In, it can correctly recognize the lane recognition method and its device of the vehicle in track.
Background technology
Track keeps accessory system（LKAS：Lane Keeping Assistance System）It is to utilize camera identification
The technology of track and auto-steering, using the image procossing of camera, determines the horizontal position of lane width, vehicle on track
Put, with the distance between both sides track and track form, road curvature radius, utilize obtained vehicle location and road information control
Vehicle processed.
The LKAS performances are, according to the lane information confidence level obtained by camera, its control performance to be produced very big
Influence.But the track on Ordinary Rd is not solid line, it is made up of dotted line, because of railing or central shunting area, railing shadow etc.
And cause unidentified and misrecognition phenomenon.
Straight line is not only on actual highway, also many curved sections, even straightway, are tinted according to the track on road surface
The pavement state such as state and rainy day, it is impossible to which the situation of stable received image signal also happens occasionally.
KR published patent application No. 10-2009-53412 and No. 10-2010-34409, United States Patent (USP) 7,532,981, U.S.
State's Patent Application Publication 2010/0076684 etc. is the conventional art about recognizing track method.
Filtering technique in lane recognition method is used according to conventional art, more firm property is played during unidentified track
Can, but it is then relatively weaker during misrecognition.
, need to be by concern area's offering question and image for the conventional art for lane identification using image processing techniques
In multiple stages of processing, its operand is relative therewith increases.
The content of the invention
Technical task
The present invention is created under the technical background, its object is to provide it is a kind of in misrecognition track or not
Strong vehicle lane recognition methods and its device in track are still accurately identified under the situation of identification.
It is a kind of under unidentified for a long time and misrecognition situation another object of the present invention is to provide, it can also stablize
Implement the lane recognition method and its device of the vehicle of LKAS controls.
Solution
To solve described problem, Ben Fa the technical scheme adopted is that image to being obtained from camera, using multiple filter
The weighted value of ripple device and each wave filter, excludes the misrecognition problem in track, steady implementation LKAS controls.
One aspect of the present invention is related to the lane recognition method of vehicle, and implementation step includes：To being obtained from vehicle image device
The left-hand lane information obtained is applicable more than two left side local filters；To the right side obtained from the image device of the vehicle
Lane information is applicable more than two right side local filters；Calculate the penalty factor of the left side and right-hand lane information；It is right
The result filtered by the left side local filter more than described two obtains left-hand lane estimate using the penalty factor；
Right-hand lane is obtained to the result filtered by described two right side local filters above using the penalty factor to estimate
Value.
The left side and right side local filter is the Kalman filter for meeting following [mathematical expression 1].
[mathematical expression 1]
(P is system covariance, and Q and R are respectively process noise covariance and measurement noise covariance, and K is to utilize association side
The kalman gain that difference is calculated).
The penalty factor can be calculated according to following [mathematical expression 2].
[mathematical expression 2]
(W:Minimum lane width
D:Maximum unidentified command range
V:Speed
t:Unidentified/time-out time of mistaking
α:Filter weights).
The Lane recognition device for the vehicle that another aspect of the present invention is related to is to receive left side and right side from the camera of vehicle
The image information in track, obtains the estimate of the left side and right-hand lane, and its composition includes：Left side local filter, at least
There are two, filter the left-hand lane information；Right side local filter, filters the right-hand lane information by least two；Punish
Penalty factor block, calculates the penalty factor of the left side and right-hand lane information；Left side senior filter, to utilizing more than described two
The filtering of left side local filter result, obtain left-hand lane estimate using the penalty factor；Right side senior filter, it is right
The result filtered using the right side local filter more than described two, using the penalty factor, obtains right-hand lane estimation
Value.
Beneficial effect
According to the present invention, even if because external disturbance only identifies side track, but using lane width information and with interference
The multiple filter technology of level, can also improve lane identification rate.
And the present embodiments relate to utilization multiple filter lane recognition method, can forcefully tackle mistake
Identification, lane width is reduced using the function of time, even if unidentified for a long time/misrecognition track, and still steady implementation LKAS is controlled
System.
Brief description of the drawings
Fig. 1 is the structure chart of the multiple filter used in the lane recognition method of the vehicle of the embodiment of the present invention.
Fig. 2 is the lane identification result signal for representing lane identification result and the embodiment of the present invention using existing wave filter
Figure.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.This hair
The bright middle term used, only to illustrate embodiment, is not to limit the invention.Singulative in this specification,
On the premise of there is no special suggestion in sentence, also comprising plural form.Used in specification " including（comprises）" or
" including (comprising) " be not excluded for beyond involved component, step, action and/or element it is more than one its
Its component, step, action and/or the presence of element or supplement.
Below in conjunction with the accompanying drawings, accessory system and its method are kept to the track of the vehicle of the embodiment of the present invention, carried out in detail
Description.
Fig. 1 is the structure chart of the multiple filter used in the lane recognition method of the vehicle of the embodiment of the present invention.
As shown in figure 1, the multiple filter 100 used in the lane recognition method of the vehicle of the embodiment of the present invention is to taking the photograph
As the left-side signal 110 of head and the right-side signal 120 of camera are respectively using two local filters.That is, to camera
Left-side signal 110 uses local filter L1112 and local filter L2114, and camera left-side signal 120 is filtered using local
Ripple device R1122 and local filter R2124.Wave filter used is only limited using two, can be adjusted according to controlled level.
The embodiment of the present invention is for the facility on illustrating, to be defined to two.
The Kalman filter that each local filter is represented by such as following [mathematical expression 1] is constituted.
【Mathematical expression 1】
(P is system covariance, and Q and R represent process noise covariance and measurement noise covariance respectively, and K is to utilize association side
The kalman gain that difference is calculated)
Signal passes through each local filter, is sent to left side senior filter 116 and right side senior filter 126.
Obtain according to the signal difference change entered by camera and passed after the weighted value of time in penalty factor block 130
Give each senior filter 116,126.
In penalty factor block weighted value is obtained according to following [mathematical expression 2].
【Mathematical expression 2】
W:Minimum lane width
D:Maximum unidentified command range
V:Speed
t:Unidentified/misrecognition time-out time
α:Filtration combined weighted value
Then utilized in senior filter 116,126 from the value of local filter acquisition and from the acquisition of penalty factor block with letter
Number the change of divergence and the weighted value of time, obtain final track estimate.
Fig. 2 is the lane identification result for representing lane identification result and the embodiment of the present invention using existing wave filter.Fig. 2
Upper plot be existing wave filter, Fig. 2 bottom component table is to represent the lane identification knot using the embodiment of the present invention respectively
Really, red to represent right-hand lane, green represents left-hand lane.
No. 1 is the example for representing driver oneself change lane in Fig. 2, and No. 2 are the examples for misidentifying left-hand lane.
From the point of view of using the lane identification example of existing wave filter technology（Upper No. 2）, directly estimate left-hand lane, it is impossible to
Detect that track is misidentified, but using the lane recognition method of the embodiment of the present invention（Lower No. 2）, then in the situation in misrecognition track
Under, track estimate will not also follow misrecognition track, but forcefully tackle.
As described above, according to the present invention, because of external disturbance, only during identification side track, lane width letter can also be utilized
Cease and with the multiple filter technology of noise level, improve lane identification rate.
Using the lane recognition method of various filters it is that can forcefully tackle the mistake in track in the embodiment of the present invention
Identification situation, it is possible to use even if the function of time reduces lane width and unidentified for a long time/misrecognition track, can still stablize
Implement LKAS controls.
Above example and particular terms are merely illustrative of the technical solution of the present invention, rather than its limitations；Although reference
The present invention is described in detail previous embodiment, it will be understood by those within the art that：It still can be right
Technical scheme described in foregoing embodiments is modified, or carries out equivalent substitution to which part technical characteristic；And these
Modification is replaced, and the essence of appropriate technical solution is departed from the scope of technical scheme described in various embodiments of the present invention.
Claims (4)
1. a kind of lane recognition method of vehicle, implementation step includes：
More than two left side local filters are applicable to the left-hand lane information obtained from vehicle image device；
More than two right side local filters are applicable to the right-hand lane information obtained from the vehicle image device；
Calculate the penalty factor of the left-hand lane information and right-hand lane information；
Left-hand lane is obtained using the penalty factor to the result by described two left side local filter filtering above
Estimate；
Right-hand lane is obtained using the penalty factor to the result by described two right side local filter filtering above
Estimate,
The penalty factor be according to the signal difference change entered by the vehicle image device and the weighted value of time,
Wherein, the penalty factor is calculated according to following [mathematical expression 1],
[mathematical expression 1]
<mrow>
<mi>W</mi>
<mfrac>
<mrow>
<mi>V</mi>
<mi>t</mi>
</mrow>
<mi>D</mi>
</mfrac>
<mo>+</mo>
<mrow>
<mo>(</mo>
<mi>&alpha;</mi>
<mo>&times;</mo>
<msub>
<mi>filter</mi>
<mn>1</mn>
</msub>
<mo>+</mo>
<mo>(</mo>
<mrow>
<mn>1</mn>
<mo>-</mo>
<mi>&alpha;</mi>
</mrow>
<mo>)</mo>
<mo>&times;</mo>
<msub>
<mi>filter</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<mfrac>
<mrow>
<mi>V</mi>
<mi>t</mi>
</mrow>
<mi>D</mi>
</mfrac>
<mo>)</mo>
</mrow>
</mrow>
W:Minimum lane width,
D:Maximum unidentified command range,
V:Speed,
t:Unidentified/time-out time of mistaking,
α:Filter weights, 0≤α≤1,
VtIt is the product of speed (V) and unidentified/misrecognition time-out time (t),
filter1It is to ask one in the left side local filter in the case of left-hand lane estimate, seeks right-hand lane estimate
In the case of right side local filter in one,
filter2It is to seek another in the left side local filter in the case of left-hand lane estimate, asks right-hand lane to estimate
Another in right side local filter in the case of value.
2. the lane recognition method of vehicle according to claim 1, it is characterised in that the left side local filter and the right side
Side local filter is the Kalman filter for meeting following [mathematical expression 2],
[mathematical expression 2]
<mrow>
<msubsup>
<mi>P</mi>
<mi>K</mi>
<mo>-</mo>
</msubsup>
<mo>=</mo>
<msub>
<mi>F</mi>
<mrow>
<mi>K</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msub>
<msubsup>
<mi>P</mi>
<mrow>
<mi>K</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mo>+</mo>
</msubsup>
<msubsup>
<mi>F</mi>
<mrow>
<mi>K</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</msubsup>
<mo>+</mo>
<msub>
<mi>Q</mi>
<mrow>
<mi>K</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msub>
</mrow>
<mrow>
<msub>
<mi>K</mi>
<mi>K</mi>
</msub>
<mo>=</mo>
<msubsup>
<mi>P</mi>
<mi>K</mi>
<mo>-</mo>
</msubsup>
<msubsup>
<mi>H</mi>
<mi>K</mi>
<mi>T</mi>
</msubsup>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>H</mi>
<mi>k</mi>
</msub>
<msubsup>
<mi>P</mi>
<mi>K</mi>
<mo>-</mo>
</msubsup>
<msubsup>
<mi>H</mi>
<mi>K</mi>
<mi>T</mi>
</msubsup>
<mo>+</mo>
<msub>
<mi>R</mi>
<mi>K</mi>
</msub>
<mo>)</mo>
</mrow>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msup>
</mrow>
<mrow>
<msubsup>
<mi>P</mi>
<mi>K</mi>
<mo>+</mo>
</msubsup>
<mo>=</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<msub>
<mi>K</mi>
<mi>K</mi>
</msub>
<msub>
<mi>H</mi>
<mi>K</mi>
</msub>
<mo>)</mo>
</mrow>
<msubsup>
<mi>P</mi>
<mi>K</mi>
<mo>-</mo>
</msubsup>
<msup>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<msub>
<mi>K</mi>
<mi>K</mi>
</msub>
<msub>
<mi>H</mi>
<mi>K</mi>
</msub>
<mo>)</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>+</mo>
<msub>
<mi>K</mi>
<mi>K</mi>
</msub>
<msub>
<mi>R</mi>
<mi>K</mi>
</msub>
<msubsup>
<mi>K</mi>
<mi>K</mi>
<mi>T</mi>
</msubsup>
</mrow>
P is system covariance, and Q and R are respectively process noise covariance and measurement noise covariance, and K is to utilize covariance meter
The kalman gain of calculation,
It is the system covariance of the first estimation at K time points,
FK-1It is the state transition matrix at k-1 time points,
It is the measured value of the system covariance at k-1 time points,
It is FK-1Prematrix,
QK-1It is the process noise covariance at K-1 time points,
KKIt is the kalman gain at k time points,
HKIt is the observing matrix at K time points,
It is HKPrematrix,
RKIt is the measurement noise covariance at k time points,
It is the first-estimated state parameter at k time points, is the estimated state parameter for estimating k time pointsIt is preceding formerly to estimate
Variable of state,
It is the estimated state parameter at k-1 time points,
It is the estimated state parameter at k time points,
yKBe k time points current driving in track actual measured value,
It is the system covariance of the estimation at k time points,
It is KKPrematrix.
3. a kind of Lane recognition device of vehicle, it is characterised in that receive the image information of left-hand lane from the camera of vehicle
With the image information of right-hand lane, the left-hand lane estimate and right-hand lane estimate are obtained, its composition includes：
Left side local filter, filters the image information of the left-hand lane by least two；
Right side local filter, filters the image information of the right-hand lane by least two；
Penalty factor block, calculates the penalty factor of the image information of the left-hand lane and the image information of the right-hand lane；
Left side senior filter, to the result using more than two left side local filters filtering, using the punishment because
Son obtains the left-hand lane estimate；
Right side senior filter, to the result using more than two right side local filters filtering, using the punishment because
Son, obtains the right-hand lane estimate,
The penalty factor is the signal difference change and the weighted value of time entered according to the camera by the vehicle,
The penalty factor is calculated according to following [mathematical expression 1],
[mathematical expression 1]
<mrow>
<mi>W</mi>
<mfrac>
<mrow>
<mi>V</mi>
<mi>t</mi>
</mrow>
<mi>D</mi>
</mfrac>
<mo>+</mo>
<mrow>
<mo>(</mo>
<mi>&alpha;</mi>
<mo>&times;</mo>
<msub>
<mi>filter</mi>
<mn>1</mn>
</msub>
<mo>+</mo>
<mo>(</mo>
<mrow>
<mn>1</mn>
<mo>-</mo>
<mi>&alpha;</mi>
</mrow>
<mo>)</mo>
<mo>&times;</mo>
<msub>
<mi>filter</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<mfrac>
<mrow>
<mi>V</mi>
<mi>t</mi>
</mrow>
<mi>D</mi>
</mfrac>
<mo>)</mo>
</mrow>
</mrow>
W:Minimum lane width,
D:Maximum unidentified command range,
V:Speed,
t:Unidentified/misrecognition time-out time,
α:Filter weights, 0≤α≤1,
Vt is the product of speed (V) and unidentified/misrecognition time-out time (t),
filter1It is to ask one in the left side local filter in the case of left-hand lane estimate, seeks right-hand lane estimate
In the case of right side local filter in one,
filter2It is to seek another in the left side local filter in the case of left-hand lane estimate, asks right-hand lane to estimate
Another in right side local filter in the case of value.
4. the Lane recognition device of vehicle according to claim 3, it is characterised in that the left side local filter and the right side
Side local filter is the Kalman filter for meeting following [mathematical expression 2],
[mathematical expression 2]
<mrow>
<msubsup>
<mi>P</mi>
<mi>K</mi>
<mo>-</mo>
</msubsup>
<mo>=</mo>
<msub>
<mi>F</mi>
<mrow>
<mi>K</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msub>
<msubsup>
<mi>P</mi>
<mrow>
<mi>K</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mo>+</mo>
</msubsup>
<msubsup>
<mi>F</mi>
<mrow>
<mi>K</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mi>T</mi>
</msubsup>
<mo>+</mo>
<msub>
<mi>Q</mi>
<mrow>
<mi>K</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msub>
</mrow>
<mrow>
<msub>
<mi>K</mi>
<mi>K</mi>
</msub>
<mo>=</mo>
<msubsup>
<mi>P</mi>
<mi>K</mi>
<mo>-</mo>
</msubsup>
<msubsup>
<mi>H</mi>
<mi>K</mi>
<mi>T</mi>
</msubsup>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>H</mi>
<mi>k</mi>
</msub>
<msubsup>
<mi>P</mi>
<mi>K</mi>
<mo>-</mo>
</msubsup>
<msubsup>
<mi>H</mi>
<mi>K</mi>
<mi>T</mi>
</msubsup>
<mo>+</mo>
<msub>
<mi>R</mi>
<mi>K</mi>
</msub>
<mo>)</mo>
</mrow>
<mrow>
<mo>-</mo>
<mn>1</mn>
</mrow>
</msup>
</mrow>
<mrow>
<msubsup>
<mi>P</mi>
<mi>K</mi>
<mo>+</mo>
</msubsup>
<mo>=</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<msub>
<mi>K</mi>
<mi>K</mi>
</msub>
<msub>
<mi>H</mi>
<mi>K</mi>
</msub>
<mo>)</mo>
</mrow>
<msubsup>
<mi>P</mi>
<mi>K</mi>
<mo>-</mo>
</msubsup>
<msup>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<msub>
<mi>K</mi>
<mi>K</mi>
</msub>
<msub>
<mi>H</mi>
<mi>K</mi>
</msub>
<mo>)</mo>
</mrow>
<mi>T</mi>
</msup>
<mo>+</mo>
<msub>
<mi>K</mi>
<mi>K</mi>
</msub>
<msub>
<mi>R</mi>
<mi>K</mi>
</msub>
<msubsup>
<mi>K</mi>
<mi>K</mi>
<mi>T</mi>
</msubsup>
</mrow>
P is system covariance, and Q and R are respectively process noise covariance and measurement noise covariance, and K is by covariance meter
The kalman gain of calculation,
It is the system covariance of the first estimation at K time points,
FK-1It is the state transition matrix at k-1 time points,
It is the measured value of the system covariance at k-1 time points,
It is FK-1Prematrix,
QK-1It is the process noise covariance at K-1 time points,
KKIt is the kalman gain at k time points,
HKIt is the observing matrix at K time points,
It is HKPrematrix,
RKIt is the measurement noise covariance at k time points,
It is the first-estimated state parameter at k time points, is the estimated state parameter for estimating k time pointsIt is preceding formerly to estimate
Variable of state,
It is the estimated state parameter at k-1 time points,
It is the estimated state parameter at k time points,
yKBe k time points current driving in track actual measured value,
It is the system covariance of the estimation at k time points,
It is KKPrematrix.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR10-2011-0084594 | 2011-08-24 | ||
| KR1020110084594A KR101805717B1 (en) | 2011-08-24 | 2011-08-24 | Method and apparatus for lane detection of vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103077371A CN103077371A (en) | 2013-05-01 |
| CN103077371B true CN103077371B (en) | 2017-10-13 |
Family
ID=48153895
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210306455.7A Active CN103077371B (en) | 2011-08-24 | 2012-08-24 | The lane recognition method and its device of vehicle |
Country Status (2)
| Country | Link |
|---|---|
| KR (1) | KR101805717B1 (en) |
| CN (1) | CN103077371B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101882249B1 (en) * | 2012-06-04 | 2018-08-24 | 현대모비스 주식회사 | Method and Appartus for Recogniting Lane Using Difference Weight, Method and Appartus for Controlling Lane Keeping Assist System Using the Same |
| KR20140062240A (en) * | 2012-11-14 | 2014-05-23 | 현대모비스 주식회사 | Lane recognition system and method |
| KR101519277B1 (en) | 2013-12-24 | 2015-05-11 | 현대자동차주식회사 | Apparatus and Method for Recognize of Drive Way of Vehicle |
| KR101558786B1 (en) | 2014-06-30 | 2015-10-07 | 현대자동차주식회사 | Apparatus and method for recognizing driving lane of vehicle |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630412A (en) * | 2008-07-18 | 2010-01-20 | 通用汽车环球科技运作公司 | Camera-based lane marker detection |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3885818B2 (en) * | 2005-05-27 | 2007-02-28 | トヨタ自動車株式会社 | Vehicle departure determination device |
| US8055445B2 (en) * | 2008-09-24 | 2011-11-08 | Delphi Technologies, Inc. | Probabilistic lane assignment method |
-
2011
- 2011-08-24 KR KR1020110084594A patent/KR101805717B1/en active IP Right Grant
-
2012
- 2012-08-24 CN CN201210306455.7A patent/CN103077371B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630412A (en) * | 2008-07-18 | 2010-01-20 | 通用汽车环球科技运作公司 | Camera-based lane marker detection |
Non-Patent Citations (1)
| Title |
|---|
| "应用方向可调滤波器的车道线识别方法";郭磊 等;《机械工程学报》;20080831;第44卷(第8期);第214-218、226页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103077371A (en) | 2013-05-01 |
| KR20130021987A (en) | 2013-03-06 |
| KR101805717B1 (en) | 2017-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107730520B (en) | Lane line detection method and system | |
| CN108389430B (en) | Intersection pedestrian and motor vehicle collision prediction method based on video detection | |
| CN103077371B (en) | The lane recognition method and its device of vehicle | |
| CN111516673B (en) | Lane line fusion system and method based on intelligent camera and high-precision map positioning | |
| US9740203B2 (en) | Drive assist apparatus | |
| CN105069859B (en) | Vehicle running state monitoring method and device | |
| CN100492437C (en) | Quick identification method for object vehicle lane changing | |
| CN110304063B (en) | Automatic lane changing method and system for vehicle and vehicle | |
| CN104657727B (en) | A kind of detection method of lane line | |
| JP5926080B2 (en) | Traveling lane marking recognition device and program | |
| CN103839264A (en) | Detection method of lane line | |
| JP5966965B2 (en) | Lane boundary departure control device and lane boundary departure suppression method | |
| CN101923782B (en) | Method for acquiring transportation traffic speed based on geomagnetic sensing technology | |
| WO2015106913A1 (en) | Method and system for estimating a course of a traffic lane | |
| CN101949704B (en) | Reliability evaluation device, reliability evaluation method | |
| CN110018632A (en) | A kind of vehicle lane change control method and device | |
| CN106778593A (en) | A kind of track level localization method based on the fusion of many surface marks | |
| CN106096525A (en) | A kind of compound lane recognition system and method | |
| CN104318258A (en) | Time domain fuzzy and kalman filter-based lane detection method | |
| CN109386155A (en) | Nobody towards automated parking ground parks the alignment method of transfer robot | |
| CN109835337B (en) | Turning control method and device and automatic driving vehicle | |
| CN104408917B (en) | Based on smart mobile phone acceleration transducer real-time traffic method of estimation | |
| CN110228524A (en) | Vehicle automatic steering control method based on multi-layer Fuzzy control | |
| CN112241175B (en) | Road full-traversal sweeping path planning method for unmanned sweeper | |
| CN106494172A (en) | Method for determining the current horizontal location of vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |