CN103523021B - Lane detection confidence level method of calculating and perform its computer device - Google Patents
Lane detection confidence level method of calculating and perform its computer device Download PDFInfo
- Publication number
- CN103523021B CN103523021B CN201310205432.1A CN201310205432A CN103523021B CN 103523021 B CN103523021 B CN 103523021B CN 201310205432 A CN201310205432 A CN 201310205432A CN 103523021 B CN103523021 B CN 103523021B
- Authority
- CN
- China
- Prior art keywords
- confidence level
- lane
- edge
- motion vector
- frame
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 17
- 239000013598 vector Substances 0.000 claims abstract description 35
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 8
- 238000000605 extraction Methods 0.000 description 2
- 208000035278 mandibuloacral dysplasia progeroid syndrome Diseases 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D15/00—Steering not otherwise provided for
- B62D15/02—Steering position indicators ; Steering position determination; Steering aids
- B62D15/025—Active steering aids, e.g. helping the driver by actively influencing the steering system after environment evaluation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/10—Path keeping
- B60W30/12—Lane keeping
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
- B60W40/06—Road conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
- B62D—MOTOR VEHICLES; TRAILERS
- B62D15/00—Steering not otherwise provided for
- B62D15/02—Steering position indicators ; Steering position determination; Steering aids
- B62D15/029—Steering assistants using warnings or proposing actions to the driver without influencing the steering system
- B62D15/0295—Steering assistants using warnings or proposing actions to the driver without influencing the steering system by overlaying a vehicle path based on present steering angle over an image without processing that image
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2552/00—Input parameters relating to infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Combustion & Propulsion (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Human Computer Interaction (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a kind of confidence level method of calculating of lane detection, as the confidence level method of calculating of the lane detection based on the image obtained from device for image, comprising: a) step, Edge detected in the frame of described image; B) step, from the described limb recognition lane mark detected; C) step, calculates the unique point of the described lane mark of identification; D) when described frame is not the initial frame of described image, the difference of the unique point of frame before calculating at least one of the unique point of the present frame of described image and storage, generates motion vector; And e) step, based on edge strength and the described motion vector at the edge of the representative lane mark in the edge of described present frame, calculate lane detection confidence level; The advantageous effects that can calculate the confidence level of lane detection is more accurately provided.
Description
Technical field
The present invention relates to lane detection confidence level method of calculating and perform its computer device, particularly relate to the present frame of image as the lane detection confidence level method of calculating of the lane mark change of frame before benchmark reflection and the computer device performing it.
Background technology
In the control system of intelligent vehicle, lane mark keeps ancillary system (LaneKeepingAssistSystem, hereinafter referred to as " LKAS ") or lane mark departure warning system (LaneDepartureWarningSystem, hereinafter referred to as " LDWS ") be ensure driver safety requisite system.This system is based on lane detection.For carrying out lane detection, utilize the information of multiple sensors.Particularly based on the lane detection system of video, its advantage is low cost, can export bulk information, can utilize original various video processnig algorithms, thus widely use.
The lane mark information of this lane detection systems axiol-ogy based on video is very important key element for the safety traffic of chaufeur.Therefore, be necessary to examine or check the confidence level about the lane mark detected.Propose the diversified method of the confidence level calculating lane detection, wherein, a kind of utilization is proposed from the distance between the edge (edge) and vehicle of the Image detection obtained to calculate the scheme of lane detection confidence level, but this scheme is the mode of the confidence level of the specific image calculating lane detection being confined to obtain time point.Therefore, Problems existing is, in Credibility judgement, be not included in the frame before of specific image, the change of lane detection result there occurs much changes.
Summary of the invention
(technical matters that will solve)
Therefore, the present invention researches and develops to solve the problem just, its object is to provide a kind of and can calculate the lane detection confidence level method of calculating of the confidence level of lane detection more accurately and perform its computer device.
(method of dealing with problems)
Be intended to the confidence level method of calculating that the invention provides a kind of lane detection reaching described object, as the confidence level method of calculating of the lane detection based on the image obtained from device for image, it comprises: a) step, Edge detected in the frame of described image; B) step, from the described limb recognition lane mark detected; C) step, calculates the unique point of the described lane mark of identification; D) step, when described frame is not the initial frame of described image, the difference of the unique point of frame before calculating at least one of the unique point of the present frame of described image and storage, generates motion vector; And e) step, based on edge strength and the described motion vector at the edge of the representative lane mark in the edge of described present frame, calculate lane detection confidence level.
Preferably, the confidence level of described e) step can with the function stand of the size of described motion vector and described edge strength.
Preferably, the confidence level of described e) step can calculate with the weighted sum of the size of described motion vector and described edge strength.
Preferably, the confidence level of described e) step can be multiplied by the value of the 1st weighted value with the size sum of described motion vector, described edge strength sum is multiplied by the value sum representative that the value that deducts the 2nd weighted value from 1 obtains.
On the other hand, the another kind invention being intended to reach described object can provide a kind of confidence level computer device of lane detection, as the confidence level computer device of the lane detection based on the image obtained from device for image, it comprises: rim detection portion, and it is from the frame Edge detected of described image; Lane detection portion, it is from the described limb recognition lane mark detected; Unique point calculating section, it calculates the unique point of the described lane mark of identification; Storage part, it stores the unique point of described lane mark; Motion vector generating unit, it calculates the difference of the unique point of frame before at least two that the unique point of the present frame of described image and described storage part store, and generates motion vector; And lane detection confidence calculation section, its intensity based on the edge of the representative lane mark in the edge of described present frame and described motion vector, calculate lane detection confidence level.
Preferably, described confidence level can with the function stand of the size of described motion vector and described intensity.
Preferably, described confidence level can calculate with the weighted sum of the size of described motion vector and described edge strength.
Preferably, described confidence level can be multiplied by the value of the 1st weighted value with the size sum of described motion vector, described edge strength sum is multiplied by the value sum representative that the value that deducts the 2nd weighted value from 1 obtains.
(effect of invention)
According to the credible method of calculating of lane detection of the present invention and the computer device performing it, with the present frame of image for benchmark, based on frame before, reflect the change of the lane mark of identification, the advantageous effects that can calculate the confidence level of lane detection is more accurately provided.
Accompanying drawing explanation
Fig. 1 is the figure that diagram LKAS is formed.
Fig. 2 is the diagram of circuit of the lane detection confidence level method of calculating of diagram a preferred embodiment of the invention,
Fig. 3 is the figure of the lane detection confidence level computer device of diagram a preferred embodiment of the invention,
Fig. 4 is the figure of display motion vector.
< nomenclature >
110: rim detection portion
120: Lane detection portion
130: unique point calculating section
140: storage part
150: motion vector generating unit
160: lane detection confidence calculation section
Detailed description of the invention
With reference to the accompanying drawings, the preferred embodiments of the present invention are described in detail.It is initially noted that giving in reference marks the inscape of each figure, for identical inscape, even if show on different figure, also give identical symbol as far as possible.In addition, preferred embodiments of the present invention will be described below, but technological thought of the present invention non-limiting or be limited to this, diversely can be out of shape enforcement by person of ordinary skill in the field, this is self-evident.
Fig. 1 is the figure of the formation of diagram LKAS.
As shown in Figure 1, LKASECU1 accepts to input about the chaufeur input information of switch, direction, wiper and the vehicle multidate information such as yaw velocity (yawrate), deflection angle, the speed of a motor vehicle of vehicle, the transmission of lane mark information and road information is accepted from road information extraction unit 2, control electric mode power steering system (MDPS:MotorDrivenPowerSteering, hereinafter referred to as " MDPS ") 3, make vehicle not run-off-road line.
The present invention is as the technology of confidence level calculating the lane mark information transmitted about road information extraction unit 2, and its technical characteristic is benchmark with present frame, and the lane mark information of frame before reflection, calculates the confidence level of the lane mark information extracted based on present frame.
Fig. 2 is the diagram of circuit of the lane detection confidence level method of calculating of diagram a preferred embodiment of the invention, and Fig. 3 is the figure of the lane detection confidence level computer device of diagram a preferred embodiment of the invention.On the other hand, Fig. 4 is the figure of display motion vector.
As shown in Figure 2 to 4, first, from the frame of image Edge detected (edge) (S100).Rim detection portion (110) is to every frame Edge detected one by one of the image obtained from camera.Wherein, so-called edge, refers to the place of change or inverse variation from the brightness lower value of image to high value.Change or the brightness of major part color value change greatly place, and be shown in the border of object, therefore, Edge detected, can extract the border of the object in image.As the representational first order differential operator of Edge detected, can for Sobel shade (sobelmask).
Next, after rim detection, from the limb recognition lane mark (S200) detected.Lane detection portion (120) is identified in the edge representing lane mark in the edge of detection.
If assuming that road is smooth, then typically, lane mark is straight line, and the width of two lane maries is set, and two lane maries intersect a vanishing point.And vanishing point has the feature be present on ground line.Therefore, in edge, vertical direction edge is not that the probability of lane mark is higher, so, can not consider as lane mark candidate.In addition, through extracting the candidate point that lane mark width had both been shaped as, and through extracting line composition based on this, the line composition towards vanishing point is identified as the step of lane mark.Described Lane detection step is any one example, and non-limiting the present invention.
The t of Fig. 4 take present frame as the lane mark of benchmark identification, the lane mark that the t-1 of Fig. 4 is is benchmark identification with frame before present frame.In addition, the lane mark that the t-2 of Fig. 4 is is benchmark identification with the in addition front frame of present frame.
Next, calculate the unique point of the lane mark of identification and it is stored (S300).Unique point calculating section 130 can calculate multiple unique point on the lane mark identified.Unique point based on the lane mark of present frame identification can use a1, a2, a3, a4 of Fig. 4 ... representative, the unique point based on the lane mark of frame identification before can use a1 ', a2 ', a3 ', the a4 ' of Fig. 4 ..., a1 ' ', a2 ' ', a3 ' ', a4 ' ' ... representative.The unique point calculated is stored in storage part 140.
Next, when the frame of image is not initial frame, calculates the unique point of present frame and the difference of the unique point of frame before, generate motion vector (S400).
Motion vector generating unit 150 is generated as motion vector the two-dimensional position of the unique point of the lane mark based on present frame identification with the relative change of the two-dimensional position of the unique point of the lane mark based on frame identification before.Such as, as shown in Figure 4, when taking present frame as benchmark, set unique point is mobile to a1-a1-' a1 '.
Wherein, can with the unique point a1 of present frame for benchmark, the two-dimensional location difference of the unique point a1 ' of frame is before generated as motion vector V11.In addition, with the unique point a1 of present frame for benchmark, the two-dimensional location difference of the unique point a1 ' ' of frame before is in addition generated as motion vector V21.In Fig. 4, graphic other motion vectors V12, V22, V13, V24, V14, V24 are also by as above generating.The number of motion vector corresponds to the number of the unique point of lane mark.
Next, based on edge strength (hereinafter referred to as lane mark edge strength) and the above-mentioned motion vector at the edge of the representative lane mark in the edge of present frame, lane detection confidence level (S500) is calculated.
Lane detection confidence calculation section 160, by following mathematical expression 1, calculates lane detection confidence level.
< mathematical expression 1>
Confidence level=ω
1∑ | motion vector |+(1-ω
2) ∑ | lane mark edge
Wherein, ω
1represent the 1st weighted value about motion vector, ω
2represent the 2nd weighted value about lane mark edge strength.In one embodiment, the representative of lane mark edge strength utilizes Sobel shade (sobelmask) from the edge that the present frame of image detects about the brightness value sum of each pixel at edge being chosen as lane mark.
More than illustrate and just technological thought of the present invention is exemplarily described, as long as those skilled in the art, in the scope not exceeding internal characteristic of the present invention, can multiple amendment, change and displacement be carried out.Therefore, disclosed embodiment and accompanying drawing in the present invention, be not for limit technological thought of the present invention but for illustration of, the scope of technological thought of the present invention not limited by these embodiments and accompanying drawing.Protection scope of the present invention should make an explanation according to following request scope, and all technological thoughts in equivalents with it, should be interpreted as being included in interest field of the present invention.
Claims (4)
1. a confidence level method of calculating for lane detection, as the confidence level method of calculating of the lane detection based on the image obtained from device for image, is characterized in that, comprising:
A) step, Edge detected in the frame of described image;
B) step, from the described limb recognition lane mark detected;
C) step, calculates the unique point of the described lane mark of identification;
D) step, when described frame is not the initial frame of described image, the difference of the unique point of frame before calculating at least one of the unique point of the present frame of described image and storage, generates motion vector; And
E) step, based on edge strength and the described motion vector at the edge of the representative lane mark in the edge of described present frame, calculates lane detection confidence level;
Wherein, the confidence level of described e) step calculates with the weighted sum of the size of described motion vector and described edge strength.
2. the confidence level method of calculating of lane detection according to claim 1, is characterized in that,
The confidence level of described e) step is multiplied by the value of the 1st weighted value with the size sum of described motion vector, described edge strength sum is multiplied by the value sum representative that the value that deducts the 2nd weighted value from 1 obtains.
3. a confidence level computer device for lane detection, as the confidence level computer device of the lane detection based on the image obtained from device for image, is characterized in that, comprising:
Rim detection portion, it is from the frame Edge detected of described image;
Lane detection portion, it is from the described limb recognition lane mark detected;
Unique point calculating section, it calculates the unique point of the described lane mark of identification;
Storage part, it stores the unique point of described lane mark;
Motion vector generating unit, it calculates the difference of the unique point of frame before at least two that the unique point of the present frame of described image and described storage part store, and generates motion vector; And
Lane detection confidence calculation section, represents the intensity at the edge of lane mark and described motion vector in its edge based on described present frame, calculates lane detection confidence level;
Wherein, described confidence level calculates with the weighted sum of the size of described motion vector and described edge strength.
4. the confidence level computer device of lane detection according to claim 3, is characterized in that,
Described confidence level is multiplied by the value of the 1st weighted value with the size sum of described motion vector, described edge strength sum is multiplied by the value sum representative that the value that deducts the 2nd weighted value from 1 obtains.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020120071924A KR101912085B1 (en) | 2012-07-02 | 2012-07-02 | Reliability calaulation method of lane detection and Apparatus for calcaulating for performing thereof |
KR10-2012-0071924 | 2012-07-02 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103523021A CN103523021A (en) | 2014-01-22 |
CN103523021B true CN103523021B (en) | 2016-01-20 |
Family
ID=49925486
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310205432.1A Active CN103523021B (en) | 2012-07-02 | 2013-05-29 | Lane detection confidence level method of calculating and perform its computer device |
Country Status (2)
Country | Link |
---|---|
KR (1) | KR101912085B1 (en) |
CN (1) | CN103523021B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105292122B (en) * | 2015-10-22 | 2018-07-06 | 四川膨旭科技有限公司 | The method that road conditions are identified in vehicle travel process |
CN106652097A (en) * | 2016-12-16 | 2017-05-10 | 东莞市炫彩光电科技有限公司 | Multifunctional event data recorder and control method of mobile terminal APP |
CN107697154B (en) * | 2017-08-30 | 2019-11-22 | 宝沃汽车(中国)有限公司 | Steering angle correcting method, electronic power assist steering system and vehicle |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101567086A (en) * | 2009-06-03 | 2009-10-28 | 北京中星微电子有限公司 | Method of lane line detection and equipment thereof |
CN102385698A (en) * | 2011-10-26 | 2012-03-21 | 潘承志 | Image processing method based on belief propagation |
CN102427982A (en) * | 2009-05-19 | 2012-04-25 | 株式会社伊美吉内柯斯特 | Lane departure sensing method and apparatus using images that surround a vehicle |
Family Cites Families (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH05314396A (en) * | 1992-05-13 | 1993-11-26 | Omron Corp | Continuous line tracking device |
JP3630100B2 (en) | 2000-12-27 | 2005-03-16 | 日産自動車株式会社 | Lane detection device |
JP4162618B2 (en) * | 2004-03-12 | 2008-10-08 | 株式会社豊田中央研究所 | Lane boundary judgment device |
JP4539415B2 (en) * | 2005-04-15 | 2010-09-08 | 株式会社デンソー | Image processing device |
JP4659631B2 (en) | 2005-04-26 | 2011-03-30 | 富士重工業株式会社 | Lane recognition device |
JP2007011490A (en) * | 2005-06-28 | 2007-01-18 | Toyota Motor Corp | Device and method for detecting road parameter |
JP4923520B2 (en) * | 2005-11-07 | 2012-04-25 | 日産自動車株式会社 | VEHICLE POSITION ESTIMATION DEVICE, VEHICLE TRAVEL SUPPORT DEVICE, AND VEHICLE POSITION ESTIMATION METHOD |
JP2009252198A (en) | 2008-04-11 | 2009-10-29 | Suzuki Motor Corp | Travel environment presuming device, method and program, and traffic lane deviation alarm device and steering assisting apparatus |
JP5310027B2 (en) | 2009-01-26 | 2013-10-09 | 日産自動車株式会社 | Lane recognition device and lane recognition method |
-
2012
- 2012-07-02 KR KR1020120071924A patent/KR101912085B1/en active IP Right Grant
-
2013
- 2013-05-29 CN CN201310205432.1A patent/CN103523021B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102427982A (en) * | 2009-05-19 | 2012-04-25 | 株式会社伊美吉内柯斯特 | Lane departure sensing method and apparatus using images that surround a vehicle |
CN101567086A (en) * | 2009-06-03 | 2009-10-28 | 北京中星微电子有限公司 | Method of lane line detection and equipment thereof |
CN102385698A (en) * | 2011-10-26 | 2012-03-21 | 潘承志 | Image processing method based on belief propagation |
Also Published As
Publication number | Publication date |
---|---|
KR101912085B1 (en) | 2018-10-26 |
KR20140004410A (en) | 2014-01-13 |
CN103523021A (en) | 2014-01-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10246030B2 (en) | Object detection apparatus and driving assistance apparatus | |
EP2767927B1 (en) | Road surface information detection apparatus, vehicle device control system employing road surface information detection apparatus, and carrier medium of road surface information detection program | |
EP3007099B1 (en) | Image recognition system for a vehicle and corresponding method | |
US9077958B2 (en) | Road departure warning system | |
JP5074365B2 (en) | Camera device | |
KR101143176B1 (en) | Method and Apparatus for Recognizing Parking Slot Marking by Using Bird's Eye View and Parking Assist System Using Same | |
US9569673B2 (en) | Method and device for detecting a position of a vehicle on a lane | |
US9360332B2 (en) | Method for determining a course of a traffic lane for a vehicle | |
JP6453192B2 (en) | Image recognition processing apparatus and program | |
EP2963634B1 (en) | Stereo camera device | |
CN107845290B (en) | Intersection warning method, processing system, intersection warning system and vehicle | |
Shin et al. | Visual lane analysis and higher-order tasks: a concise review | |
JP6376429B2 (en) | Target point arrival detection device, target point arrival detection program, mobile device control system, and mobile | |
US20050102070A1 (en) | Vehicle image processing device | |
KR20090088210A (en) | Method and apparatus for detecting target parking location by using two reference point and parking assist system using same | |
CN107792070B (en) | Driving assistance device for vehicle | |
JP2021510227A (en) | Multispectral system for providing pre-collision alerts | |
JP6337811B2 (en) | Image processing apparatus and image processing method | |
US8559727B1 (en) | Temporal coherence in clear path detection | |
JP4951481B2 (en) | Road marking recognition device | |
CN103523021B (en) | Lane detection confidence level method of calculating and perform its computer device | |
US20200193184A1 (en) | Image processing device and image processing method | |
JP5097681B2 (en) | Feature position recognition device | |
KR101658089B1 (en) | Method for estimating a center lane for lkas control and apparatus threof | |
Jung et al. | 3D vision system for the recognition of free parking site location |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |