CN105966398A - Method and device for early warning lane departure of vehicle - Google Patents
Method and device for early warning lane departure of vehicle Download PDFInfo
- Publication number
- CN105966398A CN105966398A CN201610460415.6A CN201610460415A CN105966398A CN 105966398 A CN105966398 A CN 105966398A CN 201610460415 A CN201610460415 A CN 201610460415A CN 105966398 A CN105966398 A CN 105966398A
- Authority
- CN
- China
- Prior art keywords
- lane line
- information
- early warning
- image
- road
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 238000001914 filtration Methods 0.000 claims description 17
- 230000000052 comparative effect Effects 0.000 claims description 15
- 230000001143 conditioned effect Effects 0.000 claims description 15
- 206010039203 Road traffic accident Diseases 0.000 abstract 1
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
Classifications
-
- 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
- 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
- B60W40/12—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 parameters of the vehicle itself, e.g. tyre models
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The invention provides a method and device for early warning lane departure of a vehicle. The method comprises the steps of estimating, wherein current actual lane line information is estimated according to lane line information of the precious frame of a road image; comparing, wherein preset lane line information of the vehicle is acquired, and if a comparing result of the actual lane line information and the preset lane line information does not meet preset conditions, it is judged that the vehicle departs from the lane; early warning, wherein running information of the vehicle is acquired, and if it is judged that the vehicle needs to be early warned according to the running information, an early warning prompt is sent. According to the method and device, detection on the lane line is more accurate, and therefore whether the vehicle departs from the lane or not can be judged more accurately; when the vehicle driven by a driver departs from the lane, the early warning prompt can be given in time, and then traffic accidents are prevented from occurring.
Description
Technical field
The present invention relates to electronic applications, particularly relate to a kind of method and apparatus that automotive run-off-road is carried out early warning.
Background technology
In prior art, photographic head, vehicle sensed data, current vehicle location information and roadmap data is utilized to carry out lane identification, the mode of detection vehicle whether run-off-road, needs communication module and accurately roadmap data accurately, and otherwise real-time and accuracy are difficult to ensure that.Use the mode of dual camera detection vehicle whether run-off-road, need two photographic head are installed, install trouble, the image of different photographic head is merged process and also adds difficulty to processing procedure, have impact on the real-time processing image simultaneously.
Therefore, it is necessary to improvement drawbacks mentioned above.
Summary of the invention
Based on problem above, the present invention proposes a kind of method and apparatus that automotive run-off-road is carried out early warning.Current actual lane line information is estimated by the lane line information according to former frame road image;Obtain the default lane line information of vehicle, if the comparative result of actual lane line information and default lane line information is unsatisfactory for pre-conditioned, then judge automotive run-off-road;Obtain the operation information of vehicle, if according to operation information, judge to need vehicle is carried out early warning, then send the mode of early warning, make the detection to lane line more accurate, thus judge vehicle whether run-off-road more accurately, make when driver-operated automotive run-off-road, early warning can be given in time, thus avoid vehicle accident.
On the one hand, the present invention proposes a kind of method that automotive run-off-road is carried out early warning, including:
Estimate step, including: estimate current actual lane line information according to the lane line information of former frame road image;
Comparison step, including: obtain the default lane line information of described vehicle, if the comparative result of described actual lane line information and described default lane line information is unsatisfactory for pre-conditioned, then judge that described vehicle deviates described track;
Warning step, including: obtain the operation information of described vehicle, if according to described operation information, it is judged that need described vehicle is carried out early warning, then send early warning.
Additionally, described method also includes obtaining present frame lane line information Step, including:
Obtain image sub-step, including: obtain present frame road image;
Pretreatment sub-step, including: described present frame road image carries out the pretreatment operation of image, and described pretreatment operation includes being purged the non-lane line in described present frame road image, and pretreated described present frame road image is pretreatment image;
Detection sub-step, including: the lane line in described pretreatment image is detected, it is thus achieved that the lane line information of described lane line.
Additionally, also include sub-step of filtering, including: described lane line information is carried out Kalman filtering, estimates out the actual lane line information of next frame road image.
Additionally, before the non-lane line in described present frame road image is purged, also include: find vanishing line in described present frame road image, described present frame road image intercepts the image of below described vanishing line, and it is carried out denoising and filtering.
Additionally, described it is carried out denoising and filtering after, also include: according to the lane line information of the road image of the former frame of described present frame road image, determine region or the position of lane line in described present road image.
In addition, described detection sub-step specifically includes: detect all of line segment in described pretreatment image, can not remove at the line segment that end point intersects and/or the line segment not meeting lane line feature is removed after extending, make remaining line segment become described lane line, and obtain the lane line information of described lane line.
Making remaining line segment become described lane line described in additionally, specifically include: according to fitting algorithm, be fitted remaining line segment so that it is become continuous print straight line, described straight line is described lane line.
Additionally, described operation information includes: velocity information and/or direction information.
In addition, if described actual lane line information is unsatisfactory for pre-conditioned with the comparative result of default lane line information, specifically include: if the difference of the distance between the reference component of described vehicle and lane line and the predeterminable range value in described default lane line information is more than preset difference value, then it is assumed that described comparative result is unsatisfactory for described pre-conditioned.
On the other hand, the present invention proposes a kind of device that automotive run-off-road carries out early warning, including:
Estimate module, be used for: estimate current actual lane line information according to the lane line information of former frame road image;
Comparison module, is used for: obtain the default lane line information of described vehicle, if the comparative result of described actual lane line information and described default lane line information is unsatisfactory for pre-conditioned, then judges that described vehicle deviates described track;
Warning module, is used for: obtain the operation information of described vehicle, if according to described operation information, it is judged that needs described vehicle is carried out early warning, then sends early warning.
Use technique scheme, have the advantages that
Current actual lane line information is estimated by the lane line information according to former frame road image;Obtain the default lane line information of vehicle, if the comparative result of actual lane line information and default lane line information is unsatisfactory for pre-conditioned, then judge automotive run-off-road;Obtain the operation information of vehicle, if according to operation information, judge to need vehicle is carried out early warning, then send the mode of early warning, make the detection to lane line more accurate, thus judge vehicle whether run-off-road more accurately, make when driver-operated automotive run-off-road, early warning can be given in time, thus avoid vehicle accident.
Accompanying drawing explanation
Fig. 1 is the flow chart of the method that automotive run-off-road carries out early warning according to an embodiment of the invention;
Fig. 2 is the flow chart of the method that automotive run-off-road carries out early warning in accordance with another embodiment of the present invention;
Fig. 3 is the flow chart of the method that automotive run-off-road carries out early warning in accordance with another embodiment of the present invention;
Fig. 4 is the flow chart of the method that automotive run-off-road carries out early warning in accordance with another embodiment of the present invention;
Fig. 5 is the flow chart of the method that automotive run-off-road carries out early warning in accordance with another embodiment of the present invention;
Fig. 6 is the block diagram of the device that automotive run-off-road carries out early warning in accordance with another embodiment of the present invention.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is a part of embodiment of the present invention rather than whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art are obtained under not making creative work premise, broadly fall into the scope of protection of the invention.
With reference to Fig. 1, the present invention proposes a kind of method that automotive run-off-road is carried out early warning, including:
Estimate step S001, including: estimate current actual lane line information according to the lane line information of former frame road image;
Comparison step S002, including: obtain the default lane line information of vehicle, if the comparative result of actual lane line information and default lane line information is unsatisfactory for pre-conditioned, then judge automotive run-off-road;
Warning step S003, including: obtain the operation information of vehicle, if according to operation information, it is judged that need vehicle is carried out early warning, then send early warning.
In estimating step S001, present frame road image is carried out pretreatment operation, and the mode detecting lane line also is able to obtain current actual lane line information.Lane line information according to former frame road image estimates the mode of current actual lane line information, make the actual lane line information obtained more accurate, if only with the mode that the lane line in present frame road image is detected, may result in the result mistake of detection and the problem that produces false alarm.In one of which embodiment, by the lane line information of former frame road image with present frame road image is detected the lane line information obtained combine the actual lane line information that obtains, in this way, it is possible to obtain result more accurately.
In comparison step S002, obtain the default lane line information of vehicle, presetting lane line information is default lane line information, including: such as the distance of the left front headstock distance left-lane line of vehicle, when the center of the front windshield that the photographic head being arranged on vehicle is arranged on vehicle, the distance of the left front headstock distance lane line of vehicle is recorded as an information in default lane line information;And for example: the distance of the right front headstock distance right lane line of vehicle or the distance of other reference component distance lane line of vehicle.
Relatively actual lane line information and default lane line information, as: the distance of the left front headstock distance left-lane line of the vehicle in actual lane line information is 5 centimetres, and the distance presetting the left front headstock distance left-lane line of vehicle in lane line information is 20 centimetres, the difference 15 of the two is more than the difference threshold 10 preset, then it is assumed that vehicle now has deviated from track.
In warning step S003, obtain the operation information of vehicle, as when vehicle is about to changing Lane or turns, left or right steering indicating light can be opened, if left or right steering indicating light opened by vehicle, then it is assumed that vehicle is now normal run-off-road, so not carrying out alarm;When the situation that vehicle simply normally moves forward, vehicle is carried out alarm.By the way of sound and/or image, user is carried out alarm.
Road image is that the camera head by being arranged on vehicle obtains, and in one of which embodiment, installs a camera head on the front windshield of vehicle, and camera head includes photographic head.
Operation information includes: velocity information or direction information.
Current actual lane line information is estimated by the lane line information according to former frame road image;Obtain the default lane line information of vehicle, if the comparative result of actual lane line information and default lane line information is unsatisfactory for pre-conditioned, then judge automotive run-off-road;Obtain the operation information of vehicle, if according to operation information, judge to need vehicle is carried out early warning, then send the mode of early warning, make the detection to lane line more accurate, thus judge vehicle whether run-off-road more accurately, make when driver-operated automotive run-off-road, early warning can be given in time, thus avoid vehicle accident.
With reference to Fig. 2, in one of which embodiment, method also includes obtaining present frame lane line information Step, including:
Obtain image sub-step S201, including: obtain present frame road image;
Pretreatment sub-step S202, including: present frame road image carries out the pretreatment operation of image, and pretreatment operation includes being purged the non-lane line in present frame road image, and pretreated present frame road image is pretreatment image;
Detection sub-step S203, including: the lane line in pretreatment image is detected, it is thus achieved that the lane line information of lane line.
Obtain in image sub-step S201, obtain present frame road image by the photographic head being arranged on the front windshield of vehicle.
S202 in pretreatment sub-step, first carries out pretreatment operation to present frame road image, and pretreatment operation step includes:
First present frame road image is converted to gray level image, vanishing line is found in gray level image, intercept the image of below vanishing line, this parts of images is region of interest ROI (ROI:region of interest), by intercepting the image of below vanishing line, image below vanishing line is processed, advantageously reduces the amount of calculation to image, it is also possible to strengthen the real-time of image procossing.
The gray threshold of adaptive polo placement gray level image, use gray threshold that gray level image is carried out Canny Filtering Processing, filtered image is carried out profile pretreatment, filter the fence of the interference contour line in obvious non-track, such as vehicle's contour, both sides, ground spray printing word or other chaff interference, because these interference contour lines are obvious, it will not be the alternative profile of lane line, so preferentially getting rid of, reapplying Hough transform and remaining line segment is fitted, fitting to lane line.In one of which embodiment, if former frame road image has been detected by lane line, so can be in conjunction with the position of the lane line of former frame, determine region or the position of lane line in present frame road image, because the lane line displacement front and back in two field picture is the least, only can search for the lane line of present frame in the lane line certain limit that former frame detects, reduce detection region the most further, such that it is able to process image faster.
In detection sub-step S203, according to Geometrical imaging characteristics, line segment is screened, because in mapping geometry, in space, all parallel straight lines can intersect at infinity, and this infinite point is referred to as end point (Vanishing Point).In actual road environment, there are substantial amounts of parallel lines, such as lane line, road boundary etc., these lines can be compared to a bit in the plane of delineation, forming end point, and other parallel lines can intersect at other end point, finally these end points form a vanishing line.For fixing photographic head, the position of vanishing line and end point is fixing, utilizes the feature of end point and vanishing line, and the line segment that can not intersect near end point for own or extended line filters, and filters the interference line segment of obvious non-lane line;Meanwhile, according to the width filter of lane line non-track line segment, if the developed width of the lane line of a road is 15CM, then width be 25 line segment be just filtered, different width can be set for filtering non-lane line.Color characteristic according to lane line filters non-lane line, such as: white and yellow, filters out non-lane line according to color characteristic.Filter out non-lane line according to lane width, if the normal width in track is 3.25M, the line segment not meeting lane width is removed.Lane line according to rectilinear stretch line model matching current road.By these modes, non-lane line is removed, thus leave real lane line so as to get lane line more press close to real lane line.
In one of which embodiment, also include sub-step of filtering, including: lane line information is carried out Kalman filtering, estimates out the actual lane line information of next frame road image.
Kalman (Kalman:Kalman filtering) wave filter is a kind of algorithm utilizing linear system state equation to realize optimal estimation.In this algorithm, the lane line information that input parameter is the former frame having been detected by of wave filter, output parameter is the lane line information of present frame, actual lane line as present frame uses, and the lane line information of present frame is as the input parameter of Kalman filter next time, it is used for predicting next frame lane line information.
Use Kalman filter the lane detection interference that causes of the factor such as inconspicuous to lane line, intermittent, light change to correct, thus tracking to lane line continuous-stable is better achieved.
In one of which embodiment, before the non-lane line in present frame road image is purged, also include: in present frame road image, find vanishing line, present frame road image intercepts the image of below vanishing line, and it is carried out denoising and filtering.Because the image below vanishing line includes lane line, so the base image that the image intercepting below vanishing line processes as successive image, make the computing of image procossing reduce, enhance the real-time of image procossing.
In one of which embodiment, after it is carried out denoising and filtering, also include: according to the lane line information of the road image of the former frame of present frame road image, determine region or the position of lane line in present road image.Because the lane line information in two continuous frames road image typically changes not quite, so region or the position of lane line in present road image can be determined by the lane line information of former frame road image, lane line is further determined that in the region determined or position, so that the detection to lane line is more accurate, decrease the detection time.
In one of which embodiment, detection sub-step specifically includes: all of line segment detecting in pretreatment image, can not remove at the line segment that end point intersects and/or the line segment not meeting lane line feature is removed after extending, make remaining line segment become lane line, and obtain the lane line information of lane line.Non-lane line is removed, thus leave real lane line so as to get lane line more press close to real lane line.
In one of which embodiment, making remaining line segment become lane line, specifically include: according to fitting algorithm, be fitted remaining line segment so that it is become continuous print straight line, straight line is lane line.The line segment detected in image procossing is probably desultory line, so using fitting algorithm, makes these line segments become a continuous print straight line, and straight line is as lane line.Discontinuous line segment is made to become continuous print lane line by fitting algorithm.The lane line detected is shown in the way of highlighting.
In one of which embodiment, operation information includes: velocity information and/or direction information.Negotiation speed information and/or direction information judge that whether vehicle now is in lane change or turning.
In one of which embodiment, if actual lane line information is unsatisfactory for pre-conditioned with the comparative result of default lane line information, specifically include: if the difference of the distance between the reference component of vehicle and lane line and the predeterminable range value in default lane line information is more than preset difference value, then it is assumed that comparative result is unsatisfactory for pre-conditioned.
Relatively actual lane line information and default lane line information, as: the distance of the left front headstock distance left-lane line of the vehicle in actual lane line information is 5 centimetres, and the distance presetting the left front headstock distance left-lane line of vehicle in lane line information is 20 centimetres, the difference 15 of the two is more than the difference threshold 10 preset, then it is assumed that vehicle now has deviated from track.By the comparison with preset difference value, thus obtain vehicle whether run-off-road.
The flow process of an embodiment in the present invention is described with reference to Fig. 3, Fig. 4 and Fig. 5.
Step S301, obtains the pavement image of photographic head shooting;
Step S302, reads present frame pavement image F1, and is converted into gray level image;
Step S303, intercepts the following region of interest ROI of vanishing line;
Step S304, calculates the adaptive threshold in region of interest ROI, and road pavement image is filtered processing, and obtains road surface lane line profile;
Step S305, profile processes, and filtration is not the interference line segment of lane line;
Step S306, it is judged that whether former frame pavement image F0 has been detected by lane line, the most then perform step S307, if it is not, then perform step S308;
Step S307, according to the lane line position of former frame F0 detection, reduces present frame F1 lane detection scope;
Step S308, obtains lane line region and track profile.
So far, the pretreatment operation of road pavement image terminates, and detects lane line below in pretreatment image.
Step S401, filters interference line segment according to vanishing line, end point;
Step S402, according to lane line color, lane line width, lane width information filtering interference line segment;
Step S403, according to lane line preset model matching lane line.
So far, lane line is detected.
Step S501, if lane line being detected at present frame road image F1, then performs step S502, otherwise performs step S504;
Step S502, detects the actual lane line in road image;
Step S503, detection of end;
Step S504, whether former frame road image F0 has been detected by lane line, the most then perform step S505, otherwise perform step S507;
Step S505, if continuous detecting is less than frame number < threshold value N, then execution step S506, otherwise execution step S507 of lane line;
Step S506, Kalman filter is estimated lane line, is jumped to step S503;
Step S507, obtains present road image and there is not the conclusion of lane line, jump to step S503.
With reference to Fig. 6, the present invention proposes a kind of device that automotive run-off-road carries out early warning, including:
Estimate module 601, be used for: estimate current actual lane line information according to the lane line information of former frame road image;
Comparison module 602, is used for: obtain the default lane line information of vehicle, if the comparative result of actual lane line information and default lane line information is unsatisfactory for pre-conditioned, then judges automotive run-off-road;
Warning module 603, is used for: obtain the operation information of vehicle, if according to operation information, it is judged that need vehicle is carried out early warning, then send early warning.
Device embodiment described above is only schematically, the wherein said unit illustrated as separating component can be or may not be physically separate, the parts shown as unit can be or may not be physical location, i.e. may be located at a place, or can also be distributed on multiple NE.Some or all of module therein can be selected according to the actual needs to realize the purpose of the present embodiment scheme.Those of ordinary skill in the art, in the case of not paying performing creative labour, are i.e. appreciated that and implement.
Through the above description of the embodiments, those skilled in the art is it can be understood that can add the mode of required general hardware platform by software to each embodiment and realize, naturally it is also possible to pass through hardware.Based on such understanding, the part that prior art is contributed by technique scheme the most in other words can embody with the form of software product, this computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD etc., including some instructions with so that a computer equipment (can be personal computer, server, or the network equipment etc.) perform the method described in some part of each embodiment or embodiment.
Last it is noted that above example is only in order to illustrate technical scheme, it is not intended to limit;Although the present invention being described in detail with reference to previous embodiment, it will be understood by those within the art that: the technical scheme described in foregoing embodiments still can be modified by it, or wherein portion of techniques feature is carried out equivalent;And these amendments or replacement, do not make the essence of appropriate technical solution depart from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
1. the method that automotive run-off-road is carried out early warning, it is characterised in that including:
Estimate step, including: estimate current actual lane line information according to the lane line information of former frame road image;
Comparison step, including: obtain the default lane line information of described vehicle, if the comparative result of described actual lane line information and described default lane line information is unsatisfactory for pre-conditioned, then judge that described vehicle deviates described track;
Warning step, including: obtain the operation information of described vehicle, if according to described operation information, it is judged that need described vehicle is carried out early warning, then send early warning.
The method that automotive run-off-road is carried out early warning the most according to claim 1, it is characterised in that:
Described method also includes obtaining present frame lane line information Step, including:
Obtain image sub-step, including: obtain present frame road image;
Pretreatment sub-step, including: described present frame road image carries out the pretreatment operation of image, and described pretreatment operation includes being purged the non-lane line in described present frame road image, and pretreated described present frame road image is pretreatment image;
Detection sub-step, including: the lane line in described pretreatment image is detected, it is thus achieved that the lane line information of described lane line.
The method that automotive run-off-road is carried out early warning the most according to claim 2, it is characterised in that:
Also include sub-step of filtering, including: described lane line information is carried out Kalman filtering, estimates out the actual lane line information of next frame road image.
The method that automotive run-off-road is carried out early warning the most according to claim 2, it is characterised in that:
Before non-lane line in described present frame road image is purged, also include: in described present frame road image, find vanishing line, described present frame road image intercepts the image of below described vanishing line, and it is carried out denoising and filtering.
The method that automotive run-off-road is carried out early warning the most according to claim 4, it is characterised in that:
Described it is carried out denoising and filtering after, also include: according to the lane line information of the road image of the former frame of described present frame road image, determine region or the position of lane line in described present road image.
The method that automotive run-off-road is carried out early warning the most according to claim 2, it is characterised in that:
Described detection sub-step specifically includes: detect all of line segment in described pretreatment image, can not remove at the line segment that end point intersects and/or the line segment not meeting lane line feature is removed after extending, make remaining line segment become described lane line, and obtain the lane line information of described lane line.
The method that automotive run-off-road is carried out early warning the most according to claim 6, it is characterised in that:
Described making remaining line segment become described lane line, specifically include: according to fitting algorithm, be fitted remaining line segment so that it is become continuous print straight line, described straight line is described lane line.
8. according to the method that automotive run-off-road is carried out early warning described in any one of claim 1 to 7, it is characterised in that:
Described operation information includes: velocity information and/or direction information.
9. according to the method that automotive run-off-road is carried out early warning described in any one of claim 1 to 7, it is characterised in that:
If described actual lane line information is unsatisfactory for pre-conditioned with the comparative result of default lane line information, specifically include: if the difference of the distance between the reference component of described vehicle and lane line and the predeterminable range value in described default lane line information is more than preset difference value, then it is assumed that described comparative result is unsatisfactory for described pre-conditioned.
10. the device that automotive run-off-road is carried out early warning, it is characterised in that including:
Estimate module, be used for: estimate current actual lane line information according to the lane line information of former frame road image;
Comparison module, is used for: obtain the default lane line information of described vehicle, if the comparative result of described actual lane line information and described default lane line information is unsatisfactory for pre-conditioned, then judges that described vehicle deviates described track;
Warning module, is used for: obtain the operation information of described vehicle, if according to described operation information, it is judged that needs described vehicle is carried out early warning, then sends early warning.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610460415.6A CN105966398B (en) | 2016-06-21 | 2016-06-21 | A kind of method and apparatus that early warning is carried out to automotive run-off-road |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610460415.6A CN105966398B (en) | 2016-06-21 | 2016-06-21 | A kind of method and apparatus that early warning is carried out to automotive run-off-road |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105966398A true CN105966398A (en) | 2016-09-28 |
CN105966398B CN105966398B (en) | 2017-05-31 |
Family
ID=57022523
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610460415.6A Expired - Fee Related CN105966398B (en) | 2016-06-21 | 2016-06-21 | A kind of method and apparatus that early warning is carried out to automotive run-off-road |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105966398B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106504542A (en) * | 2016-09-30 | 2017-03-15 | 北京中星微电子有限公司 | Speed intelligent monitoring method and system |
CN106529493A (en) * | 2016-11-22 | 2017-03-22 | 北京联合大学 | Robust multi-lane line detection method based on perspective drawing |
CN106627575A (en) * | 2016-12-30 | 2017-05-10 | 吉林大学 | Method and system for early warning vehicle yaw |
CN106803061A (en) * | 2016-12-14 | 2017-06-06 | 广州大学 | A kind of simple and fast method for detecting lane lines based on dynamic area-of-interest |
CN107451539A (en) * | 2017-07-13 | 2017-12-08 | 华域汽车系统股份有限公司 | A kind of lane departure warning method and system |
CN107599957A (en) * | 2017-08-30 | 2018-01-19 | 北京新能源汽车股份有限公司 | A kind of turn signal state reminding method, device and automobile |
CN107884795A (en) * | 2016-09-30 | 2018-04-06 | 厦门雅迅网络股份有限公司 | The determination methods and its system in the disengaging region based on GPS |
CN108170135A (en) * | 2016-12-07 | 2018-06-15 | 株式会社万都 | For along the device and method of canonical path driving vehicle |
CN108171154A (en) * | 2017-12-27 | 2018-06-15 | 邦鼓思电子科技(上海)有限公司 | A kind of method that target detection is combined with lane detection in automatic Pilot |
CN109271959A (en) * | 2018-09-30 | 2019-01-25 | 京东方科技集团股份有限公司 | A kind of vehicle shift method for early warning and device |
CN110298216A (en) * | 2018-03-23 | 2019-10-01 | 中国科学院沈阳自动化研究所 | Vehicle deviation warning method based on lane line gradient image adaptive threshold fuzziness |
CN110610153A (en) * | 2019-09-10 | 2019-12-24 | 重庆工程职业技术学院 | Lane recognition method and system for automatic driving |
CN111105594A (en) * | 2018-10-29 | 2020-05-05 | 长城汽车股份有限公司 | Vehicle and recognition method and device for fatigue driving of driver |
CN113487901A (en) * | 2021-07-30 | 2021-10-08 | 重庆长安汽车股份有限公司 | Lane width checking method and system based on camera perception |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103448724A (en) * | 2013-08-23 | 2013-12-18 | 奇瑞汽车股份有限公司 | Lane departure early warning method and device |
CN104085396A (en) * | 2014-07-03 | 2014-10-08 | 上海纵目科技有限公司 | Panoramic lane departure warning method and system |
CN104129389A (en) * | 2014-08-06 | 2014-11-05 | 中电海康集团有限公司 | Method for effectively judging and recognizing vehicle travelling conditions and device thereof |
JP2015197794A (en) * | 2014-04-01 | 2015-11-09 | 本田技研工業株式会社 | Lane detector, lane keeping assist system, and lane detection method |
CN105069859A (en) * | 2015-07-24 | 2015-11-18 | 深圳市佳信捷技术股份有限公司 | Vehicle driving state monitoring method and apparatus thereof |
CN204895461U (en) * | 2015-08-28 | 2015-12-23 | 南京创来科技有限公司 | Skew early warning system in lane |
CN105599765A (en) * | 2015-12-11 | 2016-05-25 | 上海卓易科技股份有限公司 | Lane departure judging and early warning method |
CN105675006A (en) * | 2015-12-30 | 2016-06-15 | 惠州市德赛西威汽车电子股份有限公司 | Road deviation detection method |
-
2016
- 2016-06-21 CN CN201610460415.6A patent/CN105966398B/en not_active Expired - Fee Related
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103448724A (en) * | 2013-08-23 | 2013-12-18 | 奇瑞汽车股份有限公司 | Lane departure early warning method and device |
JP2015197794A (en) * | 2014-04-01 | 2015-11-09 | 本田技研工業株式会社 | Lane detector, lane keeping assist system, and lane detection method |
CN104085396A (en) * | 2014-07-03 | 2014-10-08 | 上海纵目科技有限公司 | Panoramic lane departure warning method and system |
CN104129389A (en) * | 2014-08-06 | 2014-11-05 | 中电海康集团有限公司 | Method for effectively judging and recognizing vehicle travelling conditions and device thereof |
CN105069859A (en) * | 2015-07-24 | 2015-11-18 | 深圳市佳信捷技术股份有限公司 | Vehicle driving state monitoring method and apparatus thereof |
CN204895461U (en) * | 2015-08-28 | 2015-12-23 | 南京创来科技有限公司 | Skew early warning system in lane |
CN105599765A (en) * | 2015-12-11 | 2016-05-25 | 上海卓易科技股份有限公司 | Lane departure judging and early warning method |
CN105675006A (en) * | 2015-12-30 | 2016-06-15 | 惠州市德赛西威汽车电子股份有限公司 | Road deviation detection method |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107884795B (en) * | 2016-09-30 | 2021-06-29 | 厦门雅迅网络股份有限公司 | Method and system for judging entering and exiting areas based on GPS |
CN106504542A (en) * | 2016-09-30 | 2017-03-15 | 北京中星微电子有限公司 | Speed intelligent monitoring method and system |
CN107884795A (en) * | 2016-09-30 | 2018-04-06 | 厦门雅迅网络股份有限公司 | The determination methods and its system in the disengaging region based on GPS |
CN106529493A (en) * | 2016-11-22 | 2017-03-22 | 北京联合大学 | Robust multi-lane line detection method based on perspective drawing |
CN106529493B (en) * | 2016-11-22 | 2019-12-20 | 北京联合大学 | Robust multi-lane line detection method based on perspective view |
CN108170135A (en) * | 2016-12-07 | 2018-06-15 | 株式会社万都 | For along the device and method of canonical path driving vehicle |
CN108170135B (en) * | 2016-12-07 | 2022-02-18 | 万都移动系统股份公司 | Apparatus and method for driving a vehicle along a standard route |
US10809087B2 (en) | 2016-12-07 | 2020-10-20 | Mando Corporation | Apparatus and method for driving vehicle along normal route |
CN106803061A (en) * | 2016-12-14 | 2017-06-06 | 广州大学 | A kind of simple and fast method for detecting lane lines based on dynamic area-of-interest |
CN106627575A (en) * | 2016-12-30 | 2017-05-10 | 吉林大学 | Method and system for early warning vehicle yaw |
CN106627575B (en) * | 2016-12-30 | 2019-04-26 | 吉林大学 | A kind of vehicle yaw method for early warning and system |
CN107451539A (en) * | 2017-07-13 | 2017-12-08 | 华域汽车系统股份有限公司 | A kind of lane departure warning method and system |
CN107451539B (en) * | 2017-07-13 | 2020-11-27 | 华域汽车系统股份有限公司 | Lane departure early warning method and system |
CN107599957A (en) * | 2017-08-30 | 2018-01-19 | 北京新能源汽车股份有限公司 | A kind of turn signal state reminding method, device and automobile |
CN108171154A (en) * | 2017-12-27 | 2018-06-15 | 邦鼓思电子科技(上海)有限公司 | A kind of method that target detection is combined with lane detection in automatic Pilot |
CN110298216A (en) * | 2018-03-23 | 2019-10-01 | 中国科学院沈阳自动化研究所 | Vehicle deviation warning method based on lane line gradient image adaptive threshold fuzziness |
CN110298216B (en) * | 2018-03-23 | 2021-07-23 | 中国科学院沈阳自动化研究所 | Vehicle deviation alarm method based on lane line gradient image self-adaptive threshold segmentation |
US10759448B2 (en) | 2018-09-30 | 2020-09-01 | Boe Technology Group Co., Ltd. | Method and apparatus for early warning of vehicle offset |
CN109271959A (en) * | 2018-09-30 | 2019-01-25 | 京东方科技集团股份有限公司 | A kind of vehicle shift method for early warning and device |
CN111105594A (en) * | 2018-10-29 | 2020-05-05 | 长城汽车股份有限公司 | Vehicle and recognition method and device for fatigue driving of driver |
CN110610153A (en) * | 2019-09-10 | 2019-12-24 | 重庆工程职业技术学院 | Lane recognition method and system for automatic driving |
CN113487901A (en) * | 2021-07-30 | 2021-10-08 | 重庆长安汽车股份有限公司 | Lane width checking method and system based on camera perception |
Also Published As
Publication number | Publication date |
---|---|
CN105966398B (en) | 2017-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105966398A (en) | Method and device for early warning lane departure of vehicle | |
CN106611512B (en) | Method, device and system for processing starting of front vehicle | |
JP7081438B2 (en) | Object speed estimation method and equipment and image processing equipment | |
JP6254083B2 (en) | In-vehicle ambient environment recognition device | |
JP5966965B2 (en) | Lane boundary departure control device and lane boundary departure suppression method | |
US8406472B2 (en) | Method and system for processing image data | |
JP2019517089A (en) | Image processing method for recognizing ground markings, and system for detecting ground markings | |
US11023744B2 (en) | Road parameter calculator | |
US11288833B2 (en) | Distance estimation apparatus and operating method thereof | |
CN107804226A (en) | Trailer lane departur warning and wave alarm | |
CN107924569B (en) | Image processing apparatus, image processing method, and storage medium | |
US20150269445A1 (en) | Travel division line recognition apparatus and travel division line recognition program | |
CN110555362B (en) | Object recognition device | |
CN107209998B (en) | Lane line recognition device and lane line recognition method | |
CN109829365B (en) | Multi-scene adaptive driving deviation and turning early warning method based on machine vision | |
US20200285913A1 (en) | Method for training and using a neural network to detect ego part position | |
JP6105524B2 (en) | Traveling lane marking recognition device and traveling lane marking recognition program | |
WO2019224103A1 (en) | Lane detection based on lane models | |
JP2018060422A (en) | Object detection device | |
JP2006140636A (en) | Obstacle detecting device and method | |
CN113361299B (en) | Abnormal parking detection method and device, storage medium and electronic equipment | |
JP5559650B2 (en) | Lane estimation device | |
Ben Romdhane et al. | A lane detection and tracking method for driver assistance system | |
KR101595317B1 (en) | Precise positioning of the vehicle for detecting a road surface display method and system | |
JP6200780B2 (en) | Lane recognition determination device |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170531 |