CN101804814A - Method, device and system for determining lane departure - Google Patents
Method, device and system for determining lane departure Download PDFInfo
- Publication number
- CN101804814A CN101804814A CN201010033839A CN201010033839A CN101804814A CN 101804814 A CN101804814 A CN 101804814A CN 201010033839 A CN201010033839 A CN 201010033839A CN 201010033839 A CN201010033839 A CN 201010033839A CN 101804814 A CN101804814 A CN 101804814A
- Authority
- CN
- China
- Prior art keywords
- lane boundary
- straight line
- gradient direction
- gradient
- pixel
- 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 26
- 238000001514 detection method Methods 0.000 claims description 17
- 238000005315 distribution function Methods 0.000 claims description 16
- 238000003708 edge detection Methods 0.000 abstract 1
- 238000003672 processing method Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 239000004744 fabric Substances 0.000 description 4
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
- G01C21/3602—Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method, a device and a system for determining lane departure, which relates to the technical field of intelligent vehicles, can accurately judge whether lane departure occurs under the conditions of no a plurality of types of sensors and no need of camera calibration results, and saves the system cost. The method provided by the embodiment of the invention is as follows that: edge detection is carried out to a lane image, to obtain the gradient size and the gradient direction of all pixels in the lane image; the gradient direction of the lane boundary is determined according to the gradient size and the gradient direction of all the pixels; the lane boundary is fitted by a straight line with the gradient size and the gradient direction of all the pixels as well as the gradient direction of the lane boundary to obtain the lane boundary straight line; and whether the lane departure occurs is determined according to the inclination angle of the lane boundary straight line. The invention is applicable to occasions on which lane departure needs to be determined.
Description
Technical field
The present invention relates to the intelligent vehicle art, relate in particular to a kind of deviation decision-making technique, device and system.
Background technology
In road traffic accident, it is owing to the not inadvertently traffic accident that causes of steering wheel rotation generation deviation of chaufeur that quite a few accident is arranged.Therefore develop lane-departure warning system to the generation that reduces this type of accident, save the people life and property damage significant.
Prior art provides a kind of lane-departure warning system.In this system, utilize imageing sensor to come the geometrical structure parameter in perception vehicle front track, utilize speed sensor and angular transducer to come the speed and the steering wheel angle of perception vehicle.Utilize subsequently respective algorithms with the geometrical structure parameter in track and vehicle-state parameter estimate the deviation time (Time to Lane Crossing, TLC).As TLC during less than pre-set threshold, system gives a warning to chaufeur, to avoid taking place deviation.
In realizing process of the present invention, the contriver finds that there are the following problems at least in the prior art:
The lane-departure warning system of prior art except the needs pick up camera, also needs additionally to be provided with multiple sensors when determining whether deviation takes place, as speed sensor, angular transducer etc., cause cost too high; And owing to need estimate, must obtain camera calibration result accurately, and in the camera calibration operation of reality, often have error, thereby can't accurately judge departing from of track the geometrical structure parameter in track.
Summary of the invention
For solving problems of the prior art, embodiments of the invention provide a kind of methods, devices and systems of definite deviation.
For achieving the above object, embodiments of the invention adopt following technical scheme:
The embodiment of the invention provides a kind of method of definite deviation, and described method comprises:
Carriageway image is carried out rim detection, obtain the gradient magnitude and the gradient direction of each pixel in the carriageway image;
The gradient direction of determining lane boundary according to the gradient magnitude and the gradient direction of described each pixel;
Utilize the gradient direction described lane boundary of fitting of a straight line of gradient magnitude, gradient direction and the described lane boundary of described each pixel, obtain the lane boundary straight line;
Leaning angle according to described lane boundary straight line determines whether to take place deviation.
The embodiment of the invention also provides a kind of device of definite deviation, and described device comprises:
Detecting unit is used for carriageway image is carried out rim detection, obtains the gradient magnitude and the gradient direction of each pixel in the carriageway image;
Track direction determining unit is used for the gradient direction of determining lane boundary according to the gradient magnitude and the gradient direction of described each pixel;
Lane boundary match unit, the gradient direction of gradient magnitude, gradient direction and described lane boundary that is used to utilize described each pixel obtains the lane boundary straight line with fitting of a straight line described lane boundary;
Depart from determining unit, be used for determining whether to take place deviation according to the leaning angle of described lane boundary straight line.
The embodiment of the invention also provides a kind of lane-departure warning system, and described system comprises camera head, determines the device and the warning device of deviation,
Described camera head is used to take carriageway image, and described carriageway image is sent to the device of described definite deviation;
The device of described definite deviation is used for described carriageway image is carried out rim detection, obtains the gradient magnitude and the gradient direction of each pixel in the carriageway image; The gradient direction of determining lane boundary according to the gradient magnitude and the gradient direction of described each pixel; Utilize the gradient direction described lane boundary of fitting of a straight line of gradient magnitude, gradient direction and the described lane boundary of described each pixel, obtain the lane boundary straight line; Whether the leaning angle decision-making according to described lane boundary straight line deviation takes place, and notifies described warning device with the result of decision,
Described warning device is used for making warning when the described result of decision is the generation deviation.
The technical scheme of the embodiment of the invention, detection obtains the gradient magnitude and the gradient direction of each pixel in the carriageway image, thereby determine the gradient direction of lane boundary, and use the fitting of a straight line lane boundary, determine whether to take place deviation according to the lane boundary straight line that obtains.The technical scheme of the embodiment of the invention, based on a kind of processing method of machine vision, can be under the situation of only utilizing graphicinformation, accurately determine whether to take place deviation, and do not need additionally to be provided with multiple sensors, do not need the Camera calibration result yet, saved the cost of system.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art, to do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art below, apparently, accompanying drawing in describing below only is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain other accompanying drawing according to these accompanying drawings.
The method flow diagram of definite deviation that Fig. 1 provides for the embodiment of the invention one;
The principle schematic of definite deviation that Fig. 2 provides for the embodiment of the invention two;
The apparatus structure scheme drawing of definite deviation that Fig. 3 provides for the embodiment of the invention three;
The lane-departure warning system scheme drawing that Fig. 4 provides for the embodiment of the invention four;
Fig. 5 is the top perspective of the camera head in the lane-departure warning system of the embodiment of the invention four;
Fig. 6 is the lateral plan of the camera head in the lane-departure warning system of the embodiment of the invention four.
The specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills belong to the scope of protection of the invention not making the every other embodiment that is obtained under the creative work prerequisite.
The embodiment of the invention one provides a kind of method of definite deviation, and as shown in Figure 1, described method comprises:
Step S1: carriageway image is carried out rim detection, obtain the gradient magnitude and the gradient direction of each pixel in the carriageway image;
Step S2: the gradient direction of determining lane boundary according to the gradient magnitude and the gradient direction of described each pixel;
Step S3: utilize the gradient direction described lane boundary of fitting of a straight line of gradient magnitude, gradient direction and the described lane boundary of described each pixel, obtain the lane boundary straight line;
Step S4: the leaning angle according to described lane boundary straight line determines whether to take place deviation.
Further, after step S4, also comprise: step S5: when determining deviation takes place, make warning.If in step S4, determine deviation does not take place, then continue step S1 to S4; After in step S5, making warning, also continue step S1 to S4, continue to monitor and determine whether to occur deviation, when deviation takes place, make warning, thereby guarantee the normal driving of vehicle to chaufeur.
The technical scheme of the embodiment of the invention, detection obtains the gradient magnitude and the gradient direction of each pixel in the carriageway image, thereby determine the gradient direction of lane boundary, and use the fitting of a straight line lane boundary, determine whether to take place deviation according to the lane boundary straight line that obtains.The technical scheme of the embodiment of the invention, based on a kind of processing method of machine vision, can be under the situation of only utilizing graphicinformation, accurately determine whether to take place deviation, and do not need additionally to be provided with multiple sensors, do not need the Camera calibration result yet, saved the cost of system.
The method of definite deviation that the embodiment of the invention two is provided is elaborated below.Mainly comprise the steps:
Step 1: carriageway image is carried out rim detection, obtain the gradient magnitude and the gradient direction of each pixel in the carriageway image.
At first, utilize pick up camera to take and obtain carriageway image, after pick up camera can be positioned at vehicle windscreen, camera optical axis was downward-sloping, and the yaw angle of pick up camera and roll angle are 0.Carry out gradient calculation by the carriageway image that shooting is obtained,, obtain the gradient magnitude and the gradient direction of each pixel in the carriageway image so that this carriageway image is carried out rim detection.
Adopt the Sobel operator carriageway image to be carried out image gradient in the embodiment of the invention and calculate a width of cloth gradient magnitude image and a width of cloth gradient direction image wherein as the convolution template, a kind of Sobel operator of 3 * 3 of computed image gradient can have following form:
s
xAnd s
yIt is respectively the convolution template of calculating x and y direction gradient size.To arbitrary pixel I (x, y), when the gradient magnitude of x direction that calculates and y direction is respectively G
xAnd G
yThe time, then the gradient magnitude of this pixel is
Gradient direction be θ (x, y)=arctan (G
y/ G
x).When the compute gradient direction,, can set in advance a look-up table and be used to store the corresponding relation of numerical value and angle, thereby directly obtain gradient direction by this look-up table for fear of the calculating of trigonometric function.
By aforementioned calculation, the gradient magnitude of all pixels is formed a width of cloth gradient magnitude image in the carriageway image, and the gradient direction of all pixels is formed a width of cloth gradient direction image.
Step 2: the gradient direction of determining lane boundary according to the gradient magnitude and the gradient direction of described each pixel.
At first, edge calculation distribution function.In order to determine the orientation of lane boundary, definition and edge calculation distribution function, as with as described in gradient direction be independent variable, as described in gradient magnitude be functional value structure marginal distribution function.This marginal distribution function can be expressed as the histogram of gradient magnitude with respect to gradient direction.The embodiment of the invention is when setting up this marginal distribution function, and the sampling interval of edge direction is 2 °, and sample range is [90,90 °].
Exemplary, with the independent variable of gradient direction as marginal distribution function, this argument list is shown θ, and then the functional value of marginal distribution function satisfies down for gradient direction θ | θ-θ (x, y) | the gradient magnitude of all pixels of<1 and.
Lane boundary comprises track left margin and track right margin.Because lane boundary is a linearity target main in the carriageway image, so the border, the left and right sides in track will cause the functional value of marginal distribution function to produce two local maximum functional values.If these two pairing angles of local maximum functional value are respectively α
LAnd α
R, these two gradient directions that angle is respectively border, the left and right sides, track then, α
LBe the gradient direction of track left margin, α
RGradient direction for the track right margin.Be about to the gradient direction of the pairing gradient direction of local maximum functional value of marginal distribution function as described lane boundary straight line.
Utilize above-mentioned gradient direction α
LAnd α
R, determined the roughly direction of border, the left and right sides, track in carriageway image.
Step 3:, obtain the left and right sides, track boundary straight line with border, the left and right sides, fitting of a straight line track;
Utilize the gradient direction described lane boundary of fitting of a straight line of gradient magnitude, gradient direction and the above-mentioned lane boundary of above-mentioned each pixel, obtain the lane boundary straight line, specifically comprise: utilize the gradient direction of gradient magnitude, gradient direction and the lane boundary of each pixel in the carriageway image to remove interference pixel in the carriageway image, obtain lane boundary image g (x, y); Utilize the pixel in the lane boundary image, adopt least-square fitting approach fitting of a straight line lane boundary, obtain the lane boundary straight line.
Further, utilize following formula to obtain left-lane boundary image g respectively
L(x is y) with right lane boundary image g
R(x, y), to be used for utilizing border, the left and right sides, fitting of a straight line carriageway image track.
Wherein, threshold value T=2 °, α represents α
LPerhaps α
R, g (x, y) expression lane boundary image.Utilize α according to above-mentioned formula (1)
LCalculate g
L(x y), utilizes α
RCalculate g
R(x, y).
Utilize the gradient direction α on border, the left and right sides, track by above-mentioned formula (1)
LAnd α
RRemove the noise spot in the carriageway image, utilized the new images g that obtains
L(x, y) and g
R(x, y) point in is used border, the left and right sides, fitting of a straight line track.
Because it is identical to calculate the process of the left and right sides, track boundary straight line, be that example describes to calculate track left margin straight line below.The embodiment of the invention with least-square fitting approach to image g
L(x, y) non-zero points in is carried out match, and then left margin straight line in track can be expressed as equation:
y=xtanβ
L+b
L
By image g
L(x, y) non-zero points in is carried out match, and then obtains the angle of inclination beta of track left margin straight line
LWith constant b
L
To track right margin straight line, adopt and use the same method, based on image g
R(x, y) non-zero points in obtains the equation of track right margin straight line as follows with least square fitting:
y=xtanβ
R+b
R
Wherein, β
RBe the leaning angle of track right margin straight line, b
RBe constant.
As shown in Figure 2, β
LAnd β
RBe respectively the angle of the left and right sides, track boundary straight line and x direction, after determining positive dirction, β
LAnd β
ROpposite in sign.
Step 4: deviation decision-making
Leaning angle according to described lane boundary straight line determines whether to take place deviation.When pick up camera is installed in front part of vehicle and is tilted to down, when roll angle was zero, border, the left and right sides, track should be symmetrical in image when vehicle travelled at the center, track, promptly had β
L+ β
R=0.For example, when anticlockwise direction is positive dirction, β
LFor on the occasion of, β
RBe negative value, then vehicle when the track left departs from, β
LAnd β
RAll increase, vehicle departs from β to the track is right-hand
LAnd β
RAll reduce.Under the both of these case that deviation takes place, | β
L+ β
R| value all depart from from zero.Make Δ β=| β
L+ β
R|, this moment, the decision-making technique of definite deviation of the present invention can be expressed as:
As Δ β>T
LThe time, determining deviation takes place, system gives a warning to chaufeur; Wherein, in embodiments of the present invention, T
L=15 °.
In order to reduce The noise, calculate the pairing β of some frame carriageway images
LAnd β
R, as the pairing β of continuous 4 frame carriageway images before the calculating current time
LAnd β
R, to a plurality of β that obtain
LWith a plurality of β
RThe difference averaged is with this β
LAviation value and β
RAviation value as the β of current time
LAnd β
R, and according to the β in this current moment
LAnd β
RJudge whether deviation takes place.
Owing to be installed in front part of vehicle and be tilted to down at pick up camera, when yaw angle and roll angle are zero, during the vehicle normal driving in the carriageway image about the direction of two lane boundary should be symmetrical.The present invention utilizes marginal distribution function to obtain the general direction of both bounded sides, track in carriageway image, utilizes the noise spot in this direction value removal edge image subsequently and obtains new image.Utilize the point in this new image of straight line difference match, obtain the equation of straight line on border, the left and right sides, track.Relation according to this straight line leaning angle determines whether to take place deviation.
The embodiment of the invention has overcome the shortcoming that traditional lane departur warning algorithm needs more sensor output, and the embodiment of the invention does not need pick up camera is demarcated.
From the above mentioned, the technical scheme of the embodiment of the invention detects the gradient magnitude and the gradient direction that obtain each pixel in the carriageway image, thereby determines the gradient direction of lane boundary, and use the fitting of a straight line lane boundary, determine whether to take place deviation according to the lane boundary straight line that obtains.The technical scheme of the embodiment of the invention, based on a kind of processing method of machine vision, can be under the situation of only utilizing graphicinformation, accurately determine whether to take place deviation, and do not need additionally to be provided with multiple sensors, do not need the Camera calibration result yet, saved the cost of system.
The embodiment of the invention three also provides a kind of device of definite deviation, and as shown in Figure 3, described device comprises:
Detecting unit 31 is used for carriageway image is carried out rim detection, obtains the gradient magnitude and the gradient direction of each pixel in the carriageway image;
Track direction determining unit 32 is used for the gradient direction of determining lane boundary according to the gradient magnitude and the gradient direction of described each pixel;
Lane boundary match unit 33, the gradient direction of gradient magnitude, gradient direction and described lane boundary that is used to utilize described each pixel obtains the lane boundary straight line with fitting of a straight line described lane boundary;
Depart from determining unit 34, be used for determining whether to take place deviation according to the leaning angle of described lane boundary straight line.
Further, described detecting unit 31 specifically is used to utilize the Sobel operator that described carriageway image is carried out rim detection, obtains the gradient magnitude and the gradient direction of each pixel in the carriageway image.
Further, described track direction determining unit 32, specifically being used for described gradient direction is that independent variable, described gradient magnitude are functional value structure marginal distribution function;
With the pairing gradient direction of local maximum functional value of marginal distribution function gradient direction as described lane boundary straight line.
Further, described lane boundary match unit 33 specifically is used for utilizing the gradient direction of gradient magnitude, gradient direction and the described lane boundary of described each pixel to remove the interference pixel of described carriageway image, obtains the lane boundary image; According to the pixel in the described lane boundary image, adopt least-square fitting approach with the described lane boundary of fitting of a straight line, obtain the lane boundary straight line.
Wherein, above-mentioned lane boundary match unit 33 specifically is used for utilizing the gradient direction of gradient magnitude, gradient direction and the described lane boundary of described each pixel to remove the interference pixel of described carriageway image according to following formula, obtains the lane boundary image:
Wherein, threshold value T=2 °, α represents α
LPerhaps α
R, g (x, y) expression lane boundary image; And, according to the non-zero pixels point in the described lane boundary image, adopt the least-square fitting approach described lane boundary of fitting of a straight line, obtain lane boundary straight line as follows:
Y=xtan β+b, wherein, β is the leaning angle of lane boundary straight line, b is a constant.
The above-mentioned determining unit 34 that departs from, when specifically being used for absolute value when the leaning angle sum of the leaning angle of track left margin straight line and track right margin straight line greater than warning threshold, determine to take place deviation, otherwise, judge deviation does not take place, wherein, described lane boundary straight line comprises track left margin straight line and track right margin straight line.
The concrete mode of operation of each functional module and unit is referring to the inventive method embodiment among apparatus of the present invention embodiment.Each functional module and unit can be realized separately among apparatus of the present invention embodiment, also can be integrated in one or more unit and realize.For example, the device of above-mentioned definite deviation can be realized by microprocessor.
From the above mentioned, the technical scheme of the embodiment of the invention detects the gradient magnitude and the gradient direction that obtain each pixel in the carriageway image, thereby determines the gradient direction of lane boundary, and use the fitting of a straight line lane boundary, determine whether to take place deviation according to the lane boundary straight line that obtains.The technical scheme of the embodiment of the invention, based on a kind of processing method of machine vision, can be under the situation of only utilizing graphicinformation, accurately determine whether to take place deviation, and do not need additionally to be provided with multiple sensors, do not need the Camera calibration result yet, saved the cost of system.
The embodiment of the invention four provides a kind of lane-departure warning system, and as shown in Figure 4, described system comprises camera head, determines the device and the warning device of deviation,
Described camera head is used to take carriageway image, and described carriageway image is sent to the device of described definite deviation;
The device of described definite deviation is used for described carriageway image is carried out rim detection, obtains the gradient magnitude and the gradient direction of each pixel in the carriageway image; The gradient direction of determining lane boundary according to the gradient magnitude and the gradient direction of described each pixel; Utilize the gradient direction described lane boundary of fitting of a straight line of gradient magnitude, gradient direction and the described lane boundary of described each pixel, obtain the lane boundary straight line; Whether the leaning angle decision-making according to described lane boundary straight line deviation takes place, and notifies described warning device with the result of decision,
Described warning device is used for making warning when the described result of decision is the generation deviation.
During for assurance vehicle normal driving, the direction on border, the left and right sides, track is symmetrical in the carriageway image, and can photograph desirable carriageway image, referring to Fig. 5, above-mentioned camera head (as pick up camera) is arranged on front part of vehicle and is tilted to down, as be obliquely installed on the axial direction of front part of vehicle.Referring to Fig. 6, pick up camera is arranged at the Windshield of vehicle after, the optical axis direction of pick up camera has a down dip and horizontal direction has inclination angle phi.The yaw angle of pick up camera and roll angle are 0.
The concrete mode of operation of the device of above-mentioned definite deviation is referring to the inventive method embodiment, when the device of determining deviation makes a policy the result when deviation takes place, above-mentioned warning device is made warning, for example, this warning device sends prompting sound, as buzzer, music, or vibrates, also can be simultaneously with the captions demonstration etc., thereby remind lane for driver to be offset.
From the above mentioned, the technical scheme of the embodiment of the invention detects the gradient magnitude and the gradient direction that obtain each pixel in the carriageway image, thereby determines the gradient direction of lane boundary, and use the fitting of a straight line lane boundary, determine whether to take place deviation according to the lane boundary straight line that obtains.The technical scheme of the embodiment of the invention, based on a kind of processing method of machine vision, can be under the situation of only utilizing graphicinformation, accurately determine whether to take place deviation, and do not need additionally to be provided with multiple sensors, do not need the Camera calibration result yet, saved the cost of system.
Those skilled in the art can be well understood to the present invention and can realize by the mode that software adds essential general hardware platform.Based on such understanding, the part that technical scheme of the present invention contributes to prior art in essence in other words can software product form embody, this computer software product can be stored in the storage medium, as ROM/RAM, magnetic disc, CD etc., comprise that some instructions are with so that a computer equipment (can be a Personal Computer, server, the perhaps network equipment etc.) carry out the described method of some part of each embodiment of the present invention or embodiment.
The above; only be the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, anyly is familiar with those skilled in the art in the technical scope that the present invention discloses; can expect easily changing or replacing, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claim.
Claims (12)
1. the method for a definite deviation is characterized in that, described method comprises:
Carriageway image is carried out rim detection, obtain the gradient magnitude and the gradient direction of each pixel in the carriageway image;
The gradient direction of determining lane boundary according to the gradient magnitude and the gradient direction of described each pixel;
Utilize the gradient direction described lane boundary of fitting of a straight line of gradient magnitude, gradient direction and the described lane boundary of described each pixel, obtain the lane boundary straight line;
Leaning angle according to described lane boundary straight line determines whether to take place deviation.
2. method according to claim 1 is characterized in that, described carriageway image is carried out rim detection, and the gradient magnitude and the gradient direction that obtain each pixel in the carriageway image comprise:
Utilize the Sobel operator that described carriageway image is carried out rim detection, obtain the gradient magnitude and the gradient direction of each pixel in the carriageway image.
3. method according to claim 1 is characterized in that, the described gradient direction of determining lane boundary according to the gradient magnitude and the gradient direction of described each pixel comprises:
With described gradient direction is that independent variable, described gradient magnitude are functional value structure marginal distribution function;
With the pairing gradient direction of local maximum functional value of marginal distribution function gradient direction as described lane boundary.
4. method according to claim 1 is characterized in that, the described gradient direction described lane boundary of fitting of a straight line of utilizing gradient magnitude, gradient direction and the described lane boundary of described each pixel obtains the lane boundary straight line and comprises:
Utilize the gradient direction of gradient magnitude, gradient direction and the described lane boundary of each pixel in the described carriageway image to remove interference pixel in the described carriageway image, obtain the lane boundary image;
According to the pixel in the described lane boundary image, adopt least-square fitting approach with the described lane boundary of fitting of a straight line, obtain the lane boundary straight line.
5. method according to claim 4 is characterized in that,
According to following formula, utilize the gradient direction of gradient magnitude, gradient direction and the described lane boundary of described each pixel to remove interference pixel in the described carriageway image, obtain the lane boundary image:
Wherein, g (x y) is the lane boundary image,
For pixel I (x, gradient magnitude y), θ (x, y) be pixel I (x, gradient direction y), T are threshold value;
According to the non-zero pixels point in the described lane boundary image, adopt the least-square fitting approach described lane boundary of fitting of a straight line, obtain lane boundary straight line as follows:
Y=xtan β+b, wherein, β is the leaning angle of lane boundary straight line, b is a constant.
6. method according to claim 1 is characterized in that, described leaning angle according to described lane boundary straight line determines whether to take place deviation and specifically comprises:
Described lane boundary straight line comprises track left margin straight line and track right margin straight line, when the absolute value of the leaning angle sum of the leaning angle of described track left margin straight line and track right margin straight line decidable generation deviation during greater than warning threshold, otherwise, judge deviation do not take place.
7. the device of a definite deviation is characterized in that, described device comprises:
Detecting unit is used for carriageway image is carried out rim detection, obtains the gradient magnitude and the gradient direction of each pixel in the carriageway image;
Track direction determining unit is used for the gradient direction of determining lane boundary according to the gradient magnitude and the gradient direction of described each pixel;
Lane boundary match unit, the gradient direction of gradient magnitude, gradient direction and described lane boundary that is used to utilize described each pixel obtains the lane boundary straight line with fitting of a straight line described lane boundary;
Depart from determining unit, be used for determining whether to take place deviation according to the leaning angle of described lane boundary straight line.
8. device according to claim 7 is characterized in that, described detecting unit specifically is used to utilize the Sobel operator that described carriageway image is carried out rim detection, obtains the gradient magnitude and the gradient direction of each pixel in the carriageway image.
9. device according to claim 7 is characterized in that, described track direction determining unit, and specifically being used for described gradient direction is that independent variable, described gradient magnitude are functional value structure marginal distribution function; With the pairing gradient direction of local maximum functional value of marginal distribution function gradient direction as described lane boundary.
10. device according to claim 7, it is characterized in that, described lane boundary match unit specifically is used for utilizing the gradient direction of gradient magnitude, gradient direction and the described lane boundary of described each pixel to remove the interference pixel of described carriageway image, obtains the lane boundary image; According to the pixel in the described lane boundary image, adopt least-square fitting approach with the described lane boundary of fitting of a straight line, obtain the lane boundary straight line.
11. device according to claim 7, it is characterized in that, the described determining unit that departs from, when specifically being used for absolute value when the leaning angle sum of the leaning angle of track left margin straight line and track right margin straight line greater than warning threshold, determine to take place deviation, otherwise, judge deviation does not take place, wherein, described lane boundary straight line comprises track left margin straight line and track right margin straight line.
12. a lane-departure warning system is characterized in that, described system comprises camera head, determines the device and the warning device of deviation,
Described camera head is used to take carriageway image, and described carriageway image is sent to the device of described definite deviation;
The device of described definite deviation is used for described carriageway image is carried out rim detection, obtains the gradient magnitude and the gradient direction of each pixel in the carriageway image; The gradient direction of determining lane boundary according to the gradient magnitude and the gradient direction of described each pixel; Utilize the gradient direction described lane boundary of fitting of a straight line of gradient magnitude, gradient direction and the described lane boundary of described each pixel, obtain the lane boundary straight line; Whether the leaning angle decision-making according to described lane boundary straight line deviation takes place, and notifies described warning device with the result of decision,
Described warning device is used for making warning when the described result of decision is the generation deviation.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010100338397A CN101804814B (en) | 2010-01-08 | 2010-01-08 | Method, device and system for determining lane departure |
PCT/CN2010/079770 WO2011082620A1 (en) | 2010-01-08 | 2010-12-14 | Method, device and system for determining lane departure |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2010100338397A CN101804814B (en) | 2010-01-08 | 2010-01-08 | Method, device and system for determining lane departure |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101804814A true CN101804814A (en) | 2010-08-18 |
CN101804814B CN101804814B (en) | 2012-10-31 |
Family
ID=42606813
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2010100338397A Active CN101804814B (en) | 2010-01-08 | 2010-01-08 | Method, device and system for determining lane departure |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN101804814B (en) |
WO (1) | WO2011082620A1 (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011082620A1 (en) * | 2010-01-08 | 2011-07-14 | 北京世纪高通科技有限公司 | Method, device and system for determining lane departure |
CN102156972A (en) * | 2011-04-19 | 2011-08-17 | 清华大学 | Image tilting correcting method and system |
CN102336163A (en) * | 2011-08-31 | 2012-02-01 | 同济大学 | Vehicle yaw detection device |
CN102649408A (en) * | 2011-02-23 | 2012-08-29 | 歌乐株式会社 | Lane departure warning apparatus and system |
CN102663356A (en) * | 2012-03-28 | 2012-09-12 | 柳州博实唯汽车科技有限公司 | Method for extraction and deviation warning of lane line |
CN103593649A (en) * | 2013-10-24 | 2014-02-19 | 惠州华阳通用电子有限公司 | Lane line detection method for lane departure early warning |
US8902053B2 (en) | 2011-11-16 | 2014-12-02 | Industrial Technology Research Institute | Method and system for lane departure warning |
CN104648397A (en) * | 2013-11-19 | 2015-05-27 | 沙漠科技股份有限公司 | System and method for warning lane departure |
CN105136121A (en) * | 2015-09-15 | 2015-12-09 | 歌尔声学股份有限公司 | Image detection method and system for determining tool state |
CN105447892A (en) * | 2015-11-05 | 2016-03-30 | 奇瑞汽车股份有限公司 | Method and device for determining yaw angle of vehicle |
CN105810015A (en) * | 2016-03-18 | 2016-07-27 | 上海欧菲智能车联科技有限公司 | Lane departure early warning method and system and vehicle |
CN108263387A (en) * | 2016-12-30 | 2018-07-10 | 意法半导体股份有限公司 | For generating the method for lane departure warning, related system in the car |
CN108422998A (en) * | 2018-03-14 | 2018-08-21 | 合肥工业大学 | A kind of deviation supplementary controlled system and method |
CN108490931A (en) * | 2018-03-07 | 2018-09-04 | 曲阜师范大学 | Intelligent vehicle drive-control system based on improved sobel method and method |
CN109910739A (en) * | 2018-12-21 | 2019-06-21 | 嘉兴智驾科技有限公司 | A method of judging that intelligent driving is alarmed by voice recognition |
CN110654382A (en) * | 2018-06-28 | 2020-01-07 | 比亚迪股份有限公司 | Calibration method and calibration system of lane yaw early warning system and vehicle |
CN111220197A (en) * | 2016-09-12 | 2020-06-02 | 上海沃尔沃汽车研发有限公司 | Test system and test method for lane line deviation alarm system |
CN112078578A (en) * | 2020-08-11 | 2020-12-15 | 江苏大学 | Self-parking position planning method facing to perception uncertainty in lane keeping system |
CN114067001A (en) * | 2022-01-14 | 2022-02-18 | 天津所托瑞安汽车科技有限公司 | Vehicle-mounted camera angle calibration method, terminal and storage medium |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102629326A (en) * | 2012-03-19 | 2012-08-08 | 天津工业大学 | Lane line detection method based on monocular vision |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1804928A (en) * | 2005-11-24 | 2006-07-19 | 上海交通大学 | Machine vision based estimation method for local geometry of driveway and vehicle location |
JP4797846B2 (en) * | 2006-07-12 | 2011-10-19 | トヨタ自動車株式会社 | Lane marking device and lane detection device |
CN1945207A (en) * | 2006-09-15 | 2007-04-11 | 江苏大学 | Auxiliary method and device for keeping lane for driver |
CN101470801B (en) * | 2007-12-24 | 2011-06-01 | 财团法人车辆研究测试中心 | Vehicle shift inspection method |
CN101620732A (en) * | 2009-07-17 | 2010-01-06 | 南京航空航天大学 | Visual detection method of road driving line |
CN101804814B (en) * | 2010-01-08 | 2012-10-31 | 北京世纪高通科技有限公司 | Method, device and system for determining lane departure |
-
2010
- 2010-01-08 CN CN2010100338397A patent/CN101804814B/en active Active
- 2010-12-14 WO PCT/CN2010/079770 patent/WO2011082620A1/en active Application Filing
Cited By (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2011082620A1 (en) * | 2010-01-08 | 2011-07-14 | 北京世纪高通科技有限公司 | Method, device and system for determining lane departure |
CN102649408A (en) * | 2011-02-23 | 2012-08-29 | 歌乐株式会社 | Lane departure warning apparatus and system |
CN102649408B (en) * | 2011-02-23 | 2015-05-20 | 歌乐株式会社 | Lane departure warning apparatus and system |
CN102156972A (en) * | 2011-04-19 | 2011-08-17 | 清华大学 | Image tilting correcting method and system |
CN102336163A (en) * | 2011-08-31 | 2012-02-01 | 同济大学 | Vehicle yaw detection device |
CN102336163B (en) * | 2011-08-31 | 2014-06-25 | 同济大学 | Vehicle yaw detection device |
US8902053B2 (en) | 2011-11-16 | 2014-12-02 | Industrial Technology Research Institute | Method and system for lane departure warning |
CN102663356A (en) * | 2012-03-28 | 2012-09-12 | 柳州博实唯汽车科技有限公司 | Method for extraction and deviation warning of lane line |
CN102663356B (en) * | 2012-03-28 | 2015-04-08 | 柳州博实唯汽车科技有限公司 | Method for extraction and deviation warning of lane line |
CN103593649A (en) * | 2013-10-24 | 2014-02-19 | 惠州华阳通用电子有限公司 | Lane line detection method for lane departure early warning |
CN103593649B (en) * | 2013-10-24 | 2017-12-08 | 惠州华阳通用电子有限公司 | A kind of method for detecting lane lines for lane departure warning |
CN104648397B (en) * | 2013-11-19 | 2017-05-17 | 沙漠科技股份有限公司 | System and method for warning lane departure |
CN104648397A (en) * | 2013-11-19 | 2015-05-27 | 沙漠科技股份有限公司 | System and method for warning lane departure |
CN105136121A (en) * | 2015-09-15 | 2015-12-09 | 歌尔声学股份有限公司 | Image detection method and system for determining tool state |
CN105447892B (en) * | 2015-11-05 | 2018-04-17 | 奇瑞汽车股份有限公司 | The definite method and device at vehicle yaw angle |
CN105447892A (en) * | 2015-11-05 | 2016-03-30 | 奇瑞汽车股份有限公司 | Method and device for determining yaw angle of vehicle |
CN105810015A (en) * | 2016-03-18 | 2016-07-27 | 上海欧菲智能车联科技有限公司 | Lane departure early warning method and system and vehicle |
CN105810015B (en) * | 2016-03-18 | 2018-07-17 | 上海欧菲智能车联科技有限公司 | Lane departure warning method and system and vehicle |
CN111220197A (en) * | 2016-09-12 | 2020-06-02 | 上海沃尔沃汽车研发有限公司 | Test system and test method for lane line deviation alarm system |
CN111220197B (en) * | 2016-09-12 | 2022-02-22 | 上海沃尔沃汽车研发有限公司 | Test system and test method for lane line deviation alarm system |
CN108263387A (en) * | 2016-12-30 | 2018-07-10 | 意法半导体股份有限公司 | For generating the method for lane departure warning, related system in the car |
CN108263387B (en) * | 2016-12-30 | 2021-09-24 | 意法半导体股份有限公司 | Method for generating lane departure warning in a vehicle, related system |
CN108490931A (en) * | 2018-03-07 | 2018-09-04 | 曲阜师范大学 | Intelligent vehicle drive-control system based on improved sobel method and method |
CN108422998A (en) * | 2018-03-14 | 2018-08-21 | 合肥工业大学 | A kind of deviation supplementary controlled system and method |
CN110654382A (en) * | 2018-06-28 | 2020-01-07 | 比亚迪股份有限公司 | Calibration method and calibration system of lane yaw early warning system and vehicle |
CN109910739A (en) * | 2018-12-21 | 2019-06-21 | 嘉兴智驾科技有限公司 | A method of judging that intelligent driving is alarmed by voice recognition |
CN112078578A (en) * | 2020-08-11 | 2020-12-15 | 江苏大学 | Self-parking position planning method facing to perception uncertainty in lane keeping system |
CN114067001A (en) * | 2022-01-14 | 2022-02-18 | 天津所托瑞安汽车科技有限公司 | Vehicle-mounted camera angle calibration method, terminal and storage medium |
CN114067001B (en) * | 2022-01-14 | 2022-04-26 | 天津所托瑞安汽车科技有限公司 | Vehicle-mounted camera angle calibration method, terminal and storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2011082620A1 (en) | 2011-07-14 |
CN101804814B (en) | 2012-10-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101804814B (en) | Method, device and system for determining lane departure | |
US7509211B2 (en) | Apparatus for estimating of deviation from lane, and apparatus for warning of same and method for same | |
US9135709B2 (en) | Vehicle-to-vehicle distance calculation apparatus and method | |
US7400236B2 (en) | Vehicular lane monitoring system utilizing front and rear cameras | |
KR102207325B1 (en) | Apparatus for driver assistance | |
JP5045374B2 (en) | Operating state determination device | |
US9912933B2 (en) | Road surface detection device and road surface detection system | |
WO2014129312A1 (en) | Device for suppressing deviation from lane boundary line | |
US20160107645A1 (en) | Departure prevention support apparatus | |
US20050201593A1 (en) | Vehicle state sensing system and vehicle state sensing method | |
JP6979985B2 (en) | Road deviation prevention system | |
JP2004268845A (en) | Lane deviation alarm device | |
KR101481134B1 (en) | System and method for estimating the curvature radius of autonomous vehicles using sensor fusion | |
CN109753841B (en) | Lane line identification method and device | |
US11565751B2 (en) | Lane separation line detection correcting device, lane separation line detection correcting method, and automatic driving system | |
WO2015015939A1 (en) | Vehicle position/bearing estimation device and vehicle position/bearing estimation method | |
CN105599765A (en) | Lane departure judging and early warning method | |
CN105774901A (en) | Lane keeping control system and method and vehicle | |
JP2015202758A (en) | Drive support apparatus | |
JPWO2019065564A1 (en) | Automatic operation control device and method | |
US10077048B2 (en) | Lane departure prevention apparatus | |
JP2015221636A (en) | Lane-keep support apparatus | |
JP4419560B2 (en) | Vehicle lane travel support device | |
US20140240487A1 (en) | Vehicle-to-vehicle distance calculation apparatus and method | |
US10363936B2 (en) | Vehicle control apparatus and method |
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 |