CN104657735A - Lane line detection method and system, as well as lane departure early warning method and system - Google Patents
Lane line detection method and system, as well as lane departure early warning method and system Download PDFInfo
- Publication number
- CN104657735A CN104657735A CN201310593577.3A CN201310593577A CN104657735A CN 104657735 A CN104657735 A CN 104657735A CN 201310593577 A CN201310593577 A CN 201310593577A CN 104657735 A CN104657735 A CN 104657735A
- Authority
- CN
- China
- Prior art keywords
- image
- lane
- lane line
- line
- mentioned
- 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
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a lane line detection method which comprises the steps of: S1, acquiring an image, converting the color image into a grayscale image, S2, selecting a region of interest of the image, dividing the region of interest into a left side image and a right side image, S3, calculating a greyscale binarization threshold of each row of each of the left side image and the right side image by binarization, extracting pixel point sets with grayscale values greater than or equal to the greyscale binarization thresholds from the left side image and the right side image, S4, obtaining edge images of the left side image and the right side image by using a one-dimensional sobel operator, calculating edge binarization thresholds of the edge images, extracting inner edge point sets of the left side edge image and the right side edge image, S5, selecting an intersection of the pixel point set in the left side image and the inner edge point set as an inner edge point of a left lane line, selecting an intersection of the pixel point set in the right side image and the inner edge point set as an inner edge point of a right lane line, and S6, calculating the left lane line and the right lane line according to the inner edge point of the left lane line and the inner edge point of the right lane line.
Description
Technical field
The present invention relates to vehicle safety and assist driving technology field, particularly relate to a kind of method for detecting lane lines, system, lane departure warning method and system.
Background technology
Along with the development of society, automobile has become the popular vehicles, because fatigue driving or dispersion attention, the accident that automotive run-off-road line causes also is on the increase, and when this type of accident occurs, the usual speed of a motor vehicle is higher, and therefore harmfulness is higher.
Research shows, if potential traffic hazard occurs to driver's early warning front 1 second, then can avoid the similar traffic hazard of the overwhelming majority.Therefore, real-time inspection vehicle diatom, identifies vehicle whether run-off-road, reminds driver in time, greatly can improve travel safety when driver does not carry out lane change operation but vehicle is tending towards run-off-road.
Cause the situation of automotive run-off-road line a lot of in driving procedure, as driving habits, fatigue driving, dispersion attention etc.The deviation that driving habits causes initiatively can be avoided by driver, and the deviation that fatigue driving, dispersion attention cause cannot rely on driver initiatively to avoid, and often causes traffic hazard.
In order to overcome the problems referred to above, Lane Departure Warning System arises at the historic moment, and the most crucial part of Lane Departure Warning System is exactly lane detection system.Traditional lane detection system work process is as follows: first, is comprised the image of vehicle place lane line by camera shooting; Then utilize binarization method to extract lane line inward flange point in above-mentioned image, finally utilize Hough transformation to extract straight line, thus obtain lane line.
In above-mentioned method for detecting lane lines, in edge, track impact point, only use an image binaryzation to extract lane line edge inward flange point, the lane line inward flange point extracted has a large portion not to be actual lane line inward flange point, it is likely the noise that the hot spot that exists in image and other brightness are larger, and then affect the accuracy of lane line inward flange point detection, make lane detection not accurate enough.
Summary of the invention
Technical matters to be solved by this invention is the problem postponed for large the caused system response of existing method for detecting lane lines calculated amount, provides a kind of method for detecting lane lines.
The present invention solves the problems of the technologies described above adopted technical scheme, provides a kind of method for detecting lane lines, comprises the following steps:
S1, gather and comprise the image of the left and right lane line in track, vehicle place, and coloured image is converted to gray level image;
S2, in above-mentioned gray level image, choose the interesting image regions that may there is left and right lane line, above-mentioned interesting image regions is divided into left-side images and image right;
S3, utilize image binaryzation method to ask for the binarization of gray value threshold value of left-side images and the every a line of image right respectively, and extract gray-scale value in left-side images and image right respectively and be more than or equal to the pixel set of binarization of gray value threshold value;
S4, one dimension sobel operator is utilized to calculate the edge image of left-side images and image right respectively, ask for the edge binary-state threshold of left side edge image and right side edge image respectively, and use above-mentioned edge binary-state threshold to carry out binaryzation to left side edge image and right side edge image, then extract the inward flange point set of left side edge image and right side edge image respectively;
S5, the common factor choosing the above-mentioned inward flange point set that above-mentioned pixel set that step S3 in left-side images extracts is extracted with step S4 are left-lane line inward flange point, and the common factor choosing the above-mentioned inward flange point set that the above-mentioned pixel set of step S3 extraction in image right and step S4 extract is right lane line inward flange point;
The left-lane line inward flange point that S6, basis are chosen and right lane line inward flange point obtain left-lane line and right lane line respectively.
Further, after step S1, before step S2, also comprise Image semantic classification step:
Gaussian filter is utilized to carry out denoising and smoothing processing to above-mentioned image.
Further, step S1 is specially:
Comprised the image of the left and right lane line in track, vehicle place by forward sight camera or two, left and right camera shooting vehicle front, and picture signal is inputed to Video Decoder;
Video Decoder is by Input Control Element after image signal decoding, and control module gathers above-mentioned picture signal by the video input interface on it, and the picture signal collected is converted to gray level image storage in memory.
Further, the interesting image regions chosen in step S2 by do not comprise the image of sky portion in collection image.
Further, the method asking for the binarization of gray value threshold value of left-side images and the every a line of image right in step S3 is specially:
The binarization of gray value threshold value of left-side images and the every a line of image right is asked for respectively by histogram Two-peak method;
Reduce according to the pixel reasonable quantity meeting binarization of gray value threshold value in the binary image of left-side images and image right or increase binarization of gray value threshold value;
By the binarization of gray value threshold value of present frame in the binary image of left-side images and image right compared with the binarization of gray value threshold value of former frame, binarization of gray value changes of threshold is exceeded to the row of preset range, then set the final binarization of gray value threshold value of this row according to different specific weight in conjunction with the binarization of gray value threshold value of present frame and former frame.
Further, step S4 is specially:
One dimension sobel operator is utilized to calculate the edge image of left-side images and image right respectively, asked for the edge binary-state threshold of left side edge image and right side edge image by histogram Two-peak method respectively, and use the edge binary-state threshold of the edge binary-state threshold of above-mentioned left side edge image and right side edge image to carry out binaryzation to left side edge image and right side edge image respectively;
Left-lane line inward flange point is extracted as the pixel (x, y) meeting following condition after left side edge image binaryzation:
Y(x，y)＝255；
Y(x－1，y)＝255；
Y(x+1，y)＝0；
Wherein (x-1, y) is the left neighbor pixel of (x, y), and (x+1, y) is the right neighbor pixel of (x, y), and Y represents the gray-scale value after this pixel binaryzation;
Initial right lane line inward flange point is extracted as the pixel (x, y) meeting following condition after right side edge image binaryzation:
Y(x，y)＝0；
Y(x－1，y)＝255；
Y(x+1，y)＝255；
Wherein (x-1, y) is the left neighbor pixel of (x, y), and (x+1, y) is the right neighbor pixel of (x, y), and Y represents the gray-scale value after this pixel binaryzation.
Further, step S6 is specially:
Utilize Radon to convert and the rectangular coordinate plane comprising left-lane line inward flange point and right lane line inward flange point is transformed to pole coordinate parameter space plane (ρ, θ), obtain the straight line of left-side images and image right existence respectively;
To represent that the polar coordinates ρ-θ of parameter space is quantized into multiple identical little lattice, according to the every bit coordinate (x of expression lane line in rectangular coordinate system X-Y, y), according to each polar angle θ value that formula ρ=xcos θ+ysin θ goes forward one by one with the step-length of little lattice to the region within 0-180 in parameter space °, calculate each footpath, pole ρ value, footpath, gained pole ρ value falls in certain little lattice, just makes the summary counter of these little lattice add 1; After points whole in rectangular coordinate system has all calculated, test to little lattice, chosen the little lattice of summary counter numerical value front three, (ρ, θ) value of these little lattice of three corresponds to three straight lines in rectangular coordinate;
Choose the straight line that corresponding summary counter numerical value is greater than preset value;
Judge straight line that above-mentioned steps chooses whether within the scope of (ρ, the θ) value preset;
The straight line confidence level meeting above-mentioned judgement is set to 1, and preserves (ρ, the θ) value corresponding to it;
Enter next frame to detect, compared with the straight line that the new straight line detected and former frame are detected, if having the difference of (ρ, θ) value of two straight lines in preset range, then assert that these two straight lines are same straight line, then the confidence level of this straight line adds 1; If the straight line that present frame detects, can not with arbitrary matching line segments of former frame, then think that this straight line is new straight line, its confidence level be set to 1, and record its (ρ, θ) value; If all straight lines that the straight line that former frame detects and present frame detect all cannot mate, then think that this straight line disappears in the current frame, its confidence level is subtracted 1;
Repeat above-mentioned steps, if the confidence level of straight line reaches 25, remain unchanged, and (ρ, θ) value of this straight line is updated to (ρ, θ) value of present frame detection;
Judge the confidence level of all straight lines of record, if the confidence level of straight line equals 25, then judge that this straight line is the lane line that will detect; If the confidence level of certain straight line is reduced to 0, then delete this straight line from (ρ, θ) record.
Further, described method also comprises the steps:
According to the position of lane line in the current frame image detected, Kalman filter is utilized to predict the position of lane line in next frame image;
Left and right lane line former frame detected expands the lane detection region of 50 pixels as next frame respectively to left and right.
According to method for detecting lane lines of the present invention, when detecting left and right lane line inward flange point, first utilize image binaryzation method to ask for the binarization of gray value threshold value of left-side images and the every a line of image right respectively, and extract gray-scale value in left-side images and image right respectively and be more than or equal to the pixel set of binarization of gray value threshold value; Recycling one dimension sobel operator calculates the edge image of left-side images and image right respectively, ask for the edge binary-state threshold of left side edge image and right side edge image respectively, and use above-mentioned edge binary-state threshold to carry out binaryzation to left side edge image and right side edge image, extract the inward flange point set of left side edge image and right side edge image respectively; Then, the common factor choosing the above-mentioned inward flange point set that above-mentioned pixel set that step S3 in left-side images extracts is extracted with step S4 is left-lane line inward flange point, and the common factor choosing the above-mentioned inward flange point set that the above-mentioned pixel set of step S3 extraction in image right and step S4 extract is right lane line inward flange point.Like this, by first time binary conversion treatment, the shade that exists in image and the less noise of other brightness can be removed, and carry out second time binaryzation by the edge image asked for one dimension sobel operator, the non-edge noise in first time binaryzation can be removed again, as the hot spot in image and the larger noise of other brightness, thus substantially increase the accuracy that lane line inward flange detects, and then make lane detection more accurate, improve the security of vehicle driving.
In addition, present invention also offers a kind of lane detection system, comprise image taking module and image processing module, described image processing module comprises control module, Video Decoder and storer;
Described image taking module, for taking the image of the left and right lane line comprising track, vehicle place;
Described image processing module, comprises image capture module and lane detection module;
Described image capture module, for the picture signal by Video Decoder accepts image taking module photograph, and by Input Control Element after image signal decoding, control module gathers above-mentioned picture signal by the video input interface on it, and the picture signal collected is converted to gray level image storage in memory;
Described lane detection module, for choosing the interesting image regions that may there is left and right lane line in above-mentioned gray level image, and is divided into left-side images by above-mentioned interesting image regions and image right processes respectively; Then, utilize image binaryzation method to ask for the binarization of gray value threshold value of left-side images and the every a line of image right respectively, and extract gray-scale value in left-side images and image right respectively and be more than or equal to the pixel set of binarization of gray value threshold value; One dimension sobel operator is utilized to calculate the edge image of left-side images and image right respectively, ask for the edge binary-state threshold of left side edge image and right side edge image respectively, and use above-mentioned edge binary-state threshold to carry out binaryzation to left side edge image and right side edge image, then extract the inward flange point set in left side edge image and right side edge image respectively; Then, the common factor choosing the above-mentioned inward flange point set that above-mentioned pixel set that step S3 in left-side images extracts is extracted with step S4 is left-lane line inward flange point, and the common factor choosing the above-mentioned inward flange point set that the above-mentioned pixel set of step S3 extraction in image right and step S4 extract is right lane line inward flange point; Finally, left-lane line and right lane line is obtained respectively according to the left-lane line inward flange point extracted and right lane line inward flange point.
Further, described image processing module also comprises the image pre-processing module be connected between described image capture module and lane detection module, and described image pre-processing module utilizes Gaussian filter to carry out denoising and smoothing processing to above-mentioned image.
Further, described image taking module is the forward sight camera of vehicle viewing system, and described image taking module is forward sight camera or two, the left and right camera of vehicle viewing system.
In addition, present invention also offers a kind of lane departure warning method, comprise the steps:
Detect according to above-mentioned method for detecting lane lines and obtain lane line;
According to the lane line detected and the relative position of vehicle and the current state of vehicle, determine whether to need early warning;
When determining to need early warning, with the form early warning of sound and/or light.
According to lane departure warning method of the present invention, by first time binary conversion treatment, the shade that exists in image and the less noise of other brightness can be removed, and carry out second time binaryzation by the edge image asked for one dimension sobel operator, the non-edge noise in first time binaryzation can be removed again, as the hot spot in image and the larger noise of other brightness, thus the accuracy that lane line inward flange detects is substantially increased, and then make lane detection more accurate, improve the security of vehicle driving.
In addition, present invention also offers a kind of Lane Departure Warning System, comprise above-mentioned lane detection system, vehicle and lane line relative position detection module, early warning logic judgment module and warning module;
Described vehicle and lane line relative position detection module, in conjunction with the position of the lane line detected by described lane detection system and vehicle calibration parameter, determine the current relative position with lane line of vehicle;
Described early warning logic judgment module, carries out Logic judgment according to the relative position of Current vehicle and lane line and vehicle's current condition, determines whether to need early warning;
Described warning module, warning module, according to the judged result of described early warning logic judgment module, carries out the early warning of sound and/or light form in advance to user.
Accompanying drawing explanation
Fig. 1 is the block diagram of the lane departure warning method that one embodiment of the invention provides;
Fig. 2 is the block diagram of the Lane Departure Warning System that one embodiment of the invention provides.
Mark in accompanying drawing is as follows:
10, image taking module; 20, image processing module; 21, image capture module; 22, lane detection module; 23, image pre-processing module; 24, vehicle and lane line relative position detection module; 25, early warning logic judgment module; 30, warning module.
7, the method for detecting lane lines according to claim 1 to 5 any one, is characterized in that, adopts least square method to obtain left-lane line and right lane line in step S6.
Embodiment
In order to make technical matters solved by the invention, technical scheme and beneficial effect clearly understand, below in conjunction with drawings and Examples, the present invention is described in further detail.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
The method for detecting lane lines that one embodiment of the invention provides, comprises the following steps:
S1, gather and comprise the image of the left and right lane line in track, vehicle place, and coloured image is converted to gray level image;
S2, in above-mentioned gray level image, choose the interesting image regions that may there is left and right lane line, above-mentioned interesting image regions is divided into left-side images and image right;
S3, image binaryzation method is utilized to ask for the binarization of gray value threshold value GrayTL1 of left-side images and the every a line of image right respectively ... GrayTLn and GrayTR1 ... GrayTRn, and extract gray-scale value in left-side images and image right respectively and be more than or equal to the pixel set of binarization of gray value threshold value;
S4, one dimension sobel operator is utilized to calculate the edge image of left-side images and image right respectively, ask for edge binary-state threshold EdgeTL and EdgeTR of left side edge image and right side edge image respectively and use above-mentioned edge binary-state threshold EdgeTL and EdgeTR to carry out binaryzation to left side edge image and right side edge image, then extracting the inward flange point set of left side edge image and right side edge image respectively; ;
S5, the common factor choosing the above-mentioned inward flange point set that above-mentioned pixel set that step S3 in left-side images extracts is extracted with step S4 are left-lane line inward flange point, and the common factor choosing the above-mentioned inward flange point set that the above-mentioned pixel set of step S3 extraction in image right and step S4 extract is right lane line inward flange point;
The left-lane line inward flange point that S6, basis are chosen and right lane line inward flange point obtain left-lane line and right lane line respectively.
In the present embodiment, after step S1, before step S2, also comprise Image semantic classification step.Described Image semantic classification step carries out denoising and smoothing processing to above-mentioned image, to improve picture quality for utilizing Gaussian filter.
In the present embodiment, step S1 is specially:
Comprised the image of the left and right lane line in track, vehicle place by forward sight camera or two, left and right camera shooting vehicle front, and picture signal is inputed to Video Decoder; A kind of specification of camera is as follows: effective resolution is 640x480, and frame per second is 30 frames/second.When utilization is installed on the camera collection vehicle both sides image of left and right rearview mirror, there is visibility point advantage relative to the forward sight camera being installed on windshield place.On the one hand, left and right camera can be arranged in rearview mirror, and obliquely (camera lens is towards front lower place) is installed, be not vulnerable to the impact of light, sunlight can be avoided to shine directly on camera in the morning with at dusk, also not by the impact of other automobile front lamp light, ensure the picture quality of Real-time Collection in the evening, greatly improves lane identification rate; On the other hand, the left and right camera be arranged in rearview mirror is not vulnerable to windscreen wiper and rain water mitigation in the rainy day yet.
The picture signal (simulating signal) that camera inputs by Video Decoder is decoded as Input Control Element after the digital signal of YUV, control module gathers above-mentioned picture signal by the video input interface on it, and the picture signal collected is converted to gray level image and is stored in the storer of flash memory Flash and/or internal memory DDR type.Control module is preferably DSP(Digital Signal Processing, digital signal processor) chip.
The interesting image regions chosen in step S2 by do not comprise the image of sky portion in collection image.According to Theory of Projections, when camera illumination is parallel to the ground or at an angle, the top in camera view is generally the backgrounds such as sky, and road surface is in the latter half of image, and the present invention adopts image the latter half as area-of-interest.For reducing calculated amount and can selecting rational area-of-interest, by the setting angle of camera, the present invention ensures that rational area-of-interest is selected.When camera is installed, the ratio making sky and ground in image account for image by the adjustment of camera setting angle is 4:6, and therefore system can select rational interesting image regions ROI(Region Of Interest fast).When camera is arranged on the rearview mirror of left and right, in the image that left and right camera obtains, track lays respectively at the left side and the right of image, and therefore area-of-interest is finally chosen as the trapezoid area surrounding nearside lane line by the present invention.
In the present embodiment, the method asking for the binarization of gray value threshold value of left-side images and the every a line of image right in step S3 is specially:
The binarization of gray value threshold value GrayTL1 of left-side images and the every a line of image right is asked for respectively by histogram Two-peak method ... GrayTLn and GrayTR1 ... GrayTRn; Certainly in other embodiments, binary-state threshold GrayTL1 ... GrayTLn and GrayTR1 ... the acquisition methods of GrayTRn also can be P parametric method, Da-Jin algorithm, maximum entropy threshold method or process of iteration etc.Cross the binarization of gray value threshold value that histogram Two-peak method asks for left-side images and the every a line of image right respectively, carry out binaryzation adaptability relative to entire image greatly to improve, the method can avoid the impact of the outer complex environment of vehicle greatly, improves lane line endpoint detections efficiency.
Reduce according to the pixel reasonable quantity meeting binarization of gray value threshold value in the binary image of left-side images and image right or increase binarization of gray value threshold value GrayTL1 ... GrayTLn and GrayTR1 ... GrayTRn.Marginal point quantity to be selected can control within the specific limits by the method.
By the binarization of gray value threshold value of present frame in the binary image of left-side images and image right compared with the binarization of gray value threshold value of former frame, binarization of gray value changes of threshold is exceeded to the row of preset range, then set the final binarization of gray value threshold value of this row according to different specific weight in conjunction with the binarization of gray value threshold value of present frame and former frame.
Certainly, in other embodiments, the left-side images asked for by histogram Two-peak method and the binarization of gray value threshold value GrayTL1 of the every a line of image right ... GrayTLn and GrayTR1 ... GrayTRn also directly can be set as the binarization of gray value threshold value that this row is final.Comparatively speaking, the method computing is more simple, but more less better than method precision above.
In the present embodiment, during step S4 " carries out edge binary-state threshold EdgeTL and EdgeTR of binaryzation in the hope of left side edge image and right side edge image to the edge image of left-side images and all row of image right " respectively, the acquisition methods of edge binary-state threshold EdgeTL and EdgeTR can be Two-peak method, P parametric method, Da-Jin algorithm, maximum entropy threshold method or process of iteration etc.
In the present embodiment, left-lane line inward flange point is extracted as the pixel (x, y) meeting following condition in left-side images:
Y(x，y)＝255；
Y(x－1，y)＝255；
Y(x+1，y)＝0；
Wherein (x-1, y) is the left neighbor pixel of (x, y), and (x+1, y) is the right neighbor pixel of (x, y), and Y represents the gray-scale value after this pixel binaryzation.
And right lane line inward flange point is extracted as the pixel (x, y) meeting following condition in image right:
Y(x，y)＝0；
Y(x－1，y)＝255；
Y(x+1，y)＝255；
Wherein (x-1, y) is the left neighbor pixel of (x, y), and (x+1, y) is the right neighbor pixel of (x, y), and Y represents the gray-scale value after this pixel binaryzation.
In the present embodiment, step S6 is specially:
Utilize Radon to convert and the rectangular coordinate plane comprising left-lane line inward flange point and right lane line inward flange point is transformed to pole coordinate parameter space plane (ρ, θ), obtain the straight line of left-side images and image right existence respectively; To represent that the polar coordinates ρ-θ of parameter space is quantized into multiple identical little lattice, according to the every bit coordinate (x of expression lane line in rectangular coordinate system X-Y, y), according to each polar angle θ value that formula ρ=xcos θ+ysin θ goes forward one by one with the step-length of little lattice to the region within 0-180 in parameter space °, calculate each footpath, pole ρ value, footpath, gained pole ρ value falls in certain little lattice, just makes the summary counter of these little lattice add 1; After points whole in rectangular coordinate system has all calculated, test to little lattice, chosen the little lattice of summary counter numerical value front three, (ρ, θ) value of these little lattice of three corresponds to three straight lines in rectangular coordinate;
Choose the straight line that corresponding summary counter numerical value is greater than preset value;
Judge straight line that above-mentioned steps chooses whether within the scope of (ρ, the θ) value preset;
The straight line confidence level meeting above-mentioned judgement is set to 1, and preserves (ρ, the θ) value corresponding to it;
Enter next frame to detect, compared with the straight line that the new straight line detected and former frame are detected, if having the difference of (ρ, θ) value of two straight lines in preset range, then assert that these two straight lines are same straight line, then the confidence level of this straight line adds 1; If the straight line that present frame detects, can not with arbitrary matching line segments of former frame, then think that this straight line is new straight line, its confidence level be set to 1, and record its (ρ, θ) value; If all straight lines that the straight line that former frame detects and present frame detect all cannot mate, then think that this straight line disappears in the current frame, its confidence level is subtracted 1;
Repeat above-mentioned steps, if the confidence level of straight line reaches 25, remain unchanged, and (ρ, θ) value of this straight line is updated to (ρ, θ) value of present frame detection;
Judge the confidence level of all straight lines of record, if the confidence level of straight line equals 25, then judge that this straight line is the lane line that will detect; If the confidence level of certain straight line is reduced to 0, then delete this straight line from (ρ, θ) record.
The determination methods of above-mentioned lane line, by arranging the confidence level of straight line, improve accuracy and the continuity of lane detection, greatly improving the warning efficiency of system.
In the present embodiment, described method also comprises the steps:
According to the position of lane line in the current frame image detected, Kalman filter is utilized to predict the position of lane line in next frame image; Kalman filter is utilized to incorporate the lane information of former frame, the interference of stress release treatment point.Left and right lane line former frame detected expands the lane detection region of 50 pixels as next frame respectively to left and right.
Road image video is continuous print (30 frames/second), the situation that the image between successive frame there will not be direction, track to suddenly change.The position of the lane line that therefore can detect according to former frame sets the surveyed area of a region as next frame image.The lane line that in the present invention, former frame detects by artwork embodiment sets the surveyed area of 50 pixels as next frame respectively to left and right, and the impact of the effective stress release treatment noise spot of this constraint condition, improves accuracy rate and the efficiency of lane detection.
Method for detecting lane lines according to the above embodiment of the present invention, when detecting left and right lane line inward flange point, first utilize image binaryzation method to ask for the binarization of gray value threshold value of left-side images and the every a line of image right respectively, and extract gray-scale value in left-side images and image right respectively and be more than or equal to the pixel set of binarization of gray value threshold value; Recycling one dimension sobel operator calculates the edge image of left-side images and image right respectively, ask for the edge binary-state threshold of left side edge image and right side edge image respectively, and use above-mentioned edge binary-state threshold to carry out binaryzation to left side edge image and right side edge image, extract the inward flange point set of left side edge image and right side edge image respectively; Then, the common factor choosing the above-mentioned inward flange point set that above-mentioned pixel set that step S3 in left-side images extracts is extracted with step S4 is left-lane line inward flange point, and the common factor choosing the above-mentioned inward flange point set that the above-mentioned pixel set of step S3 extraction in image right and step S4 extract is right lane line inward flange point.Like this, by first time binary conversion treatment, the shade that exists in image and the less noise of other brightness can be removed, and carry out second time binaryzation by the edge image asked for one dimension sobel operator, the non-edge noise in first time binaryzation can be removed again, as the hot spot in image and the larger noise of other brightness, thus substantially increase the accuracy that lane line inward flange detects, and then make lane detection more accurate, improve the security of vehicle driving.
In addition, as shown in Figure 1, one embodiment of the invention additionally provides a kind of lane detection system, and comprise image taking module 10 and image processing module 20, described image processing module comprises control module, Video Decoder and storer;
Described image taking module 10, for taking the image of the left and right lane line comprising track, vehicle place;
Described image processing module 20, comprises image capture module 21 and lane detection module 22;
Described image capture module, for the picture signal by Video Decoder accepts image taking module photograph, and by Input Control Element after image signal decoding, control module gathers above-mentioned picture signal by the video input interface on it, and the picture signal collected is converted to gray level image storage in memory; Storer can be DDR internal memory or FLASH flash memory.Control module is preferably dsp chip.
Described lane detection module 22, for choosing the interesting image regions that may there is left and right lane line in above-mentioned gray level image, and is divided into left-side images and image right by above-mentioned interesting image regions; Then, image binaryzation method is utilized to ask for the binary-state threshold GrayTL1 of left-side images and the every a line of image right respectively ... GrayTLn and GrayTR1 ... GrayTRn, and extract gray-scale value in left-side images and image right respectively and be more than or equal to the pixel set of binarization of gray value threshold value; One dimension sobel operator is utilized to calculate the edge image of left-side images and image right respectively, ask for edge binary-state threshold EdgeTL and EdgeTR of the edge image of left side edge image and image right respectively, and use above-mentioned edge binary-state threshold to carry out binaryzation to left side edge image and right side edge image, then extract the inward flange point set in left side edge image and right side edge image respectively; Then, the common factor choosing the above-mentioned inward flange point set that above-mentioned pixel set that step S3 in left-side images extracts is extracted with step S4 is left-lane line inward flange point, and the common factor choosing the above-mentioned inward flange point set that the above-mentioned pixel set of step S3 extraction in image right and step S4 extract is right lane line inward flange point; Finally, left-lane line and right lane line is obtained respectively according to the left-lane line inward flange point extracted and right lane line inward flange point.Lane detection module 22 is integrated in dsp chip, realizes lane detection function by writing corresponding software in dsp chip.
In the present embodiment, described image processing module 20 also comprises the image pre-processing module 23 be connected between described image capture module and lane detection module, and described image pre-processing module 23 utilizes Gaussian filter to carry out denoising and smoothing processing to above-mentioned image.Image pre-processing module 23 is integrated in dsp chip.
In the present embodiment, described image taking module 10 is forward sight camera or two, the left and right camera of vehicle viewing system, two cameras in preferential employing left and right.Utilize the existing viewing system of vehicle to realize lane detection, and without the need to increasing miscellaneous equipment, be conducive to reducing parts and reducing production cost.When utilization is installed on the camera collection vehicle both sides image of left and right rearview mirror, there is visibility point advantage relative to the forward sight camera being installed on windshield place.On the one hand, left and right camera can be arranged in rearview mirror, and obliquely (camera lens is towards front lower place) is installed, be not vulnerable to the impact of light, sunlight can be avoided to shine directly on camera in the morning with at dusk, also not by the impact of other automobile front lamp light, ensure the picture quality of Real-time Collection in the evening, greatly improves lane identification rate; On the other hand, the left and right camera be arranged in rearview mirror is not vulnerable to windscreen wiper and rain water mitigation in the rainy day yet.
In addition, one embodiment of the invention additionally provides a kind of lane departure warning method, comprises the steps:
Detect according to above-mentioned method for detecting lane lines and obtain lane line;
According to the lane line detected and the relative position of vehicle and the current state of vehicle, determine whether to need early warning; The method step is known technological means, and the present invention is no longer not described in detail.
The present embodiment uses two cameras in left and right to detect left and right lane line respectively, then use this lane line to judge whether track departs from when only detecting side lane line, if detect the lane line of both sides simultaneously, then need according to the state comprehensive descision vehicle of both sides lane line whether run-off-road line.Therefore, while only improving alarm rate when vehicle departs from, rate of false alarm is reduced.
When determining to need early warning, with the form early warning of sound and/or light.The method step is known technological means, and the present invention is no longer not described in detail.
Lane departure warning method according to the above embodiment of the present invention, by first time binary conversion treatment, the shade that exists in image and the less noise of other brightness can be removed, and carry out second time binaryzation by the edge image asked for one dimension sobel operator, the non-edge noise in first time binaryzation can be removed again, as the hot spot in image and the larger noise of other brightness, thus the accuracy that lane line inward flange detects is substantially increased, and then make lane detection more accurate, improve the security of vehicle driving.
In addition, as shown in Figure 2, one embodiment of the invention additionally provides a kind of Lane Departure Warning System, comprises above-mentioned lane detection system, vehicle and lane line relative position detection module 24, early warning logic judgment module 25 and warning module 30; Described vehicle and lane line relative position detection module 24, early warning logic judgment module 25 are all integrated in dsp chip, realize lane detection function by writing corresponding software in dsp chip, namely vehicle and lane line relative position detection module 24 and early warning logic judgment module 25 are a part for image processing module.
Described vehicle and lane line relative position detection module 24, in conjunction with the position of the lane line detected by described lane detection system and vehicle calibration parameter, determine the current relative position with lane line of vehicle; This is known technological means, and the present invention is no longer not described in detail.
Described early warning logic judgment module 25, carries out Logic judgment according to the relative position of Current vehicle and lane line and vehicle's current condition, determines whether to need early warning; This is known technological means, and the present invention is no longer not described in detail.
Described warning module 30, warning module is according to the judged result of described early warning logic judgment module, user is carried out in advance to the early warning of sound and/or light form, such as send early warning by hummer, or show early warning information on vehicle DVD, or in panel board liquid crystal display screen display early warning information.This is known technological means, and the present invention is no longer not described in detail.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (13)
1. a method for detecting lane lines, is characterized in that, comprises the following steps:
S1, gather and comprise the image of the left and right lane line in track, vehicle place, and coloured image is converted to gray level image;
S2, in above-mentioned gray level image, choose the interesting image regions that may there is left and right lane line, above-mentioned interesting image regions is divided into left-side images and image right;
S3, utilize image binaryzation method to ask for the binarization of gray value threshold value of left-side images and the every a line of image right respectively, and extract gray-scale value in left-side images and image right respectively and be more than or equal to the pixel set of binarization of gray value threshold value;
S4, one dimension sobel operator is utilized to calculate the edge image of left-side images and image right respectively, ask for the edge binary-state threshold of left side edge image and right side edge image respectively, and use above-mentioned edge binary-state threshold to carry out binaryzation to left side edge image and right side edge image, then extract the inward flange point set of left side edge image and right side edge image respectively;
S5, the common factor choosing the above-mentioned inward flange point set that above-mentioned pixel set that step S3 in left-side images extracts is extracted with step S4 are left-lane line inward flange point, and the common factor choosing the above-mentioned inward flange point set that the above-mentioned pixel set of step S3 extraction in image right and step S4 extract is right lane line inward flange point;
The left-lane line inward flange point that S6, basis are chosen and right lane line inward flange point obtain left-lane line and right lane line respectively.
2. method for detecting lane lines according to claim 1, is characterized in that, after step S1, also comprises Image semantic classification step before step S2:
Gaussian filter is utilized to carry out denoising and smoothing processing to above-mentioned image.
3. method for detecting lane lines according to claim 1, is characterized in that, step S1 is specially:
Comprised the image of the left and right lane line in track, vehicle place by forward sight camera or two, left and right camera shooting vehicle front, and picture signal is inputed to Video Decoder;
Video Decoder is by Input Control Element after image signal decoding, and control module gathers above-mentioned picture signal by the video input interface on it, and the picture signal collected is converted to gray level image storage in memory.
4. method for detecting lane lines according to claim 3, is characterized in that, the interesting image regions chosen in step S2 by do not comprise the image of sky portion in collection image.
5. method for detecting lane lines according to claim 4, is characterized in that, the method asking for the binarization of gray value threshold value of left-side images and the every a line of image right in step S3 is specially:
The binarization of gray value threshold value of left-side images and the every a line of image right is asked for respectively by histogram Two-peak method;
Reduce according to the pixel reasonable quantity meeting binary-state threshold in the binary image of left-side images and image right or increase binarization of gray value threshold value;
By the binarization of gray value threshold value of present frame in the binary image of left-side images and image right compared with the binarization of gray value threshold value of former frame, binarization of gray value changes of threshold is exceeded to the row of preset range, then set the final binarization of gray value threshold value of this row according to different specific weight in conjunction with the binarization of gray value threshold value of present frame and former frame.
6. method for detecting lane lines according to claim 4, is characterized in that, step S4 is specially:
One dimension sobel operator is utilized to calculate the edge image of left-side images and image right respectively, asked for the edge binary-state threshold of left side edge image and right side edge image by histogram Two-peak method respectively, and use the edge binary-state threshold of the edge binary-state threshold of above-mentioned left side edge image and right side edge image to carry out binaryzation to left side edge image and right side edge image respectively;
Left-lane line inward flange point is extracted as the pixel (x, y) meeting following condition after left side edge image binaryzation:
Y(x，y)＝255；
Y(x－1，y)＝255；
Y(x+1，y)＝0；
Wherein (x-1, y) is the left neighbor pixel of (x, y), and (x+1, y) is the right neighbor pixel of (x, y), and Y represents the gray-scale value after this pixel binaryzation;
Initial right lane line inward flange point is extracted as the pixel (x, y) meeting following condition after right side edge image binaryzation:
Y(x，y)＝0；
Y(x－1，y)＝255；
Y(x+1，y)＝255；
Wherein (x-1, y) is the left neighbor pixel of (x, y), and (x+1, y) is the right neighbor pixel of (x, y), and Y represents the gray-scale value after this pixel binaryzation.
7. the method for detecting lane lines according to claim 1 to 6 any one, is characterized in that, step S6 is specially:
Utilize Radon to convert and the rectangular coordinate plane comprising left-lane line inward flange point and right lane line inward flange point is transformed to pole coordinate parameter space plane (ρ, θ), obtain the straight line of left-side images and image right existence respectively;
To represent that the polar coordinates ρ-θ of parameter space is quantized into multiple identical little lattice, according to the every bit coordinate (x of expression lane line in rectangular coordinate system X-Y, y), according to each polar angle θ value that formula ρ=xcos θ+ysin θ goes forward one by one with the step-length of little lattice to the region within 0-180 in parameter space °, calculate each footpath, pole ρ value, footpath, gained pole ρ value falls in certain little lattice, just makes the summary counter of these little lattice add 1; After points whole in rectangular coordinate system has all calculated, test to little lattice, chosen the little lattice of summary counter numerical value front three, (ρ, θ) value of these little lattice of three corresponds to three straight lines in rectangular coordinate;
Choose the straight line that corresponding summary counter numerical value is greater than preset value;
Judge straight line that above-mentioned steps chooses whether within the scope of (ρ, the θ) value preset;
The straight line confidence level meeting above-mentioned judgement is set to 1, and preserves (ρ, the θ) value corresponding to it;
Enter next frame to detect, compared with the straight line that the new straight line detected and former frame are detected, if having the difference of (ρ, θ) value of two straight lines in preset range, then assert that these two straight lines are same straight line, then the confidence level of this straight line adds 1; If the straight line that present frame detects, can not with arbitrary matching line segments of former frame, then think that this straight line is new straight line, its confidence level be set to 1, and record its (ρ, θ) value; If all straight lines that the straight line that former frame detects and present frame detect all cannot mate, then think that this straight line disappears in the current frame, its confidence level is subtracted 1;
Repeat above-mentioned steps, if the confidence level of straight line reaches 25, remain unchanged, and (ρ, θ) value of this straight line is updated to (ρ, θ) value of present frame detection;
Judge the confidence level of all straight lines of record, if the confidence level of straight line equals 25, then judge that this straight line is the lane line that will detect; If the confidence level of certain straight line is reduced to 0, then delete this straight line from (ρ, θ) record.
8. the method for detecting lane lines according to claim 1 to 6 any one, is characterized in that, described method also comprises the steps:
According to the position of lane line in the current frame image detected, Kalman filter is utilized to predict the position of lane line in next frame image;
Left and right lane line former frame detected expands the lane detection region of 50 pixels as next frame respectively to left and right, if without lane line in this region, then selects area-of-interest according to (S2).
9. a lane detection system, is characterized in that, comprises image taking module and image processing module, and described image processing module comprises control module, Video Decoder and storer;
Described image taking module, for taking the image of the left and right lane line comprising track, vehicle place;
Described image processing module, comprises image capture module and lane detection module;
Described image capture module, for the picture signal by Video Decoder accepts image taking module photograph, and by Input Control Element after image signal decoding, control module gathers above-mentioned picture signal by the video input interface on it, and the picture signal collected is converted to gray level image storage in memory;
Described lane detection module, for choosing the interesting image regions that may there is left and right lane line in above-mentioned gray level image, and is divided into left-side images and image right by above-mentioned interesting image regions; Then, utilize image binaryzation method to ask for the binarization of gray value threshold value of left-side images and the every a line of image right respectively, and extract gray-scale value in left-side images and image right respectively and be more than or equal to the pixel set of binarization of gray value threshold value; One dimension sobel operator is utilized to calculate the edge image of left-side images and image right respectively, ask for the edge binary-state threshold to left side edge image and right side edge image respectively, and use above-mentioned edge binary-state threshold to carry out binaryzation to left side edge image and right side edge image, then extract the inward flange point set in left side edge image and right side edge image respectively; Then, the common factor choosing the above-mentioned inward flange point set that above-mentioned pixel set that step S3 in left-side images extracts is extracted with step S4 is left-lane line inward flange point, and the common factor choosing the above-mentioned inward flange point set that the above-mentioned pixel set of step S3 extraction in image right and step S4 extract is right lane line inward flange point; Finally, left-lane line and right lane line is obtained respectively according to the left-lane line inward flange point extracted and right lane line inward flange point.
10. lane detection system according to claim 9, it is characterized in that, described image processing module also comprises the image pre-processing module be connected between described image capture module and lane detection module, and described image pre-processing module utilizes Gaussian filter to carry out denoising and smoothing processing to above-mentioned image.
11. lane detection systems according to claim 9 or 10, it is characterized in that, described image taking module is forward sight camera or two, the left and right camera of vehicle viewing system.
12. 1 kinds of lane departure warning methods, is characterized in that, comprise the steps:
Method for detecting lane lines according to claim 1 to 8 any one detects and obtains lane line;
According to the lane line detected and the relative position of vehicle and the current state of vehicle, determine whether to need early warning;
When determining to need early warning, with the form early warning of sound and/or light.
13. 1 kinds of Lane Departure Warning System, is characterized in that, comprise the lane detection system described in claim 9 to 11 any one, vehicle and lane line relative position detection module, early warning logic judgment module and warning module;
Described vehicle and lane line relative position detection module, in conjunction with the position of the lane line detected by described lane detection system and vehicle calibration parameter, determine the current relative position with lane line of vehicle;
Described early warning logic judgment module, carries out Logic judgment according to the relative position of Current vehicle and lane line and vehicle's current condition, determines whether to need early warning;
Described warning module, according to the judged result of described early warning logic judgment module, carries out the early warning of sound and/or light form in advance to user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310593577.3A CN104657735B (en) | 2013-11-21 | 2013-11-21 | Method for detecting lane lines, system, lane departure warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310593577.3A CN104657735B (en) | 2013-11-21 | 2013-11-21 | Method for detecting lane lines, system, lane departure warning method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104657735A true CN104657735A (en) | 2015-05-27 |
| CN104657735B CN104657735B (en) | 2018-01-23 |
Family
ID=53248835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310593577.3A Active CN104657735B (en) | 2013-11-21 | 2013-11-21 | Method for detecting lane lines, system, lane departure warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104657735B (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105216694A (en) * | 2015-10-14 | 2016-01-06 | 南宁学院 | A kind of Lane Departure Warning System |
| CN105539293A (en) * | 2016-02-03 | 2016-05-04 | 北京中科慧眼科技有限公司 | Lane-departure early warning method and device and automobile driving assistance system |
| CN105678791A (en) * | 2016-02-24 | 2016-06-15 | 西安交通大学 | Lane line detection and tracking method based on parameter non-uniqueness property |
| CN105868696A (en) * | 2016-03-23 | 2016-08-17 | 奇瑞汽车股份有限公司 | Method and device for detecting multiple lane lines |
| WO2017028742A1 (en) * | 2015-08-17 | 2017-02-23 | 比亚迪股份有限公司 | Image denoising system and image denoising method |
| CN106682646A (en) * | 2017-01-16 | 2017-05-17 | 北京新能源汽车股份有限公司 | Lane line identification method and device |
| CN107465892A (en) * | 2017-07-13 | 2017-12-12 | 湖南中南楷思科技发展有限公司 | Digital signal processing image identifying system and recognition methods |
| CN107729814A (en) * | 2017-09-19 | 2018-02-23 | 浙江大华技术股份有限公司 | A kind of method and device for detecting lane line |
| CN107909047A (en) * | 2017-11-28 | 2018-04-13 | 上海信耀电子有限公司 | A kind of automobile and its lane detection method and system of application |
| CN107944388A (en) * | 2017-11-24 | 2018-04-20 | 海信集团有限公司 | A kind of method for detecting lane lines, device and terminal |
| CN108182430A (en) * | 2018-02-27 | 2018-06-19 | 高秀晶 | Dual area Lane detection system and method |
| CN108304749A (en) * | 2017-01-13 | 2018-07-20 | 比亚迪股份有限公司 | The recognition methods of road speed line, device and vehicle |
| CN108345855A (en) * | 2018-02-08 | 2018-07-31 | 青岛慧拓智能机器有限公司 | A kind of track crimping detection method and system |
| CN108509906A (en) * | 2018-03-30 | 2018-09-07 | 长安大学 | Unmanned plane road baseline spot captures dual threshold Radon recognition methods |
| CN108875657A (en) * | 2018-06-26 | 2018-11-23 | 北京茵沃汽车科技有限公司 | A kind of method for detecting lane lines |
| CN109325389A (en) * | 2017-07-31 | 2019-02-12 | 比亚迪股份有限公司 | Lane detection method, apparatus and vehicle |
| CN109448011A (en) * | 2018-10-22 | 2019-03-08 | 浙江科技学院 | A kind of windbreak early warning method of photovoltaic power generation apparatus |
| CN109558765A (en) * | 2017-09-25 | 2019-04-02 | 比亚迪股份有限公司 | The detection method of automobile and lane line, device |
| CN110088766A (en) * | 2019-01-14 | 2019-08-02 | 京东方科技集团股份有限公司 | Lane detection method, Lane detection device and non-volatile memory medium |
| CN110386065A (en) * | 2018-04-20 | 2019-10-29 | 比亚迪股份有限公司 | Monitoring method, device, computer equipment and the storage medium of vehicle blind zone |
| CN110414385A (en) * | 2019-07-12 | 2019-11-05 | 淮阴工学院 | A kind of method for detecting lane lines and system based on homography conversion and characteristic window |
| CN111002997A (en) * | 2019-12-06 | 2020-04-14 | 武汉中海庭数据技术有限公司 | Lane departure prompting method and device |
| CN111881878A (en) * | 2020-08-07 | 2020-11-03 | 吉林大学 | Lane line identification method for look-around multiplexing |
| CN113815648A (en) * | 2021-10-29 | 2021-12-21 | 广州理工学院 | Control method of vehicle control system |
| CN114001706A (en) * | 2021-12-29 | 2022-02-01 | 阿里巴巴达摩院(杭州)科技有限公司 | Course angle estimation method and device, electronic equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102303609A (en) * | 2011-06-16 | 2012-01-04 | 广东铁将军防盗设备有限公司 | System and method for prewarning lane deviation |
| CN102663744A (en) * | 2012-03-22 | 2012-09-12 | 杭州电子科技大学 | Complex road detection method under gradient point pair constraint |
-
2013
- 2013-11-21 CN CN201310593577.3A patent/CN104657735B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102303609A (en) * | 2011-06-16 | 2012-01-04 | 广东铁将军防盗设备有限公司 | System and method for prewarning lane deviation |
| CN102663744A (en) * | 2012-03-22 | 2012-09-12 | 杭州电子科技大学 | Complex road detection method under gradient point pair constraint |
Non-Patent Citations (1)
| Title |
|---|
| 杨喜宁等: "基于改进Hough变换的车道线检测技术", 《计算机测量与控制》 * |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017028742A1 (en) * | 2015-08-17 | 2017-02-23 | 比亚迪股份有限公司 | Image denoising system and image denoising method |
| CN105216694A (en) * | 2015-10-14 | 2016-01-06 | 南宁学院 | A kind of Lane Departure Warning System |
| CN105539293A (en) * | 2016-02-03 | 2016-05-04 | 北京中科慧眼科技有限公司 | Lane-departure early warning method and device and automobile driving assistance system |
| CN105678791A (en) * | 2016-02-24 | 2016-06-15 | 西安交通大学 | Lane line detection and tracking method based on parameter non-uniqueness property |
| CN105678791B (en) * | 2016-02-24 | 2018-07-17 | 西安交通大学 | One kind being based on the not unique lane detection and tracking method of parameter |
| CN105868696A (en) * | 2016-03-23 | 2016-08-17 | 奇瑞汽车股份有限公司 | Method and device for detecting multiple lane lines |
| CN105868696B (en) * | 2016-03-23 | 2019-06-14 | 奇瑞汽车股份有限公司 | A kind of method and apparatus detecting multilane lane line |
| CN108304749A (en) * | 2017-01-13 | 2018-07-20 | 比亚迪股份有限公司 | The recognition methods of road speed line, device and vehicle |
| CN106682646A (en) * | 2017-01-16 | 2017-05-17 | 北京新能源汽车股份有限公司 | Lane line identification method and device |
| CN106682646B (en) * | 2017-01-16 | 2020-12-22 | 北京新能源汽车股份有限公司 | Lane line identification method and device |
| CN107465892A (en) * | 2017-07-13 | 2017-12-12 | 湖南中南楷思科技发展有限公司 | Digital signal processing image identifying system and recognition methods |
| CN109325389A (en) * | 2017-07-31 | 2019-02-12 | 比亚迪股份有限公司 | Lane detection method, apparatus and vehicle |
| CN107729814A (en) * | 2017-09-19 | 2018-02-23 | 浙江大华技术股份有限公司 | A kind of method and device for detecting lane line |
| CN107729814B (en) * | 2017-09-19 | 2020-06-23 | 浙江大华技术股份有限公司 | Method and device for detecting lane line |
| CN109558765B (en) * | 2017-09-25 | 2022-02-08 | 比亚迪股份有限公司 | Automobile and lane line detection method and device |
| CN109558765A (en) * | 2017-09-25 | 2019-04-02 | 比亚迪股份有限公司 | The detection method of automobile and lane line, device |
| CN107944388A (en) * | 2017-11-24 | 2018-04-20 | 海信集团有限公司 | A kind of method for detecting lane lines, device and terminal |
| CN107909047B (en) * | 2017-11-28 | 2021-07-06 | 上海信耀电子有限公司 | Automobile and lane detection method and system applied to automobile |
| CN107909047A (en) * | 2017-11-28 | 2018-04-13 | 上海信耀电子有限公司 | A kind of automobile and its lane detection method and system of application |
| CN108345855B (en) * | 2018-02-08 | 2020-08-18 | 青岛平行智能产业管理有限公司 | Lane line pressing detection method and system |
| CN108345855A (en) * | 2018-02-08 | 2018-07-31 | 青岛慧拓智能机器有限公司 | A kind of track crimping detection method and system |
| CN108182430A (en) * | 2018-02-27 | 2018-06-19 | 高秀晶 | Dual area Lane detection system and method |
| CN108182430B (en) * | 2018-02-27 | 2022-01-14 | 厦门蔚森智能科技有限公司 | Double-area lane line identification system and method |
| CN108509906A (en) * | 2018-03-30 | 2018-09-07 | 长安大学 | Unmanned plane road baseline spot captures dual threshold Radon recognition methods |
| CN108509906B (en) * | 2018-03-30 | 2022-02-08 | 长安大学 | Double-threshold Radon identification method for line light point capture of unmanned aerial vehicle aerial photography roadbed |
| CN110386065A (en) * | 2018-04-20 | 2019-10-29 | 比亚迪股份有限公司 | Monitoring method, device, computer equipment and the storage medium of vehicle blind zone |
| CN108875657A (en) * | 2018-06-26 | 2018-11-23 | 北京茵沃汽车科技有限公司 | A kind of method for detecting lane lines |
| CN109448011A (en) * | 2018-10-22 | 2019-03-08 | 浙江科技学院 | A kind of windbreak early warning method of photovoltaic power generation apparatus |
| CN109448011B (en) * | 2018-10-22 | 2021-01-15 | 浙江科技学院 | Wind-proof early warning method for photovoltaic power generation device |
| CN110088766A (en) * | 2019-01-14 | 2019-08-02 | 京东方科技集团股份有限公司 | Lane detection method, Lane detection device and non-volatile memory medium |
| WO2020146980A1 (en) * | 2019-01-14 | 2020-07-23 | 京东方科技集团股份有限公司 | Lane line recognizing method, lane line recognizing device, and nonvolatile storage medium |
| US11430226B2 (en) | 2019-01-14 | 2022-08-30 | Boe Technology Group Co., Ltd. | Lane line recognition method, lane line recognition device and non-volatile storage medium |
| CN110088766B (en) * | 2019-01-14 | 2023-10-03 | 京东方科技集团股份有限公司 | Lane line recognition method, lane line recognition device, and nonvolatile storage medium |
| CN110414385B (en) * | 2019-07-12 | 2021-06-25 | 淮阴工学院 | Lane line detection method and system based on homography transformation and characteristic window |
| CN110414385A (en) * | 2019-07-12 | 2019-11-05 | 淮阴工学院 | A kind of method for detecting lane lines and system based on homography conversion and characteristic window |
| CN111002997A (en) * | 2019-12-06 | 2020-04-14 | 武汉中海庭数据技术有限公司 | Lane departure prompting method and device |
| CN111881878A (en) * | 2020-08-07 | 2020-11-03 | 吉林大学 | Lane line identification method for look-around multiplexing |
| CN111881878B (en) * | 2020-08-07 | 2024-02-02 | 吉林大学 | Lane line identification method for look-around multiplexing |
| CN113815648A (en) * | 2021-10-29 | 2021-12-21 | 广州理工学院 | Control method of vehicle control system |
| CN114001706A (en) * | 2021-12-29 | 2022-02-01 | 阿里巴巴达摩院(杭州)科技有限公司 | Course angle estimation method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104657735B (en) | 2018-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104657735A (en) | Lane line detection method and system, as well as lane departure early warning method and system | |
| Wu et al. | Lane-mark extraction for automobiles under complex conditions | |
| CN107392103B (en) | Method and device for detecting road lane line and electronic equipment | |
| CN107862290B (en) | Lane line detection method and system | |
| Kuo et al. | Vision-based vehicle detection for a driver assistance system | |
| TWI607901B (en) | Image inpainting system area and method using the same | |
| Yan et al. | A method of lane edge detection based on Canny algorithm | |
| Li et al. | Nighttime lane markings recognition based on Canny detection and Hough transform | |
| CN107891808B (en) | Driving reminding method and device and vehicle | |
| CN104517111A (en) | Lane line detection method and system, and lane deviation early warning method and system | |
| EP3026885A1 (en) | Dirty lens detection device and dirty lens detection method | |
| US20150161796A1 (en) | Method and device for recognizing pedestrian and vehicle supporting the same | |
| CN105047019B (en) | A kind of passenger stock prevent rear car overtake other vehicles after lane change determination methods and device suddenly | |
| US9224052B2 (en) | Method for in-image periodic noise pixel inpainting | |
| JP5223675B2 (en) | Vehicle detection device, vehicle detection method, and vehicle detection program | |
| CN106096512B (en) | Detection device and method for recognizing vehicle or pedestrian by using depth camera | |
| CN107886034B (en) | Driving reminding method and device and vehicle | |
| CN106887004A (en) | A kind of method for detecting lane lines based on Block- matching | |
| JP2010102572A (en) | Periphery monitoring device for vehicle | |
| Liu et al. | Development of a vision-based driver assistance system with lane departure warning and forward collision warning functions | |
| Niksaz | Automatic traffic estimation using image processing | |
| Wu et al. | A Real‐Time Embedded Blind Spot Safety Assistance System | |
| CN202134079U (en) | Unmanned vehicle lane marker line identification and alarm device | |
| CN103034843A (en) | Method for detecting vehicle at night based on monocular vision | |
| CN111046741A (en) | Method and device for identifying lane line |
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 |