CN110516550A - A kind of lane line real-time detection method based on FPGA - Google Patents
A kind of lane line real-time detection method based on FPGA Download PDFInfo
- Publication number
- CN110516550A CN110516550A CN201910684088.6A CN201910684088A CN110516550A CN 110516550 A CN110516550 A CN 110516550A CN 201910684088 A CN201910684088 A CN 201910684088A CN 110516550 A CN110516550 A CN 110516550A
- Authority
- CN
- China
- Prior art keywords
- lane line
- lane
- image
- pixel
- birds
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of lane line real-time detection method based on FPGA, comprising: image input step: image data is acquired;Image preprocessing step: by splitting lane line from original image;Segmentation result fusion steps: corresponding pixel points superposition is carried out by binary image, three kinds of color space segmentation results are merged.Inverse perspective mapping step: it determines the area-of-interest of inverse perspective mapping, obtains birds-eye view.Lane line fit procedure: by using sliding window and traversal birds-eye view, the fitting to lane line is realized;It extracts lane information step: solving direction and the distance at automotive run-off-road center.Perspective transform step: inversion operation is carried out by inverse perspective mapping matrix, reads perspective transform image.The present invention extracts lane line using various ways, and by a variety of methods for merging of extraction results, reduces single extracting mode and the incomplete degree of the lane line that occurs, while the detection to lane line can be rapidly completed.
Description
Technical field
The present invention relates to intelligent transportation field more particularly to a kind of lane line real-time detection methods based on FPGA.
Background technique
With popularizing for autonomous driving vehicle, being measured in real time to the lane line in vehicle travel process becomes safety certainly
The dynamic primary background task driven.Lane detection content includes the direction at automotive run-off-road center, distance, the bending in lane
The information such as degree, and these information both contribute to realize the automatic Pilot of safety.
It is at present the development platform based on PC mostly to the research of lane detection, is realized simultaneously using the high flexibility of CPU
And the detection effect of rapid comparison algorithms of different, but the platform cost performance is low, power consumption is high, volume is big, real-time is difficult to reach
It is required that not being suitable in vehicle-mounted scene, while realizing that the image processing algorithm of lane detection is easier to be illuminated by the light uneven, yin
Shadow, which blocks etc., to be influenced, and the lane line extracted is caused incomplete phenomenon occur.It is therefore proposed that one kind is in FPGA hardware platform
It is upper to use image processing algorithm, it realizes the lane line real-time detection in environment, avoids based on conventional PC development platform
The problem that existing power consumption is big, cost performance is low.The present invention extracts lane line using various ways simultaneously, and by a variety of extraction results
The method merged reduces the incomplete problem of the lane line occurred using single extracting mode.
Summary of the invention
It is an object of the present invention in view of the above-mentioned problems, propose a kind of lane line real-time detection method based on FPGA.
A kind of lane line real-time detection method based on FPGA, includes the following steps:
S1: image preprocessing step: left and right lane line threshold range is respectively set in multicolour space respectively, by vehicle
Diatom is split from original image, and is saved in the form of binaryzation, by the way that a variety of binary images are carried out corresponding pixel points
Three kinds of color space segmentation results are merged in superposition.
S2: inverse perspective mapping step: by picture drop-out point and actual conditions, the area-of-interest of inverse perspective mapping is determined
8 coordinate positions are obtained, 8 coordinate values are substituted into and utilize Gaussian elimination method, solve inverse perspective mapping matrix;Then using inverse saturating
Depending on transformation matrix, the image in step s1 is subjected to inverse perspective mapping, obtains birds-eye view.
S3: lane line fit procedure: by using sliding window and traversal birds-eye view, the fitting to lane line is realized.
S4: it extracts lane information step: solving lane curvature radius, lane bending side using the matched curve of lane line
To, further according to the lane line position of acquisition, and center and the corresponding actual range of pixel of present image are got,
Solve direction and the distance at automotive run-off-road center.
S5: perspective transform step: by carrying out inversion operation to inverse perspective mapping matrix obtained in S2, birds-eye view is traversed
The position of middle all pixels finally reads perspective transform image from memory block.
The step s1 includes following sub-step:
S11: finding out respectively in tri- kinds of color spaces of RGB, HSL, HSV, the pixel numerical value in yellow, white lane line
The threshold range at place.
S12: according to three kinds of threshold ranges, each of input picture is traversed and obtains image the value of pixel, by vehicle
Diatom is split from original image, and is saved in the form of binaryzation, and the segmentation result figure of three lane lines is obtained;
S13: the value of three kinds of segmentation result corresponding pixel points positions is overlapped, if the value of a certain position is more than or equal to
1 output 1.
The step s2 includes following sub-step:
S21: by picture drop-out point and lane line actual conditions, the lane region of interest converted is determined
Domain, and four apex coordinates in the region are got, and the coordinate of four points is corresponded to after transformation.
S22: coordinate is substituted into formula 1, inverse perspective mapping matrix is solved using Gaussian elimination method, obtains coordinate transform square
Battle array.
S23: opening up new memory block, and the image after substituting into segmentation, writing pixel value, is got a bird's eye view in new memory block
Figure.
The step s3 includes following sub-step:
S31: the number of each column non-zero pixels point in birds-eye view and statistical chart is traversed, finds out non-zero pixels after traversal
Two most column of point calculate left and right lane line spacing as the initial position of left and right lane line, while according to initial position;
S32: centered on initial position, each 50 pixel in left and right draws the rectangle frame of two wide high 32 pixel of 100 pixel,
It is denoted as first group of rectangle frame;
S33: the most position conduct of non-zero pixels point is found out in non-zero pixels point distribution in first group of rectangle frame of statistics respectively
The center of next group of rectangle frame;
S34: repeating step S32, S33, until whole birds-eye view traversal is completed;
S35:, will be each in step s33 by the system of linear equations of least square method derived for solving fit equation coefficient
The center position coordinates of a rectangle frame are that sampled point substitutes into equation group, and solves equation coefficient using Gaussian elimination method, are substituted into
Image coordinate after segmentation finds out the coordinate for meeting the pixel of matched curve, and the pixel of these coordinates is just in lane line
On.
The step S4 includes following sub-step:
S41: according to matched curve expression formula and curvature radius calculation formula, lane curvature radius, calculation formula are solved
It is as follows:
Wherein, ρ indicates radius of curvature, and k indicates curvature, a2Indicate the coefficient of lane line quadratic fit equation, a1Indicate primary
Term coefficient.
S42: by calculate picture centre and lane center relative position, calculate vehicle whether run-off-road center,
And direction and the distance of run-off-road.
S43: the bending direction of road ahead is judged according to the coefficient of Fitting curve equation.
Beneficial effects of the present invention: the present invention proposes a kind of method for completing lane detection using FPGA development platform,
By optimizing program lifting system real-time, the deficiency of bending lane line is detected for Hough transformation, the present invention uses sliding window
The method of mouth and conic fitting realizes lane line fitting, and calculates and export lane curvature radius, lane bending side
To the important informations such as the direction at, automotive run-off-road center and distance, so that the more Practical significance of the invention.
Detailed description of the invention
Fig. 1 is the lane line real-time detection flow chart of FPGA;
Fig. 2 is rgb color space segmentation result figure;
Fig. 3 is HSL color space segmentation result figure;
Fig. 4 is HSV color space segmentation result figure;
Fig. 5 is three kinds of segmentation result fusion figures;
Fig. 6 is former topic and inverse transformed result comparison diagram;
Fig. 7 is that rectangle frame finds lane line and lane line curve matching figure;
Fig. 8 is that lane information extracts result figure;
Fig. 9 is lane detection time result figure.
Specific embodiment
For a clearer understanding of the technical characteristics, objects and effects of the present invention, this hair of Detailed description of the invention is now compareed
Bright specific embodiment.
In the present embodiment, Fig. 1 is the lane line real-time detection flow chart of FPGA, and a kind of lane line based on FPGA is examined in real time
Survey method, includes the following steps:
S1: image input step: format is carried out to camera acquired image data and coffret is converted, really
Image data is protected correctly completely to transmit;
S2: image preprocessing step: left and right lane line threshold range is respectively set in multicolour space respectively, by vehicle
Diatom is split from original image, and is saved in the form of binaryzation.
S3: segmentation result fusion steps: corresponding pixel points superposition is carried out by a variety of binary images, by three kinds of color skies
Between segmentation result merge.
S4: inverse perspective mapping step: by picture drop-out point and actual conditions, the region of interest of inverse perspective mapping is determined
Domain, gets 4 apex coordinates in the region, and the coordinate by 4 points corresponding after inverse perspective mapping is arranged, and is always obtained
8 coordinate positions substitute into 8 coordinate values and utilize Gaussian elimination method, solve inverse perspective mapping matrix;Then become using inverse perspective
Matrix is changed, the image of step S2 is subjected to inverse perspective mapping, obtains birds-eye view.
S5: lane line fit procedure: by using sliding window and traversal birds-eye view, the fitting to lane line is realized.
S6: it extracts lane information step: solving lane curvature radius, lane bending side using the matched curve of lane line
To, further according to the lane line position of acquisition, and center and the corresponding actual range of pixel of present image are got,
Solve direction and the distance at automotive run-off-road center.
S7: perspective transform step: by carrying out inversion operation to inverse perspective mapping matrix obtained in S3, birds-eye view is traversed
The position of middle all pixels finally reads perspective transform image from memory block.
The step S2 includes following sub-step:
S21: such as Fig. 2, Fig. 3 and Fig. 4, finding out in tri- kinds of color spaces of RGB, HSL, HSV respectively, yellow, white lane
The threshold range where pixel numerical value on line.
Rgb color space: Red ∈ [0,150], Green ∈ [170,220], Blue ∈ [200,255], while meeting and mentioning
Extracting yellow lane line;Red ∈ [210,255], Green ∈ [210,255], Blue ∈ [210,255], while meeting extraction white
Lane line;
HSL color space: L ∈ [150,255], S ∈ [80,255];Meet simultaneously and extracts yellow, white lane line;
HSV color space: H ∈ [35,77], S ∈ [43,255], V ∈ [46,255], while meeting and extracting yellow lane
Line;H ∈ [0,180], S ∈ [0,30], V ∈ [221,255], while meeting the white lane line of extraction;
S22: according to three kinds of threshold ranges, each of input picture is traversed and obtains image the value of pixel, by vehicle
Diatom is split from original image, and (pixel value on lane line is 1, other area pixel values for preservation in the form of binaryzation
For the segmentation result figure for 0), obtaining three lane lines, as shown in Figure 5;
S23: the value of three kinds of segmentation result corresponding pixel points positions is overlapped, if the value of a certain position is more than or equal to
1 output 1, otherwise exports 0.
The step S4 includes following sub-step:
S41: by picture drop-out point and lane line actual conditions, the lane region of interest converted is determined
Domain, and four apex coordinates in the region are got, and the coordinate of four points is corresponded to after transformation.
S42: coordinate is substituted into formula 1, inverse perspective mapping matrix is solved using Gaussian elimination method, obtains coordinate transform square
Battle array.
S43: opening up new memory block, the image after substituting into segmentation, in (t_row, the t_col) of new memory block in write-in
The pixel value of (row, col) obtains birds-eye view
For row=0 to rows do
For col=0 to cols do
Rows indicates the line number of image, and col indicates the columns of image, a11...a22Respectively correspond a [0] of transformation matrix
[0] ... [2] [2] a, coordinate (t_row, t_col) be in original image each pixel coordinate (row, col) after matrixing
Obtained new coordinate.
The step s6 includes following sub-step:
S51: the number of each column non-zero pixels point in birds-eye view and statistical chart is traversed, finds out non-zero pixels after traversal
Two most column of point calculate left and right lane line spacing as the initial position of left and right lane line, while according to initial position;
S52: centered on initial position, each 50 pixel in left and right draws the rectangle frame of two wide high 32 pixel of 100 pixel,
It is denoted as first group of rectangle frame;
S53: the most position conduct of non-zero pixels point is found out in non-zero pixels point distribution in first group of rectangle frame of statistics respectively
The center of next group of rectangle frame;
S54: repeating step S52, S53, until whole birds-eye view traversal is completed, as shown in Figure 6;
S55:, will be each in step S53 by the system of linear equations of least square method derived for solving fit equation coefficient
The center position coordinates of a rectangle frame are that sampled point substitutes into equation group, and solves equation coefficient using Gaussian elimination method
a2...a0, image coordinate after substituting into segmentation finds out the coordinate for meeting the pixel of matched curve, and the pixel of these coordinates
Just on lane line.
The step S6 includes following sub-step:
S61: according to matched curve expression formula and curvature radius calculation formula, lane curvature radius is solved, in order to look forward to the prospect
The considerations of property, the radius of curvature at x=0 can be calculated, show that calculation formula is as follows:
Wherein, ρ indicates radius of curvature, and k indicates curvature, a2The coefficient of lane line quadratic fit equation, a1Indicate a term system
Number.
S62: it is generally 3.6 meters wide according to lane, and wide about 450 pixels in lane in the picture, therefore estimate transverse direction
Each pixel represents about 0.8 centimetre, therefore the relative position by calculating picture centre and lane center, and calculating vehicle is
Direction and the distance of no run-off-road center and run-off-road.
S63: judging the bending direction of road ahead according to the coefficient of Fitting curve equation, if the coefficient of fit equation
a2Bend is indicated to the left less than 0, is indicated bend to the right greater than 0, is indicated to keep straight on equal to 0.
The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, without departing from the spirit and scope of the present invention, various changes and improvements may be made to the invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent thereof.
Claims (5)
1. a kind of lane line real-time detection method based on FPGA, which comprises the steps of:
S1: lane picture number image input step: is acquired using in-vehicle camera;
S2: image preprocessing step: being respectively set left and right lane line threshold range in multicolour space, by lane line from original image
In split to obtain three color segmentation figures, and saved in the form of binaryzation, by the way that a variety of binary images are carried out corresponding picture
Vegetarian refreshments superposition, three kinds of color space segmentation results are merged to obtain segmentation result fusion figure;
S3: inverse perspective mapping step: determine that the area-of-interest of inverse perspective mapping obtains 8 coordinate bits by picture drop-out point
It sets, substitute into 8 coordinate values and utilizes Gaussian elimination method, obtain inverse perspective mapping matrix;Wherein, using the inverse perspective mapping square
Segmentation result described in step S2 is merged figure and carries out inverse perspective mapping, obtains birds-eye view by battle array;
S4: lane line fit procedure: by using sliding window and traversal birds-eye view, the fitting to lane line is realized;
S5: extract lane information step: using lane line matched curve solve lane curvature radius, lane bending direction, then
According to the lane line position of acquisition, center and the corresponding actual range of pixel of present image are got, and is solved
The direction at automotive run-off-road center and distance out;
S6: perspective transform step: by carrying out inversion operation to inverse perspective mapping matrix obtained in S2, institute in birds-eye view is traversed
There is the position of pixel, perspective transform image is finally read from memory block.
2. a kind of lane line real-time detection method based on FPGA according to claim 1, which is characterized in that the step
S2 includes following sub-step:
S21: finding out respectively in tri- kinds of color spaces of RGB, HSL, HSV, where the pixel numerical value in yellow, white lane line
Threshold range;
S22: according to three kinds of threshold ranges, each of input picture is traversed and obtains image the value of pixel, by lane line
It splits from original image, and is saved in the form of binaryzation, obtain the segmentation result figure of three lane lines;
S23: the value of three kinds of segmentation result corresponding pixel points positions is overlapped, if the value of a certain position is more than or equal to 1
Output 1, otherwise exports 0.
3. a kind of lane line real-time detection method based on FPGA according to claim 1, which is characterized in that the step
S3 includes following sub-step:
S31: by picture drop-out point and lane line actual conditions, determining the lane area-of-interest converted, and
Four apex coordinates in the region are got, and transformation corresponds to the coordinate of four points later;
S32: inverse perspective mapping matrix is solved using Gaussian elimination method, obtains transformation matrix of coordinates;
S33: opening up new memory block, the image after substituting into segmentation, and the writing pixel value in new memory block obtains birds-eye view.
4. a kind of lane line real-time detection method based on FPGA according to claim 1, which is characterized in that the step
S4 includes following sub-step:
S41: the number of each column non-zero pixels point in birds-eye view and statistical chart is traversed, finds out non-zero pixels point most after traversal
Two more column calculate left and right lane line spacing as the initial position of left and right lane line, while according to initial position;
S42: centered on initial position, each 50 pixel in left and right is drawn the rectangle frame of two wide high 32 pixel of 100 pixel, is denoted as
First group of rectangle frame;
S43: non-zero pixels point distribution in first group of rectangle frame of statistics finds out the most position of non-zero pixels point as next respectively
The center of group rectangle frame;
S44: repeating step S32, S33, until whole birds-eye view traversal is completed;
S45: by the system of linear equations of least square method derived for solving fit equation coefficient, by each square in step S33
The center position coordinates of shape frame are that sampled point substitutes into equation group, and solves equation coefficient using Gaussian elimination method, substitute into segmentation
Image coordinate afterwards finds out the coordinate for meeting the pixel of matched curve.
5. a kind of lane line real-time detection method based on FPGA according to claim 1, which is characterized in that the step
S5 includes following sub-step:
S51: according to matched curve expression formula and curvature radius calculation formula, lane curvature radius is solved, calculation formula is such as
Under:
Wherein, ρ indicates radius of curvature, and k indicates curvature, a2Indicate the coefficient of lane line quadratic fit equation, a1Indicate a term system
Number.
S52: by calculate picture centre and lane center relative position, calculate vehicle whether run-off-road center, and
The direction of run-off-road and distance;
S53: the bending direction of road ahead is judged according to the coefficient of Fitting curve equation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910684088.6A CN110516550B (en) | 2019-07-26 | 2019-07-26 | FPGA-based lane line real-time detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910684088.6A CN110516550B (en) | 2019-07-26 | 2019-07-26 | FPGA-based lane line real-time detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110516550A true CN110516550A (en) | 2019-11-29 |
CN110516550B CN110516550B (en) | 2022-07-05 |
Family
ID=68623720
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910684088.6A Active CN110516550B (en) | 2019-07-26 | 2019-07-26 | FPGA-based lane line real-time detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110516550B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111914787A (en) * | 2020-08-11 | 2020-11-10 | 重庆文理学院 | Register configuration method for finger vein recognition SOC (system on chip) |
CN112307953A (en) * | 2020-10-29 | 2021-02-02 | 无锡物联网创新中心有限公司 | Clustering-based adaptive inverse perspective transformation lane line identification method and system |
CN112329512A (en) * | 2020-08-11 | 2021-02-05 | 华南理工大学 | Intelligent identification method for intelligent network combined model type vehicle on-loop simulation sand table lane line |
CN112598762A (en) * | 2020-09-16 | 2021-04-02 | 禾多科技(北京)有限公司 | Three-dimensional lane line information generation method, device, electronic device, and medium |
CN112613344A (en) * | 2020-12-01 | 2021-04-06 | 浙江大华汽车技术有限公司 | Vehicle lane occupation detection method and device, computer equipment and readable storage medium |
CN113011293A (en) * | 2021-03-05 | 2021-06-22 | 郑州天迈科技股份有限公司 | Real-time extraction method for lane line parameters |
CN113077528A (en) * | 2020-01-06 | 2021-07-06 | 阿里巴巴集团控股有限公司 | Method and device for adding lane line and storage medium |
CN113537100A (en) * | 2021-07-22 | 2021-10-22 | 元橡科技(苏州)有限公司 | Vehicle auxiliary driving system, lane line space-time fitting system and method, and FPGA chip |
CN113988112A (en) * | 2021-12-08 | 2022-01-28 | 深圳佑驾创新科技有限公司 | Method, device and equipment for detecting lane line and storage medium |
CN114550118A (en) * | 2022-02-23 | 2022-05-27 | 烟台大学 | Full-automatic intelligent expressway marking method based on video image driving |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2001239478A1 (en) * | 2000-02-28 | 2001-11-22 | Glaxosmithkline Biologicals S.A. | Hybrid expression of neisserial proteins |
CN103198320A (en) * | 2013-04-24 | 2013-07-10 | 厦门大学 | Self-adaptive vision-aided driving device |
US20170039436A1 (en) * | 2015-08-03 | 2017-02-09 | Nokia Technologies Oy | Fusion of RGB Images and Lidar Data for Lane Classification |
CN107180228A (en) * | 2017-05-02 | 2017-09-19 | 开易(北京)科技有限公司 | A kind of grad enhancement conversion method and system for lane detection |
CN107330377A (en) * | 2017-06-08 | 2017-11-07 | 暨南大学 | A kind of virtual navigation channel in bridge collision prevention system is built and DEVIATION detection method |
CN107578012A (en) * | 2017-09-05 | 2018-01-12 | 大连海事大学 | A kind of drive assist system based on clustering algorithm selection sensitizing range |
CN107590438A (en) * | 2017-08-16 | 2018-01-16 | 中国地质大学(武汉) | A kind of intelligent auxiliary driving method and system |
CN108124102A (en) * | 2017-12-28 | 2018-06-05 | 北京小米移动软件有限公司 | Image processing method, device and computer readable storage medium |
CN108229386A (en) * | 2017-12-29 | 2018-06-29 | 百度在线网络技术(北京)有限公司 | For detecting the method, apparatus of lane line and medium |
CN108537142A (en) * | 2018-03-21 | 2018-09-14 | 华南理工大学 | A kind of method for detecting lane lines based on multiple color spaces |
CN109614884A (en) * | 2018-11-21 | 2019-04-12 | 江苏科技大学 | A kind of vehicle environmental cognitive method based on FPGA |
CN109657632A (en) * | 2018-12-25 | 2019-04-19 | 重庆邮电大学 | A kind of lane detection recognition methods |
CN109785291A (en) * | 2018-12-20 | 2019-05-21 | 南京莱斯电子设备有限公司 | A kind of lane line self-adapting detecting method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2001064922A2 (en) * | 2000-02-28 | 2001-09-07 | Chiron Spa | Heterologous expression of neisserial proteins |
-
2019
- 2019-07-26 CN CN201910684088.6A patent/CN110516550B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2001239478A1 (en) * | 2000-02-28 | 2001-11-22 | Glaxosmithkline Biologicals S.A. | Hybrid expression of neisserial proteins |
CN103198320A (en) * | 2013-04-24 | 2013-07-10 | 厦门大学 | Self-adaptive vision-aided driving device |
US20170039436A1 (en) * | 2015-08-03 | 2017-02-09 | Nokia Technologies Oy | Fusion of RGB Images and Lidar Data for Lane Classification |
CN107180228A (en) * | 2017-05-02 | 2017-09-19 | 开易(北京)科技有限公司 | A kind of grad enhancement conversion method and system for lane detection |
CN107330377A (en) * | 2017-06-08 | 2017-11-07 | 暨南大学 | A kind of virtual navigation channel in bridge collision prevention system is built and DEVIATION detection method |
CN107590438A (en) * | 2017-08-16 | 2018-01-16 | 中国地质大学(武汉) | A kind of intelligent auxiliary driving method and system |
CN107578012A (en) * | 2017-09-05 | 2018-01-12 | 大连海事大学 | A kind of drive assist system based on clustering algorithm selection sensitizing range |
CN108124102A (en) * | 2017-12-28 | 2018-06-05 | 北京小米移动软件有限公司 | Image processing method, device and computer readable storage medium |
CN108229386A (en) * | 2017-12-29 | 2018-06-29 | 百度在线网络技术(北京)有限公司 | For detecting the method, apparatus of lane line and medium |
CN108537142A (en) * | 2018-03-21 | 2018-09-14 | 华南理工大学 | A kind of method for detecting lane lines based on multiple color spaces |
CN109614884A (en) * | 2018-11-21 | 2019-04-12 | 江苏科技大学 | A kind of vehicle environmental cognitive method based on FPGA |
CN109785291A (en) * | 2018-12-20 | 2019-05-21 | 南京莱斯电子设备有限公司 | A kind of lane line self-adapting detecting method |
CN109657632A (en) * | 2018-12-25 | 2019-04-19 | 重庆邮电大学 | A kind of lane detection recognition methods |
Non-Patent Citations (6)
Title |
---|
ANANDHALLI 等: ""A novel approach in real-time vehicle detection and tracking using Raspberry Pi"", 《 ALEXANDRIA ENGINEERING JOURNAL》 * |
SAHAR MALMIR 等: ""Design and FPGA implementation of dual-stage 1 and detection based on Hough transform and localized stripe features"", 《MICROPROCESSORS AND MICROSYSTEMS》 * |
王文奇: ""基于数字图像处理的车道线检测算法研究"", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 * |
詹海浪: ""基于计算机视觉的车道线检测与交通路标识别"", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 * |
赵洋: ""基于多通道的高速并行采样信号重建算法研究"", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 * |
赵聃: ""基于车载视频的前驶车辆测速方法与应用研究"", 《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113077528A (en) * | 2020-01-06 | 2021-07-06 | 阿里巴巴集团控股有限公司 | Method and device for adding lane line and storage medium |
CN112329512B (en) * | 2020-08-11 | 2023-06-20 | 华南理工大学 | Intelligent recognition method for intelligent network connection model vehicle on-loop simulation sand table lane line |
CN112329512A (en) * | 2020-08-11 | 2021-02-05 | 华南理工大学 | Intelligent identification method for intelligent network combined model type vehicle on-loop simulation sand table lane line |
CN111914787A (en) * | 2020-08-11 | 2020-11-10 | 重庆文理学院 | Register configuration method for finger vein recognition SOC (system on chip) |
CN111914787B (en) * | 2020-08-11 | 2023-05-26 | 重庆文理学院 | Register configuration method for finger vein recognition SOC system |
CN112598762A (en) * | 2020-09-16 | 2021-04-02 | 禾多科技(北京)有限公司 | Three-dimensional lane line information generation method, device, electronic device, and medium |
CN112307953A (en) * | 2020-10-29 | 2021-02-02 | 无锡物联网创新中心有限公司 | Clustering-based adaptive inverse perspective transformation lane line identification method and system |
CN112613344A (en) * | 2020-12-01 | 2021-04-06 | 浙江大华汽车技术有限公司 | Vehicle lane occupation detection method and device, computer equipment and readable storage medium |
CN112613344B (en) * | 2020-12-01 | 2024-04-16 | 浙江华锐捷技术有限公司 | Vehicle track occupation detection method, device, computer equipment and readable storage medium |
CN113011293A (en) * | 2021-03-05 | 2021-06-22 | 郑州天迈科技股份有限公司 | Real-time extraction method for lane line parameters |
CN113011293B (en) * | 2021-03-05 | 2022-09-30 | 郑州天迈科技股份有限公司 | Real-time extraction method for lane line parameters |
CN113537100A (en) * | 2021-07-22 | 2021-10-22 | 元橡科技(苏州)有限公司 | Vehicle auxiliary driving system, lane line space-time fitting system and method, and FPGA chip |
CN113988112A (en) * | 2021-12-08 | 2022-01-28 | 深圳佑驾创新科技有限公司 | Method, device and equipment for detecting lane line and storage medium |
CN113988112B (en) * | 2021-12-08 | 2022-04-05 | 深圳佑驾创新科技有限公司 | Method, device and equipment for detecting lane line and storage medium |
CN114550118A (en) * | 2022-02-23 | 2022-05-27 | 烟台大学 | Full-automatic intelligent expressway marking method based on video image driving |
Also Published As
Publication number | Publication date |
---|---|
CN110516550B (en) | 2022-07-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110516550A (en) | A kind of lane line real-time detection method based on FPGA | |
CN107330376B (en) | Lane line identification method and system | |
CN108961235B (en) | Defective insulator identification method based on YOLOv3 network and particle filter algorithm | |
CN108648161B (en) | Binocular vision obstacle detection system and method of asymmetric kernel convolution neural network | |
CN109784333B (en) | Three-dimensional target detection method and system based on point cloud weighted channel characteristics | |
CN109615611B (en) | Inspection image-based insulator self-explosion defect detection method | |
CN109657632B (en) | Lane line detection and identification method | |
CN107045629A (en) | A kind of Multi-lane Lines Detection method | |
CN107492094A (en) | A kind of unmanned plane visible detection method of high voltage line insulator | |
CN104766071B (en) | A kind of traffic lights fast algorithm of detecting applied to pilotless automobile | |
CN110414385B (en) | Lane line detection method and system based on homography transformation and characteristic window | |
CN108038416A (en) | Method for detecting lane lines and system | |
CN108171695A (en) | A kind of express highway pavement detection method based on image procossing | |
CN108647664B (en) | Lane line detection method based on look-around image | |
CN116279592A (en) | Method for dividing travelable area of unmanned logistics vehicle | |
CN107194342A (en) | Method for detecting lane lines based on inverse perspective mapping | |
CN113762134A (en) | Method for detecting surrounding obstacles in automobile parking based on vision | |
CN104899898B (en) | Pavement detection method based on multidimensional information probabilistic model | |
CN112836573A (en) | Lane line image enhancement and completion method based on confrontation generation network | |
CN111241911A (en) | Self-adaptive lane line detection method | |
CN112926365A (en) | Lane line detection method and system | |
CN114972335A (en) | Image classification method and device for industrial detection and computer equipment | |
CN115187790A (en) | Image contour extraction method based on reference region binarization result | |
CN115034577A (en) | Electromechanical product neglected loading detection method based on virtual-real edge matching | |
CN110414386B (en) | Lane line detection method based on improved SCNN (traffic channel network) |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |