CN111931560B - Linear acceleration lane marking line detection method suitable for formula-free racing car - Google Patents
Linear acceleration lane marking line detection method suitable for formula-free racing car Download PDFInfo
- Publication number
- CN111931560B CN111931560B CN202010579870.4A CN202010579870A CN111931560B CN 111931560 B CN111931560 B CN 111931560B CN 202010579870 A CN202010579870 A CN 202010579870A CN 111931560 B CN111931560 B CN 111931560B
- Authority
- CN
- China
- Prior art keywords
- image
- line
- lane
- lines
- road
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method for detecting a straight acceleration lane marking line suitable for an unmanned formula racing car, which is mainly suitable for detecting a starting line and a terminating line of a racing track and detecting the lane marking line of the straight acceleration racing track, carries out graying processing on an image, adopts a Gaussian filter to remove noise, carries out road edge enhancement based on a Sobel operator, and obtains a road preprocessing image by carrying out binarization processing on the image; extracting the edges of the lane lines by using a Canny edge detection operator, then establishing a self-adaptive triangular interested area by combining the features of the lane lines, dividing the image into a left part and a right part, respectively fitting and identifying lane marking lines by using Hough transformation to detect the road boundary, and finally outputting two lane lines and overlapping the two lane lines into an original image; the invention can be applied to a driving auxiliary system in the field of unmanned driving, and casualty accidents caused by driver distraction are reduced.
Description
Technical Field
The invention relates to a method for detecting a mark line of a linear acceleration lane suitable for an unmanned formula racing car, and belongs to the technical field of unmanned driving.
Background
The Chinese college student unmanned equation competition integrates the top technology of unmanned vehicles, covers key technologies such as multivariate information fusion, visual SLAM, vehicle path planning and tracking and the like, wherein dynamic events comprise a linear acceleration test, an 8-shaped loop test, a controllability test (with people) and a high-speed tracking test, and the functions of perception, planning, decision making, control and the like of the participating vehicles are mainly tested; the linear acceleration dynamic race mainly tests the acceleration capability of the racing car, so the detection of the start line and the end line of the lane of the racing car and the detection of the lane line during the linear acceleration are particularly important, the lane line detection technology of the unmanned formula can be applied to a driving auxiliary system in the field of unmanned driving, and the detection method of the lane line is favorable for reducing casualty accidents caused by that a driver deviates from a normal race track due to the fact that the driver is not concentrated.
The current lane line detection method based on vision is mainly a method based on characteristics and a method based on a model, wherein the method based on characteristics is to extract the characteristics of textures, edges, color gradients and the like of roads from a gray image or a color image to detect lane lines; the model-based method is to adopt different parameter models to realize lane line detection according to different roads, and the model mainly comprises hyperbolic curves, spline curve models and the like; in addition, the interest area in the current road detection algorithm mainly adopts a fixed and unchangeable interest area which is usually rectangular, and the rectangular interest area has a large amount of useless areas, so that the calculation complexity is increased, the efficiency of the lane line detection algorithm is reduced, and the real-time detection of the vehicle-mounted video lane line detection algorithm on the front information of the road is difficult to meet; finally, because the road may have the factors of the defect of the lane marking line, serious pollution, easy road surface interference on the lane starting and stopping line and the like, and the existing algorithm based on the road model has the serious problems of weak adaptability, low recognition accuracy, interference and the like, the lane recognition algorithm with high recognition accuracy, good robustness and good real-time property is needed.
Disclosure of Invention
The invention provides a method for detecting the mark line of a linear acceleration lane suitable for an unmanned formula racing car, which reduces noise interference, improves algorithm speed and meets the real-time requirement of the unmanned racing car.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a method for detecting a straight acceleration lane marking line suitable for an unmanned formula racing car specifically comprises the following steps:
the first step is as follows: acquiring a road image based on the unmanned equation linear acceleration track video to obtain an initial line image;
the second step: preprocessing the initial line image, namely converting the color image into a gray image, performing gray processing, performing Gaussian filtering, extracting a threshold value by adopting an adaptive threshold method, and performing binarization processing on the initial line image to obtain an initial line preprocessed image;
the third step: performing Hough transform on the initial line image obtained by binarization processing, and detecting straight lines to obtain all possible straight lines in the initial line;
the fourth step: observing pixel values in the range of upper and lower fixed pixel points of all possible straight lines, recording a set of points which accord with color constraints and do not accord with the color constraints, calculating the proportion of the points which accord with the color constraints of each straight line, considering the points as initial lines if the proportion is greater than a set threshold value, sending a signal to a chassis control system of the racing car at the moment, starting the racing car, considering the points as non-initial lines if the proportion is less than or equal to the set threshold value, and returning to the first step for re-detection at the moment;
the fifth step: after the racing car is started, acquiring a lane line image, preprocessing the lane line image, namely converting a color image into a gray image, performing gray processing, performing Gaussian filtering processing, performing road edge enhancement based on a Sobel operator, eliminating useless messages in the lane line image, extracting a threshold value by adopting an adaptive threshold value method, and performing binarization processing on the lane line image to obtain a lane line preprocessed image;
and a sixth step: extracting the lane line edge by adopting a Canny edge detection operator;
the seventh step: establishing extraction of a triangular self-adaptive region of interest, and generating a road preprocessing image;
eighth step: dividing the road preprocessing image into a left image and a right image, and detecting left and right lane lines in the left image and the right image by using Hough transform;
the ninth step: superposing two lane lines output by the left image and the right image detection to the original image to obtain a termination line image;
the tenth step: preprocessing the terminating line image, namely converting the color image into a gray image, performing gray processing, performing Gaussian filtering processing, extracting a threshold value by adopting a self-adaptive threshold value method, and performing binarization processing on the terminating line image to obtain a pre-processed terminating line image;
the eleventh step: carrying out line termination detection based on Hough transform, transmitting the obtained feedback signal to a chassis control system of the racing car, braking the racing car and completing a linear accelerated match;
as a further preferred aspect of the present invention, the extracting the lane line edge by using a Canny edge detection operator in the sixth step specifically includes:
step 61, solving the brightness gradient of the lane line image, and detecting whether the road edge is a horizontal line, a vertical line or a diagonal line on the smooth lane line image by using Sobel along an x axis and a y axis;
step 62, adopting a non-maximum value inhibition idea to refine the edge, and detecting whether each pixel value is a local maximum value in the previously calculated gradient direction;
step 63, after non-maximum inhibition, confirming that the strong pixel is in the final edge mapping, analyzing the weak pixel, and confirming whether the weak pixel is a lane line edge or noise;
as a further preferred aspect of the present invention, the establishing of the extraction of the triangular adaptive region of interest in the seventh step, and the generating of the road preprocessing image specifically include:
step 71, setting a triangular initialization area in the first image after the lane line edge enhancement, and taking three points of the lower left corner, the lower right corner and the center of the top edge of the image of the triangular image as triangular fixed point coordinates;
step 72, filling all pixel values of the original image to be 0, wherein the pixels in the triangular area are filled to be 255, and the rest areas are reserved with 0, carrying out bitwise AND operation, and regenerating a road preprocessing image;
preferably, in the eighth step, the road preprocessed image is divided into a left image and a right image, hough transformation is sequentially performed on the left image and the right image to obtain a left lane line in the left image and a right lane line in the right image, hough transformation is performed on each pixel point in the region of interest of the image by using linear polar coordinates, duality relation between image space and hough parameter space is used for hough transformation, a straight line of a two-dimensional space is obtained by solving a curve intersection point of the hough space, and the conversion relation between the two-dimensional space and the hough space is that
ρ=x cosθ+y sinθ
In the formula, rho is the distance from an original point to a straight line in a Cartesian coordinate system, namely a polar diameter, theta is the included angle between the perpendicular line of the straight line and the x axis, and x and y are two-dimensional coordinates of pixel points on the straight line in an image;
wherein the angle theta is in the range of 0, 360]The range of the pole diameter is [0, rho ]max],ρmaxThe maximum value of the pole diameter can be determined by the following formula:
in the above formula, w is the width of the image, and h is the height of the image;
as a further preferred aspect of the present invention, the ρ and θ of all possible lane lines in the left image and the right image are respectively subjected to an average solution, two lane lines are output, and the two lane lines are superimposed into the original image;
as a further preferred aspect of the present invention, the road model assumption on which the lane line detection is based includes three types,
firstly, the left and right acceleration lane lines are assumed to be parallel, namely the left and right lane lines are assumed to be parallel in the near field range;
secondly, linear model hypothesis, namely that a left lane line and a right lane line in a supposed near-sight range can be fitted by a linear model;
thirdly, the lane continuity is assumed, that is, the lane line state is continuous assuming that there are virtual edge points in the break point area such as the broken lane line and the blocked lane line.
Through the technical scheme, compared with the prior art, the invention has the following beneficial effects:
1. in the traditional road detection algorithm, an interest area is mainly a fixed and unchangeable interest area which is usually rectangular and has a large amount of useless area;
2. aiming at the situations that a lane marking line is damaged and seriously polluted on a road and a lane starting and stopping line is easily interfered by a road surface, the FSAC lane line detection technology based on the improved Hough transformation and the lane starting and stopping line identification algorithm provided by the invention can improve the accuracy of algorithm identification, can reach 98 percent under the condition of good road condition, have good robustness and meet the real-time requirement of the unmanned racing car.
Drawings
The invention is further illustrated with reference to the following figures and examples.
FIG. 1 is a flow chart of a lane marking detection algorithm for formula racing unmanned vehicles according to the present invention;
FIG. 2 is a diagram of a triangular adaptive region of interest involved in the detection method provided by the present invention;
fig. 3 is a schematic diagram of a lane line superimposed on an original image in the detection method provided by the present invention.
Detailed Description
The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic views illustrating only the basic structure of the present invention in a schematic manner, and thus show only the constitution related to the present invention.
In the current road detection algorithm, the region of interest mainly adopts a fixed region of interest, and the region of interest is usually rectangular, so that a large amount of useless area exists in the rectangular region of interest, the calculation complexity is increased, the efficiency of the lane line detection algorithm is reduced, and meanwhile, because the lane marking line of the road is damaged and seriously polluted, the start and stop line of the lane is easily interfered by the road surface and other factors, the existing algorithm has the serious problems of low adaptability, low identification accuracy, interference and the like.
Based on the above problems in the prior art, the present application provides a method for detecting a straight acceleration lane marking line suitable for formula-free racing shown in fig. 1, and it should be noted that the method provided in the present application is based on the following three road model assumptions:
the first method comprises the following steps: the left and right acceleration lane lines are assumed to be parallel, namely the left and right lane lines are assumed to be parallel in the near field range;
and the second method comprises the following steps: linear model hypothesis, namely, the left lane line and the right lane line in the assumed near-sightedness range can be fitted by a linear model;
and the third is that: assuming lane continuity, namely assuming that virtual edge points exist in break point areas such as lane line breakage and shielding, and the like, and the lane line state is continuous;
under the assumption of the three road models, the method specifically comprises the following steps:
the first step is as follows: acquiring a road image based on the unmanned equation linear acceleration track video to obtain an initial line image;
in the application, the vehicle-mounted video acquisition equipment is arranged right above a designed unmanned formula racing car head and is fixed with a main ring of a racing car, the acquisition equipment is MANTAG-504C, the data processing platform is ARK-3520p, the optical axis of a camera is parallel to the plane of a chassis of the racing car, and the direction of the camera is the same as the running direction of the car; debugging hardware parameters such as camera aperture, exposure time, acquisition speed and the like before racing, adjusting the acquisition speed to 25 frames per second, dynamically setting the exposure time, and debugging the focal length and aperture of the camera to the optimal position to enable the acquired image to be in the clearest state;
the second step is that: preprocessing the initial line image, namely converting the color image into a gray image, performing gray processing, performing Gaussian filtering processing, extracting a threshold value by adopting a self-adaptive threshold value method, and performing binarization processing on the initial line image to obtain an initial line preprocessed image;
the third step: carrying out Hough transform on the initial line image obtained by binarization processing, and detecting straight lines to obtain all possible straight lines in the initial line;
the fourth step: observing pixel values in the range of upper and lower fixed pixel points of all possible straight lines, recording a set of points which accord with color constraints and do not accord with the color constraints, calculating the proportion of the points which accord with the color constraints of each straight line, considering the points as initial lines if the proportion is greater than a set threshold value, sending a signal to a chassis control system of the racing car at the moment, starting the racing car, considering the points as non-initial lines if the proportion is less than or equal to the set threshold value, and returning to the first step for re-detection at the moment;
the fifth step: after the racing car is started, acquiring a lane line image, preprocessing the lane line image, namely converting a color image into a gray image, performing gray processing, performing Gaussian filtering processing, performing road edge enhancement based on a Sobel operator, eliminating useless messages in the lane line image, extracting a threshold value by adopting an adaptive threshold value method, and performing binarization processing on the lane line image to obtain a lane line preprocessed image;
and a sixth step: adopting a Canny edge detection operator to extract the lane line edge to obtain the balance of noise suppression and edge detection, and detecting all possible lines in the image by detecting the direction with sharp change of brightness and larger gradient change and comparing the direction with a preset threshold value, wherein the method specifically comprises the following steps:
step 61, solving the brightness gradient of the lane line image, and detecting whether the road edge is a horizontal line, a vertical line or a diagonal line on the smooth lane line image by using Sobel along an x axis and a y axis;
step 62, adopting a non-maximum value inhibition idea to refine the edge, and detecting whether each pixel value is a local maximum value in the previously calculated gradient direction;
step 63, after non-maximum inhibition, confirming that the strong pixel is in the final edge mapping, analyzing the weak pixel, and confirming whether the weak pixel is a lane line edge or noise;
if the gradient is larger than the maximum threshold maxVal, the detection line is a road edge; if the gradient is smaller than the minimum threshold value minVal, detecting that the line is not the road edge and deleting the line; if the gradient is smaller than the maximum threshold maxVal and larger than the minimum threshold minVal, the edge is only formed when the edge is connected with the pixel of which the gradient is larger than the maximum threshold maxVal;
the seventh step: the method comprises the following steps of segmenting a road surface area to generate a triangular self-adaptive region of interest, knowing that the region of interest of a common lane line is the lower half part of an image according to the installation condition of a camera and the information of a shot image, mainly reducing noise generated by non-lane factors such as sky, road surface, trees and the like in other areas, mainly concentrating image processing on the triangular area of the lower half part of the image in order to reduce preprocessing time, and needing to perform interval constraint on parameters to obtain the region of interest, wherein the specific steps are as follows:
step 71, setting a triangle initialization area in the first image after the lane line edge is enhanced, manually designating a triangle to divide a road surface area, taking three points of the left lower corner, the right lower corner and the top edge center of the image of the triangle as triangle fixed point coordinates, reducing a search area, removing interference of other background areas such as sky and the like, and forming a triangle interesting area shown in fig. 2 in the first image;
step 72, filling all pixel values of the original image to be 0, wherein the pixels in the triangular area are filled to be 255, and the rest areas still keep 0, carrying out bitwise AND operation, and regenerating a road preprocessing image;
eighth step: dividing a road preprocessing image into a left image and a right image, sequentially carrying out Hough transformation on the left image and the right image to obtain a left lane line in the left image and a right lane line in the right image, adopting Hough transformation of a linear polar coordinate because the lane line of a racing car lane may be vertical to a bottom edge in the image, converting a two-dimensional space and a linear polar coordinate space in the image by utilizing the duality relation of an image space and a Hough parameter space, and mapping points in a Cartesian coordinate system to a Hough space curve; carrying out Hough transformation on each pixel point in the region of interest of the image, and solving the curve intersection point of Hough space to obtain a straight line of two-dimensional space, wherein the conversion relation between the two-dimensional space and the Hough space is
ρ=x cosθ+y sinθ
In the formula, rho is the distance from an original point to a straight line in a Cartesian coordinate system, namely a polar diameter, theta is the included angle between the perpendicular line of the straight line and an x axis, and x and y are two-dimensional coordinates of pixel points on the straight line in an image respectively;
wherein the angle theta is in the range of 0, 360]The range of the pole diameter is [0, rho ]max],ρmaxThe maximum value of the pole diameter can be determined by the following formula:
in the above formula, w is the width of the image, and h is the height of the image;
the ninth step: respectively carrying out average value solving on rho and theta of all possible lane lines in the left image and the right image, outputting two lane lines, superposing the two lane lines detected and output by the left image and the right image into the original image, and acquiring a termination line image as shown in FIG. 3;
the tenth step: preprocessing the stop line image, namely converting the color image into a gray image, performing graying processing, performing Gaussian filtering processing, extracting a threshold value by adopting an adaptive threshold method, and performing binarization processing on the stop line image to obtain a stop line preprocessed image;
the eleventh step: and (4) detecting the termination line based on Hough transform, transmitting the obtained feedback signal to a chassis control system of the racing car, braking the racing car and finishing the linear acceleration competition.
The unmanned formula lane line detection technology can be applied to a driving assistance system in the field of unmanned driving, and casualty accidents caused by driver distraction are reduced.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The meaning of "and/or" as used herein is intended to include both the individual components or both.
The term "connected" as used herein may mean either a direct connection between components or an indirect connection between components via other components.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (6)
1. A method for detecting a straight acceleration lane marking line suitable for an unmanned formula car is characterized by comprising the following steps of: the method specifically comprises the following steps:
the first step is as follows: acquiring a road image based on the unmanned equation linear acceleration track video to obtain an initial line image;
the second step: preprocessing the initial line image, namely converting the color image into a gray image, performing gray processing, performing Gaussian filtering processing, extracting a threshold value by adopting a self-adaptive threshold value method, and performing binarization processing on the initial line image to obtain an initial line preprocessed image;
the third step: carrying out Hough transform on the initial line image obtained by binarization processing, and detecting straight lines to obtain all possible straight lines in the initial line;
the fourth step: observing pixel values in the range of upper and lower fixed pixel points of all possible straight lines, recording a set of points which accord with color constraints and do not accord with the color constraints, calculating the proportion of the points which accord with the color constraints of each straight line, considering the points as initial lines if the proportion is greater than a set threshold value, sending a signal to a chassis control system of the racing car at the moment, starting the racing car, considering the points as non-initial lines if the proportion is less than or equal to the set threshold value, and returning to the first step for re-detection at the moment;
the fifth step: after the racing car is started, acquiring a lane line image, preprocessing the lane line image, namely converting a color image into a gray image, performing gray processing, performing Gaussian filtering processing, performing road edge enhancement based on a Sobel operator, eliminating useless messages in the lane line image, extracting a threshold value by adopting an adaptive threshold value method, and performing binarization processing on the lane line image to obtain a lane line preprocessed image;
and a sixth step: extracting the lane line edge by adopting a Canny edge detection operator;
the seventh step: establishing extraction of a triangular self-adaptive region of interest, and generating a road preprocessing image;
eighth step: dividing the road preprocessing image into a left image and a right image, and detecting left and right lane lines in the left image and the right image by using Hough transform;
the ninth step: superposing two lane lines output by the left image and the right image detection to the original image to obtain a termination line image;
the tenth step: preprocessing the terminating line image, namely converting the color image into a gray image, performing gray processing, performing Gaussian filtering processing, extracting a threshold value by adopting a self-adaptive threshold value method, and performing binarization processing on the terminating line image to obtain a pre-processed terminating line image;
the eleventh step: and (4) detecting the termination line based on Hough transform, transmitting the obtained feedback signal to a chassis control system of the racing car, braking the racing car and finishing the linear acceleration competition.
2. The method for detecting straight accelerating lane marking line of formula-free racing car as claimed in claim 1, wherein: the extracting the lane line edge by using a Canny edge detection operator in the sixth step specifically comprises the following steps:
step 61, solving the brightness gradient of the lane line image, and detecting whether the road edge is a horizontal line, a vertical line or a diagonal line on the smooth lane line image by using Sobel along an x axis and a y axis;
step 62, adopting a non-maximum value inhibition idea to refine the edge, and detecting whether each pixel value is a local maximum value in the previously calculated gradient direction;
and step 63, after non-maximum inhibition, confirming that the strong pixel is in the final edge mapping, analyzing the weak pixel, and confirming whether the weak pixel is a lane line edge or noise.
3. The method for detecting straight accelerating lane marking line of formula-free racing car as claimed in claim 2, wherein: the step seven of establishing the extraction of the triangular self-adaptive region of interest, and generating the road preprocessing image specifically includes:
step 71, setting a triangular initialization area in the first image after the lane line edge enhancement, and taking three points of the lower left corner, the lower right corner and the center of the top edge of the image of the triangular image as triangular fixed point coordinates;
and step 72, filling all pixel values of the original image to be 0, wherein the pixels in the triangular area are filled to be 255, and the rest areas are reserved with 0, carrying out bitwise AND operation, and regenerating the road preprocessing image.
4. The method for detecting straight accelerating lane marking line of formula-free racing car as claimed in claim 3, wherein: dividing the road preprocessing image into a left image and a right image in the eighth step, sequentially carrying out Hough transformation on the left image and the right image to obtain a left lane line in the left image and a right lane line in the right image, carrying out Hough transformation on each pixel point in the region of interest of the images by adopting linear polar coordinate Hough transformation and utilizing the duality relation between an image space and Hough parameter space, obtaining a straight line of a two-dimensional space by solving the curve intersection point of the Hough space, wherein the conversion relation between the two-dimensional space and the Hough space is
ρ=xcosθ+ysinθ
In the formula, rho is the distance from an original point to a straight line in a Cartesian coordinate system, namely a polar diameter, theta is the included angle between the perpendicular line of the straight line and an x axis, and x and y are two-dimensional coordinates of pixel points on the straight line in an image respectively;
wherein the angle theta is in the range of 0, 360]The range of the pole diameter is [0, rho ]max],ρmaxThe maximum value of the pole diameter can be determined by the following formula:
in the above formula, w represents the width of the image, and h represents the height of the image.
5. The method for detecting straight accelerating lane marking line of formula-free racing car as claimed in claim 4, wherein: and respectively carrying out average value solving on rho and theta of all possible lane lines in the left image and the right image, outputting two lane lines, and superposing the two lane lines into the original image.
6. The method for detecting straight accelerating lane marking line of formula-free racing car as claimed in claim 1, wherein: the aforementioned road model assumption on which lane line detection is based includes the following three,
firstly, the left and right acceleration lane lines are assumed to be parallel, namely the left and right lane lines are assumed to be parallel in the near field range;
secondly, linear model hypothesis, namely that a left lane line and a right lane line in a supposed near-sight range can be fitted by a linear model;
thirdly, the lane continuity is assumed, that is, virtual edge points exist in a break point area such as broken lane lines and blocked lane lines, and the lane line state is continuous.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010579870.4A CN111931560B (en) | 2020-06-23 | 2020-06-23 | Linear acceleration lane marking line detection method suitable for formula-free racing car |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010579870.4A CN111931560B (en) | 2020-06-23 | 2020-06-23 | Linear acceleration lane marking line detection method suitable for formula-free racing car |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111931560A CN111931560A (en) | 2020-11-13 |
CN111931560B true CN111931560B (en) | 2022-11-01 |
Family
ID=73317626
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010579870.4A Active CN111931560B (en) | 2020-06-23 | 2020-06-23 | Linear acceleration lane marking line detection method suitable for formula-free racing car |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111931560B (en) |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101608924B (en) * | 2009-05-20 | 2011-09-14 | 电子科技大学 | Method for detecting lane lines based on grayscale estimation and cascade Hough transform |
CN110298216B (en) * | 2018-03-23 | 2021-07-23 | 中国科学院沈阳自动化研究所 | Vehicle deviation alarm method based on lane line gradient image self-adaptive threshold segmentation |
CN109086671B (en) * | 2018-07-04 | 2021-05-11 | 同济大学 | Night lane marking line video detection method suitable for unmanned driving |
-
2020
- 2020-06-23 CN CN202010579870.4A patent/CN111931560B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN111931560A (en) | 2020-11-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108038416B (en) | Lane line detection method and system | |
CN108189838B (en) | A kind of pattern of fusion adaptive cruise curve control method and device | |
CN107330376B (en) | Lane line identification method and system | |
CN107862290B (en) | Lane line detection method and system | |
CN107577996A (en) | A kind of recognition methods of vehicle drive path offset and system | |
CN107590438A (en) | A kind of intelligent auxiliary driving method and system | |
CN101030256B (en) | Method and apparatus for cutting vehicle image | |
CN110298216A (en) | Vehicle deviation warning method based on lane line gradient image adaptive threshold fuzziness | |
CN107609486A (en) | To anti-collision early warning method and system before a kind of vehicle | |
CN108528336A (en) | A kind of vehicle crimping gives warning in advance system | |
CN110688903B (en) | Barrier extraction method based on train AEB system camera data | |
CN112800974A (en) | Subway rail obstacle detection system and method based on machine vision | |
CN109635737A (en) | Automobile navigation localization method is assisted based on pavement marker line visual identity | |
CN105933611A (en) | Dynamic envelope line drawing method for preventing camera jitter in rail foreign matter invasion recognition | |
Sun | Vision based lane detection for self-driving car | |
CN107798688A (en) | Motion estimate method, method for early warning and automobile anti-rear end collision prior-warning device | |
CN108284793A (en) | A kind of vehicle sub-controlling unit | |
CN111046741A (en) | Method and device for identifying lane line | |
CN111652033A (en) | Lane line detection method based on OpenCV | |
CN106803073B (en) | Auxiliary driving system and method based on stereoscopic vision target | |
CN109800641B (en) | Lane line detection method based on threshold value self-adaptive binarization and connected domain analysis | |
CN106340031A (en) | Method and device for detecting moving object | |
WO2019200937A1 (en) | System for performing effective identification of vehicle line pressing and giving early prompt | |
CN111931560B (en) | Linear acceleration lane marking line detection method suitable for formula-free racing car | |
DE102020213799A1 (en) | Obstacle detection device and obstacle detection method |
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 |