CN108629292B - Curved lane line detection method and device and terminal - Google Patents
Curved lane line detection method and device and terminal Download PDFInfo
- Publication number
- CN108629292B CN108629292B CN201810336585.2A CN201810336585A CN108629292B CN 108629292 B CN108629292 B CN 108629292B CN 201810336585 A CN201810336585 A CN 201810336585A CN 108629292 B CN108629292 B CN 108629292B
- Authority
- CN
- China
- Prior art keywords
- image
- sub
- line
- lane
- lane line
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The application provides a method, a device and a terminal for detecting a curved lane line, which relate to the technical field of assistant driving, wherein the method comprises the following steps: longitudinally dividing an edge binary image of a road image to be detected into a preset number of sub-images; determining a road vanishing point and a lane center line of the sub-image according to the candidate lane line detected in the sub-image in the edge binarization image; judging whether a curved part exists on the lane line according to the discrete degree of the road vanishing point and the slope of the lane center line; and if so, fitting a curve for representing the curved part of the lane line in the edge binary image. By applying the method, the curved lane line can be accurately detected, so that the lane departure early warning system is assisted to realize correct early warning as much as possible.
Description
Technical Field
The application relates to the technical field of assistant driving, in particular to a method, a device and a terminal for detecting a curved lane line.
Background
The Lane Departure Warning System (LDWS for short) is an important component in the advanced driving assistance field of automobiles, and can assist drivers to reduce traffic accidents caused by Lane Departure in an alarm manner, and Lane line detection is a core link in the work flow of the Lane Departure Warning System, so that the accuracy of the Lane line detection result directly affects the working effect of the Lane Departure Warning System.
At present, in a lane departure warning system, a straight line is fitted in a road image by using a traditional method, for example, a hough transform straight line detection method, and the fitted straight line is used as a lane line. However, a straight lane and a curved lane may exist in a real road, and when the curved lane exists in the real road, a lane line detected by using a conventional method is not accurate, so that the lane departure warning system cannot realize accurate warning.
Disclosure of Invention
In view of this, the present application provides a method, an apparatus, and a terminal for detecting a curved lane line, so as to accurately detect the curved lane line, thereby assisting a lane departure warning system to achieve correct warning as much as possible.
Specifically, the method is realized through the following technical scheme:
according to a first aspect of embodiments of the present application, there is provided a curved lane line detection method, the method including:
longitudinally dividing an edge binary image of a road image to be detected into a preset number of sub-images;
determining a road vanishing point and a lane center line of the sub-image according to the candidate lane line detected in the sub-image in the edge binarization image;
judging whether a curved part exists on the lane line according to the discrete degree of the road vanishing point and the slope of the lane center line;
and if so, fitting a curve for representing the curved part of the lane line in the edge binary image.
Optionally, the determining the road vanishing point and the lane center line of the sub-image according to the candidate lane lines detected in the sub-image includes:
determining road vanishing points of the sub-images according to the candidate lane lines detected in the sub-images;
determining a midpoint between the intersection points of the two candidate lane lines detected in the sub-image positioned at the bottommost part of the edge binary image and the lower boundary of the edge binary image as the midpoint of the lower boundary of the sub-image positioned at the bottommost part of the edge binary image;
determining an intersection point between a connecting line connecting the lower boundary midpoint of the sub-image positioned at the bottommost part of the edge binary image and the road vanishing point and the upper boundary of the sub-image positioned at the bottommost part of the edge binary image as the upper boundary midpoint of the sub-image positioned at the bottommost part of the edge binary image;
for other sub-images except the sub-image at the bottommost part of the edge binarization image, determining the middle point of the upper boundary of the sub-image immediately below the sub-image as the middle point of the lower boundary, and determining the intersection point between a connecting line connecting the middle point of the lower boundary and the road vanishing point and the upper boundary as the middle point of the upper boundary;
and for each sub-image, connecting the middle point of the upper boundary and the middle point of the lower boundary of the sub-image to obtain the lane center line of the sub-image.
Optionally, the determining whether a curved portion exists on the lane line according to the degree of dispersion of the road vanishing point and the slope of the lane line includes:
respectively calculating a first variance between X-axis coordinate values of vanishing points of each road and a second variance between slopes of center lines of each lane;
respectively comparing the first variance with a first preset threshold value, and comparing the second variance with a second preset threshold value;
and if the first variance is larger than the first preset threshold value and the second variance is larger than the second preset threshold value, determining that a curved part exists on the lane line, otherwise, determining that the curved part does not exist on the lane line.
Optionally, fitting a curve representing a curved portion of the lane line in the edge binarized image includes:
determining the corresponding position of the transition position of the curved part and the straight part of the lane line in the edge binary image;
determining a line range from the line of the corresponding position to the upper boundary of the edge binarization image as a designated line range;
determining pixel points corresponding to the curved part of the lane line in the specified line range;
and fitting a curve for representing the curved part of the lane line in the edge binarization image by using the pixel points corresponding to the curved part of the lane line.
Optionally, the determining the corresponding position of the transition position of the curved portion and the straight portion of the lane line in the edge binarized image includes:
traversing pixel points on the detected candidate lane lines line by line from the intersection point of the candidate lane line detected from the sub-image at the bottommost part of the edge binary image and the lower boundary of the edge binary image;
judging whether the currently traversed pixel point meets a set condition;
and if the currently traversed pixel point meets the set condition, determining the position of the currently traversed pixel point as the corresponding position of the transition position of the curved part and the straight part of the lane line in the edge binary image.
Optionally, the determining the pixel point corresponding to the curved portion of the lane line in the row range includes:
aiming at each pixel point on the lane central line in the specified line range, in the line where the pixel point is located, respectively searching pixel points with pixel values not being 0 leftwards and rightwards by taking the pixel point as a starting point;
and determining the found pixel point with the first pixel value not being 0 as the corresponding pixel point of the curved part of the lane line in the edge binarization image.
Optionally, the determining whether the currently traversed candidate pixel meets the set condition includes:
on the detected candidate lane line, taking the pixel points traversed currently as starting points, and selecting the pixel points upwards and downwards respectively;
respectively calculating the vertical distance between each selected pixel point and the candidate lane line detected in the sub-image positioned at the bottommost part of the edge binarization image;
and determining whether the currently traversed candidate pixel point meets a set condition according to the vertical distance corresponding to each pixel point.
According to a second aspect of embodiments of the present application, there is provided a curved lane line detecting device, the device including:
the segmentation module is used for longitudinally segmenting the edge binary image of the road image to be detected into a preset number of sub-images;
the detection module is used for determining the road vanishing point and the lane center line of the sub-image according to the candidate lane line detected in the sub-image in the edge binarization image;
the judging module is used for judging whether a curved part exists on the lane line according to the discrete degree of the road vanishing point and the slope of the lane line;
and the fitting module is used for fitting a curve for representing the curved part of the lane line in the edge binary image if the curved part exists on the lane line.
Optionally, the detection module includes:
a vanishing point determining submodule for determining road vanishing points of the sub-images according to the candidate lane lines detected in the sub-images;
a first determining submodule, configured to determine a midpoint between respective intersection points of two candidate lane lines detected in the sub-image located at the bottommost portion of the edge binarized image and the lower boundary of the edge binarized image as a lower boundary midpoint of the sub-image located at the bottommost portion of the edge binarized image;
the second determining submodule is used for determining an intersection point between a connecting line connecting the middle point of the lower boundary of the sub-image positioned at the bottommost part of the edge binary image and the road vanishing point and the upper boundary of the sub-image positioned at the bottommost part of the edge binary image as the middle point of the upper boundary of the sub-image positioned at the bottommost part of the edge binary image;
the third determining submodule is used for determining the middle point of the upper boundary of the sub-image immediately below the sub-image except the sub-image positioned at the bottommost part of the edge binarization image as the middle point of the lower boundary of the sub-image, and determining the intersection point between a connecting line connecting the middle point of the lower boundary and the road vanishing point of the sub-image and the upper boundary of the sub-image as the middle point of the upper boundary of the sub-image;
and the connecting submodule is used for connecting the middle point of the upper boundary and the middle point of the lower boundary of the sub-images aiming at each sub-image to obtain the lane middle line of the sub-image.
Optionally, the determining module includes:
the calculation submodule is used for calculating a first variance between X-axis coordinate values of the road vanishing points and a second variance between slopes of lane center lines;
the comparison submodule is used for respectively comparing the first variance with a first preset threshold value and the second variance with a second preset threshold value;
and the fourth determining submodule is used for determining that a curved part exists on the lane line if the first variance is larger than the first preset threshold value and the second variance is larger than the second preset threshold value, otherwise, determining that the curved part does not exist on the lane line.
Optionally, the fitting module includes:
the position determining submodule is used for determining the corresponding position of the transition position of the curved part and the straight part of the lane line in the edge binary image;
a line range determining submodule for determining a line range between the line of the corresponding position and the upper boundary of the edge binarization image as a designated line range;
the pixel point determining submodule is used for determining pixel points corresponding to the bent parts of the lane lines in the specified row range;
and the processing submodule is used for fitting a curve for representing the curved part of the lane line in the edge binary image by using the pixel points corresponding to the curved part of the lane line.
Optionally, the position determining sub-module includes:
the traversal submodule is used for traversing pixel points on the detected candidate lane lines line by line from the intersection point of the detected candidate lane line in the sub-image positioned at the bottommost part of the edge binary image and the lower boundary of the edge binary image;
the judgment submodule is used for judging whether the currently traversed pixel point meets the set condition;
and the fifth determining submodule is used for determining the position of the currently traversed pixel point as the corresponding position of the transition position of the curved part and the straight part of the lane line in the edge binary image if the currently traversed pixel point meets the set condition.
Optionally, the pixel point determining submodule includes:
the searching submodule is used for respectively searching pixel points with pixel values not being 0 leftwards and rightwards by taking the pixel points as starting points in a row where the pixel points are located aiming at the pixel points on the lane central line in the specified row range;
and the sixth determining submodule is used for determining the found pixel point with the first pixel value not being 0 as the corresponding pixel point of the curved part of the lane line in the edge binarization image.
Optionally, the determining sub-module includes:
the selection submodule is used for selecting pixel points upwards and downwards on the detected candidate lane line by taking the pixel points traversed currently as starting points;
the distance calculation submodule is used for respectively calculating the vertical distance between each selected pixel point and the candidate lane line detected in the sub-image positioned at the bottommost part of the edge binarization image;
and the seventh determining submodule is used for determining whether the currently traversed candidate pixel point meets the set condition according to the vertical distance corresponding to each pixel point.
According to a third aspect of the embodiments of the present application, there is provided a curved lane line detection terminal, including a memory, a processor, a communication interface, a camera assembly, and a communication bus;
the memory, the processor, the communication interface and the camera assembly are communicated with each other through the communication bus;
the camera assembly is used for collecting a road image to be detected and sending the road image to be detected to the processor through the communication bus;
the memory is used for storing a computer program;
the processor is configured to execute the computer program stored in the memory, and when the processor executes the computer program, the processor implements any one of the curved lane line detection methods provided in the embodiments of the present application.
According to a fourth aspect of the embodiments of the present application, there is provided a computer-readable storage medium having a computer program stored therein, where the computer program is executed by a processor to implement any one of the curved lane line detection methods provided by the embodiments of the present application.
It can be seen from the above embodiments that, by longitudinally dividing the edge binarized image of the road image to be detected into a preset number of sub-images, in the edge binarized image, determining the road vanishing point and the lane center line of the sub-images according to the candidate lane lines detected in the sub-images, and determining whether a curved portion exists on the lane line according to the degree of dispersion of the road vanishing point and the slope of the lane center line, if so, fitting a curve representing the curved portion of the lane line in the edge binarized image.
The edge binarization image is longitudinally divided into a preset number of sub-images, candidate lane lines are detected aiming at each sub-image, namely the lane lines are divided into a plurality of sections to be respectively detected, the detection range is reduced, the detection precision is improved, meanwhile, the road vanishing point and the lane center line of each sub-image are determined, whether the candidate lane lines in each sub-image deviate in the inclination degree can be judged according to the dispersion degree of the road vanishing point and the slope of the lane center line, whether curved parts exist on the lane lines is judged, when the curved parts exist, curves used for representing the curved parts on the lane lines are fitted in the edge binarization image aiming at the curved parts, and therefore the finally fitted lane lines can better reflect the real road condition.
In summary, the method for detecting the curved lane line can accurately detect the curved lane line, so that the lane departure early warning system can realize correct early warning as much as possible.
Drawings
FIG. 1 is a flowchart illustrating an embodiment of a curved lane line detection method according to an exemplary embodiment of the present disclosure;
FIG. 2 is an example of a gray scale image of a road image to be detected;
fig. 3 is an example of longitudinally dividing an edge binarized image into a preset number of sub-images;
fig. 4 is an example of a lane line candidate detected in the sub-image;
fig. 5 is another example of a lane line candidate detected in the sub-image;
FIG. 6 is a flowchart illustrating an embodiment of another curved lane line detection method according to an exemplary embodiment of the present disclosure;
FIG. 7 is a flowchart illustrating an embodiment of yet another curved lane line detection method according to an exemplary embodiment of the present application;
FIG. 8 is a schematic view of a complete lane line fitted using the curved lane line detection method provided herein;
fig. 9 is a block diagram of an embodiment of a curved lane line detection apparatus according to an exemplary embodiment of the present application;
fig. 10 is a hardware configuration diagram of a curved lane line detection terminal in which the curved lane line detection apparatus of the present application is located.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
Referring to fig. 1, a flowchart of an embodiment of a curved lane line detection method according to an exemplary embodiment of the present application is shown, where the method may include the following steps:
step 101: and longitudinally dividing the edge binary image of the road image to be detected into a preset number of sub-images.
In the embodiment of the present application, a camera may be used to collect road images, where the camera may be disposed on a vehicle, and is called a vehicle-mounted camera, and the camera may be a binocular camera or a monocular camera.
In the embodiment of the application, it is considered that the road image acquired by the vehicle-mounted camera includes not only the road surface, but also roadside buildings, distant sky, and the like, and other areas except the road surface are not the lane line detection areas, so in order to reduce the calculation amount of the lane departure warning system, an area of interest may be defined in the original road image, for example, the area of interest may be framed on the original road image by manually selecting a frame, and for example, a road missing line may be determined on the original road image, and from the road missing line, a portion to the lowest end of the road image is determined as the area of interest, so that the area of interest includes only the road surface as much as possible.
In the embodiment of the present application, the defined region of interest may be used as a road image to be detected, for example, as shown in fig. 2, the region of interest is an example of a grayscale image of the road image to be detected.
Further, the Canny edge detection algorithm can be utilized to process the road image to be detected, and an edge binarization image is obtained.
It should be noted that the above-mentioned obtaining of the edge binary image of the road image to be detected by using the Canny edge detection algorithm is only an example, and in practical applications, the edge binary image of the road image to be detected may also be obtained by using other algorithms, for example, Sobel, which is not limited in this application.
Further, the obtained edge binary image may be longitudinally divided into a preset number of sub-images, for example, into 4 sub-images, and in consideration of the law of "near-far-near-small" when the actual physical space is projected onto the image plane, the divided sub-images may be caused to exhibit a phenomenon of "narrow top and wide bottom", that is, the height of the sub-image is larger closer to the lower boundary of the edge binary image, for example, as shown in fig. 3, for an example of longitudinally dividing the edge binary image into the preset number of sub-images, in fig. 3, the edge binary image is longitudinally divided into 4 sub-images, and for the convenience of description, the 4 sub-images are respectively referred to as R1, R2, R3, and R4, and the height of the 4 sub-images satisfies the sequence of "R4 > R3 > R2 > R1".
It should be noted that, in order to effectively ensure the accuracy of the subsequent curved lane line detection, in this step, it is not suitable to divide the edge binarized image into a small number of sub-images, for example, into 2 sub-images, and at the same time, in order to effectively improve the working efficiency of the lane departure warning system, it is also not suitable to divide the edge binarized image into a large number of sub-images, as for the specific number of the sub-images obtained by division, a person skilled in the art may set the number according to the actual scene and the actual requirements, which is not limited in this application.
Step 102: in the edge binarization image, the road vanishing point and the lane center line of the sub-image are determined according to the candidate lane lines detected in the sub-image.
In the embodiment of the present application, hough transform straight line detection may be performed for each sub-image, and it is understood by those skilled in the art that the present application is performed for a lane line, and the lane line on the road surface generally has two left and right lines, so that two straight line segments may be detected in each sub-image, and the two straight line segments may be used as candidate lane lines, for example, as shown in fig. 4 and 5, which is an example of the candidate lane lines detected in the sub-image.
Subsequently, for the candidate lane lines detected in each sub-image, two candidate lane lines are extended above the edge binary image, and the intersection point of the two extension lines is the road vanishing point of the sub-image, for example, for convenience of description, the road vanishing point of the sub-image R1 is denoted as V1, the road vanishing point of the sub-image R2 is denoted as V2, the road vanishing point of the sub-image R3 is denoted as V3, the road vanishing point of the sub-image R4 is denoted as V4, see specifically fig. 4 and 5, in fig. 4, the road vanishing point of the 4 sub-images is located at the same position, in fig. 5, the sub-image R3 is located at the same position as the road vanishing point of the sub-image R4, and theoretically, by the camera internal parameters and the imaging principle, and the roads in the 4 sub-images are actually different areas on the same road surface, so that the road vanishing points of the 4 sub-images are located on the same horizontal line.
Further, determining a lane center line of each sub-image according to the road vanishing point, where the lane center line may be understood as a center line of an area surrounded by two candidate lane lines in the sub-image and upper and lower boundaries of the sub-image, and the specific process may be as follows:
the lane center lines of the respective sub-images are sequentially determined starting from the sub-image (e.g., the sub-image R4) located at the bottommost portion of the edge binarized image, and first, with respect to the sub-image R4, intersection points between each of the two candidate lane lines detected in the sub-image R4 and the lower boundary of the edge binarized image are determined, and then a midpoint between the two intersection points is determined, for example, as illustrated in fig. 4 and fig. 5 as P4, which is determined as the lower boundary midpoint of the sub-image R4.
Thereafter, the middle point of the lower boundary of the sub-image R4 is connected to the road vanishing point V4 thereof, and the intersection between the connection line and the upper boundary of the sub-image R4, for example, P3 as illustrated in fig. 4 and 5, is determined as the middle point of the upper boundary of the sub-image R4.
Further, for the sub-image R3, the upper boundary midpoint of the sub-image R4, i.e., P3, immediately below the sub-image R3 is determined as the lower boundary midpoint of the sub-image R3, and subsequently, the lower boundary midpoint P3 of the sub-image R3 is connected to the road vanishing point V3 thereof, and the intersection point between the connection line and the upper boundary of the sub-image R3, e.g., P2 as illustrated in fig. 4 and 5, is determined as the upper boundary midpoint of the sub-image R3.
Further, for the sub-image R2, the upper boundary midpoint of the sub-image R3, i.e., P2, immediately below the sub-image R2 is determined as the lower boundary midpoint of the sub-image R2, and subsequently, the lower boundary midpoint P2 of the sub-image R2 is connected to the road vanishing point V2 thereof, and the intersection point between the connection line and the upper boundary of the sub-image R2, e.g., P1 as illustrated in fig. 4 and 5, is determined as the upper boundary midpoint of the sub-image R2.
Further, for the sub-image R1, the upper boundary midpoint of the sub-image R2, i.e., P1, immediately below the sub-image R1 is determined as the lower boundary midpoint of the sub-image R1, and subsequently, the lower boundary midpoint P1 of the sub-image R1 is connected to the road vanishing point V1 thereof, and the intersection point between the connection line and the upper boundary of the sub-image R1, e.g., P0 as illustrated in fig. 4 and 5, is determined as the upper boundary midpoint of the sub-image R1.
Finally, for each sub-image, connecting the middle point of the upper boundary and the middle point of the lower boundary of the sub-image, i.e. as shown in fig. 4 and 5, the lane middle line of the sub-image R1 is "P0-P1", the lane middle line of the sub-image R2 is "P1-P2", the lane middle line of the sub-image R3 is "P2-P3", and the lane middle line of the sub-image R4 is "P3-P4".
Step 103: and judging whether a curved part exists on the lane line according to the discrete degree of the road vanishing point and the slope of the lane center line.
In this step, the flow of the embodiment illustrated in fig. 6 may be executed to determine whether or not there is a curved portion on the lane line.
Referring to fig. 6, a flowchart of another embodiment of a curved lane line detection method according to an exemplary embodiment of the present application is shown, where the method may include the following steps:
step 601: a first variance between X-axis coordinate values of the road vanishing points is calculated.
Step 602: comparing the first variance with a first preset threshold, and if the first variance is not greater than the first preset threshold, executing step 606; if the comparison result shows that the first variance is greater than the first preset threshold, step 603 is executed.
Step 603: a second variance between the slopes of the center lines of the respective lanes is calculated.
Step 604: comparing the second variance with a second preset threshold, and if the second variance is greater than the second preset threshold, executing step 605; if the comparison result shows that the second variance is not greater than the second preset threshold, step 606 is executed.
Step 605: the presence of a curved portion on the lane line is determined.
Step 606: it is determined that there is no curved portion on the lane line.
The above steps 601 to 606 are explained in detail as follows:
first, in the embodiment of the present application, the image coordinate system is based on the upper left corner of the image as the origin, the horizontal right direction as the positive X-axis direction, and the horizontal down direction as the positive Y-axis direction, for example, as shown in fig. 2.
As can be seen from the above description, the road vanishing points of the sub-images are located on the same horizontal line even if they are not located at the same position, that is, the Y-axis coordinate values of the road vanishing points of the sub-images are the same, based on this, in this embodiment of the present application, the variance between the X-axis coordinate values of the road vanishing points can be calculated.
Based on this, in the embodiment of the present application, a first preset threshold may be set, the first variance is compared with the first preset threshold, if the first variance is not greater than the first preset threshold, it may be considered that the distribution of the road vanishing points is concentrated, for example, as shown in fig. 4, then step 606 is performed, that is, it is determined that the real lane line is a straight line and there is no curved portion, at this time, the detected lane line may be as shown in fig. 4; if the comparison result shows that the first variance is greater than the first preset threshold, it may be preliminarily determined that the distribution of the road vanishing points is more dispersed, for example, as shown in fig. 5, at this time, in order to more accurately determine whether a curved portion exists on the lane line, the subsequent step 603 may be continuously performed.
In step 603, the slopes of the center lines of the respective lanes are calculated, and further, the variance between the respective slopes, which may be referred to as a second variance for convenience of description, is calculated.
In step 604, the second variance is compared with a second preset threshold, if the second variance is greater than the second preset threshold, the inclination degrees of the lane center lines of different sub-images may be considered to be different greatly, for example, as shown in fig. 5, and then step 605 is performed, i.e., it is determined that a curved portion exists on the lane line; if the comparison shows that the second variance is not greater than the second preset threshold, the inclination degrees of the lane center lines of the different sub-images may be considered to be smaller, for example, as shown in fig. 4, and then step 606 is performed, i.e., it is determined that there is no curved portion on the lane line.
Step 104: if the curve exists, a curve representing the curved portion of the lane line is fitted to the edge binarized image.
In this step, the flow of the embodiment illustrated in fig. 7 may be performed to fit a curve representing a curved portion of the lane line in the edge binarized image.
Referring to fig. 7, a flowchart of another embodiment of a curved lane line detection method according to an exemplary embodiment of the present application is shown, where the method may include the following steps:
step 701: and determining the corresponding position of the transition position of the curved part and the straight part of the lane line in the edge binary image.
First, it is understood by those skilled in the art that when there is a curved portion on a lane line, it may be considered that, in visual effect, the near lane line is close to a straight line and is a straight line portion, and the far lane line shows a distinct curve and is a curved portion, then, in order to detect a curve corresponding to the curved portion in the edge binary image, a corresponding position of a transition position of the curved portion and the straight line portion of the lane line in the edge binary image may be determined first, and a specific process of determining the corresponding position may include:
from the intersection point of the left candidate lane line detected in the sub-image R4 and the lower boundary of the edge binarization image, traversing line by line the pixel points on the left candidate lane line detected in the above step 102, determining whether the currently traversed pixel point satisfies the set condition, and if so, determining the position of the currently traversed pixel point as the corresponding position of the transition position of the curved portion and the straight portion of the lane line in the edge binarization.
The process of determining whether the currently traversed pixel meets the set condition may include: on the detected candidate lane line on the left side, taking the currently traversed pixel point as a starting point, and selecting a preset number of pixel points upwards and downwards respectively according to a preset line interval, for example, selecting a candidate pixel point every other line upwards and downwards respectively, and selecting 5 candidate pixel points up and down respectively.
Subsequently, the vertical distance between each selected candidate pixel point and the extended line of the candidate lane line detected in the sub-image R4 is calculated, for example, as shown in fig. 5, if the point p is the selected candidate pixel point, and d represents the vertical distance between the candidate pixel point and the extended line of the candidate lane line detected in the sub-image R4.
Subsequently, whether the currently traversed pixel point meets a set condition is determined based on the calculated vertical distances, wherein the set condition can be: the vertical distance corresponding to the candidate pixel point selected below the currently traversed pixel point is close to 0, for example, smaller than a preset distance threshold, while the vertical distance corresponding to the candidate pixel point selected above the currently traversed pixel point is larger, for example, larger than the preset distance threshold, and the closer the selected candidate pixel point is to the upper boundary of the edge binarization image, the larger the corresponding vertical distance is.
For example, as shown in fig. 5, assuming that the currently traversed pixel point is k, 5 candidate pixel points are selected above the pixel point, and 5 candidate pixel points are selected below the pixel point, it can be known from fig. 5 that the vertical distances corresponding to the 5 candidate pixel points selected above the pixel point are greater than 0 and increase, and the vertical distances corresponding to the 5 candidate pixel points selected below the pixel point are almost 0, and it can be known from the above description that the pixel point k satisfies the setting condition, and the location of the pixel point k is the corresponding location of the transition location of the curved portion and the straight portion of the real lane line in the edge binary image.
Step 702: and determining the line range from the line of the corresponding position to the upper boundary of the edge binary image as the designated line range.
After determining the corresponding position of the transition position of the curved portion and the straight portion of the lane line in the edge binarized image, the belonging line of the corresponding position is determined, for example, as shown in fig. 5, assuming that the line r0 represents the belonging line of the corresponding position, and subsequently, the line range from the belonging line to the upper boundary of the edge binarized image may be determined as the specified line range.
Step 703: and determining pixel points corresponding to the curved part of the lane line in the specified line range.
In this step, for each pixel point on the lane central line within the specified line range, such as "P0-P1" and "P1-P2", with the pixel point as the starting point, in the line where the pixel point is located, pixel points with pixel values not 0 are respectively searched for left and right, and the searched pixel point with the first pixel value not 0 is determined as the corresponding pixel point of the curved portion of the lane line in the edge binary image.
Step 704: and fitting a curve for representing the curved part of the lane line in the edge binary image by using the pixel points corresponding to the curved part of the lane line.
In the embodiment of the present application, after determining the corresponding pixel points of the curved portion of the real lane line in the edge binary image, a curve corresponding to the curved portion of the real lane line in the edge binary image may be fitted to the pixel points by using a RANSAC (RANdom Sample Consensus) method.
Furthermore, as will be understood by those skilled in the art, for the straight line portion of the lane line, the candidate lane line detected in step 102 may be used as the lane line corresponding to the straight line portion, and finally, the complete lane line fitted in the edge binary image may be as shown in fig. 8.
It can be seen from the above embodiments that, by longitudinally dividing the edge binarized image of the road image to be detected into a preset number of sub-images, in the edge binarized image, determining the road vanishing point and the lane center line of the sub-images according to the candidate lane lines detected in the sub-images, and determining whether a curved portion exists on the lane line according to the degree of dispersion of the road vanishing point and the slope of the lane center line, if so, fitting a curve representing the curved portion of the lane line in the edge binarized image.
The edge binarization image is longitudinally divided into a preset number of sub-images, candidate lane lines are detected aiming at each sub-image, namely the lane lines are divided into a plurality of sections to be respectively detected, the detection range is reduced, the detection precision is improved, meanwhile, the road vanishing point and the lane center line of each sub-image are determined, whether the candidate lane lines in each sub-image deviate in the inclination degree can be judged according to the dispersion degree of the road vanishing point and the slope of the lane center line, whether curved parts exist on the lane lines is judged, when the curved parts exist, curves used for representing the curved parts on the lane lines are fitted in the edge binarization image aiming at the curved parts, and therefore the finally fitted lane lines can better reflect the real road condition.
In summary, the method for detecting the curved lane line can accurately detect the curved lane line, so that the lane departure early warning system can realize correct early warning as much as possible.
Corresponding to the embodiment of the method for detecting the curved lane line, the application also provides an embodiment of a device for detecting the curved lane line.
Referring to fig. 9, a block diagram of an embodiment of a curved lane line detection apparatus according to an exemplary embodiment of the present application is provided, where the apparatus may include: a segmentation module 91, a detection module 92, a judgment module 93 and a fitting module 94.
The segmentation module 91 may be configured to longitudinally segment the edge binarized image of the road image to be detected into a preset number of sub-images;
the detection module 92 may be configured to determine, in the edge binarization image, a road vanishing point and a lane center line of the sub-image according to the candidate lane lines detected in the sub-image;
the judging module 93 may be configured to judge whether a curved portion exists on a lane line according to the degree of dispersion of the road vanishing point and the slope of the lane center line;
the fitting module 94 may be configured to fit a curve representing a curved portion of the lane line in the edge binarized image if the curved portion exists on the lane line.
In one embodiment, the detection module 92 may include (not shown in fig. 9):
a vanishing point determining submodule for determining road vanishing points of the sub-images according to the candidate lane lines detected in the sub-images;
a first determining submodule, configured to determine a midpoint between respective intersection points of two candidate lane lines detected in the sub-image located at the bottommost portion of the edge binarized image and the lower boundary of the edge binarized image as a lower boundary midpoint of the sub-image located at the bottommost portion of the edge binarized image;
the second determining submodule is used for determining an intersection point between a connecting line connecting the middle point of the lower boundary of the sub-image positioned at the bottommost part of the edge binary image and the road vanishing point and the upper boundary of the sub-image positioned at the bottommost part of the edge binary image as the middle point of the upper boundary of the sub-image positioned at the bottommost part of the edge binary image;
the third determining submodule is used for determining the middle point of the upper boundary of the sub-image immediately below the sub-image except the sub-image positioned at the bottommost part of the edge binarization image as the middle point of the lower boundary of the sub-image, and determining the intersection point between a connecting line connecting the middle point of the lower boundary and the road vanishing point of the sub-image and the upper boundary of the sub-image as the middle point of the upper boundary of the sub-image;
and the connecting submodule is used for connecting the middle point of the upper boundary and the middle point of the lower boundary of the sub-images aiming at each sub-image to obtain the lane middle line of the sub-image.
In one embodiment, the determining module 93 may include (not shown in fig. 9):
the calculation submodule is used for calculating a first variance between X-axis coordinate values of the road vanishing points and a second variance between slopes of lane center lines;
the comparison submodule is used for respectively comparing the first variance with a first preset threshold value and the second variance with a second preset threshold value;
and the fourth determining submodule is used for determining that a curved part exists on the lane line if the first variance is larger than the first preset threshold value and the second variance is larger than the second preset threshold value, otherwise, determining that the curved part does not exist on the lane line.
In one embodiment, the fitting module 94 may include (not shown in fig. 9):
the position determining submodule is used for determining the corresponding position of the transition position of the curved part and the straight part of the lane line in the edge binary image;
a line range determining submodule for determining a line range between the line of the corresponding position and the upper boundary of the edge binarization image as a designated line range;
the pixel point determining submodule is used for determining pixel points corresponding to the bent parts of the lane lines in the specified row range;
and the processing submodule is used for fitting a curve for representing the curved part of the lane line in the edge binary image by using the pixel points corresponding to the curved part of the lane line.
In an embodiment, the position determination sub-module may include (not shown in fig. 9):
the traversal submodule is used for traversing pixel points on the detected candidate lane lines line by line from the intersection point of the detected candidate lane line in the sub-image positioned at the bottommost part of the edge binary image and the lower boundary of the edge binary image;
the judgment submodule is used for judging whether the currently traversed pixel point meets the set condition;
and the fifth determining submodule is used for determining the position of the currently traversed pixel point as the corresponding position of the transition position of the curved part and the straight part of the lane line in the edge binary image if the currently traversed pixel point meets the set condition.
In an embodiment, the pixel point determination submodule may include (not shown in fig. 9):
the searching submodule is used for respectively searching pixel points with pixel values not being 0 leftwards and rightwards by taking the pixel points as starting points in a row where the pixel points are located aiming at the pixel points on the lane central line in the specified row range;
and the sixth determining submodule is used for determining the found pixel point with the first pixel value not being 0 as the corresponding pixel point of the curved part of the real lane line in the edge binarization image.
In an embodiment, the determining sub-module may include (not shown in fig. 9):
the selection submodule is used for selecting pixel points upwards and downwards on the detected candidate lane line by taking the pixel points traversed currently as starting points;
the distance calculation submodule is used for respectively calculating the vertical distance between each selected pixel point and the candidate lane line detected in the sub-image positioned at the bottommost part of the edge binarization image;
and the seventh determining submodule is used for determining whether the currently traversed candidate pixel point meets the set condition according to the vertical distance corresponding to each pixel point.
The embodiment of the curved lane line detection device can be applied to a curved lane line detection terminal. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. The device in the logic meaning is formed by reading corresponding computer program instructions in the nonvolatile memory into the memory for operation through the processor of the curved lane line detection terminal where the device is located. From a hardware aspect, as shown in fig. 10, a hardware structure diagram of a curved lane line detection terminal where the curved lane line detection device of the present application is located is shown, where a processor 1001 is a control center of the curved lane line detection terminal 1000, connects various parts of the entire curved lane line detection device by using various interfaces and lines, and executes various functions and processes data of the curved lane line detection device 1000 by running or executing software programs and/or modules stored in a memory 1002 and calling the data stored in the memory 1002, thereby performing overall monitoring of the curved lane line detection device.
Optionally, processor 1001 may include (not shown in fig. 10) one or more processing cores; optionally, the processor 1001 may integrate an application processor and a modem processor, wherein the application processor mainly handles operating systems, user interfaces, application programs, and the like, and the modem processor mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 1001.
The memory 1002 may be used to store software programs and modules, and the processor 1001 executes various functional applications and data processing by operating the software programs and modules stored in the memory 1002. The memory 1002 mainly includes (not shown in fig. 10) a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created by the curved lane line detection apparatus 1000 (such as a collected road image to be detected, a calculated edge binary image, or a processed grayscale image), and the like.
In addition, the memory 1002 may include (not shown in FIG. 10) high-speed random access memory, and may also include (not shown in FIG. 10) non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 1002 may also include (not shown in fig. 10) a memory controller to provide the processor 1001 access to the memory 1002.
In some embodiments, the apparatus 1000 may further include: a peripheral interface 1003 and at least one peripheral. Processor 1001, memory 1002 and peripheral interface 1003 may be connected by a communication bus or signal line (not shown in fig. 10). Various peripheral devices may be connected to peripheral interface 1003 by communication buses or signal lines. Specifically, the peripheral device may include: at least one of a radio frequency component 1004, a touch screen display 1005, a camera component 1006, an audio component 1007, a positioning component 1008, and a power component 1009.
The camera assembly 1006 is used for collecting an image of a road to be detected.
In some embodiments, camera assembly 1006 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.
In addition to the hardware illustrated in fig. 10, the curved lane line detection terminal where the device is located in the embodiment may also include other hardware generally according to the actual function of the terminal, which is not described again.
It can be understood by those skilled in the art that the curved lane line detection terminal illustrated in fig. 10 can be applied to an automobile, and can also be applied to other devices such as a computer and a smart phone, which is not limited in the present application.
The embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the computer program implements any of the curved lane line detection methods provided in the embodiments of the present application.
The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (9)
1. A curved lane line detection method, the method comprising:
longitudinally dividing an edge binary image of a road image to be detected into a preset number of sub-images;
determining a road vanishing point of the sub-image according to the candidate lane line detected in the sub-image in the edge binarization image; determining a midpoint between the intersection points of the two candidate lane lines detected in the sub-image positioned at the bottommost part of the edge binary image and the lower boundary of the edge binary image as the midpoint of the lower boundary of the sub-image positioned at the bottommost part of the edge binary image; determining an intersection point between a connecting line connecting the middle point of the lower boundary of the sub-image at the bottommost part of the edge binary image and the road vanishing point and the upper boundary of the sub-image at the bottommost part of the edge binary image as the middle point of the upper boundary of the sub-image at the bottommost part of the edge binary image; for other sub-images except the sub-image at the bottommost part of the edge binarization image, determining the middle point of the upper boundary of the sub-image immediately below the sub-image as the middle point of the lower boundary, and determining the intersection point between a connecting line connecting the middle point of the lower boundary and the road vanishing point and the upper boundary as the middle point of the upper boundary; for each sub-image, connecting the middle point of the upper boundary and the middle point of the lower boundary of the sub-image to obtain the lane center line of the sub-image;
judging whether a curved part exists on the lane line according to the discrete degree of the road vanishing point and the slope of the lane center line;
and if so, fitting a curve for representing the curved part of the lane line in the edge binary image.
2. The method according to claim 1, wherein the determining whether a curved portion exists on a lane line according to the degree of dispersion of the road vanishing points and the slope of the lane line comprises:
respectively calculating a first variance between X-axis coordinate values of vanishing points of each road and a second variance between slopes of center lines of each lane;
respectively comparing the first variance with a first preset threshold value, and comparing the second variance with a second preset threshold value;
and if the first variance is larger than the first preset threshold value and the second variance is larger than the second preset threshold value, determining that a curved part exists on the lane line, otherwise, determining that the curved part does not exist on the lane line.
3. The method according to claim 1, wherein fitting a curve representing a curved portion of the lane line in the edge binarized image comprises:
determining the corresponding position of the transition position of the curved part and the straight part of the lane line in the edge binary image;
determining a line range from the line of the corresponding position to the upper boundary of the edge binarization image as a designated line range;
determining pixel points corresponding to the curved part of the lane line in the specified line range;
and fitting a curve for representing the curved part of the lane line in the edge binarization image by using the pixel points corresponding to the curved part of the lane line.
4. The method according to claim 3, wherein the determining the corresponding position of the transition position of the curved part and the straight part of the lane line in the edge binarized image comprises:
traversing pixel points on the detected candidate lane lines line by line from the intersection point of the candidate lane line detected from the sub-image at the bottommost part of the edge binary image and the lower boundary of the edge binary image;
judging whether the currently traversed pixel point meets a set condition;
and if the currently traversed pixel point meets the set condition, determining the position of the currently traversed pixel point as the corresponding position of the transition position of the curved part and the straight part of the lane line in the edge binary image.
5. The method of claim 3, wherein the determining pixel points corresponding to curved portions of the lane lines within the row range comprises:
aiming at each pixel point on the lane central line in the specified line range, in the line where the pixel point is located, respectively searching pixel points with pixel values not being 0 leftwards and rightwards by taking the pixel point as a starting point;
and determining the found pixel point with the first pixel value not being 0 as the corresponding pixel point of the curved part of the lane line in the edge binarization image.
6. The method according to claim 4, wherein the determining whether the currently traversed candidate pixel meets a predetermined condition includes:
on the detected candidate lane line, taking the pixel points traversed currently as starting points, and selecting the pixel points upwards and downwards respectively;
respectively calculating the vertical distance between each selected pixel point and the candidate lane line detected in the sub-image positioned at the bottommost part of the edge binarization image;
and determining whether the currently traversed candidate pixel point meets a set condition according to the vertical distance corresponding to each pixel point.
7. A curved lane line detection apparatus, comprising:
the segmentation module is used for longitudinally segmenting the edge binary image of the road image to be detected into a preset number of sub-images;
the detection module is used for determining road vanishing points of the sub-images according to the candidate lane lines detected in the sub-images in the edge binarization image; determining a midpoint between the intersection points of the two candidate lane lines detected in the sub-image positioned at the bottommost part of the edge binary image and the lower boundary of the edge binary image as the midpoint of the lower boundary of the sub-image positioned at the bottommost part of the edge binary image; determining an intersection point between a connecting line connecting the middle point of the lower boundary of the sub-image at the bottommost part of the edge binary image and the road vanishing point and the upper boundary of the sub-image at the bottommost part of the edge binary image as the middle point of the upper boundary of the sub-image at the bottommost part of the edge binary image; for other sub-images except the sub-image at the bottommost part of the edge binarization image, determining the middle point of the upper boundary of the sub-image immediately below the sub-image as the middle point of the lower boundary, and determining the intersection point between a connecting line connecting the middle point of the lower boundary and the road vanishing point and the upper boundary as the middle point of the upper boundary; for each sub-image, connecting the middle point of the upper boundary and the middle point of the lower boundary of the sub-image to obtain the lane center line of the sub-image;
the judging module is used for judging whether a curved part exists on the lane line according to the discrete degree of the road vanishing point and the slope of the lane line;
and the fitting module is used for fitting a curve for representing the curved part of the lane line in the edge binary image if the curved part exists on the lane line.
8. A curved lane line detection terminal is characterized by comprising a memory, a processor, a communication interface, a camera assembly and a communication bus;
the memory, the processor, the communication interface and the camera assembly are communicated with each other through the communication bus;
the camera assembly is used for collecting a road image to be detected and sending the road image to be detected to the processor through the communication bus;
the memory is used for storing a computer program;
the processor is configured to execute the computer program stored in the memory, and when the processor executes the computer program, the processor implements the method according to any one of claims 1 to 6.
9. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810336585.2A CN108629292B (en) | 2018-04-16 | 2018-04-16 | Curved lane line detection method and device and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810336585.2A CN108629292B (en) | 2018-04-16 | 2018-04-16 | Curved lane line detection method and device and terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108629292A CN108629292A (en) | 2018-10-09 |
| CN108629292B true CN108629292B (en) | 2022-02-18 |
Family
ID=63705181
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810336585.2A Active CN108629292B (en) | 2018-04-16 | 2018-04-16 | Curved lane line detection method and device and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108629292B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111191487A (en) * | 2018-11-14 | 2020-05-22 | 北京市商汤科技开发有限公司 | Lane line detection and driving control method and device and electronic equipment |
| CN109685764B (en) * | 2018-11-19 | 2020-10-30 | 深圳市维图视技术有限公司 | Product positioning method and device and terminal equipment |
| CN109886131B (en) * | 2019-01-24 | 2023-05-02 | 淮安信息职业技术学院 | Road curve recognition method and device |
| CN109835337B (en) * | 2019-02-27 | 2021-02-19 | 北京海纳川汽车部件股份有限公司 | Turning control method and device and automatic driving vehicle |
| CN109978903B (en) * | 2019-03-13 | 2021-04-16 | 浙江大华技术股份有限公司 | Identification point identification method and device, electronic equipment and storage medium |
| CN110598517B (en) * | 2019-06-25 | 2023-11-24 | 一汽奔腾轿车有限公司 | Method for detecting lane departure of curve |
| CN111210411B (en) * | 2019-12-31 | 2024-04-05 | 驭势科技（浙江）有限公司 | Method for detecting vanishing points in image, method for training detection model and electronic equipment |
| CN113156929B (en) * | 2020-01-06 | 2024-02-23 | 苏州宝时得电动工具有限公司 | Self-moving equipment |
| CN112639814B (en) * | 2020-05-29 | 2022-02-11 | 华为技术有限公司 | Road condition detection method and device |
| CN112465925A (en) * | 2020-11-20 | 2021-03-09 | 北京赛目科技有限公司 | Method and device for processing lane line for simulation test |
| CN112733713B (en) * | 2021-01-08 | 2024-02-13 | 北京全路通信信号研究设计院集团有限公司 | Method for extracting track line from image based on image gradient angle |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014133868A1 (en) * | 2013-03-01 | 2014-09-04 | Gentex Corporation | Vehicle imaging system and method for categorizing objects using relative motion analysis |
| KR101906951B1 (en) * | 2013-12-11 | 2018-10-11 | 한화지상방산 주식회사 | System and method for lane detection |
| CN104192144B (en) * | 2014-07-25 | 2016-08-24 | 杭州电子科技大学 | A kind of automobile actively crashproof bend false-alarm removing method |
| CN104408460B (en) * | 2014-09-17 | 2017-08-11 | 电子科技大学 | A kind of lane detection and tracking detection method |
| CN104573627B (en) * | 2014-11-19 | 2017-12-29 | 湖南大学 | Lane line based on bianry image retains and detection method |
| CN105046198B (en) * | 2015-06-12 | 2018-07-06 | 上海修源网络科技有限公司 | A kind of lane detection method |
| CN106407893B (en) * | 2016-08-29 | 2019-11-22 | 东软集团股份有限公司 | A kind of method, apparatus and equipment detecting lane line |
| CN106529493B (en) * | 2016-11-22 | 2019-12-20 | 北京联合大学 | Robust multi-lane line detection method based on perspective view |
| CN106991407B (en) * | 2017-04-10 | 2018-08-07 | 吉林大学 | A kind of method and device of lane detection |
| CN107730520B (en) * | 2017-09-22 | 2020-10-27 | 智车优行科技（北京）有限公司 | Lane line detection method and system |
| CN107748882B (en) * | 2017-11-23 | 2020-10-20 | 海信集团有限公司 | Lane line detection method and device |
-
2018
- 2018-04-16 CN CN201810336585.2A patent/CN108629292B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108629292A (en) | 2018-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108629292B (en) | Curved lane line detection method and device and terminal | |
| US11205284B2 (en) | Vehicle-mounted camera pose estimation method, apparatus, and system, and electronic device | |
| CN109284674B (en) | Method and device for determining lane line | |
| CN110148148B (en) | Training method of lower edge detection model based on target detection, model and storage medium | |
| CN110929655B (en) | Lane line identification method in driving process, terminal device and storage medium | |
| JP2019139729A (en) | System and method for lane detection | |
| CN108229406B (en) | Lane line detection method, device and terminal | |
| CN108629763B (en) | Disparity map judging method and device and terminal | |
| CN107909036B (en) | Road detection method and device based on disparity map | |
| CN107748882B (en) | Lane line detection method and device | |
| CN110163039B (en) | Method, apparatus, storage medium, and processor for determining vehicle driving state | |
| US8520898B2 (en) | Method and system for determining a region of interest in an image | |
| US11164012B2 (en) | Advanced driver assistance system and method | |
| CN112598922B (en) | Parking space detection method, device, equipment and storage medium | |
| CN108197590B (en) | Pavement detection method, device, terminal and storage medium | |
| CN111243003A (en) | Vehicle-mounted binocular camera and method and device for detecting road height limiting rod | |
| CN107766847B (en) | Lane line detection method and device | |
| CN108319931B (en) | Image processing method and device and terminal | |
| CN108052921B (en) | Lane line detection method, device and terminal | |
| KR101236223B1 (en) | Method for detecting traffic lane | |
| CN108090425B (en) | Lane line detection method, device and terminal | |
| CN108389177B (en) | Vehicle bumper damage detection method and traffic safety early warning method | |
| CN113345087B (en) | Surface model fitting method and device based on monocular vision | |
| CN109740502A (en) | Road quality detection method and device | |
| JP2020095631A (en) | Image processing device and image processing 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 |