CN115187947A - Standard lane-based lane judging method and system for road diseases - Google Patents
Standard lane-based lane judging method and system for road diseases Download PDFInfo
- Publication number
- CN115187947A CN115187947A CN202210801445.4A CN202210801445A CN115187947A CN 115187947 A CN115187947 A CN 115187947A CN 202210801445 A CN202210801445 A CN 202210801445A CN 115187947 A CN115187947 A CN 115187947A
- Authority
- CN
- China
- Prior art keywords
- distance
- lane
- road
- reference point
- transverse
- 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.)
- Pending
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)
- Traffic Control Systems (AREA)
Abstract
The invention relates to a method and a system for judging a lane where a road fault is located based on a standard lane, which belong to the field of road fault monitoring, and are characterized by firstly collecting standard lane reference point data; then, determining a distance reference point according to the reference point; the distance datum points meet the condition that the distances between the adjacent distance datum points are equal; then acquiring longitude and latitude information of the monitoring vehicle and a road image shot by a vehicle-mounted camera of the monitoring vehicle; when a road disease exists in the road image, determining a first transverse distance according to the road image; calculating a second transverse distance according to the longitude and latitude information of the monitored vehicle and the longitude and latitude information of the distance reference point; calculating a third transverse distance according to the first transverse distance and the second transverse distance; and finally determining the lane where the road disease is located according to the third transverse distance and the lane width. The method can effectively improve the precision and efficiency of judging the lane where the road fault is located, and accurately and quickly judge the lane where the road fault is located.
Description
Technical Field
The invention relates to the field of road disease monitoring, in particular to a method and a system for judging a lane where a road disease is located based on a standard lane.
Background
At present, a data-driven curing mode becomes a development direction of traffic roads. For the identification and data acquisition of road pavement diseases, the lane where the diseases are located is an important attribute. The data acquisition and maintenance of road diseases are carried out according to lane-level standards, and the intelligent implementation of a road management and maintenance mode can be assisted.
The existing method for judging the lane where the road disease is located is mostly a method for identifying and judging the diseased lane based on the lane line of the image, however, the method is limited by the quality of the shot image and the actual road condition, if complex road conditions such as unclear shot image, missing lane line of the actual road condition, coexistence of a motor lane and a non-motor lane and the like occur, the time for identifying the road disease is longer, the efficiency is lower, and the accuracy for judging the diseased lane is reduced. Therefore, how to improve the accuracy and efficiency of judging the lane where the road fault is located is a problem to be solved urgently at present.
Disclosure of Invention
The invention aims to provide a method and a system for judging a lane where a road fault is located based on a standard lane, which can effectively improve the precision and efficiency of judging the lane where the road fault is located and accurately and quickly judge the lane where the road fault is located.
In order to achieve the purpose, the invention provides the following scheme:
on one hand, the invention provides a method for judging a lane where a road fault is located based on a standard lane, which comprises the following steps:
collecting standard lane datum data; the standard lane is the leftmost lane, the datum point data is longitude and latitude information which is acquired according to a specified sampling frequency when a monitoring vehicle runs along the center of the standard lane, and each longitude and latitude information corresponds to a datum point;
determining a distance reference point according to the reference point; the distance reference points meet the condition that the distances between the adjacent distance reference points are equal;
acquiring longitude and latitude information of a monitoring vehicle and a road image shot by a vehicle-mounted camera of the monitoring vehicle;
when a road disease exists in the road image, determining a first transverse distance according to the road image, wherein the first transverse distance is the transverse distance between the road disease and the vehicle-mounted camera; the transverse distance is a distance in a transverse direction, and the transverse direction is a direction perpendicular to the lane direction;
calculating a second transverse distance according to the longitude and latitude information of the monitored vehicle and the longitude and latitude information of the distance reference point, wherein the second transverse distance is the transverse distance between the monitored vehicle and the center of the standard lane;
calculating a third transverse distance according to the first transverse distance and the second transverse distance, wherein the third transverse distance is the transverse distance between the road fault and the center of a standard lane;
and determining the lane where the road damage is located according to the third transverse distance and the lane width.
Optionally, the standard lane datum data is acquired by using a GNSS device based on an RTK technology.
Optionally, the determining a distance reference point according to the reference point specifically includes:
initializing S, i and j to zero; the method comprises the following steps that S represents the accumulated running distance of a monitored vehicle, i and j are counting variables respectively, i is used for counting reference points, and j is used for counting distance reference points;
counting all the reference points, comparing the sizes of i and p-1 in real time, and determining whether to finish counting according to a comparison result, wherein the method comprises the following steps:
when i is more than p-1, finishing counting; wherein p represents the number of fiducial points;
when i is less than or equal to p-1, skipping to the step of comparing S with L and determining assignment condition according to comparison result;
comparing the size of S and L, and determining assignment condition according to the comparison result, including:
when S is less than or equal to L, assigning S as S + L i And jumping to the step of assigning i as i + 1; wherein L represents the distance between two adjacent distance reference points, L i Representing the Euclidean distance between the ith reference point and the (i-1) th reference point;
when S is larger than L, corresponding the jth distance reference point to be highRectangular coordinate of plane (M) j ，N j ) Is assigned a value of (X) i ，Y i ) And assigning S as L i After j is assigned as j +1, jumping to the step of assigning i as i + 1;
and assigning i to be i +1, returning to the step of counting each reference point, comparing the sizes of i and p-1 in real time, and determining whether to finish counting according to a comparison result, and continuing counting until i is more than p-1, and finishing counting.
Optionally, when a road fault exists in the road image, determining a first transverse distance according to the road image specifically includes:
intercepting a disease image from the road image, wherein the disease image is an image containing a road disease, and acquiring the resolution R multiplied by D of the disease image;
establishing a rectangular coordinate system by taking the top left corner vertex of the disease image as an origin, and determining coordinates (r, d) of the road disease central point in the rectangular coordinate system;
selecting a point on the central axis of the disease image along the longitudinal axis direction of the rectangular coordinate system as a mark point, and determining the coordinates (R/2, D/n) of the mark point on the rectangular coordinate system, wherein n is more than or equal to 1;
carrying out perspective transformation on the disease image, and determining a perspective transformation coordinate (r) of the road disease central point t ，d t ) And perspective transformation coordinates (R) of the marking points t ，D t )；
According to the perspective transformation coordinate (r) of the road fault central point t ，d t ) And perspective transformation coordinates (R) of the marking points t ，D t ) Using the formula x c ＝|R t -r t And | calculating to obtain the first transverse distance.
Optionally, the calculating a second transverse distance according to the longitude and latitude information of the monitored vehicle and the longitude and latitude information of the distance reference point specifically includes:
calculating Euclidean distances from the monitored vehicle to two nearest distance reference points and Euclidean distances between the two distance reference points according to the longitude and latitude information of the monitored vehicle and the longitude and latitude information of the distance reference points;
calculating the area of a triangle enclosed by the monitoring vehicle and the two distance reference points by adopting a Helen formula according to the Euclidean distances from the monitoring vehicle to the two nearest distance reference points and the Euclidean distance between the two distance reference points;
and calculating to obtain the second transverse distance according to the area of the triangle and the Euclidean distance between the two distance reference points.
Alternatively, using formulae
Calculating the third lateral distance;
wherein x is d Denotes the third lateral distance, h denotes the second lateral distance, x c Denotes a first lateral distance, r t When a road fault exists in the road image, in a rectangular coordinate system established by taking the top point of the upper left corner of the road image as an origin, a road fault central point is subjected to perspective transformation to obtain a perspective transformation horizontal coordinate; r is t And the perspective transformation abscissa is obtained by performing perspective transformation on an optional point on the central axis of the road image along the longitudinal axis direction of the rectangular coordinate system.
Alternatively, using formulae
Calculating a lane where the road diseases are located;
wherein, lane represents the lane where the road disease is located, w represents the lane width, and x d Represents a third transverse distance [ ·]Meaning rounding down.
Optionally, before the step of determining a distance reference point according to the reference point, the method further includes the following steps:
coordinate conversion is carried out on the longitude and latitude information corresponding to each reference point to obtain Gaussian plane rectangular coordinate information corresponding to each reference point;
and calculating the Euclidean distance between every two adjacent reference points according to the rectangular coordinate information of the Gaussian plane corresponding to each reference point.
Alternatively, using formulae
Calculating the Euclidean distance between every two adjacent reference points;
wherein i represents the ith reference point, X i Indicating the rectangular abscissa information of the Gaussian plane corresponding to the ith datum point, Y i Indicating the rectangular ordinate information of the Gaussian plane corresponding to the ith reference point, L i The Euclidean distance between the ith reference point and the (i-1) th reference point is shown.
On the other hand, the invention also provides a system for judging the lane where the road damage is based on the standard lane, which comprises the following steps:
the standard lane reference point data acquisition module is used for acquiring standard lane reference point data; the standard lane is the leftmost lane, the datum point data is longitude and latitude information which is acquired according to a specified sampling frequency when a monitoring vehicle runs along the center of the standard lane, and each longitude and latitude information corresponds to a datum point;
the distance reference point determining module is used for determining a distance reference point according to the reference point; the distance reference points meet the condition that the distances between the adjacent distance reference points are equal;
the position acquisition and road image shooting module is used for acquiring longitude and latitude information of a monitoring vehicle and a road image shot by a vehicle-mounted camera of the monitoring vehicle;
the first transverse distance calculation module is used for determining a first transverse distance according to the road image when the road image has a road fault, and the first transverse distance is the transverse distance between the road fault and the vehicle-mounted camera; the transverse distance is a distance in a transverse direction, and the transverse direction is a direction perpendicular to the lane direction;
the second transverse distance calculation module is used for calculating a second transverse distance according to the longitude and latitude information of the monitored vehicle and the longitude and latitude information of the distance reference point, wherein the second transverse distance is the transverse distance between the monitored vehicle and the center of a standard lane;
a third transverse distance calculating module, configured to calculate a third transverse distance according to the first transverse distance and the second transverse distance, where the third transverse distance is a transverse distance between the road defect and a center of a standard lane;
and the lane determining module is used for determining the lane where the road disease is located according to the third transverse distance and the lane width.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a method and a system for judging a lane where a road fault is located based on a standard lane, which are based on the distance dimension, wherein the leftmost lane is taken as the standard lane, the central dividing line of the standard lane is taken as the reference, after a monitored vehicle shoots the road fault, the first transverse distance between the road fault and a vehicle-mounted camera of the monitored vehicle is calculated, and the second transverse distance between the monitored vehicle and the center of the standard lane is taken, so that the distance between the road fault and the center of the standard lane, namely the third transverse distance, can be calculated, the lane where the road fault is located can be directly determined according to the third transverse distance and the lane width, the lane where the fault is located is positioned by the distance, the judgment precision of the lane where the road fault is located can be effectively improved, the accuracy and the reliability of the judgment result of the fault lane are improved, and the problem that the traditional method for identifying the fault lane based on an image lane line excessively depends on the definition of a shot image, and the judgment precision is low is solved. In addition, each reference point in the standard lane reference point data is converted into a fixed-distance reference point, and the distance between two adjacent fixed-distance reference points is equal, so that the calculation amount and the complexity are reduced, the judgment on the damaged lane is simpler and more convenient, the time consumption is shorter, and the efficiency of judging the lane where the road damage is located is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts. The following drawings are not intended to be drawn to scale in actual size, with emphasis instead being placed upon illustrating the principles of the invention.
Fig. 1 is a flowchart of a method for determining a lane where a road fault is located based on a standard lane according to embodiment 1 of the present invention;
fig. 2 is a schematic diagram of a format of collected standard lane reference point data provided in embodiment 1 of the present invention;
FIG. 3 is a flow chart of determining a distance reference point from a reference point according to embodiment 1 of the present invention;
fig. 4 is a schematic diagram of calculation of a first lateral distance according to embodiment 1 of the present invention;
fig. 5 is a perspective transformation diagram of a schematic diagram of calculation of a first lateral distance provided in embodiment 1 of the present invention;
fig. 6 is a schematic diagram of calculation of a second lateral distance provided in embodiment 1 of the present invention;
FIG. 7 is a schematic diagram illustrating exemplary calculation of a third lateral distance according to embodiment 1 of the present invention;
fig. 8 is a structural diagram of a lane judgment system for a road fault based on a standard lane according to embodiment 2 of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
As used in this disclosure and in the claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.
Although the present invention makes various references to certain modules in a system according to embodiments of the present invention, any number of different modules may be used and run on the user terminal and/or server. The modules are merely illustrative and different aspects of the systems and methods may use different modules.
Flow charts are used in the present invention to illustrate the operations performed by a system according to embodiments of the present invention. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.
The invention aims to provide a method and a system for judging a lane where a road fault is located based on a standard lane, which can effectively improve the precision and efficiency of judging the lane where the road fault is located and accurately and quickly judge the lane where the road fault is located.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Example 1
As shown in fig. 1, this embodiment provides a method for determining a lane where a road fault is located based on a standard lane, and the method specifically includes the following steps:
s1, collecting standard lane datum data; the standard lane is the leftmost lane, the datum point data is longitude and latitude information which is acquired according to a specified sampling frequency when a monitoring vehicle runs along the center of the standard lane, and each longitude and latitude information corresponds to a datum point. Data fields and examples of standard lane reference data are shown in fig. 2.
In this embodiment, the standard lane reference point data is acquired by using a GNSS (Global Navigation Satellite System) device based on an RTK (Real-Time Kinematic) technique.
In practical application, the monitoring vehicle carries a GNSS device based on an RTK technology and a vehicle-mounted camera, wherein the GNSS device based on the RTK technology is used for collecting datum data of a standard lane according to a preset frequency and recording longitude and latitude information of each position of the monitoring vehicle in the driving process of the standard lane in real time; the vehicle-mounted camera is used for collecting and monitoring images of a road surface in front of the vehicle in the driving process.
S2, determining a distance reference point according to the reference point; the distance reference points satisfy a condition that the distances between adjacent distance reference points are equal.
Because the distance between each reference point in the standard lane reference point data acquired at the fixed frequency has certain difference under the influence of the speed and the road condition of the monitored vehicle, in order to facilitate subsequent data processing, the invention determines the distance reference point according to the reference point, namely, the original standard lane reference point data is converted into the standard lane reference point data with the fixed distance, so that the distance between two adjacent distance reference points is equal.
In this embodiment, when converting the original standard lane reference point data into fixed-distance standard lane reference point data, coordinate conversion is first performed on longitude and latitude information corresponding to each reference point to obtain gaussian plane rectangular coordinate information corresponding to each reference point. Assuming that a road section to be detected has n reference points, namely n longitude and latitude coordinates, converting the n longitude and latitude coordinates into n Gaussian plane rectangular coordinates (X, Y), and when i =1, expressing the Gaussian plane rectangular coordinate (X) of the 1 st reference point 1 ，Y 1 ) (ii) a When i =2, a gaussian plane rectangular coordinate (X) representing the 2 nd reference point 2 ，Y 2 ). And then calculating the Euclidean distance between every two adjacent reference points according to the rectangular coordinate information of the Gaussian plane corresponding to each reference point. And finally, determining distance reference points according to the reference points by adopting a cyclic counting assignment methodTherefore, the conversion from the original standard lane reference point data to the fixed-distance standard lane reference point data is realized.
In this embodiment, the euclidean distance between every two adjacent reference points is calculated by using equation (1):
wherein i represents the ith reference point, X i Indicating the rectangular abscissa information of the Gaussian plane corresponding to the ith reference point, Y i Indicating the rectangular ordinate information of the Gaussian plane corresponding to the ith reference point, L i The Euclidean distance between the ith reference point and the (i-1) th reference point is shown.
In this embodiment, the distance reference points are determined according to the reference points by using a cycle count assignment method, as shown in fig. 3, which specifically includes the following steps:
s2.1, initializing S, i and j to zero; the method comprises the following steps that S represents the accumulated running distance of a monitored vehicle, i and j are counting variables respectively, i is used for counting reference points, and j is used for counting distance reference points;
s2.2, counting all the reference points, comparing the sizes of i and p-1 in real time, and determining whether to finish counting according to a comparison result, wherein the method comprises the following steps:
when i is more than p-1, finishing counting; wherein p represents the number of fiducial points;
when i is less than or equal to p-1, skipping to the step S2.3, namely, the step of comparing S with L and determining assignment condition according to the comparison result;
s2.3, comparing the sizes of the S and the L, and determining the assignment condition according to the comparison result, wherein the step comprises the following steps:
when S is less than or equal to L, assigning S as S + L i And jumping to step S2.4, namely, assigning i as i + 1; in the embodiment, for convenience of calculation, the value of L is 1m; l is i Representing the Euclidean distance between the ith reference point and the (i-1) th reference point;
when S is larger than L, corresponding the jth distance reference point to the Gaussian plane rectangular coordinate (M) j ，N j ) Is assigned a value of (X) i ，Y i ) And assigning S as L i After j is assigned as j +1, jumping to step S2.4, namely assigning i as i + 1;
and S2.4, assigning i to i +1, returning to the step S2.2, namely counting all reference points, comparing the sizes of i and p-1 in real time, and determining whether to finish counting according to the comparison result, and continuing counting until i is greater than p-1, and finishing counting.
According to the method, after the standard lane datum point data are obtained, the distance reference points are determined according to the datum points in the standard lane datum point data, so that the standard lane datum point data are converted into the distance standard lane datum point data, the spacing distances of the distance reference points are equal and are all located on the central dividing line of the standard lane, and the distance reference points are involved in the process of judging the damaged lane, so that the calculation amount and the complexity are reduced, the method is simpler, more convenient and shorter in time consumption, and the efficiency of judging the lane where the road damage is located is further improved. And the distance reference points are used as data bases to judge the lanes where the road diseases are located, errors caused by factors such as vehicle speed and road conditions monitoring in the process of collecting the original standard lane reference point data are eliminated, and the accuracy of judging the lanes where the road diseases are located is improved.
And S3, acquiring longitude and latitude information of the monitoring vehicle and a road image shot by a vehicle-mounted camera of the monitoring vehicle.
The method comprises the steps of collecting standard lane datum point data in the step S1 and determining a distance datum point according to the datum point in the step S2, obtaining basic data based on the standard lane and the distance datum point, starting image shooting, analysis processing and disease lane judgment on a road disease of a road section to be monitored in the step S3, and when a vehicle-mounted camera is used for shooting a road image, wherein the vehicle-mounted camera is mounted at the central point of a monitored vehicle or the central dividing line of the monitored vehicle and shoots the road image in front of the monitored vehicle facing the driving direction.
The vehicle-mounted camera of the monitoring vehicle shoots the road image in the whole driving process, wherein the road diseases can not appear in most images, and the road diseases can only appear in a small part of images. Therefore, when the road damage is shot, the distance reference points in a certain distance range at the two sides of the monitored vehicle are screened by taking the position point of the monitored vehicle as the center, so that the calculated amount is reduced, and the efficiency of judging the lane where the lane damage is located is improved.
In the embodiment, distance reference points within 50m of the two sides of the monitored vehicle are screened, the longitude and latitude of the position of the vehicle when the road surface damage is shot are converted into Gaussian plane rectangular coordinates x and y, distance base road points within 50m above and below the Gaussian plane rectangular coordinates x and y are screened by taking the position point of the monitored vehicle as the center, and the calculation method is as shown in formula (2):
wherein (M) j ，N j ) The rectangular coordinates of the Gaussian plane representing the jth distance reference point by defining M j ，N j To screen out distance reference points within 50m above and below the x and y coordinates, (m) j ，n j ) The j-th distance reference point within 50m from the position point where the monitored vehicle is located is shown.
S4, when a road disease exists in the road image, determining a first transverse distance according to the road image, wherein the first transverse distance is the transverse distance between the road disease and the vehicle-mounted camera; the lateral distance is a distance in a lateral direction, which is a direction perpendicular to a lane direction.
Step S4 specifically includes:
s4.1, intercepting a disease image from the road image, wherein the disease image is an image containing the road disease, and acquiring the resolution R multiplied by D of the disease image, namely, R pixel points in the transverse direction and D pixel points in the longitudinal direction. When the camera is calibrated, a homography matrix M is obtained, the homography matrix is used for describing the position mapping relation of the object between a world coordinate system and a pixel coordinate system, and a corresponding transformation matrix is called as a homography matrix.
And S4.2, establishing a rectangular coordinate system by taking the top point of the upper left corner of the defect image as an origin, and determining the coordinates (r, d) of the road defect central point in the rectangular coordinate system, as shown in FIG. 4.
S4.3, selecting a point on the central axis of the disease image along the longitudinal axis direction of the rectangular coordinate system as a mark point, and determining the coordinate (R/2, D/n) of the mark point on the rectangular coordinate system, wherein n is more than or equal to 1; for the sake of simplicity of calculation, the marker point selected in this embodiment is (R/2, D), as shown in FIG. 4.
Step S4.4, because the image captured by the vehicle-mounted camera is not a rectangular image, but an inverted trapezoidal image spreading from the captured point of the vehicle-mounted camera to a distant lane, the embodiment performs perspective transformation on the disease image, the disease image after the perspective transformation is as shown in fig. 5, and determines the perspective transformation coordinates (r) of the road disease center point t ，d t ) And the perspective transformation coordinates (R) of the marking points t ，D t )。
S4.5, according to the perspective transformation coordinate (r) of the road disease central point t ，d t ) And perspective transformation coordinates (R) of the marking points t ，D t ) Since the transverse distance is calculated, the first transverse distance x can be obtained by taking the abscissa after perspective transformation of the two as the difference c As in formula (3):
x c ＝|R t -r t | (3)
the first lateral distance is a lateral distance between the road defect and the vehicle-mounted camera, and since the vehicle-mounted camera is mounted on a central point or a central dividing line of the monitored vehicle, the first lateral distance is a lateral distance from the road defect to the monitored vehicle.
And S5, calculating a second transverse distance according to the longitude and latitude information of the monitored vehicle and the longitude and latitude information of the distance reference point, wherein the second transverse distance is the transverse distance between the monitored vehicle and the center of a standard lane.
Step S5 specifically includes:
and S5.1, calculating Euclidean distances from the monitored vehicle to two nearest distance reference points and the Euclidean distance between the two distance reference points according to the longitude and latitude information of the monitored vehicle and the longitude and latitude information of the distance reference points.
In the present embodiment, the euclidean distances from the monitored vehicle to the nearest two distance reference points are calculated by equation (4):
wherein l j The jth distance reference point is indicated.
Let us assume two distance reference points which are closest to the monitored vehicle, one of which is point a, when j = a, and which is denoted as l a (ii) a Another distance reference point is point B, when j = B, which distance reference point is denoted as l b . Since the distance between two adjacent distance reference points preset in the present embodiment is 1m, the coordinates at which the monitoring vehicle is located must fall between the points a and B. Since the monitoring vehicle is unlikely to make a large turn at a distance of 1m, the straight-line distance between points a and B can be considered to be equal to the road distance between points a and B.
Recording the position of the monitored vehicle as a point C, and respectively calculating the Euclidean distance l between the point A and the point C according to the formula ac Euclidean distance l between points B and C bc And the Euclidean distance l between the points A and B ab As shown in fig. 6.
Step S5.2, according to Euclidean distances from the monitored vehicle to two nearest distance reference points respectively andcalculating the Euclidean distance between the two distance reference points by adopting a Helen formula to calculate the area S of a triangle formed by the monitoring vehicle and the two distance reference points ABC 。
The Helen formula used in this example is as follows:
wherein p is a semi-circumference of a triangle surrounded by the monitoring vehicle and two nearest distance reference points, and is represented by formula (6):
and S5.3, calculating to obtain the second transverse distance according to the area of the triangle and the Euclidean distance between the two distance reference points.
Since the second lateral distance represents the lateral distance between the monitoring vehicle and the center of the standard lane, that is, the perpendicular distance h from the monitoring vehicle to the reference lane line in fig. 6, where the reference lane line is a straight line obtained by connecting a plurality of distance reference points, and since the monitoring vehicle travels along the central dividing line of the standard lane, and the collected reference points on the standard lane are located on the same straight line, the distance reference points determined according to the reference points are also located on the straight line, and the straight line is the reference lane line and is also the central dividing line of the standard lane.
In step S5.2, the triangle area S is calculated by utilizing the Helen formula ABC Then, the area formula of the triangle can also be expressed as formula (7):
and (5), the step (6) and the step (7) are combined, namely, the second transverse distance h can be calculated and is expressed by the formula (8):
and S6, calculating a third transverse distance according to the first transverse distance and the second transverse distance, wherein the third transverse distance is the transverse distance between the road fault and the center of a standard lane.
In the present embodiment, the third lateral distance x is calculated by equation (9) d ：
Wherein x is d Denotes the third lateral distance, h denotes the second lateral distance, x c Denotes a first lateral distance, r t When a road fault exists in the road image, in a rectangular coordinate system established by taking the top point of the upper left corner of the road image as an origin, a road fault central point is subjected to perspective transformation to obtain a perspective transformation horizontal coordinate; r t And the perspective transformation abscissa is obtained by performing perspective transformation on an optional point on the central axis of the road image along the longitudinal axis direction of the rectangular coordinate system.
And S7, determining a lane where the road damage is located according to the third transverse distance and the lane width.
In this embodiment, the third transverse distance x is obtained d Then, the lane where the road fault is located can be judged by using the formula (10) according to the known lane width w:
wherein lane represents a lane where a road fault is located, w represents the lane width, the lane width of a road with more than two levels is usually 3.75m d Represents a third transverse distance, [ ·]Indicating a rounding down.
In order to facilitate understanding of the method for determining a damaged lane according to the present invention, the following example is illustrated:
as shown in fig. 7, if the third transverse distance is 7W/8, the calculation result of the lane where the road fault is located is shown in equation (11):
wherein, the value of 0 is obtained after 3/8 is rounded down, and finally the road fault is judged to be located in the second lane under the condition, and the judgment result is consistent with that shown in fig. 7.
The invention provides a method for judging a lane where a road fault is located based on a standard lane, which starts from the dimension of distance, takes the leftmost lane as the standard lane and takes the central dividing line of the standard lane as the reference, and after a monitored vehicle shoots the road fault, the method can calculate the distance between the road fault and the center of the standard lane, namely the third transverse distance, by calculating the first transverse distance between a vehicle-mounted camera of the monitored vehicle and the second transverse distance between the monitored vehicle and the center of the standard lane and monitoring the second transverse distance between the vehicle and the center of the standard lane, so that the distance between the road fault and the center of the standard lane can be calculated and the lane where the road fault is located can be directly determined according to the third transverse distance and the width of the lane, the lane where the fault is located can be positioned by the distance, the judgment precision of the road fault can be effectively improved, the accuracy and the reliability of the judgment result of the fault lane can be improved, and the problem that the traditional method for identifying the fault lane based on image lane is too dependent on the definition of the image lane can be solved, and the judgment precision is low.
Example 2
As shown in fig. 8, this embodiment provides a system for determining a lane where a road fault is located based on a standard lane, where functions of modules in the system are the same as and correspond to steps of the determination method in embodiment 1 one by one, and the system specifically includes:
the standard lane datum point data acquisition module M1 is used for acquiring standard lane datum point data; the standard lane is the leftmost lane, the datum point data is longitude and latitude information which is acquired according to a specified sampling frequency when a monitoring vehicle runs along the center of the standard lane, and each longitude and latitude information corresponds to a datum point;
a distance reference point determining module M2, configured to determine a distance reference point according to the reference point; the distance reference points meet the condition that the distances between the adjacent distance reference points are equal;
the position acquisition and road image shooting module M3 is used for acquiring longitude and latitude information of the monitoring vehicle and road images shot by a vehicle-mounted camera of the monitoring vehicle;
the first transverse distance calculation module M4 is used for determining a first transverse distance according to the road image when a road fault exists in the road image, wherein the first transverse distance is the transverse distance between the road fault and the vehicle-mounted camera; the transverse distance is a distance in a transverse direction, and the transverse direction is a direction perpendicular to the lane direction;
the second transverse distance calculating module M5 is used for calculating a second transverse distance according to the longitude and latitude information of the monitored vehicle and the longitude and latitude information of the distance reference point, wherein the second transverse distance is the transverse distance between the monitored vehicle and the center of the standard lane;
a third transverse distance calculating module M6, configured to calculate a third transverse distance according to the first transverse distance and the second transverse distance, where the third transverse distance is a transverse distance between the road defect and a center of a standard lane;
and the road fault location lane determining module M7 is used for determining the lane where the road fault is located according to the third transverse distance and the lane width.
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 invention 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 relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The foregoing is illustrative of the present invention and is not to be construed as limiting thereof. Although a few exemplary embodiments of this invention have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this invention. Accordingly, all such modifications are intended to be included within the scope of this invention as defined in the claims. It is to be understood that the foregoing is illustrative of the present invention and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The invention is defined by the claims and their equivalents.
Claims (10)
1. A method for judging a lane where a road fault is located based on a standard lane is characterized by comprising the following steps:
collecting standard lane datum data; the standard lane is the leftmost lane, the datum point data is longitude and latitude information which is acquired according to a specified sampling frequency when a monitoring vehicle runs along the center of the standard lane, and each longitude and latitude information corresponds to a datum point;
determining a distance reference point according to the reference point; the distance reference points meet the condition that the distances between the adjacent distance reference points are equal;
acquiring longitude and latitude information of a monitoring vehicle and a road image shot by a vehicle-mounted camera of the monitoring vehicle;
when a road fault exists in the road image, determining a first transverse distance according to the road image, wherein the first transverse distance is the transverse distance between the road fault and the vehicle-mounted camera; the transverse distance is a distance in a transverse direction, and the transverse direction is a direction perpendicular to the lane direction;
calculating a second transverse distance according to the longitude and latitude information of the monitored vehicle and the longitude and latitude information of the distance reference point, wherein the second transverse distance is the transverse distance between the monitored vehicle and the center of a standard lane;
calculating a third transverse distance according to the first transverse distance and the second transverse distance, wherein the third transverse distance is the transverse distance between the road fault and the center of a standard lane;
and determining the lane where the road disease is located according to the third transverse distance and the lane width.
2. The method according to claim 1, characterized in that the standard lane reference point data is acquired using a GNSS device based on RTK technology.
3. The method of claim 1, wherein determining a distance reference point from the reference point comprises:
initializing S, i and j to zero; the method comprises the following steps that S represents the accumulated running distance of a monitored vehicle, i and j are counting variables respectively, i is used for counting reference points, and j is used for counting distance reference points;
counting all the reference points, comparing the sizes of i and p-1 in real time, and determining whether to finish counting according to a comparison result, wherein the method comprises the following steps:
when i is more than p-1, finishing counting; wherein p represents the number of reference points;
when i is not more than p-1, skipping to the step of comparing S and L and determining assignment condition according to the comparison result;
comparing the size of the S and the L, and determining the assignment condition according to the comparison result, wherein the steps comprise:
when S is less than or equal to L, assigning S as S + L i And jumping to the step of assigning i as i + 1; wherein L represents the distance between two adjacent distance reference points, L i Representing the Euclidean distance between the ith reference point and the (i-1) th reference point;
when S is larger than L, corresponding the jth distance reference point to the Gaussian plane rectangular coordinate (M) j ，N j ) Is assigned a value of (X) i ，Y i ) And assigning S as L i After j is assigned as j +1, jumping to the step of assigning i as i + 1;
and assigning i as i +1, returning to the step of counting all the reference points, comparing the sizes of i and p-1 in real time, and determining whether to finish counting according to the comparison result until i is greater than p-1, and finishing counting.
4. The method according to claim 1, wherein when a road fault exists in the road image, determining a first lateral distance according to the road image specifically includes:
intercepting a disease image from the road image, wherein the disease image is an image containing road diseases, and acquiring the resolution R multiplied by D of the disease image;
establishing a rectangular coordinate system by taking the top left corner vertex of the disease image as an origin, and determining coordinates (r, d) of the road disease central point in the rectangular coordinate system;
selecting a point on the central axis of the disease image along the longitudinal axis direction of the rectangular coordinate system as a mark point, and determining the coordinates (R/2, D/n) of the mark point on the rectangular coordinate system, wherein n is more than or equal to 1;
carrying out perspective transformation on the disease image, and determining a perspective transformation coordinate (r) of the road disease central point t ，d t ) And perspective transformation coordinates (R) of the marking points t ，D t )；
According to the perspective transformation coordinate (r) of the road disease central point t ，d t ) And the perspective transformation coordinates (R) of the marking points t ，D t ) Using the formula x c ＝|R t -r t And | calculating to obtain the first transverse distance.
5. The method according to claim 1, wherein the calculating a second lateral distance according to the latitude and longitude information of the monitored vehicle and the latitude and longitude information of the distance reference point specifically comprises:
calculating Euclidean distances from the monitored vehicle to two nearest distance reference points and Euclidean distances between the two distance reference points according to the longitude and latitude information of the monitored vehicle and the longitude and latitude information of the distance reference points;
calculating the area of a triangle enclosed by the monitoring vehicle and the two distance reference points by adopting a Helen formula according to the Euclidean distances from the monitoring vehicle to the two nearest distance reference points and the Euclidean distance between the two distance reference points;
and calculating to obtain the second transverse distance according to the area of the triangle and the Euclidean distance between the two distance reference points.
6. Method according to claim 1, characterized in that a formula is used
Calculating the third lateral distance;
wherein x is d Denotes the third lateral distance, h denotes the second lateral distance, x c Denotes a first lateral distance, r t When a road disease exists in the road image, in a rectangular coordinate system established by taking the top left corner vertex of the road image as an origin, a perspective transformation abscissa is obtained after a road disease center point is subjected to perspective transformation; r t And the coordinate system represents a perspective transformation abscissa obtained by subjecting any point on the central axis of the road image to perspective transformation along the longitudinal axis direction of the rectangular coordinate system.
7. The method of claim 1, wherein a formula is utilized
Calculating a lane where the road diseases are located;
wherein lane represents a lane where the road damage is located, w represents lane width, and x d Represents a third transverse distance [ ·]Indicating a rounding down.
8. The method according to any of claims 1-7, further comprising, before the step of determining a distance reference point from said reference point, the steps of:
coordinate conversion is carried out on the longitude and latitude information corresponding to each reference point to obtain Gaussian plane rectangular coordinate information corresponding to each reference point;
and calculating the Euclidean distance between every two adjacent reference points according to the rectangular coordinate information of the Gaussian plane corresponding to each reference point.
9. Method according to claim 8, characterized in that the formula L is used i ＝
Calculating the Euclidean distance between every two adjacent reference points;
wherein i represents the ith reference point, X i Indicating the rectangular abscissa information of the Gaussian plane corresponding to the ith reference point, Y i Indicating the rectangular ordinate information of the Gaussian plane corresponding to the ith reference point, L i The Euclidean distance between the ith reference point and the (i-1) th reference point is shown.
10. The system for judging the lane where the road disease is based on the standard lane is characterized by comprising the following steps of:
the standard lane reference point data acquisition module is used for acquiring standard lane reference point data; the standard lane is the leftmost lane, the datum point data is longitude and latitude information which is acquired according to a specified sampling frequency when a monitoring vehicle runs along the center of the standard lane, and each longitude and latitude information corresponds to a datum point;
the distance reference point determining module is used for determining a distance reference point according to the reference point; the distance reference points meet the condition that the distances between the adjacent distance reference points are equal;
the position acquisition and road image shooting module is used for acquiring longitude and latitude information of a monitored vehicle and a road image shot by a vehicle-mounted camera of the monitored vehicle;
the first transverse distance calculation module is used for determining a first transverse distance according to the road image when a road fault exists in the road image, wherein the first transverse distance is the transverse distance between the road fault and the vehicle-mounted camera; the transverse distance is a distance in a transverse direction, and the transverse direction is a direction perpendicular to the lane direction;
the second transverse distance calculation module is used for calculating a second transverse distance according to the longitude and latitude information of the monitored vehicle and the longitude and latitude information of the distance reference point, wherein the second transverse distance is the transverse distance between the monitored vehicle and the center of a standard lane;
a third transverse distance calculating module, configured to calculate a third transverse distance according to the first transverse distance and the second transverse distance, where the third transverse distance is a transverse distance between the road defect and a center of a standard lane;
and the lane determining module is used for determining the lane where the road fault is located according to the third transverse distance and the lane width.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210801445.4A CN115187947A (en) | 2022-07-07 | 2022-07-07 | Standard lane-based lane judging method and system for road diseases |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210801445.4A CN115187947A (en) | 2022-07-07 | 2022-07-07 | Standard lane-based lane judging method and system for road diseases |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115187947A true CN115187947A (en) | 2022-10-14 |
Family
ID=83517541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210801445.4A Pending CN115187947A (en) | 2022-07-07 | 2022-07-07 | Standard lane-based lane judging method and system for road diseases |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115187947A (en) |
-
2022
- 2022-07-07 CN CN202210801445.4A patent/CN115187947A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110285793B (en) | Intelligent vehicle track measuring method based on binocular stereo vision system | |
| CN110322702B (en) | Intelligent vehicle speed measuring method based on binocular stereo vision system | |
| CN106919915B (en) | Map road marking and road quality acquisition device and method based on ADAS system | |
| CN115424232B (en) | Method for identifying and evaluating pavement pit, electronic equipment and storage medium | |
| CN109949365B (en) | Vehicle designated position parking method and system based on road surface feature points | |
| CN113421289B (en) | High-precision vehicle track data extraction method for overcoming unmanned aerial vehicle shooting disturbance | |
| JP2010530997A (en) | Method and apparatus for generating road information | |
| CN104766058A (en) | Method and device for obtaining lane line | |
| CN111553252A (en) | Road pedestrian automatic identification and positioning method based on deep learning and U-V parallax algorithm | |
| CN106558051A (en) | A kind of improved method for detecting road from single image | |
| CN111288890A (en) | Road sign dimension and height automatic measurement method based on binocular photogrammetry technology | |
| CN112990128A (en) | Multi-vehicle speed measuring method based on video tracking | |
| CN110135216B (en) | Method and device for detecting lane number change area in electronic map and storage equipment | |
| CN112446915B (en) | Picture construction method and device based on image group | |
| CN110807771A (en) | Defect detection method for road deceleration strip | |
| CN114267180B (en) | Parking management method and system based on computer vision | |
| CN107506753B (en) | Multi-vehicle tracking method for dynamic video monitoring | |
| CN111582270A (en) | Identification tracking method based on high-precision bridge region visual target feature points | |
| TW202022804A (en) | Method and system for road image reconstruction and vehicle positioning | |
| CN109345576B (en) | Vehicle running speed identification method and system | |
| CN110415299B (en) | Vehicle position estimation method based on set guideboard under motion constraint | |
| CN115187947A (en) | Standard lane-based lane judging method and system for road diseases | |
| CN111161264A (en) | Method for segmenting TFT circuit image with defects | |
| CN115035164A (en) | Moving target identification method and device | |
| CN110969875B (en) | Method and system for road intersection traffic management |
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 |