A method and system for determining the lane where road defects are located based on standard lanes

Abstract

This invention relates to a method and system for determining the lane containing road defects based on a standard lane, belonging to the field of road defect monitoring. First, standard lane reference point data is collected; then, fixed-distance reference points are determined based on the reference points; these fixed-distance reference points satisfy the condition that the distance between adjacent fixed-distance reference points is equal; next, the latitude and longitude information of the monitoring vehicle and road images captured by the vehicle's onboard camera are acquired; when road defects are present in the road images, a first lateral distance is determined based on the road images; a second lateral distance is calculated based on the latitude and longitude information of the monitoring vehicle and the fixed-distance reference points; a third lateral distance is calculated based on the first and second lateral distances; finally, the lane containing the road defect is determined based on the third lateral distance and the lane width. This method can effectively improve the accuracy and efficiency of determining the lane containing road defects, accurately and quickly identifying the lane where the road defect is located.

Description

Technical Field

[0001] This invention relates to the field of road defect monitoring, and in particular to a method and system for determining the lane where road defects are located based on a standard lane. Background Technology

[0002] Currently, data-driven maintenance has become the direction of transportation and road development. For the identification and data collection of road surface defects, the lane where the defect is located is a crucial attribute. Only by collecting and repairing road defect data at the lane level can we better support the implementation of intelligent road management and maintenance models.

[0003] Most existing methods for identifying lanes with road defects rely on image-based lane line recognition. However, this method is limited by image quality and actual road conditions. In complex situations such as unclear images, missing lane lines, or the coexistence of motor vehicle and non-motor vehicle lanes, not only is identifying road defects time-consuming and inefficient, but the accuracy of lane identification also decreases. Therefore, improving the accuracy and efficiency of identifying lanes with road defects is a pressing issue that needs to be addressed. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for determining the lane where road defects are located based on standard lanes, which can effectively improve the accuracy and efficiency of determining the lane where road defects are located, and accurately and quickly determine the lane where road defects are located.

[0005] To achieve the above objectives, the present invention provides the following solution:

[0006] On the one hand, this invention proposes a method for determining the lane where road defects are located based on a standard lane, the method comprising:

[0007] Collect reference point data for the standard lane; the standard lane is the leftmost lane, and the reference point data is the latitude and longitude information collected at a specified sampling frequency when the monitoring vehicle travels along the center of the standard lane, with each latitude and longitude information corresponding to a reference point;

[0008] Based on the aforementioned reference point, a fixed-distance reference point is determined; the fixed-distance reference point satisfies the condition that the distance between adjacent fixed-distance reference points is equal.

[0009] Acquire the latitude and longitude information of the monitoring vehicle and road images captured by the vehicle's onboard camera;

[0010] When road defects are present in the road image, a first lateral distance is determined based on the road image. The first lateral distance is the lateral distance between the road defect and the vehicle-mounted camera. The lateral distance is the distance in the lateral direction, which is a direction perpendicular to the lane direction.

[0011] Based on the latitude and longitude information of the monitoring vehicle and the latitude and longitude information of the distance reference point, the second lateral distance is calculated. The second lateral distance is the lateral distance between the monitoring vehicle and the center of the standard lane.

[0012] The third lateral distance is calculated based on the first lateral distance and the second lateral distance, and the third lateral distance is the lateral distance between the road defect and the center of the standard lane;

[0013] The lane where the road defect is located is determined based on the third lateral distance and the lane width.

[0014] Optionally, the standard lane reference point data can be collected using a GNSS device based on RTK technology.

[0015] Optionally, determining the distance reference point based on the reference point specifically includes:

[0016] Initialize S, i, and j to zero; where S represents the cumulative mileage traveled by the monitored vehicle, and i and j are counting variables, i used to count the reference points and j used to count the fixed-distance reference points.

[0017] Count each reference point and compare the magnitudes of i and p-1 in real time. Determine whether to end the counting based on the comparison result, including:

[0018] The counting ends when i > p-1; where p represents the number of reference points.

[0019] When i≤p-1, jump to the step of “comparing the size of S and L and determining the assignment based on the comparison result”;

[0020] Compare the magnitudes of S and L, and determine the assignment based on the comparison result, including:

[0021] When S≤L, assign S the value S+L. i Then jump to the step of "assigning i to i+1"; where L represents the distance between two adjacent fixed-distance reference points, L i This represents the Euclidean distance between the i-th reference point and the (i-1)-th reference point;

[0022] When S > L, the Gaussian plane rectangular coordinates (M) corresponding to the j-th fixed-distance reference point are... j N j The value assigned to (X) i Yi ), and assign the value L to S. i After assigning j to j+1, jump to the step of "assigning i to i+1";

[0023] Assign i the value of i+1, and return to the step of "counting each reference point and comparing the size of i with p-1 in real time, and determining whether to end the counting based on the comparison result" to continue counting until i > p-1, then end the counting.

[0024] Optionally, when road defects are present in the road image, determining the first lateral distance based on the road image specifically includes:

[0025] Extract the road damage image from the road image, the road damage image being an image containing road damage, and obtain the resolution R×D of the road damage image;

[0026] A rectangular coordinate system is established with the top left corner vertex of the road defect image as the origin, and the coordinates (r, d) of the center point of the road defect in the rectangular coordinate system are determined.

[0027] Choose any point on the central axis of the disease image along the vertical axis of the rectangular coordinate system as a marker point, and determine the coordinates (R / 2, D / n) of the marker point on the rectangular coordinate system, where n≥1;

[0028] Perform perspective transformation on the road defect image and determine the perspective transformation coordinates (r) of the center point of the road defect. t d t ) and the perspective transformation coordinates (R) of the marked points t D t );

[0029] Based on the perspective transformation coordinates (r) of the center point of the road defect t d t ) and the perspective transformation coordinates (R) of the marked points t D t Using the formula x c =|R t -r t The first lateral distance is calculated.

[0030] Optionally, calculating the second lateral distance based on the latitude and longitude information of the monitoring vehicle and the latitude and longitude information of the distance reference point specifically includes:

[0031] Based on the latitude and longitude information of the monitoring vehicle and the latitude and longitude information of the distance reference point, calculate the Euclidean distance from the monitoring vehicle to the two nearest distance reference points and the Euclidean distance between the two distance reference points;

[0032] Based on the Euclidean distances from the monitoring vehicle to the two nearest fixed-distance reference points and the Euclidean distance between the two fixed-distance reference points, the area of ​​the triangle formed by the monitoring vehicle and the two fixed-distance reference points is calculated using Heron's formula.

[0033] The second lateral distance is calculated based on the area of ​​the triangle and the Euclidean distance between the two fixed-distance reference points.

[0034] Optionally, use the formula Calculate the third lateral distance;

[0035] Where, x d The third lateral distance is represented by h, the second lateral distance is represented by x. c r represents the first horizontal distance. t This represents the perspective-transformed abscissa of the center point of a road defect in a rectangular coordinate system established with the top-left corner of the road image as the origin, when road defects exist in the road image; R t The x-coordinate represents the perspective transformation coordinate obtained by selecting any point on the central axis of the road image along the vertical axis of the rectangular coordinate system and performing a perspective transformation.

[0036] Optionally, use the formula Calculate the lane where the road defect is located;

[0037] Where lane represents the lane where the road defect is located, w represents the lane width, and x d [·] indicates the third horizontal distance, and [·] indicates rounding down.

[0038] Optionally, before the step of determining the distance reference point based on the reference point, the following step is further included:

[0039] The latitude and longitude information corresponding to each benchmark point is transformed to obtain the Gaussian plane rectangular coordinate information corresponding to each benchmark point.

[0040] Based on the Gaussian Cartesian coordinates of each reference point, calculate the Euclidean distance between each pair of adjacent reference points.

[0041] Optionally, use the formula Calculate the Euclidean distance between every two adjacent reference points;

[0042] Where i represents the i-th reference point, X i Y represents the Gaussian Cartesian abscissa information corresponding to the i-th reference point. i L represents the Gaussian Cartesian ordinate information corresponding to the i-th reference point. i This represents the Euclidean distance between the i-th reference point and the (i-1)-th reference point.

[0043] On the other hand, the present invention also proposes a system for determining the lane where road defects are located based on a standard lane, the system comprising:

[0044] The standard lane reference point data acquisition module is used to collect standard lane reference point data; the standard lane is the leftmost lane, and the reference point data is the latitude and longitude information collected at a specified sampling frequency when the monitoring vehicle travels along the center of the standard lane, with each latitude and longitude information corresponding to a reference point.

[0045] A distance reference point determination module is used to determine distance reference points based on the reference points; the distance reference points satisfy the condition that the distance between adjacent distance reference points is equal;

[0046] The location acquisition and road image capture module is used to acquire the latitude and longitude information of the monitoring vehicle and the road images captured by the vehicle's onboard camera;

[0047] The first lateral distance calculation module is used to determine a first lateral distance based on the road image when there are road defects in the road image. The first lateral distance is the lateral distance between the road defect and the vehicle-mounted camera. The lateral distance is the distance in the lateral direction, and the lateral direction is the direction perpendicular to the lane direction.

[0048] The second lateral distance calculation module is used to calculate the second lateral distance based on the latitude and longitude information of the monitoring vehicle and the latitude and longitude information of the distance reference point. The second lateral distance is the lateral distance between the monitoring vehicle and the center of the standard lane.

[0049] The third lateral distance calculation module is used to calculate a third lateral distance based on the first lateral distance and the second lateral distance, wherein the third lateral distance is the lateral distance between the road defect and the center of the standard lane;

[0050] The lane location determination module for road defects is used to determine the lane where the road defects are located based on the third lateral distance and the lane width.

[0051] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0052] This invention proposes a method and system for determining the lane containing road defects based on a standard lane. Starting from the dimension of distance, the leftmost lane is taken as the standard lane, and the center line of the standard lane is used as a reference. After a monitoring vehicle captures a road defect, the first lateral distance between the road defect and the onboard camera of the monitoring vehicle, and the second lateral distance between the monitoring vehicle and the center of the standard lane are calculated. This allows for the calculation of the third lateral distance between the road defect and the center of the standard lane. The lane containing the road defect can then be directly determined based on the third lateral distance and the lane width. Locating the lane containing the defect by distance effectively improves the accuracy and reliability of lane defect identification, solving the problem of low accuracy caused by the over-reliance on the clarity of the captured image in traditional image-based lane line identification methods. Furthermore, this invention converts each reference point in the standard lane reference point data into fixed-distance reference points, with equal spacing between adjacent fixed-distance reference points. This reduces the computational load and complexity, making the identification of road defects simpler, more convenient, and faster, thus improving the efficiency of identifying the lane containing road defects. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly described below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. The following drawings are not intentionally drawn to scale to actual size; their focus is on illustrating the main points of the present invention.

[0054] Figure 1 A flowchart illustrating a method for determining the lane containing road defects based on a standard lane, as provided in Embodiment 1 of the present invention;

[0055] Figure 2 This is a schematic diagram illustrating the format of the standard lane reference point data collected according to Embodiment 1 of the present invention;

[0056] Figure 3 This is a flowchart of determining a distance reference point based on a reference point, provided in Embodiment 1 of the present invention;

[0057] Figure 4 This is a schematic diagram illustrating the calculation principle of the first lateral distance provided in Embodiment 1 of the present invention;

[0058] Figure 5 A perspective transformation diagram of the calculation principle diagram of the first lateral distance provided in Embodiment 1 of the present invention;

[0059] Figure 6 This is a schematic diagram illustrating the calculation principle of the second lateral distance provided in Embodiment 1 of the present invention;

[0060] Figure 7 This is a schematic diagram illustrating the calculation of the third lateral distance, as provided in Embodiment 1 of the present invention.

[0061] Figure 8 This is a structural diagram of a road defect determination system based on a standard lane, provided in Embodiment 2 of the present invention. Detailed Implementation

[0062] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0063] As indicated in this invention and the claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0064] While this invention makes various references to certain modules in systems according to embodiments of the invention, any number of different modules can be used and run on user terminals and / or servers. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.

[0065] This invention uses flowcharts to illustrate the operations performed by the system according to embodiments of the invention. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously, as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0066] The purpose of this invention is to provide a method and system for determining the lane where road defects are located based on standard lanes, which can effectively improve the accuracy and efficiency of determining the lane where road defects are located, and accurately and quickly determine the lane where road defects are located.

[0067] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0068] Example 1

[0069] like Figure 1As shown, this embodiment provides a method for determining the lane where road defects are located based on a standard lane. The method specifically includes the following steps:

[0070] Step S1: Collect standard lane reference point data; the standard lane is the leftmost lane, and the reference point data is the latitude and longitude information collected at a specified sampling frequency when the monitoring vehicle travels along the center of the standard lane. Each latitude and longitude value corresponds to one reference point. The data fields and examples of the standard lane reference point data are as follows: Figure 2 As shown.

[0071] In this embodiment, GNSS (Global Navigation Satellite System) equipment based on RTK (Real-Time Kinematic) technology is used to collect the standard lane reference point data.

[0072] In practical applications, the monitoring vehicle is equipped with GNSS equipment based on RTK technology and an on-board camera. The RTK-based GNSS equipment is used to collect standard lane reference point data at a preset frequency and record the latitude and longitude information of the monitoring vehicle at various locations during its travel in the standard lane in real time. The on-board camera is used to collect images of the road surface in front of the monitoring vehicle during its travel.

[0073] Step S2: Determine the distance reference point based on the reference point; the distance reference point satisfies the condition that the distance between adjacent distance reference points is equal.

[0074] Because the distance between reference points in the standard lane reference point data collected by fixed frequency will vary due to the influence of vehicle speed and road conditions. In order to facilitate subsequent data processing, this invention determines fixed-distance reference points based on the reference points, that is, converts the original standard lane reference point data into fixed-distance standard lane reference point data, so that the distance between two adjacent fixed-distance reference points is equal.

[0075] In this embodiment, when converting the original standard lane reference point data into fixed-distance standard lane reference point data, the latitude and longitude information corresponding to each reference point is first transformed to obtain the Gaussian Cartesian coordinate information corresponding to each reference point. Assuming a road segment to be detected has n reference points, i.e., n latitude and longitude coordinates, these n latitude and longitude coordinates are converted into n Gaussian Cartesian coordinates (X, Y). When i = 1, it represents the Gaussian Cartesian coordinates (X1, Y1) of the first reference point; when i = 2, it represents the Gaussian Cartesian coordinates (X2, Y2) of the second reference point. Then, based on the Gaussian Cartesian coordinate information corresponding to each reference point, the Euclidean distance between each adjacent two reference points is calculated. Finally, a cyclic counting assignment method is used to determine the fixed-distance reference points based on each reference point, thereby realizing the conversion from the original standard lane reference point data to the fixed-distance standard lane reference point data.

[0076] In this embodiment, the Euclidean distance between every two adjacent reference points is calculated using equation (1):

[0077]

[0078] Where i represents the i-th reference point, X i Y represents the Gaussian Cartesian abscissa information corresponding to the i-th reference point. i L represents the Gaussian Cartesian ordinate information corresponding to the i-th reference point. i This represents the Euclidean distance between the i-th reference point and the (i-1)-th reference point.

[0079] In this embodiment, a cyclic counting assignment method is used to determine the fixed-distance reference point based on each reference point, such as... Figure 3 As shown, the specific steps include:

[0080] Step S2.1: Initialize S, i, and j to zero; where S represents the cumulative mileage traveled by the monitored vehicle, and i and j are counting variables, i is used to count the reference points, and j is used to count the fixed-distance reference points.

[0081] Step S2.2: Count each reference point and compare the magnitudes of i and p-1 in real time. Determine whether to end the counting based on the comparison result, including:

[0082] The counting ends when i > p-1; where p represents the number of reference points.

[0083] When i≤p-1, jump to step S2.3, which is the step of “comparing the size of S and L and determining the assignment based on the comparison result”.

[0084] Step S2.3: Compare the sizes of S and L, and determine the assignment based on the comparison result, including:

[0085] When S≤L, assign S the value S+L. i Then, proceed to step S2.4, which is the step of "assigning i to i+1"; where L represents the distance between two adjacent fixed-distance reference points. In this embodiment, for ease of calculation, L is set to 1m; L i This represents the Euclidean distance between the i-th reference point and the (i-1)-th reference point;

[0086] When S > L, the Gaussian plane rectangular coordinates (M) corresponding to the j-th fixed-distance reference point are... j N j The value assigned to (X) i Y i ), and assign the value L to S. i After assigning j to j+1, jump to step S2.4, which is the step of "assigning i to i+1";

[0087] Step S2.4: Assign i the value i+1 and return to step S2.2, that is, continue counting the steps of "counting each reference point and comparing the size of i with p-1 in real time, and determining whether to end the counting based on the comparison result" until i > p-1, then end the counting.

[0088] This invention, after acquiring standard lane reference point data, determines fixed-distance reference points based on each reference point in the standard lane reference point data, thereby converting the standard lane reference point data into fixed-distance standard lane reference point data. This ensures that the intervals between all fixed-distance reference points are equal and all are located on the center boundary line of the standard lane. Incorporating these fixed-distance reference points into the process of identifying lane defects reduces computational load and complexity, making it simpler, more convenient, and faster, thus improving the efficiency of identifying lanes with road defects. Furthermore, using fixed-distance reference points as the data basis for determining lanes with road defects eliminates errors caused by factors such as vehicle speed and road conditions during the collection of the original standard lane reference point data, improving the accuracy of identifying lanes with road defects.

[0089] Step S3: Obtain the latitude and longitude information of the monitoring vehicle and the road images captured by the onboard camera of the monitoring vehicle.

[0090] After collecting standard lane reference point data in step S1 and determining the distance reference point based on the reference point in step S2, basic data based on the standard lane and the distance reference point is obtained. In step S3, image capture, analysis and processing, and lane defect judgment of the road defect of the road section to be monitored are started. When using the vehicle-mounted camera to capture road images, the vehicle-mounted camera is installed at the center point of the monitoring vehicle or the center dividing line of the monitoring vehicle and faces the direction of travel to capture road images in front of the monitoring vehicle. Furthermore, this invention uses the center point of the monitoring vehicle or the installation point of the vehicle-mounted camera as the analysis and processing object, and takes the previous point of the monitoring vehicle for analysis and processing, thereby simplifying the subsequent calculation process and making the calculation process simpler and faster.

[0091] Since the vehicle-mounted camera captures road images throughout the entire journey, most of these images may not show road defects, with only a small portion revealing them. This application analyzes only the images of roads with road defects, determining which lane the defect is located in. Therefore, when road defects are captured, this invention uses the vehicle's location as the center and filters fixed-distance reference points within a certain range on both sides of the vehicle to reduce computation and improve the efficiency of determining the lane where the defect is located.

[0092] In this embodiment, fixed-distance reference points within 50m on both sides of the monitoring vehicle are selected. The latitude and longitude of the vehicle's location when the road surface defects are captured are converted into Gaussian plane rectangular coordinates x and y. Taking the location of the monitoring vehicle as the center, fixed-distance reference points within 50m above and below the Gaussian plane rectangular coordinates x and y are selected. The calculation method is as shown in equation (2):

[0093]

[0094] Among them, (M) j N j ) represents the Gaussian Cartesian coordinates of the j-th fixed-distance reference point, by limiting M j N j The range of values ​​is used to filter out fixed-distance reference points within 50m above and below the x and y coordinates. (m) j n j ) represents the j-th fixed-distance reference point within a 50m radius of the location of the monitored vehicle.

[0095] Step S4: When there are road defects in the road image, determine a first lateral distance based on the road image. The first lateral distance is the lateral distance between the road defect and the vehicle-mounted camera. The lateral distance is the distance in the lateral direction, which is the direction perpendicular to the lane direction.

[0096] Step S4 specifically includes:

[0097] Step S4.1: Extract a defect image from the road image. The defect image is an image containing road defects, and obtain the resolution R×D of the defect image, i.e., R pixels horizontally and D pixels vertically. During camera calibration, obtain the homography matrix M. The homography matrix describes the positional mapping relationship between the object in the world coordinate system and the pixel coordinate system; the corresponding transformation matrix is ​​called the homography matrix.

[0098] Step S4.2: Establish a rectangular coordinate system with the top left corner vertex of the road defect image as the origin, and determine the coordinates (r, d) of the center point of the road defect in the rectangular coordinate system, such as... Figure 4 As shown.

[0099] Step S4.3: Select any point on the central axis of the lesion image along the vertical axis of the rectangular coordinate system as a marker point, and determine the coordinates of the marker point on the rectangular coordinate system as (R / 2, D / n), where n≥1; in this embodiment, for the sake of calculation simplicity, the selected marker point is (R / 2, D), as shown below. Figure 4 As shown.

[0100] Step S4.4: Since the image captured by the vehicle-mounted camera is not actually a rectangular image, but rather an inverted trapezoidal image that spreads outwards from the camera's shooting point towards the distant lanes, this embodiment performs a perspective transformation on the defect image. The defect image after perspective transformation is as follows: Figure 5 As shown, the perspective transformation coordinates (r) of the center point of the road defect are determined. t d t ) and the perspective transformation coordinates (R) of the marked points t D t ).

[0101] Step S4.5: Based on the perspective transformation coordinates (r) of the center point of the road defect t d t ) and the perspective transformation coordinates (R) of the marked points t D t Since the calculation is for horizontal distance, the first horizontal distance x can be obtained by subtracting the x-coordinates of the two coordinates after perspective transformation. c As shown in equation (3):

[0102] x c =|R t -r t | (3)

[0103] The first lateral distance is the lateral distance between the road defect and the vehicle-mounted camera. Since the vehicle-mounted camera is installed at the center point or the central dividing line of the monitoring vehicle, the first lateral distance is also the lateral distance from the road defect to the monitoring vehicle.

[0104] Step S5: Calculate the second lateral distance based on the latitude and longitude information of the monitoring vehicle and the latitude and longitude information of the distance reference point. The second lateral distance is the lateral distance between the monitoring vehicle and the center of the standard lane.

[0105] Step S5 specifically includes:

[0106] Step S5.1: Based on the latitude and longitude information of the monitoring vehicle and the latitude and longitude information of the distance reference point, calculate the Euclidean distance from the monitoring vehicle to the two nearest distance reference points and the Euclidean distance between the two distance reference points.

[0107] In this embodiment, the Euclidean distances from the monitoring vehicle to the two nearest fixed-distance reference points are calculated using equation (4):

[0108]

[0109] Among them, l j This represents the j-th fixed-distance reference point.

[0110] Assume there are two distance reference points closest to the monitoring vehicle, one of which is point A, where j = a. This distance reference point is denoted as l. a Another reference point for distance measurement is point B, where j = b, and this reference point is represented as l. b Since the distance between two adjacent reference points is preset to 1m in this embodiment, the coordinates of the monitoring vehicle must fall between points A and B. Furthermore, because the monitoring vehicle is unlikely to make a significant turn at a distance of 1m, the straight-line distance between points A and B can be considered equal to the road distance between points A and B.

[0111] Let point C be the location of the monitored vehicle. Calculate the Euclidean distance l between points A and C using the formula above. ac The Euclidean distance l between points B and C bc And the Euclidean distance l between points A and B ab ,like Figure 6 As shown.

[0112] Step S5.2: Based on the Euclidean distances from the monitoring vehicle to the two nearest fixed-distance reference points and the Euclidean distance between the two fixed-distance reference points, calculate the area S of the triangle formed by the monitoring vehicle and the two fixed-distance reference points using Heron's formula. ABC .

[0113] The Heron formula used in this embodiment is as shown in equation (5):

[0114]

[0115] Where p is the semi-perimeter of the triangle formed by the monitoring vehicle and the two nearest fixed-distance reference points, expressed as equation (6):

[0116]

[0117] Step S5.3: Calculate the second lateral distance based on the area of ​​the triangle and the Euclidean distance between the two fixed-distance reference points.

[0118] Since the second lateral distance represents the lateral distance between the monitored vehicle and the center of the standard lane, that is, the distance from the monitored vehicle to the center of the standard lane. Figure 6 The perpendicular distance h of the reference lane line is the straight line obtained by connecting multiple fixed-distance reference points. Since the monitoring vehicle travels along the center dividing line of the standard lane, the reference points collected on the standard lane are basically located on the same straight line. Therefore, the fixed-distance reference points determined based on the reference points are also located on this straight line. This straight line is the reference lane line, which is also the center dividing line of the standard lane.

[0119] In step S5.2, the area S of the triangle is calculated using Heron's formula. ABC Furthermore, since the formula for the area of ​​a triangle can also be expressed as equation (7):

[0120]

[0121] By combining equations (5), (6), and (7), the second lateral distance h can be calculated, expressed as equation (8):

[0122]

[0123] Step S6: Calculate the third lateral distance based on the first lateral distance and the second lateral distance. The third lateral distance is the lateral distance between the road defect and the center of the standard lane.

[0124] In this embodiment, the third lateral distance x is calculated using equation (9). d :

[0125]

[0126] Where, x d The third lateral distance is represented by h, the second lateral distance is represented by x. c r represents the first horizontal distance. t This represents the perspective-transformed abscissa of the center point of a road defect in a rectangular coordinate system established with the top-left corner of the road image as the origin, when road defects exist in the road image; R tThe x-coordinate represents the perspective transformation coordinate obtained by selecting any point on the central axis of the road image along the vertical axis of the rectangular coordinate system and performing a perspective transformation.

[0127] Step S7: Determine the lane where the road defect is located based on the third lateral distance and the lane width.

[0128] In this embodiment, after obtaining the third lateral distance x d Then, combining the known lane width w, the lane where the road defect is located can be determined using equation (10):

[0129]

[0130] Where lane represents the lane where the road defect is located, w represents the lane width (typically 3.75m for Class I and II highways), and x represents the lane width. d [·] indicates the third horizontal distance, and [·] indicates rounding down.

[0131] To facilitate understanding of the method for identifying lane defects in this invention, the following examples are provided:

[0132] like Figure 7 As shown, assuming the third lateral distance is 7W / 8, the calculation result of the lane where the road defect is located is shown in equation (11):

[0133]

[0134] In this case, 3 / 8 rounded down equals 0, leading to the conclusion that the road defect is located in the second lane. This conclusion is consistent with... Figure 7 Consistent with what is shown.

[0135] This invention proposes a method for determining the lane containing road defects based on a standard lane. Starting from the dimension of distance, the leftmost lane is taken as the standard lane, and the center line of the standard lane is used as a reference. After a monitoring vehicle captures a road defect, the first lateral distance between the road defect and the onboard camera of the monitoring vehicle, and the second lateral distance between the monitoring vehicle and the center of the standard lane are calculated. This allows for the calculation of the third lateral distance between the road defect and the center of the standard lane. The lane containing the road defect can then be directly determined based on the third lateral distance and the lane width. Locating the lane containing the defect by distance effectively improves the accuracy and reliability of lane defect identification, solving the problem of low accuracy caused by the over-reliance on the clarity of captured images in traditional image-based lane line identification methods.

[0136] Example 2

[0137] like Figure 8As shown, this embodiment provides a system for determining the lane where road defects are located based on a standard lane. The functions of each module in this system are the same as and correspond one-to-one with the steps of the determination method in Embodiment 1. The system specifically includes:

[0138] The standard lane reference point data acquisition module M1 is used to collect standard lane reference point data; the standard lane is the leftmost lane, and the reference point data is the latitude and longitude information collected at a specified sampling frequency when the monitoring vehicle travels along the center of the standard lane, with each latitude and longitude information corresponding to a reference point.

[0139] The distance reference point determination module M2 is used to determine the distance reference point based on the reference point; the distance reference point satisfies the condition that the distance between adjacent distance reference points is equal;

[0140] The location acquisition and road image capture module M3 is used to acquire the latitude and longitude information of the monitoring vehicle and the road images captured by the vehicle's onboard camera.

[0141] The first lateral distance calculation module M4 is used to determine a first lateral distance based on the road image when there are road defects in the road image. The first lateral distance is the lateral distance between the road defect and the vehicle-mounted camera. The lateral distance is the distance in the lateral direction, and the lateral direction is the direction perpendicular to the lane direction.

[0142] The second lateral distance calculation module M5 is used to calculate the second lateral distance based on the latitude and longitude information of the monitoring vehicle and the latitude and longitude information of the distance reference point. The second lateral distance is the lateral distance between the monitoring vehicle and the center of the standard lane.

[0143] The third lateral distance calculation module M6 is used to calculate the third lateral distance based on the first lateral distance and the second lateral distance, wherein the third lateral distance is the lateral distance between the road defect and the center of the standard lane;

[0144] The lane determination module M7 for road defects is used to determine the lane where the road defects are located based on the third lateral distance and the lane width.

[0145] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in a common dictionary shall be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and not as having an idealized or highly formalized meaning, unless expressly defined herein.

[0146] The foregoing description is illustrative of the invention and should not be construed as limiting it. Although several exemplary embodiments of the invention have been described, those skilled in the art will readily understand that many modifications can be made to the exemplary embodiments without departing from the novel teachings and advantages of the invention. Therefore, all such modifications are intended to be included within the scope of the invention as defined in the claims. It should be understood that the foregoing description is illustrative of the invention and should not be construed as limiting it to the specific embodiments disclosed, and modifications to the disclosed embodiments and 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

1. A method for determining the lane where road defects are located based on standard lanes, characterized in that, The method includes: Collect reference point data for the standard lane; the standard lane is the leftmost lane, and the reference point data is the latitude and longitude information collected at a specified sampling frequency when the monitoring vehicle travels along the center of the standard lane, with each latitude and longitude information corresponding to a reference point; Based on the aforementioned reference point, a fixed-distance reference point is determined; the fixed-distance reference point satisfies the condition that the distance between adjacent fixed-distance reference points is equal. Acquire the latitude and longitude information of the monitoring vehicle and road images captured by the vehicle's onboard camera; When road defects are present in the road image, a first lateral distance is determined based on the road image. The first lateral distance is the lateral distance between the road defect and the vehicle-mounted camera. The lateral distance is the distance in the lateral direction, which is a direction perpendicular to the lane direction. Based on the latitude and longitude information of the monitoring vehicle and the latitude and longitude information of the distance reference point, the second lateral distance is calculated. The second lateral distance is the lateral distance between the monitoring vehicle and the center of the standard lane. The third lateral distance is calculated based on the first lateral distance and the second lateral distance, and the third lateral distance is the lateral distance between the road defect and the center of the standard lane; The lane where the road defect is located is determined based on the third lateral distance and the lane width.

2. The method according to claim 1, characterized in that, The standard lane reference point data is collected using GNSS equipment based on RTK technology.

3. The method according to claim 1, characterized in that, The step of determining the distance reference point based on the reference point specifically includes: Initialize S, i, and j to zero; where S represents the cumulative mileage traveled by the monitored vehicle, and i and j are counting variables, i used to count the reference points and j used to count the fixed-distance reference points. Count each reference point and compare the magnitudes of i and p-1 in real time. Determine whether to end the counting based on the comparison result, including: The counting ends when i > p-1; where p represents the number of reference points. When i≤p-1, jump to the step of "comparing the size of S and L and determining the assignment based on the comparison result"; Compare the magnitudes of S and L, and determine the assignment based on the comparison result, including: When S≤L, assign S the value S+L. i Then jump to the step of "assigning i to i+1"; where L represents the distance between two adjacent fixed-distance reference points. i This represents the Euclidean distance between the i-th reference point and the (i-1)-th reference point; When S > L, the Gaussian plane rectangular coordinates (M) corresponding to the j-th fixed-distance reference point are... j N j The value assigned to (X) i Y i ), and assign the value L to S. i After assigning j to j+1, jump to the step of "assigning i to i+1"; Assign i the value of i+1 and return to the step of "counting each reference point and comparing the size of i with p-1 in real time, and determining whether to end the counting based on the comparison result" to continue counting until i > p-1, then end the counting.

4. The method according to claim 1, characterized in that, When road defects are present in the road image, determining the first lateral distance based on the road image specifically includes: Extract the road damage image from the road image, the road damage image being an image containing road damage, and obtain the resolution R×D of the road damage image; A rectangular coordinate system is established with the top left corner vertex of the road defect image as the origin, and the coordinates (r, d) of the center point of the road defect in the rectangular coordinate system are determined. Choose any point on the central axis of the disease image along the vertical axis of the rectangular coordinate system as a marker point, and determine the coordinates (R / 2, D / n) of the marker point on the rectangular coordinate system, where n≥1; Perform perspective transformation on the road defect image and determine the perspective transformation coordinates (r) of the center point of the road defect. t d t ) and the perspective transformation coordinates (R) of the marked points t D t ); Based on the perspective transformation coordinates (r) of the center point of the road defect t d t ) and the perspective transformation coordinates (R) of the marked points t D t Using the formula x c =|R t -r t The first lateral distance is calculated.

5. The method according to claim 1, characterized in that, The step of calculating the second lateral distance based on the latitude and longitude information of the monitoring vehicle and the latitude and longitude information of the distance reference point specifically includes: Based on the latitude and longitude information of the monitoring vehicle and the latitude and longitude information of the distance reference point, calculate the Euclidean distance from the monitoring vehicle to the two nearest distance reference points and the Euclidean distance between the two distance reference points; Based on the Euclidean distances from the monitoring vehicle to the two nearest fixed-distance reference points and the Euclidean distance between the two fixed-distance reference points, the area of ​​the triangle formed by the monitoring vehicle and the two fixed-distance reference points is calculated using Heron's formula. The second lateral distance is calculated based on the area of ​​the triangle and the Euclidean distance between the two fixed-distance reference points.

6. The method according to claim 1, characterized in that, Using formula Calculate the third lateral distance; Where, x d The third lateral distance is represented by h, the second lateral distance is represented by x. c r represents the first horizontal distance. t This represents the perspective-transformed abscissa of the center point of a road defect in a rectangular coordinate system established with the top-left corner of the road image as the origin, when road defects exist in the road image; R t The x-coordinate represents the perspective transformation coordinate obtained by selecting any point on the central axis of the road image along the vertical axis of the rectangular coordinate system and performing a perspective transformation.

7. The method according to claim 1, characterized in that, Using formula Calculate the lane where the road defect is located; Where lane represents the lane where the road defect is located, w represents the lane width, and x d [·] indicates the third horizontal distance, and [·] indicates rounding down.

8. The method according to any one of claims 1-7, characterized in that, Before the step of determining the distance reference point based on the reference point, the following steps are also included: The latitude and longitude information corresponding to each benchmark point is transformed to obtain the Gaussian plane rectangular coordinate information corresponding to each benchmark point. Based on the Gaussian Cartesian coordinates of each reference point, calculate the Euclidean distance between each pair of adjacent reference points.

9. The method according to claim 8, characterized in that, Using formula L i = Calculate the Euclidean distance between every two adjacent reference points; Where i represents the i-th reference point, X i Y represents the Gaussian Cartesian abscissa information corresponding to the i-th reference point. i L represents the Gaussian Cartesian ordinate information corresponding to the i-th reference point. i This represents the Euclidean distance between the i-th reference point and the (i-1)-th reference point.

10. A system for determining the location of road defects in a standard lane, characterized in that, The system includes: The standard lane reference point data acquisition module is used to collect standard lane reference point data; the standard lane is the leftmost lane, and the reference point data is the latitude and longitude information collected at a specified sampling frequency when the monitoring vehicle travels along the center of the standard lane, with each latitude and longitude information corresponding to a reference point. A distance reference point determination module is used to determine distance reference points based on the reference points; the distance reference points satisfy the condition that the distance between adjacent distance reference points is equal; The location acquisition and road image capture module is used to acquire the latitude and longitude information of the monitoring vehicle and the road images captured by the vehicle's onboard camera; The first lateral distance calculation module is used to determine a first lateral distance based on the road image when there are road defects in the road image. The first lateral distance is the lateral distance between the road defect and the vehicle-mounted camera. The lateral distance is the distance in the lateral direction, and the lateral direction is the direction perpendicular to the lane direction. The second lateral distance calculation module is used to calculate the second lateral distance based on the latitude and longitude information of the monitoring vehicle and the latitude and longitude information of the distance reference point. The second lateral distance is the lateral distance between the monitoring vehicle and the center of the standard lane. The third lateral distance calculation module is used to calculate a third lateral distance based on the first lateral distance and the second lateral distance, wherein the third lateral distance is the lateral distance between the road defect and the center of the standard lane; The lane location determination module for road defects is used to determine the lane where the road defects are located based on the third lateral distance and the lane width.

Images