Pavement wear detection method based on precise three dimensions

Abstract

The application relates to the technical field of road surface detection, and provides a road surface wear detection method based on precise three dimensions, which comprises the following steps: receiving original road surface elevation data and original road surface grayscale data of each measuring point on a road acquired by a line scanning three-dimensional measuring sensor, wherein the measuring range of the line scanning three-dimensional measuring sensor covers the entire lane width; determining lane line positions and extracting target road surface elevation data and target road surface grayscale data within the lane range; reconstructing road surface three-dimensional point cloud data; determining road surface full-width structure depth based on the reconstructed road surface three-dimensional point cloud data and in combination with a preset road surface structure depth calculation model; determining the positions of left wheel track bands, right wheel track bands and lane center lines based on the lane line positions and the road surface full-width structure depth; and calculating road surface wear based on the road surface full-width structure depth and the respective positions of the left wheel track bands, the right wheel track bands and the lane center lines. The application can accurately detect road surface wear and can detect road surface wear at any position of the road surface.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of road surface detection, and in particular to a road surface wear detection method based on precise three dimensions. BACKGROUND

[0002] Road surface wear is an important indicator of road technical condition evaluation. In the prior art, the main road surface wear evaluation method is as follows: first, a longitudinal profile curve of the wheel track center is obtained through a profile depth gauge, then the road surface profile depth is calculated through a theoretical model, and finally the road surface wear is calculated through the profile depths of the left wheel track band, the right wheel track band and the center line of the lane three measuring lines measured at the same time. The profile depth gauge is usually composed of an acceleration sensor and a point laser ranging sensor. The point laser ranging sensor measures the distance between the vehicle and the road surface, and the acceleration sensor calculates the distance of the up and down vibration of the vehicle through double integration, thereby obtaining the longitudinal elevation change of the road surface, i.e. the longitudinal profile curve.

[0003] At present, the road surface wear measurement result is affected by the driving track of the driver, especially for the road sections with poor road conditions. In order to ensure the comfort and safety of driving, the driver will intentionally avoid the wheel track band position with poor road conditions during driving, thereby causing the road surface wear measurement result to be inaccurate. SUMMARY

[0004] The present application provides a road surface wear detection method based on precise three dimensions, which solves the problem of inaccurate road surface wear measurement result in the prior art.

[0005] The present application provides a road surface wear detection method based on precise three dimensions, which includes:

[0006] Receiving original road surface elevation data and original road surface grayscale data of each measuring point on the road acquired by a line scanning three-dimensional measuring sensor, and the measuring range of the line scanning three-dimensional measuring sensor covers the entire lane width;

[0007] Determining the lane line position from the original road surface elevation data and the original road surface grayscale data, and extracting target road surface elevation data and target road surface grayscale data within the lane range;

[0008] Reconstructing road surface three-dimensional point cloud data based on the target road surface elevation data and the target road surface grayscale data;

[0009] Determining the road surface full-width profile depth based on the reconstructed road surface three-dimensional point cloud data and in combination with a preset road surface profile depth calculation model;

[0010] Determining the positions of the left wheel track band, the right wheel track band and the center line of the lane based on the lane line position and the road surface full-width profile depth;

[0011] Based on the road surface full-width construction depth, and the respective positions of the left wheel track band, the right wheel track band, and the lane centerline, the road surface wear is calculated.

[0012] According to the present application, a precise three-dimensional based road surface wear detection method is provided, which determines lane line positions from original road surface elevation data and original road surface grayscale data, and extracts target road surface elevation data and target road surface grayscale data within a lane range, including:

[0013] Based on the original road surface elevation data, the elevation characteristics and geometric size characteristics of the road lane line are utilized to mark a potential lane line first area;

[0014] Based on the original road surface grayscale data, the reflection characteristics and geometric size characteristics of the road lane line are utilized to mark a potential lane line second area;

[0015] The lane line positions of the current road surface are determined by combining the potential lane line first area and the potential lane line second area;

[0016] Based on the lane line positions of the current road surface, the target road surface elevation data and the target road surface grayscale data within the lane range are extracted.

[0017] According to the present application, a precise three-dimensional based road surface wear detection method is provided, which reconstructs road surface three-dimensional point cloud data based on the target road surface elevation data and the target road surface grayscale data, including:

[0018] Based on the target road surface elevation data and the target road surface grayscale data, abnormal elevation measurement points within the lane range are determined;

[0019] Based on the target road surface elevation data of non-abnormal elevation measurement points, elevation estimation data of abnormal elevation measurement points are estimated to generate effective road surface elevation data, which includes the target road surface elevation data of non-abnormal elevation measurement points and the elevation estimation data;

[0020] Based on the effective road surface elevation data, road surface three-dimensional point cloud data is reconstructed.

[0021] According to the present application, a precise three-dimensional based road surface wear detection method is provided, which determines abnormal elevation measurement points within the lane range based on the target road surface elevation data and the target road surface grayscale data, including:

[0022] Based on the target road surface elevation data, preliminary abnormal elevation measurement points within the lane range are determined;

[0023] Based on the target road surface grayscale data and the preliminary abnormal elevation measurement points, the abnormal elevation measurement points are determined.

[0024] According to the application, a road surface wear detection method based on precise three-dimensional is provided, which comprises the following steps:

[0025] Obtaining high-frequency road surface elevation signals in the target road surface elevation data;

[0026] For any measuring point, calculating the elevation mean and elevation variance of the high-frequency road surface elevation signals of all measuring points within a first preset range around the measuring point;

[0027] For any measuring point, calculating the first abnormal elevation segmentation threshold and the second abnormal elevation segmentation threshold based on the corresponding elevation mean and elevation variance, so that the first abnormal elevation segmentation threshold is greater than the second abnormal elevation segmentation threshold;

[0028] For any measuring point, if the corresponding high-frequency road surface elevation signal is greater than the first abnormal elevation segmentation threshold or less than the second abnormal elevation segmentation threshold, the measuring point is determined as the preliminary abnormal elevation measuring point.

[0029] According to the application, a road surface wear detection method based on precise three-dimensional is provided, which comprises the following steps:

[0030] For any preliminary abnormal elevation measuring point, calculating the gray mean and gray variance of the target road surface gray data of all measuring points within a second preset range around the preliminary abnormal elevation measuring point;

[0031] For any preliminary abnormal elevation measuring point, calculating the first abnormal gray segmentation threshold and the second abnormal gray segmentation threshold based on the corresponding gray mean and gray variance, so that the first abnormal gray segmentation threshold is greater than the second abnormal gray segmentation threshold;

[0032] For any preliminary abnormal elevation measuring point, if the corresponding target road surface gray data is greater than the first abnormal elevation segmentation threshold or less than the second abnormal elevation segmentation threshold, the preliminary abnormal elevation measuring point is determined as the abnormal elevation measuring point.

[0033] According to the application, a road surface wear detection method based on precise three-dimensional is provided, which comprises the following steps:

[0034] For any abnormal elevation measuring point, estimating the elevation estimation data of the abnormal elevation measuring point based on the target road surface elevation data of the non-abnormal elevation measuring points within a predetermined area around the abnormal elevation measuring point;

[0035] The elevation estimation data and target road surface elevation data of non-anomalous elevation measurement points are determined as the effective road surface elevation data.

[0036] A pavement wear detection method based on precise three dimensions is provided, which determines pavement full-width texture depth based on reconstructed pavement three-dimensional point cloud data and a preset pavement texture depth calculation model, and includes:

[0037] The reconstructed pavement three-dimensional point cloud data is divided into a plurality of first-level point cloud units along the driving direction;

[0038] Any first-level point cloud unit is divided into a plurality of second-level point cloud units along the road width direction;

[0039] For all second-level point cloud units in any first-level point cloud unit, the texture depth of all second-level point cloud units is calculated based on a preset pavement texture depth calculation model, and then a texture depth set of each first-level point cloud unit is obtained;

[0040] The pavement full-width texture depth is determined based on the texture depth set.

[0041] A pavement wear detection method based on precise three dimensions is provided, which determines the positions of left and right wheel tracks and the center line of the lane based on the lane line position and the pavement full-width texture depth, and includes:

[0042] The distance between the left and right wheel tracks is a fixed range, and the centers of the left and right wheel tracks are located at the center of the lane, and the lane line position is combined to determine the IDs of the second-level point cloud units corresponding to the quasi-left wheel track, the quasi-right wheel track and the quasi-lane center line, respectively denoted as L', R' and M', and the IDs of the second-level point cloud units are used as the respective positions;

[0043] According to the spacing of adjacent units in the second-level point cloud unit along the road width direction, a preset search range D is determined;

[0044] Within the preset search range D, the position deviation d satisfying the constraint condition s.t. is searched according to the following maximization target Z, and based on the position deviation d and the quasi-left wheel track, the quasi-right wheel track and the quasi-lane center line, the IDs of the second-level point cloud units corresponding to the left wheel track, the right wheel track and the lane center line are obtained, respectively denoted as L, R and M,

[0045] max Z=SMTD M -(SMTD L +SMTD R ) / 2

[0046]

[0047] Among them, SMTD L 、SMTD R and SMTD M They represent the construction depths of the secondary point cloud units corresponding to the left wheel track, right wheel track, and lane centerline, respectively.

[0048] According to the present invention, a method for detecting road wear based on precise three-dimensional (3D) calculation of road wear is provided, based on the full-width structural depth of the road surface and the respective positions of the left wheel track, the right wheel track, and the center line of the lane, including: calculating at least one of the road wear at the wheel track position and the road wear at the non-wheel track position;

[0049] The calculation of the road wear at the wheel track position includes:

[0050] Based on the structural depths corresponding to the positions of the left wheel track, the right wheel track, and the center line of the lane, the pavement wear rate at the wheel track position is calculated according to the following formula to obtain the pavement wear WR1 at the wheel track position:

[0051]

[0052] Calculation of pavement wear at non-tread locations includes:

[0053] For any second-level point cloud unit in any first-level point cloud unit, the construction depth corresponding to the lane centerline position is used as the construction depth reference value without wear. The pavement wear rate is calculated according to the following formula to obtain the pavement wear WR2 at the non-wheel track position:

[0054]

[0055] Where n is the number of secondary point cloud units in each primary point cloud unit.

[0056] The application provides a precise three-dimensional pavement wear detection method, which comprises the following steps: receiving original pavement elevation data and original pavement grayscale data of each measuring point on a road acquired by a line scanning three-dimensional measuring sensor, wherein the measuring range of the line scanning three-dimensional measuring sensor covers the entire lane width; determining lane line positions from the original pavement elevation data and the original pavement grayscale data, and extracting target pavement elevation data and target pavement grayscale data within the lane range; reconstructing pavement three-dimensional point cloud data based on the target pavement elevation data and the target pavement grayscale data; determining pavement full-width profile depth based on the reconstructed pavement three-dimensional point cloud data and a preset pavement profile depth calculation model; determining the positions of left tire track bands, right tire track bands and lane center lines based on the lane line positions and the pavement full-width profile depth; and calculating pavement wear based on the pavement full-width profile depth, the positions of the left tire track bands, the right tire track bands and the lane center lines. Since the measuring range of the line scanning three-dimensional measuring sensor covers the entire lane width, the original pavement elevation data and the original pavement grayscale data are data covering the entire lane width, and the positions of the tire track bands with poor road conditions cannot be avoided. Moreover, the target pavement elevation data and the target pavement grayscale data within the lane range are used to reconstruct the pavement three-dimensional point cloud data, so that the data interference of lane lines and lane edges and other non-lane areas is removed, the pavement full-width profile depth can be accurately measured, the positions of the pavement tire track bands and the lane center lines can be accurately positioned based on the accurate pavement full-width profile depth and the lane line positions, and thus the pavement wear can be accurately measured. Meanwhile, since the pavement wear is detected based on the pavement full-width profile depth covering the entire pavement width, the pavement wear at any position in the lane can also be evaluated. BRIEF DESCRIPTION OF DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort.

[0058] Figure 1 is one of the flowcharts of the precise three-dimensional pavement wear detection method provided by the present application;

[0059] Figure 2 is another flowchart of the precise three-dimensional pavement wear detection method provided by the present application;

[0060] Figure 3 is a third flowchart of the precise three-dimensional pavement wear detection method provided by the present application;

[0061] Figure 4Figure 4 is a flowchart of a fourth process of the method for detecting pavement wear based on precise three dimensions according to the present application;

[0062] Figure 5 Figure 5 is a flowchart of a fifth process of the method for detecting pavement wear based on precise three dimensions according to the present application;

[0063] Figure 6 Figure 6 is a flowchart of a sixth process of the method for detecting pavement wear based on precise three dimensions according to the present application;

[0064] Figure 7 Figure 7 is a flowchart of a seventh process of the method for detecting pavement wear based on precise three dimensions according to the present application

[0065] Figure 8 Figure 8 is a flowchart of an eighth process of the method for detecting pavement wear based on precise three dimensions according to the present application

[0066] Figure 9 Figure 1 is a structural schematic diagram of a device for detecting full-width construction depth based on precise three dimensions according to the present application.

[0067] Figure 10 Figure 2 is a structural schematic diagram of an electronic device according to the present application. DETAILED DESCRIPTION

[0068] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0069] The method for detecting pavement wear based on precise three dimensions provided by the embodiments of the present application, as shown in Figure 1 includes the following steps.

[0070] Step S110: receiving original road elevation data and original road grayscale data of each measuring point on the road acquired by a line scanning three-dimensional measuring sensor, a measurement range of the line scanning three-dimensional measuring sensor covering the entire lane width. Specifically, the line scanning three-dimensional measuring sensor includes a laser and a high-speed three-dimensional camera, and is installed on a vehicle-mounted platform. During the measurement, the line scanning three-dimensional measuring sensor continuously collects elevation information and grayscale information of the road surface, i.e. the original road elevation data and the original road grayscale data, in the road direction. The original road elevation data and the original road grayscale data can be acquired simultaneously by receiving the data returned by the line scanning three-dimensional measuring sensor. In order to reflect the full-width pavement texture depth, the measurement range of the line scanning three-dimensional measuring sensor is required to cover the entire lane in the road width direction, and the collection interval of the original road elevation data and the original road grayscale data in the road width direction is less than or equal to 5 mm, and the collection interval in the driving direction is less than or equal to 5 mm. One or more sets of line scanning three-dimensional measuring sensors can be provided on the vehicle according to the road width, so that the total coverage width can reach full-lane coverage.

[0071] Step S120: determining the lane line position from the original road elevation data and the original road grayscale data, and extracting target road elevation data and target road grayscale data within the lane range. Specifically, since the elevation and grayscale of the lane line are greatly different from those of the conventional road surface area (not containing the marking area), the lane line position can be determined from the original road elevation data and the original road grayscale data through such differential analysis, and then the original road elevation data and the original road grayscale data outside the road edge lane line or even the lane line can be removed, so that the data for three-dimensional point cloud reconstruction only contains data within the lane, so that the final measurement result can accurately reflect the full-width pavement texture depth, and the pavement wear can also be accurately detected based on the accurate full-width pavement texture depth.

[0072] Step S130: reconstructing road three-dimensional point cloud data based on the target road elevation data and the target road grayscale data.

[0073] Step S140: determining the full-width pavement texture depth based on the reconstructed road three-dimensional point cloud data and a preset pavement texture depth calculation model.

[0074] Step S150: determining the positions of the left tire track, the right tire track and the lane center line based on the lane line position and the full-width pavement texture depth. Since the left tire track, the right tire track and the lane center line are needed for subsequent calculation of pavement wear, in this step, the positions of the left tire track, the right tire track and the lane center line are determined based on the lane line position and the full-width pavement texture depth.

[0075] Step S160: Calculate pavement wear based on the full-width pavement structural depth and the respective positions of the left and right wheel tracks and lane centerline. The structural depths corresponding to the left and right wheel tracks and lane centerline, as well as the full-width pavement structural depth, can be used to determine the respective structural depths. Thus, pavement wear at the wheel track locations can be calculated. Similarly, using the structural depth corresponding to the lane centerline as a baseline for no wear, pavement wear can also be calculated at locations other than the wheel track locations.

[0076] In this embodiment's precision 3D full-width structural depth detection method, since the line-scan 3D measurement sensor's measurement range covers the entire lane width, the raw road surface elevation data and raw road surface grayscale data cover the entire lane width, ensuring that wheel tracks in poor road conditions are not avoided. Furthermore, the 3D point cloud data of the road surface is reconstructed using target road surface elevation data and target road surface grayscale data within the lane range, eliminating data interference from lane lines and other non-lane areas at the lane edge. This allows for accurate measurement of the full-width structural depth of the road surface. Based on the accurate full-width structural depth and lane line locations, the wheel tracks and lane centerline can be precisely located, enabling accurate measurement of road wear. Furthermore, since road wear is detected based on the full-width structural depth of the road surface, covering the entire road width, it can also assess road wear at any location within the lane.

[0077] like Figure 2 As shown, in some embodiments, step S120 specifically includes:

[0078] Step S210: Based on the raw road elevation data, the potential first lane line region is marked using the elevation and geometric features of the lane lines. Typically, a lane on a road is defined by two lane lines. The geometric dimensions (i.e., width and height) of the lane lines meet relevant road standards, and the elevation of the lane lines is higher than that of the normal road surface. Therefore, the first lane line region (i.e., the region between two lane lines) can be marked using the raw road elevation data, the elevation features, and the geometric features of the lane lines.

[0079] Step S220: Based on the original road surface grayscale data, the potential second lane marking area is marked using the reflective characteristics and geometric size characteristics of the lane markings. Typically, lane markings are white or yellow, which has different reflective properties from the gray road surface. Therefore, the second lane marking area can be marked using the original road surface grayscale data, the reflective characteristics, and the geometric size characteristics of the lane markings.

[0080] Step S230: Determine the lane line position of the current road surface by combining the first potential lane line region and the second potential lane line region. Steps S210 and S220 respectively mark two different lane line regions in different ways, and the results obtained by different methods can be verified with each other. For example, if the two different lane line regions completely overlap or the overlap rate is as high as 80% or more, it is considered that the lane line regions marked by the two ways are relatively accurate. When determining the lane line position of the current road surface, the maximum region covered by the two lane line regions (i.e., the union of the two lane line regions) can be used as the lane line region, i.e., the position of the lane line. Using the maximum region covered by the two lane line regions as the lane line region can exclude abnormal points on the edge of the lane as much as possible, so that the final detected road surface wear result is more accurate.

[0081] Step S240: Extract target road surface elevation data and target road surface grayscale data within the lane range based on the lane line position of the current road surface. Specifically, since the lane line position of the current road surface is determined, i.e., the region of the lane line is determined, the lane range can be determined according to the region between the inner edges of the left lane line region and the right lane line region, so as to extract the target road surface elevation data and the target road surface grayscale data within the lane range.

[0082] In step S130, the reconstructed road surface three-dimensional point cloud data can be directly reconstructed using the target road surface elevation data and the target road surface grayscale data. However, there may be some abnormal data in the target road surface elevation data and the target road surface grayscale data within the lane range, and the detection points corresponding to the abnormal data are abnormal detection points. For road surfaces (e.g., asphalt road surfaces), the road surface aggregates are relatively dense, and the shapes of the aggregates are different. For positions where the profiles between aggregates change sharply and the gaps are deep, or for some road crack regions, there may be some invalid detection points (3D cameras cannot observe the light signals returned by the corresponding detection points), and the measurement values of these detection points are obviously abnormal, and such detection points usually exhibit characteristics such as high frequency and local mutation. If such detection points are not removed, the accuracy of the road surface wear result will be obviously affected.

[0083] Therefore, in some embodiments, the data of the abnormal detection points can be processed in a manner as shown in Figure 3 to form valid data, and then the road surface three-dimensional point cloud data is reconstructed by using the valid data. Specifically, step S130 includes:

[0084] Step S310: Determine the abnormal elevation detection points within the lane range based on the target road surface elevation data and the target road surface grayscale data.

[0085] Step S320: estimating elevation estimation data of the abnormal elevation measuring points based on the target road elevation data of the non-abnormal elevation measuring points, to generate valid road elevation data, which includes the target road elevation data of the non-abnormal elevation measuring points and the elevation estimation data.

[0086] Step S330: reconstructing road three-dimensional point cloud data based on the valid road elevation data.

[0087] As shown in Figure 4 , step S310 specifically includes:

[0088] Step S410: determining preliminary abnormal elevation measuring points within the lane range based on the target road elevation data.

[0089] Step S420: determining the abnormal elevation measuring points based on the target road grayscale data and the preliminary abnormal elevation measuring points.

[0090] In some embodiments, as shown in Figure 5 , step S410 specifically includes:

[0091] Step S510: obtaining high-frequency road elevation signals in the target road elevation data. Wherein, for each measuring point, the target road elevation data collected by the line scanning three-dimensional measuring sensor includes two parts of low-frequency signals and high-frequency signals, in this embodiment, the high-frequency signal part is extracted, and the high-frequency signal can be obtained by filtering (such as high-pass filtering) or frequency domain transformation (such as Fourier transform, wavelet transform, etc.).

[0092] Step S520: for any measuring point, calculating the elevation mean and the elevation variance of the high-frequency road elevation signals of all measuring points within a first preset range around the any measuring point, wherein the measuring points in the first preset range can be the measuring points within 5-20 rows and 5-20 columns around the any measuring point.

[0093] Step S530: for any measuring point, calculating a first abnormal elevation segmentation threshold and a second abnormal elevation segmentation threshold based on the corresponding elevation mean and the elevation variance, so that the first abnormal elevation segmentation threshold is greater than the second abnormal elevation segmentation threshold. Specifically, the calculation methods of the first abnormal elevation segmentation threshold T1 and the second abnormal elevation segmentation threshold T2 are as follows:

[0094] T1 = A h +k1*S h

[0095] T2 = A h -k2*S h

[0096] Wherein, A h is the elevation mean, and S hfor the height variance, k1 and k2 are respectively the first coefficient and the second coefficient, both of which are greater than 0. The values of T1 and T2 can be adjusted by adjusting the values of k1 and k2, so as to determine the screening range of the preliminary abnormal height measuring points.

[0097] Step S540: for any measuring point, if the corresponding high-frequency road surface height signal of the measuring point is greater than the first abnormal height segmentation threshold or less than the second abnormal height segmentation threshold, the measuring point is determined as the preliminary abnormal height measuring point, that is, the corresponding any measuring point outside the interval [T2, T1] is determined as the preliminary abnormal height measuring point.

[0098] In some embodiments, as shown in FIG. 4, step S420 specifically includes: Figure 6

[0099] Step S610: for any preliminary abnormal height measuring point, the gray mean value and the gray variance of the target road surface gray data of all measuring points within a second preset range around the preliminary abnormal height measuring point are calculated. The measuring points in the second preset range can be the measuring points within 5-100 rows and 5-100 columns around the any measuring point.

[0100] Step S620: for any preliminary abnormal height measuring point, the first abnormal gray segmentation threshold and the second abnormal gray segmentation threshold are calculated based on the corresponding gray mean value and the gray variance, so that the first abnormal gray segmentation threshold is greater than the second abnormal gray segmentation threshold. Specifically, the calculation method of the first abnormal gray segmentation threshold T3 and the second abnormal gray segmentation threshold T4 is as follows:

[0101] T3 = k g1 *A g +k3*S g

[0102] T4 = k g2 *A g -k4*S g

[0103] wherein A g is the gray mean value, S g is the gray variance, k3, k4, k g1 and k g2 are respectively the third coefficient, the fourth coefficient, the fifth coefficient and the sixth coefficient, k3, k4, k g1 and k g2 are all greater than 0. The values of T3 and T4 can be adjusted by adjusting the values of k3, k4, k g1 and k g2 , so as to determine the screening range of the abnormal height measuring points.

[0104] ​Step S630: For any preliminary abnormal elevation measuring point, if the corresponding target road surface gray data of the preliminary abnormal elevation measuring point is greater than the first abnormal elevation segmentation threshold or less than the second abnormal elevation segmentation threshold, the preliminary abnormal elevation measuring point is determined as the abnormal elevation measuring point, that is, the corresponding preliminary abnormal elevation measuring point outside the interval [T4, T3] is determined as the abnormal elevation measuring point.

[0105] In some embodiments, step S320 specifically comprises:

[0106] For any abnormal elevation measuring point, the elevation estimation data of the abnormal elevation measuring point is estimated based on the target road surface elevation data of the non-abnormal elevation measuring points in a predetermined area (for example, in a range of 5-10 rows and 5-10 columns around the measuring point) around the abnormal elevation measuring point. Specifically, the elevation estimation data of the position corresponding to the abnormal elevation measuring point can be estimated by triangulation or interpolation.

[0107] The elevation estimation data and the target road surface elevation data of the non-abnormal elevation measuring points are determined as the effective road surface elevation data.

[0108] In this embodiment, the target road surface elevation data of the abnormal elevation measuring point is estimated based on the target road surface elevation data of the normal measuring points in a predetermined area around the abnormal elevation measuring point, so that the target road surface elevation data of the abnormal elevation measuring point is regressed to the normal value in the predetermined area, thereby obtaining the effective road surface elevation data. The road surface three-dimensional point cloud data reconstructed by the effective road surface elevation data is more accurate, and thus the final detected road surface wear is also more accurate.

[0109] In some embodiments, as shown in FIG. 13, step S140 specifically comprises: Figure 7

[0110] Step S710: The reconstructed road surface three-dimensional point cloud data is divided into a plurality of first-level point cloud units along the driving direction, that is, the reconstructed road surface three-dimensional point cloud data is divided into a plurality of first-level point cloud units along the road length direction, and each first-level point cloud unit covers the entire road width. Specifically, the reconstructed road surface three-dimensional point cloud data can be divided into a plurality of first-level point cloud units along the driving direction according to the length requirement of the constructed depth calculation (for example, 0.3 meters, 1 meter, 10 meters, 20 meters, 100 meters, or 1000 meters, etc.).

[0111] Step S720: Any first-level point cloud unit is divided into a plurality of second-level point cloud units along the road width direction, that is, each first-level point cloud unit is divided into a plurality of second-level point cloud units along the road width direction.

[0112] ​Step S730: For all the secondary point cloud units in any of the primary point cloud units, the structural depths of all the secondary point cloud units are calculated based on the preset road surface structural depth calculation model, and then the structural depth set SMTD of each of the primary point cloud units is obtained, which is recorded as: {SMTD1, SMTD2, ..., SMTD n}, for the construction depth SMTD of the first-level point cloud unit i , is the construction depth of the i-th secondary point cloud unit in the said primary point cloud unit, i = 1, 2, ..., n.

[0113] Step S740: Determine the full-width construction depth of the road surface based on the construction depth set.

[0114] Specifically, this step includes:

[0115] Based on the constructed depth set, the following are determined: a left wheel track constructed depth, a right wheel track constructed depth, a lane centerline constructed depth, and the constructed depth set.

[0116] In the road wear detection, the left wheel track structure depth, the right wheel track structure depth and the lane centerline structure depth are needed. Therefore, in some embodiments, Figure 8 As shown, step S150 specifically includes:

[0117] Step S810: Using the characteristics that the distance between the left wheel track band and the right wheel track band is a fixed range, and the centers of the left wheel track band and the right wheel track band are located at the center of the lane, combined with the position of the lane line, determine the IDs of the secondary point cloud units corresponding to the quasi-left wheel track band, the quasi-right wheel track band and the quasi-lane center line, respectively, and record them as: L′, R′ and M′, and use the IDs of the corresponding secondary point cloud units as their respective positions.

[0118] Step S820: Determine a preset search range D based on the spacing between adjacent secondary point cloud units along the road width. Because lane detection results may have some deviation, and because vehicle trajectories often deviate from the lane centerline in special areas such as lane merges and curves, the IDs of the secondary point cloud units corresponding to the quasi-left wheel track band, quasi-right wheel track band, and quasi-lane centerline obtained in step S810 may be inaccurate and need to be adjusted based on the preset search range D and the following formula. The preset search range D can be the range of ±80 cm between adjacent secondary point cloud units along the road width.

[0119] Step S830: In the preset search range D, search for a position deviation d satisfying the constraint condition s.t. by maximizing the target Z, and based on the position deviation d and the quasi-left wheel track, the quasi-right wheel track and the quasi-lane center line, obtain the IDs of the second-level point cloud units corresponding to the left wheel track, the right wheel track and the lane center line respectively, denoted as L, R and M respectively.

[0120] max Z=SMTD M -(SMTD L +SMTD R ) / 2

[0121]

[0122] wherein SMTD L , SMTD R and SMTD M respectively represent the construction depth of the second-level point cloud units corresponding to the left wheel track, the right wheel track and the lane center line.

[0123] Since the road wear is detected based on the road full-width construction depth covering the entire road width, the road wear at any position in the lane can be detected. In some embodiments, step S160 comprises: calculating at least one of the road wear at the wheel track position and the road wear at the non-wheel track position.

[0124] Specifically, the calculation of the road wear at the wheel track position comprises:

[0125] Based on the construction depths corresponding to the positions of the left wheel track, the right wheel track and the lane center line, the road wear rate at the wheel track position is calculated according to the following formula, and the road wear WR1 at the wheel track position is obtained:

[0126]

[0127] Specifically, the calculation of the road wear at the non-wheel track position comprises:

[0128] For any second-level point cloud unit in any first-level point cloud unit, the construction depth corresponding to the position of the lane center line is taken as the construction depth reference value without wear, and the road wear rate is calculated according to the following formula, and the road wear WR2 at the non-wheel track position is obtained:

[0129]

[0130] wherein n is the number of second-level point cloud units in each first-level point cloud unit.

[0131] The precision three-dimensional based pavement wear detection device provided by the present application is described below, and the precision three-dimensional based pavement wear detection device described below can be correspondingly referred to the precision three-dimensional based pavement wear detection method described above.

[0132] The precision three-dimensional based pavement wear detection device provided by the present application, as shown in Figure 9 , comprises:

[0133] The data receiving module 910 is configured to receive original pavement elevation data and original pavement grayscale data of each measurement point on the road acquired by the line scanning three-dimensional measurement sensor, and the measurement range of the line scanning three-dimensional measurement sensor covers the entire lane width.

[0134] The data extraction module 920 is configured to determine lane line positions from the original pavement elevation data and the original pavement grayscale data, and extract target pavement elevation data and target pavement grayscale data within the lane range.

[0135] The data reconstruction module 930 is configured to reconstruct pavement three-dimensional point cloud data based on the target pavement elevation data and the target pavement grayscale data.

[0136] The construction depth determination module 940 is configured to determine pavement full-width construction depth based on the reconstructed pavement three-dimensional point cloud data and in combination with a preset pavement construction depth calculation model.

[0137] The position determination module 950 is configured to determine positions of left tire track bands, right tire track bands and lane centerlines based on the lane line positions and the pavement full-width construction depth.

[0138] The pavement wear calculation module 960 is configured to calculate pavement wear based on the pavement full-width construction depth and positions of the left tire track bands, the right tire track bands and the lane centerlines.

[0139] Figure 10 An example of an entity structure schematic diagram of an electronic device is shown in Figure 10 , which can include a processor 101, a communications interface 102, a memory 103 and a communications bus 104, wherein the processor 101, the communications interface 102 and the memory 103 complete mutual communication through the communications bus 104. The processor 101 can invoke logical instructions in the memory 103 to execute a precision three-dimensional based pavement wear detection method, which comprises:

[0140] Receiving original pavement elevation data and original pavement grayscale data of each measurement point on the road acquired by the line scanning three-dimensional measurement sensor, and the measurement range of the line scanning three-dimensional measurement sensor covers the entire lane width.

[0141] determining lane line positions from the original road surface elevation data and the original road surface grayscale data, and extracting target road surface elevation data and target road surface grayscale data within a lane range.

[0142] reconstructing road surface three-dimensional point cloud data based on the target road surface elevation data and the target road surface grayscale data.

[0143] determining road surface full-width texture depth based on the reconstructed road surface three-dimensional point cloud data and a preset road surface texture depth calculation model.

[0144] determining positions of left and right tire track bands and a lane center line based on the lane line positions and the road surface full-width texture depth.

[0145] calculating road surface wear based on the road surface full-width texture depth and the positions of the left and right tire track bands and the lane center line.

[0146] In addition, the logical instructions in the memory 103 described above can be implemented in the form of a software function unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0147] On the other hand, the present application also provides a computer program product, which comprises a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program can be executed by a processor to enable a computer to execute the precision three-dimensional based road surface wear detection method provided by the above-mentioned methods, the method comprising:

[0148] receiving original road surface elevation data and original road surface grayscale data of each measurement point on the road acquired by a line scanning three-dimensional measurement sensor, and the measurement range of the line scanning three-dimensional measurement sensor covers the entire lane width.

[0149] determining lane line positions from the original road surface elevation data and the original road surface grayscale data, and extracting target road surface elevation data and target road surface grayscale data within a lane range.

[0150] reconstruct road surface three-dimensional point cloud data based on the target road surface elevation data and the target road surface grayscale data.

[0151] determine road surface full-width texture depth based on the reconstructed road surface three-dimensional point cloud data and in combination with a preset road surface texture depth calculation model.

[0152] determine the positions of the left tire track band, the right tire track band and the lane center line based on the lane line positions and the road surface full-width texture depth.

[0153] calculate road surface wear based on the road surface full-width texture depth and the respective positions of the left tire track band, the right tire track band and the lane center line.

[0154] In another aspect, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the precision three-dimensional based road surface wear detection method provided by the above method, which comprises:

[0155] receive original road surface elevation data and original road surface grayscale data of each measurement point on the road acquired by a line scanning three-dimensional measurement sensor, the measurement range of the line scanning three-dimensional measurement sensor covering the entire lane width.

[0156] determine lane line positions from the original road surface elevation data and the original road surface grayscale data, and extract target road surface elevation data and target road surface grayscale data within the lane range.

[0157] reconstruct road surface three-dimensional point cloud data based on the target road surface elevation data and the target road surface grayscale data.

[0158] determine road surface full-width texture depth based on the reconstructed road surface three-dimensional point cloud data and in combination with a preset road surface texture depth calculation model.

[0159] determine the positions of the left tire track band, the right tire track band and the lane center line based on the lane line positions and the road surface full-width texture depth.

[0160] calculate road surface wear based on the road surface full-width texture depth and the respective positions of the left tire track band, the right tire track band and the lane center line.

[0161] The device embodiments described above are merely illustrative, wherein the units illustrated as separate components can or can not be physically separated, and the components illustrated as units can or can not be physical units, i.e., can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purposes of the present embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0162] Those skilled in the art can clearly understand the implementation of the various embodiments by means of software and necessary general hardware platforms through the description of the above embodiments, and of course, the embodiments can also be implemented by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, and the computer software product can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method described in each embodiment or some parts of the embodiment.

[0163] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement for some technical features thereof; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for detecting road surface wear based on precision three dimensions, characterized in that, The method comprises the following steps: receiving original road elevation data and original road grayscale data of each measuring point on the road acquired by a line scanning three-dimensional measurement sensor, wherein the measurement range of the line scanning three-dimensional measurement sensor covers the entire lane width; determining lane line positions from the original road elevation data and the original road grayscale data, and extracting target road elevation data and target road grayscale data within the lane range; reconstructing road three-dimensional point cloud data based on the target road elevation data and the target road grayscale data; determining road full-width profile depth based on the reconstructed road three-dimensional point cloud data and a preset road profile depth calculation model; determining the positions of left and right wheel tracks and the lane centerline based on the lane line positions and the road full-width profile depth; calculating road wear based on the road full-width profile depth, the positions of the left and right wheel tracks and the lane centerline; determining lane line positions from the original road elevation data and the original road grayscale data, and extracting target road elevation data and target road grayscale data within the lane range, comprising: based on the original road elevation data, using the elevation characteristics and geometric size characteristics of the road lane line to mark a potential lane line first area; based on the original road grayscale data, using the reflection characteristics and geometric size characteristics of the road lane line to mark a potential lane line second area; determining the lane line positions of the current road by combining the potential lane line first area and the potential lane line second area; extracting target road elevation data and target road grayscale data within the lane range based on the lane line positions of the current road.

2. The precision three-dimensional based pavement wear detection method according to claim 1, characterized in that, reconstructing road three-dimensional point cloud data based on the target road elevation data and the target road grayscale data, comprising: determining abnormal elevation measuring points within the lane range based on the target road elevation data and the target road grayscale data; estimating elevation estimation data of the abnormal elevation measuring points based on the target road elevation data of non-abnormal elevation measuring points to generate effective road elevation data, wherein the effective road elevation data comprises the target road elevation data of non-abnormal elevation measuring points and the elevation estimation data; reconstructing road three-dimensional point cloud data based on the effective road elevation data.

3. The precision three-dimensional based pavement wear detection method according to claim 2, wherein, determining abnormal elevation measuring points within the lane range based on the target road elevation data and the target road grayscale data, comprising: determining preliminary abnormal elevation measuring points within the lane range based on the target road elevation data; determining the abnormal elevation measuring points based on the target road grayscale data and the preliminary abnormal elevation measuring points.

4. The precision three-dimensional based pavement wear detection method according to claim 3, wherein, determining preliminary abnormal elevation measuring points within the lane range based on the target road elevation data, comprising: acquiring high-frequency road elevation signals in the target road elevation data; for any measuring point, calculating the elevation mean and the elevation variance of high-frequency road elevation signals of all measuring points within a first preset range around the measuring point; for any measuring point, calculating a first abnormal elevation segmentation threshold and a second abnormal elevation segmentation threshold based on the corresponding elevation mean and the elevation variance, wherein the first abnormal elevation segmentation threshold is greater than the second abnormal elevation segmentation threshold; For any measuring point, if the corresponding high-frequency road surface elevation signal is greater than the first abnormal elevation segmentation threshold or less than the second abnormal elevation segmentation threshold, the any measuring point is determined as the preliminary abnormal elevation measuring point.

5. The precision three-dimensional based pavement wear detection method according to claim 3, wherein, Based on the target road surface gray data and the preliminary abnormal elevation measuring point, the abnormal elevation measuring point is determined, including: For any preliminary abnormal elevation measuring point, the gray mean value and the gray variance of the target road surface gray data of all measuring points within a second preset range around the any preliminary abnormal elevation measuring point are calculated; For any preliminary abnormal elevation measuring point, the first abnormal gray segmentation threshold and the second abnormal gray segmentation threshold are calculated based on the corresponding gray mean value and the gray variance, so that the first abnormal gray segmentation threshold is greater than the second abnormal gray segmentation threshold; For any preliminary abnormal elevation measuring point, if the corresponding target road surface gray data is greater than the first abnormal elevation segmentation threshold or less than the second abnormal elevation segmentation threshold, the any preliminary abnormal elevation measuring point is determined as the abnormal elevation measuring point.

6. The precision three-dimensional based pavement wear detection method according to claim 2, wherein, Based on the target road surface elevation data of the non-abnormal elevation measuring point, the elevation estimation data of the abnormal elevation measuring point is estimated to generate the effective road surface elevation data, including: For any abnormal elevation measuring point, the elevation estimation data of the any abnormal elevation measuring point is estimated based on the target road surface elevation data of the non-abnormal elevation measuring point within a predetermined area around the any abnormal elevation measuring point; The elevation estimation data and the target road surface elevation data of the non-abnormal elevation measuring point are determined as the effective road surface elevation data.

7. The precision three-dimensional based pavement wear detection method according to any one of claims 1 to 6, characterized in that, Based on the reconstructed road surface three-dimensional point cloud data, a preset road surface structure depth calculation model is combined to determine the road surface full-width structure depth, including: The reconstructed road surface three-dimensional point cloud data is divided into a plurality of first-level point cloud units along the driving direction; Any first-level point cloud unit is divided into a plurality of second-level point cloud units along the road width direction; For all second-level point cloud units in any first-level point cloud unit, the structure depth of all second-level point cloud units is calculated based on the preset road surface structure depth calculation model, and then the structure depth set of each first-level point cloud unit is obtained; The road surface full-width structure depth is determined based on the structure depth set.

8. The precision three-dimensional based pavement wear detection method of claim 7, wherein, Based on the lane line position and the road surface full-width structure depth, the positions of the left wheel track, the right wheel track and the lane center line are determined, including: The distance between the left wheel track and the right wheel track is a fixed range, and the centers of the left wheel track and the right wheel track are located at the lane center, and the lane line position is combined to determine the IDs of the second-level point cloud units corresponding to the quasi-left wheel track, the quasi-right wheel track and the quasi-lane center line, respectively recorded as L', R' and M', and the IDs of the second-level point cloud units are used as the positions of the quasi-left wheel track, the quasi-right wheel track and the quasi-lane center line, respectively; According to the interval of adjacent units in the second-level point cloud unit along the road width direction, a preset search range D is determined; Within the preset search range D, a position deviation d satisfying a constraint condition s.t. is searched according to a following maximization target Z, and based on the position deviation d and a quasi-left wheel track band, a quasi-right wheel track band and a quasi-lane center line, IDs of second-level point cloud units corresponding to the left wheel track band, the right wheel track band and the lane center line are obtained respectively, and are recorded as L, R and M respectively, max Z = SMTD M - (SMTD L + SMTD R ) / 2 where SMTD L , SMTD R and SMTD M respectively represent the construction depth of the secondary point cloud unit corresponding to the left wheel track, the right wheel track and the lane centerline.

9. The precision three-dimensional based pavement wear detection method of claim 8, wherein, Based on the road surface full-width construction depth and the positions of the left wheel track band, the right wheel track band and the lane center line, road surface wear is calculated, including at least one of road surface wear at a wheel track band position and road surface wear at a non-wheel track band position, The road surface wear at the wheel track band position includes: Based on the construction depth corresponding to the positions of the left wheel track band, the right wheel track band and the lane center line, a road surface wear rate at the wheel track band position is calculated according to a following formula, and road surface wear WR1 at the wheel track band position is obtained: The road surface wear at the non-wheel track band position includes: For any second-level point cloud unit in any first-level point cloud unit, the construction depth corresponding to the position of the lane center line is taken as a construction depth reference value without wear, a road surface wear rate is calculated according to a following formula, and road surface wear WR2 at the non-wheel track band position is obtained: Wherein, n is the number of second-level point cloud units in each first-level point cloud unit.

Images