A road crack extraction method and device based on point cloud echo intensity adaptive convolution

Abstract

The present disclosure provides a method for extracting pavement cracks by adaptive convolution of point cloud echo intensity, comprising: dividing pavement point cloud data into multiple scan line data; performing adaptive convolution of intensity value on each laser point in each scan line data to obtain the convolution result of each scan line data, and determining crack contour points in each scan line data according to the convolution result; wherein the crack contour points correspond to the extreme value points in the convolution result of each scan line data; performing noise reduction processing on the crack contour points, and using the crack contour points after noise reduction as seed points; performing regional growth on the seed points to obtain pavement crack points of multiple scan line data. The present disclosure also provides a pavement crack extraction device, electronic device, storage medium and computer program product by adaptive convolution of point cloud echo intensity.

Description

Technical Field

[0001] The present disclosure relates to the technical field of road surface detection, and in particular to a road surface crack extraction method, device, electronic device, storage medium and program product using point cloud echo intensity adaptive convolution. Background Art

[0002] Urban roads are important areas for municipal management, and road pavement diseases are an issue that needs to be paid attention to in municipal infrastructure inspection. Among them, pavement cracks are one of the most common and most likely to occur pavement diseases. They accompany the entire service life of the road and become more serious as the road age increases. The appearance of pavement cracks not only affects the appearance of the road and the comfort of driving, but also easily expands and causes structural damage to the road surface. Therefore, the research on automatic detection and extraction technology of pavement cracks has high practical value.

[0003] The existing manual detection methods of pavement cracks are costly and inefficient. With the development of image processing technology and computer vision, manual detection methods have gradually been replaced by automatic crack detection methods based on images or videos. However, image or video data are easily affected by factors such as road lighting, shadows and stains, which makes crack identification more difficult and brings difficulties to the accurate extraction of cracks. In addition, crack detection technology based on two-dimensional data (images, videos) has limitations in obtaining the three-dimensional characteristics of pavement cracks, making it difficult to fully evaluate crack information. Mobile three-dimensional laser scanning system (MLS) can obtain high-precision dense three-dimensional point cloud of the road surface, which not only provides the reflection intensity information and three-dimensional position information of the target, but also effectively avoids the interference of factors such as lighting and shadows on crack extraction. Therefore, in recent years, mobile three-dimensional laser scanning systems have begun to be used for accurate surveys of road conditions and have stimulated related research.

[0004] Compared with asphalt pavement, crack areas usually show lower echo intensity and elevation in point cloud data. Based on the above characteristics, some reports have proposed crack extraction methods based on point cloud echo intensity, but this type of method is difficult to obtain complete crack extraction effects when the contrast between crack and pavement intensity is not obvious or there is interference from high echo intensity objects. In addition, some reports combine pavement elevation information to construct digital terrain models through point cloud data to extract cracks. However, when the crack elevation does not change significantly (for example, it is filled with sand), this method has the problem of missed detection. In summary, there are still misjudgments and missed detections in crack detection technology, and a high-precision, strong robustness, and manual intervention-free pavement crack extraction method based on point cloud data remains to be studied. Summary of the invention

[0005] In order to solve the problems existing in the prior art, the embodiments of the present invention provide a pavement crack extraction method, device, electronic device, storage medium and program product with point cloud echo intensity adaptive convolution, which improves the extraction efficiency and accuracy of pavement crack points based on point cloud echo intensity and regional growing algorithm.

[0006] The first aspect of the present disclosure provides a pavement crack extraction method using point cloud echo intensity adaptive convolution, comprising: dividing pavement point cloud data into multiple scan line data; performing intensity value adaptive convolution on each laser point in each scan line data to obtain a convolution result of each scan line data, and determining crack contour points in each scan line data based on the convolution result; wherein the crack contour points correspond to extreme value points in the convolution result of each scan line data; performing denoising on the crack contour points, and using the denoised crack contour points as seed points; and performing regional growth on the seed points to obtain pavement crack points in multiple scan line data.

[0007] Furthermore, performing regional growth on the seed points to obtain road surface crack points of multiple scan line data includes: performing regional growth on the seed points using a regional growing algorithm to obtain road surface crack points of multiple scan line data.

[0008] Furthermore, an intensity value adaptive convolution is performed on each laser point in each scan line data to obtain a convolution result of each scan line data, including: automatically generating a convolution kernel of a corresponding size according to the neighborhood point density of each laser point; and adaptively convolving the intensity value of each laser point according to the convolution kernel to generate a convolution result of each scan line data.

[0009] Further, the crack contour points in each scan line data are determined according to the convolution result, including: determining the crack contour points according to the threshold and intensity distribution characteristics generated by the convolution result of each scan line data; wherein the intensity value corresponding to the crack contour point is lower than the intensity value of the non-crack contour point

[0010] Furthermore, the crack contour points are subjected to denoising, and the denoised crack contour points are used as seed points, including: performing denoising on the crack contour points using a standard deviation ellipse method, and using the denoised crack contour points as seed points.

[0011] Furthermore, the crack contour points are denoised using the standard deviation ellipse method, and the denoised crack contour points are used as seed points, including: taking a crack contour point as the center of a circle, searching and generating a set of crack contour points in a circular neighborhood corresponding to the crack contour point according to a threshold radius; calculating the standard deviation ellipse of the crack contour point in the circular neighborhood; obtaining the flattening according to the standard deviation ellipse, and determining whether the flattening is less than a first threshold or greater than a second threshold; if so, using the crack contour point as a seed point; repeating the above steps until all crack contour points are denoised and all seed points are obtained.

[0012] Furthermore, dividing the road surface point cloud data into a plurality of scan line data includes: dividing the road surface point cloud data into a plurality of scan line data according to GPS time information.

[0013] The second aspect of the present disclosure provides a pavement crack extraction device with point cloud echo intensity adaptive convolution, including: a data preprocessing module, used to divide the pavement point cloud data into multiple scan line data; a crack contour point extraction module, used to perform intensity value adaptive convolution on each laser point in each scan line data to obtain the convolution result of each scan line data; determine the crack contour point in each scan line data according to the convolution result; wherein the crack contour point corresponds to the extreme point in the convolution result of each scan line data; a crack contour point denoising processing module, used to perform denoising on the crack contour point, and use the denoised crack contour point as the seed point; a pavement crack point generation module, used to perform regional growth on the seed point to obtain the pavement crack points of multiple scan line data.

[0014] The third aspect of the present disclosure provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the pavement crack extraction method of point cloud echo intensity adaptive convolution provided by the first aspect of the present disclosure is implemented.

[0015] The fourth aspect of the present disclosure provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the pavement crack extraction method using point cloud echo intensity adaptive convolution provided by the first aspect of the present disclosure is implemented.

[0016] A fifth aspect of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the pavement crack extraction method based on point cloud echo intensity adaptive convolution provided by the first aspect of the present disclosure.

[0017] The present disclosure provides a road crack extraction method, device, electronic device, storage medium and program product based on point cloud echo intensity adaptive convolution. The method is based on the phenomenon that the point echo intensity at the crack changes. The method extracts crack points from the road data based on the point cloud echo intensity and the regional growth algorithm, and performs adaptive convolution in combination with the first-order differential operator and the point density distribution to extract the crack contour points. The method has the advantages of accurate crack extraction results and almost no omissions. In addition, the crack width, depth and direction characteristics are calculated and counted based on the extracted crack points to facilitate the evaluation of the road condition. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] For a more complete understanding of the present disclosure and its advantages, reference will now be made to the following description taken in conjunction with the accompanying drawings, in which:

[0019] Figure 1 A flowchart of a road surface crack extraction method using point cloud echo intensity adaptive convolution according to an embodiment of the present disclosure is schematically shown;

[0020] Figure 2A A schematic diagram of road point cloud data according to an embodiment of the present disclosure is schematically shown;

[0021] Figure 2B A schematic diagram of the intensity of scan line data according to an embodiment of the present disclosure is schematically shown;

[0022] Figure 3 A flowchart of performing noise reduction processing on crack contour points according to an embodiment of the present disclosure is schematically shown;

[0023] Figure 4A Schematically shows a statistical diagram of intensity distribution of crack contour points according to an embodiment of the present disclosure;

[0024] Figure 4B Schematically shows a statistical diagram of intensity distribution of non-crack contour points according to an embodiment of the present disclosure;

[0025] Figure 5 A flowchart schematically shows a region growing process according to an embodiment of the present disclosure.

[0026] Figure 6 A schematic diagram schematically shows a crack point feature calculation according to an embodiment of the present disclosure;

[0027] Figure 7 A block diagram of a road surface crack extraction device using point cloud echo intensity adaptive convolution according to an embodiment of the present disclosure is schematically shown;

[0028] Figure 8 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0029] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0030] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of the features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0031] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification, and should not be interpreted in an idealized or overly rigid manner.

[0032] In the case of using expressions such as "at least one of A, B, and C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.). In the case of using expressions such as "at least one of A, B, or C, etc.", it should generally be interpreted in accordance with the meaning of the expression generally understood by those skilled in the art (for example, "a system having at least one of A, B, or C" should include but is not limited to a system having A alone, B alone, C alone, A and B, A and C, B and C, and / or A, B, C, etc.).

[0033] Some block diagrams and / or flow charts are shown in the accompanying drawings. It should be understood that some boxes or combinations thereof in the block diagrams and / or flow charts can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that these instructions can create a device for implementing the functions / operations described in these block diagrams and / or flow charts when executed by the processor. The technology of the present disclosure can be implemented in the form of hardware and / or software (including firmware, microcode, etc.). In addition, the technology of the present disclosure can take the form of a computer program product on a computer-readable storage medium storing instructions, which can be used by an instruction execution system or used in conjunction with an instruction execution system.

[0034] Figure 1 The flowchart of the road crack extraction method based on point cloud echo intensity adaptive convolution according to the embodiment of the present disclosure is schematically shown. Figure 1 As shown, the method includes: steps S101 to S104.

[0035] In operation S101 , road surface point cloud data is segmented into a plurality of scan line data.

[0036] In the embodiment of the present disclosure, before extracting the crack contour points, the original road surface point cloud data needs to be preprocessed, specifically, the road surface point cloud data is divided into multiple scan line data according to the GPS time information of the point cloud data, such as Figure 2A Shown is the point cloud data corresponding to a road area.

[0037] Each scan line data includes asphalt pavement points, marking line points and crack points. Figure 2A The rectangular box shown is the part of the scan line data containing crack points, and the crack point intensity of this part corresponds to Figure 2B shown.

[0038] During LiDAR scanning, the echo intensity at the cracks is usually lower than that of the asphalt pavement. Figure 2B In the intensity distribution curve, the intensity value of the crack point in the rectangular box is significantly lower than the intensity value of the asphalt pavement point, and the echo intensity at the junction of the two, that is, the crack contour (point in the rectangular box), will drop and rise sharply. Therefore, the location of the crack contour point can be determined by detecting the position where the intensity changes in the scan line. In the embodiment of the present disclosure, the intensity value of each laser point in each scan line data can be convolved by using a Gaussian first-order differential operator, and the crack contour point should correspond to the local extreme point in the convolution result.

[0039] In operation S102, intensity value adaptive convolution is performed on each laser point in each scan line data to obtain a convolution result of each scan line data; and crack contour points in each scan line data are determined based on the convolution result; wherein the crack contour points correspond to extreme value points in the convolution result of each scan line data.

[0040] In the embodiment of the present disclosure, assuming that each scan line data includes n laser points, each scan line data can be represented as {p1, p2, p3, ..., p n}, n is a positive integer. For each laser point p i (i∈[1,n]) is the center of the circle and the radius is r. The search is for each laser point pi in the scan line in the spatial circle neighborhood {p′1, p′2, p′3, ..., p′ m}, the number of points in the circular neighborhood is m. The Gaussian first-order differential operator is used as the convolution template, and the convolution kernel k of the corresponding size is adaptively generated in combination with the point density in the neighborhood. j , for the laser point p i The intensity values ​​of the points in the circle neighborhood are adaptively convolved to generate the convolution result c i .

[0041] Among them, the convolution kernel k j The specific convolution formula is as follows:

[0042]

[0043]

[0044]

[0045]

[0046] Among them, x j represents the corresponding position of the jth point in the neighborhood of laser point pi among the m points in the neighborhood, k′ j represents the convolution kernel value corresponding to the jth point in the neighborhood. According to the 3σ criterion, the laser point p is set i The m points in the neighborhood are distributed in the range of (-3σ1, 3σ1) of the Gaussian first-order differential operator. k j Represents the result of normalization of the convolution kernel value of the jth point; I j is the intensity value of the jth point in the neighborhood.

[0047] According to the above process, the laser point p is obtained. i The convolution result c i Then, the above steps are repeated until the convolution result {c1, c2, c3, ..., c n}. Since the crack contour points appear as extreme points in the convolution results, they can be extracted from the convolution results by setting the threshold T. Since the scan line convolution results approximately satisfy the normal distribution, according to the 3σ criterion, the calculation formula for setting the threshold T is as follows:

[0048] T=μ+a×σ2

[0049] Among them, μ and σ2 represent the convolution results {c1, c2, c3, ..., c n}; a is a constant, which is related to the number of crack points and asphalt pavement points in the scan line after removing the pavement marking line points. After many tests, it was found that when the number of crack points is much smaller than the number of pavement points, the constant a is preferably 3 to ensure the best extraction effect. It should be noted that the constant a can be appropriately adjusted according to the proportional relationship.

[0050] In the embodiment of the present disclosure, according to the convolution result {c1, c2, c3, ..., c n}The corresponding extreme point can be obtained to obtain the crack contour point in each scan line data. The crack contour points extracted by the above threshold T generally contain a small amount of noise. In order to obtain accurate crack contour points CP (Contour Points), the noise points can be filtered out by the following two steps: 1) The intensity distribution curve of the scan line passing through the crack area will show an obvious decrease and increase in intensity at the junction of the crack point and the road surface point (i.e., the crack contour point). Therefore, after the crack contour point is convolved with the Gaussian first-order differential operator used in the present disclosure, the convolution result should present a pair of extreme points, with the maximum value first and the minimum value second, and the order remains unchanged. 2) The Euclidean distance between a pair of crack contour points is generally close to the crack width in the road data. Therefore, the noise can be filtered out by setting a distance threshold between the two points. The value of the threshold T can be set according to the road crack situation. For example, if the crack width is 0.2mm, the threshold T can be set to 0.2mm.

[0051] It should be noted that the above threshold T, the number of laser points and the number of neighborhood points are only exemplary descriptions to facilitate those skilled in the art to understand the technical solutions of the present disclosure, and they do not constitute limitations of the embodiments of the present disclosure.

[0052] In operation S103, denoising is performed on the crack contour points, and the denoised crack contour points are used as seed points.

[0053] In the embodiment of the present disclosure, the crack contour points obtained by step S102 still include some noise points. Therefore, in order to ensure the accuracy of the seed points, improve the accuracy of the region growing results, and avoid the phenomenon of wrong extraction of crack points, the crack contour points can be denoised by the standard deviation ellipse method, and all crack contour points can be further denoised.

[0054] Specifically, Figure 3 As shown, the standard deviation ellipse method is used to perform noise reduction processing on the crack contour points, and the noise-reduced crack contour points are used as seed points, which specifically includes: steps S301 to S304.

[0055] In operation S301, a crack contour point q i As the center of the circle, the crack contour point set {q1, q2, q3, ..., q n}, where n is the number of crack points in the neighborhood.

[0056] In operation S302, a standard deviation ellipse of the crack contour points within the circle neighborhood is calculated.

[0057] In the embodiment of the present disclosure, the center point position (SDEx , SDE y ), rotation angle θ, major axis σ x and the minor axis σ y , the parameters correspond to the following relationship:

[0058]

[0059]

[0060]

[0061]

[0062]

[0063] Among them, x i With y i are the abscissa and ordinate of the i-th crack contour point in the neighborhood, respectively; and are the means of the horizontal and vertical coordinates of all the crack contour points in the neighborhood, respectively; represents the horizontal coordinate x of the i-th crack contour point i and the horizontal axis mean difference; represents the ordinate y of the i-th crack contour point i The vertical axis mean difference.

[0064] According to the crack contour point q i The standard deviation ellipse generated by the neighborhood points can be used to determine the seam contour point q by calculating the flattening α i In the directionality within the neighborhood, the closer the flattening α is to 0 or 1, the stronger the directionality is, which satisfies the following relationship:

[0065]

[0066] In operation S303, the flattening is obtained according to the standard deviation ellipse, and it is determined whether the flattening is less than a first threshold or greater than a second threshold; if so, the crack contour point is used as a seed point.

[0067] In the embodiment of the present disclosure, since the pavement crack points are usually distributed in a directional manner, it is experimentally set that if the crack contour point q i The standard deviation ellipse flattening α generated by the neighborhood points is less than the first threshold or greater than the second threshold If yes, the crack contour point is used as the seed point. and the second threshold The specific threshold value can be automatically adjusted according to the data.

[0068] In operation S304, the above steps S301 to S303 are repeated until all crack contour points are subjected to denoising processing to obtain all corresponding seed points.

[0069] In the embodiment of the present disclosure, by performing noise reduction processing on the crack contour points in all scan line data, the accuracy of the seed points is improved, so as to improve the accuracy of the regional growth result and avoid the phenomenon of wrong extraction of crack points.

[0070] In operation S104, region growing is performed on the seed points to obtain pavement crack points of a plurality of scan line data.

[0071] In the embodiment of the present disclosure, before performing region growing on the seed points, the embodiment of the present disclosure determines the growth conditions by analyzing the intensity distribution of the road surface data points. Figure 4A and Figure 4B The figure shows the statistical results of the intensity value of the point cloud of a road area collected by RIEGL VMX-2HA. Figure 4A The figure shows the intensity distribution statistics of the crack points. It can be seen that the echo intensity value of some crack points is 0, and the maximum intensity value does not exceed 10,000. Figure 4B The echo intensity statistics of non-crack points on the road surface show that the intensity values ​​of asphalt road surfaces are distributed between 10,000 and 40,000, while the intensity values ​​of road marking lines are generally greater than 40,000. Therefore, according to the above analysis results, the embodiment of the present disclosure sets the growth criterion based on the echo intensity value as follows: Figure 5 Specifically, a region growing algorithm is used to perform region growing on the seed points to obtain the pavement crack points of multiple scan line data.

[0072] like Figure 5 As shown in the figure, when the intensity value of the seed point (Seed Point) is 0, and the intensity value of the target point (TargetPoint) to be judged is also 0 or less than the intensity threshold Then the target point is a crack point; where the threshold is the upper limit of the crack point strength in the road surface point cloud statistics. For example, the threshold T I Set to 1000, etc. When the intensity value of the seed point is not 0, if the intensity value of the target point to be judged is less than the intensity threshold And the absolute value of the difference with the seed point intensity value is less than the threshold Then the target point is a crack point; where the threshold represents the acceptable range of the difference between the seed point and the target point intensity value. Its value can be set according to specific experimental data. After experiments, the threshold value set in the embodiment of the present disclosure is is 500.

[0073] It should be noted that the above threshold values ​​are only exemplary descriptions and do not constitute limitations of the embodiments of the present disclosure. They can be set according to actual conditions to ensure the accuracy of crack points extracted based on seed points.

[0074] According to an embodiment of the present disclosure, after the crack point extraction result in step S104, the method further includes calculating the direction, depth and width characteristics of the crack according to the crack point, wherein the calculation method of the crack width and direction is as follows: Figure 6 As shown in the figure, the pavement points and crack points are represented respectively. The principal component analysis method is used to calculate the main direction of the crack, and the angle θ (θ∈[-90°, 90°]) between the main direction and the road direction is taken as the crack direction. The crack width is the average value of the crack point width on each scan line, and the depth is the difference between the average elevation of the crack point and the average elevation of the pavement point on each scan line. After obtaining the information of the crack width, depth and direction, it is convenient to evaluate the pavement condition and prepare the next countermeasures.

[0075] The embodiment of the present disclosure provides a method for extracting pavement cracks by adaptive convolution of point cloud echo intensity. The method extracts crack points from pavement data based on point cloud echo intensity and regional growth algorithm. Based on the phenomenon that the point echo intensity at the crack changes, the method combines the first-order differential operator and the point density distribution to perform adaptive convolution to extract the crack contour points. The method has the advantages of accurate crack extraction results and almost no omissions. In addition, the crack width, depth and direction characteristics are calculated and counted based on the extracted crack points to facilitate the evaluation of the pavement condition.

[0076] Figure 7 The block diagram of the pavement crack extraction device using point cloud echo intensity adaptive convolution according to an embodiment of the present disclosure is schematically shown.

[0077] like Figure 7 As shown, the pavement crack extraction device 700 of point cloud echo intensity adaptive convolution includes: a data preprocessing module 710, a crack contour point extraction module 720, a crack contour point denoising processing module 730 and a pavement crack point generation module 740. The device 700 can be used to implement reference Figure 1 The pavement crack extraction method based on point cloud echo intensity adaptive convolution is described.

[0078] The data preprocessing module 710 is used to segment the road surface point cloud data into a plurality of scan line data. The data preprocessing module 710 can be used to perform the above reference Figure 1 The described step S101 will not be repeated here.

[0079] The crack contour point extraction module 720 is used to perform an intensity adaptive convolution on each laser point in each scan line data to obtain a convolution result of each scan line data; determine the crack contour point in each scan line data according to the convolution result; wherein the crack contour point corresponds to the extreme point in the convolution result of each scan line data. The crack contour point extraction module 720 can be used to perform the above reference Figure 1 The described step S102 will not be repeated here.

[0080] The crack contour point denoising processing module 730 is used to perform denoising on the crack contour points and use the denoised crack contour points as seed points. The crack contour point denoising processing module 730 can be used to perform the above reference Figure 1 The described step S103 will not be repeated here.

[0081] The pavement crack point generation module 740 is used to perform region growth on the seed point to obtain the pavement crack points of the plurality of scan line data. The pavement crack point generation module 740 can be used to perform the above reference Figure 1 The described step S104 will not be repeated here.

[0082] According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits, or at least part of the functions of any one of them can be implemented in one module. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be split into multiple modules for implementation. According to the embodiments of the present invention, any one or more of the modules, submodules, units, and subunits can be at least partially implemented as hardware circuits, such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), on-chip devices, devices on substrates, devices on packages, application-specific integrated circuits (ASICs), or can be implemented by hardware or firmware in any other reasonable way of integrating or packaging circuits, or implemented in any one of the three implementation methods of software, hardware, and firmware, or in any appropriate combination of any of them. Alternatively, according to the embodiments of the present invention, one or more of the modules, submodules, units, and subunits can be at least partially implemented as computer program modules, and when the computer program modules are run, the corresponding functions can be performed.

[0083] For example, any multiple of the data preprocessing module 710, the crack contour point extraction module 720, the crack contour point denoising processing module 730 and the pavement crack point generation module 740 can be combined in one module for implementation, or any one of the modules can be split into multiple modules. Alternatively, at least part of the functions of one or more of these modules can be combined with at least part of the functions of other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the data preprocessing module 710, the crack contour point extraction module 720, the crack contour point denoising processing module 730 and the pavement crack point generation module 740 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), an on-chip device, a device on a substrate, a device on a package, an application specific integrated circuit (ASIC), or can be implemented by hardware or firmware such as any other reasonable way of integrating or packaging the circuit, or implemented in any one of the three implementation methods of software, hardware and firmware or in an appropriate combination of any of them. Alternatively, at least one of the data preprocessing module 710, the crack contour point extraction module 720, the crack contour point denoising processing module 730 and the pavement crack point generation module 740 can be at least partially implemented as a computer program module, and when the computer program module is executed, the corresponding function can be performed.

[0084] Figure 8 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. Figure 8 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0085] like Figure 8 As shown, the electronic device 800 described in this embodiment includes: a processor 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage part 808 to a random access memory (RAM) 803. The processor 801 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 801 may also include an onboard memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0086] In RAM 803, various programs and data required for the operation of electronic device 800 are stored. Processor 801, ROM 802 and RAM 803 are connected to each other via bus 804. Processor 801 performs various operations of the method flow according to the embodiment of the present disclosure by executing the program in ROM 802 and / or RAM 803. It should be noted that the program can also be stored in one or more memories other than ROM 802 and RAM 803. Processor 801 can also perform various operations of the method flow according to the embodiment of the present disclosure by executing the program stored in the one or more memories.

[0087] According to an embodiment of the present disclosure, the electronic device 800 may further include an input / output (I / O) interface 805, which is also connected to the bus 804. The electronic device 800 may further include one or more of the following components connected to the I / O interface 805: an input portion 806 including a keyboard, a mouse, etc.; an output portion 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 808 including a hard disk, etc.; and a communication portion 809 including a network interface card such as a LAN card, a modem, etc. The communication portion 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed, so that a computer program read therefrom is installed into the storage portion 808 as needed.

[0088] According to an embodiment of the present disclosure, the method flow according to an embodiment of the present disclosure can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 809, and / or installed from the removable medium 811. When the computer program is executed by the processor 801, the above-mentioned functions defined in the device of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the apparatus, equipment, device, module, unit, etc. described above can be implemented by a computer program module.

[0089] The embodiment of the present invention also provides a computer-readable storage medium, which may be included in the device / apparatus / device described in the above embodiment; or may exist independently without being assembled into the device / apparatus / device. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the pavement crack extraction method of point cloud echo intensity adaptive convolution according to the embodiment of the present disclosure is implemented.

[0090] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In an embodiment of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution device, an apparatus or a device. For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include the ROM 802 and / or RAM 803 described above and / or one or more memories other than ROM 802 and RAM 803.

[0091] The embodiment of the present disclosure also includes a computer program product, which includes a computer program, and the computer program contains program code for executing the method shown in the flowchart. When the computer program product is run in a computer device, the program code is used to enable the computer device to implement the road surface crack extraction method of point cloud echo intensity adaptive convolution provided by the embodiment of the present disclosure.

[0092] The above functions defined in the apparatus / device of the embodiment of the present disclosure are performed when the computer program is executed by the processor 801. According to the embodiment of the present disclosure, the apparatus, device, module, unit, etc. described above can be implemented by a computer program module.

[0093] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of signals on a network medium, and downloaded and installed through the communication part 809, and / or installed from a removable medium 811. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0094] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 809, and / or installed from the removable medium 811. When the computer program is executed by the processor 801, the above functions defined in the device of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the above-described devices, equipment, means, modules, units, etc. can be implemented by computer program modules.

[0095] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, Java, C++, python, "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0096] It should be noted that the functional modules in the various embodiments of the present disclosure may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention may essentially or in other words, the part that contributes to the prior art or all or part of the technical solution may be embodied in the form of a software product.

[0097] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the devices, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of boxes in the block diagram or flow chart, can be implemented with a dedicated hardware-based device that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0098] It will be appreciated by those skilled in the art that the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments and / or claims of the present disclosure may be combined and / or combined in a variety of ways without departing from the spirit and teachings of the present disclosure. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0099] Although the present disclosure has been shown and described with reference to specific exemplary embodiments of the present disclosure, it should be understood by those skilled in the art that various changes in form and details may be made to the present disclosure without departing from the spirit and scope of the present disclosure as defined by the appended claims and their equivalents. Therefore, the scope of the present disclosure should not be limited to the above-mentioned embodiments, but should be determined not only by the appended claims, but also by the equivalents of the appended claims.

Claims

1. A pavement crack extraction method based on point cloud echo intensity adaptive convolution, characterized in that: include: Split the road surface point cloud data into multiple scan line data; Performing an intensity value adaptive convolution on each laser point in each scan line data to obtain a convolution result of each scan line data, including: automatically generating a convolution kernel of a corresponding size according to a neighborhood point density of each laser point; performing an intensity value adaptive convolution on each laser point according to the convolution kernel to generate a convolution result of each scan line data; Determine the crack contour point in each scan line data according to the convolution result; wherein the crack contour point corresponds to the extreme value point in the convolution result of each scan line data; The crack contour points are subjected to denoising and the denoised crack contour points are used as seed points, including: taking a crack contour point as the center of a circle, searching and generating a set of crack contour points in a circular neighborhood corresponding to the crack contour point according to a threshold radius; calculating a standard deviation ellipse of the crack contour point in the circular neighborhood; obtaining a flattening rate according to the standard deviation ellipse, and determining whether the flattening rate is less than a first threshold value or greater than a second threshold value; if so, using the crack contour point as a seed point; repeating the above steps until all the crack contour points are subjected to denoising to obtain all the seed points; Performing regional growth on the seed points to obtain pavement crack points of the plurality of scan line data.

2. The pavement crack extraction method based on point cloud echo intensity adaptive convolution according to claim 1 is characterized in that: The step of performing region growing on the seed point to obtain the pavement crack points of the plurality of scan line data includes: A region growing algorithm is used to perform region growing on the seed points to obtain the pavement crack points of the plurality of scan line data.

3. The pavement crack extraction method based on point cloud echo intensity adaptive convolution according to claim 1 is characterized in that: Determining the crack contour point in each scan line data according to the convolution result includes: The crack contour point is determined according to a threshold value and intensity distribution characteristics generated by the convolution result of each scan line data; wherein the intensity value corresponding to the crack contour point is lower than the intensity value of the non-crack contour point.

4. The pavement crack extraction method based on point cloud echo intensity adaptive convolution according to claim 1 is characterized in that: The step of dividing the road surface point cloud data into a plurality of scan line data includes: The road surface point cloud data is divided into multiple scan line data according to GPS time information.

5. A road crack extraction device based on point cloud echo intensity adaptive convolution, characterized in that: include: A data preprocessing module is used to segment the road surface point cloud data into multiple scan line data; A crack contour point extraction module is used to perform an intensity value adaptive convolution on each laser point in each scan line data to obtain a convolution result of each scan line data, including: automatically generating a convolution kernel of a corresponding size according to the neighborhood point density of each laser point; performing an adaptive convolution on the intensity value of each laser point according to the convolution kernel to generate a convolution result of each scan line data; determining the crack contour point in each scan line data according to the convolution result; wherein the crack contour point corresponds to an extreme point in the convolution result of each scan line data; A crack contour point denoising processing module is used to perform denoising on the crack contour points and use the denoised crack contour points as seed points, including: taking a crack contour point as the center of a circle, searching and generating a set of crack contour points in a circular neighborhood corresponding to the crack contour point according to a threshold radius; calculating a standard deviation ellipse of the crack contour point in the circular neighborhood; obtaining a flattening rate according to the standard deviation ellipse, and determining whether the flattening rate is less than a first threshold or greater than a second threshold; if so, using the crack contour point as a seed point; repeating the above steps until all the crack contour points are denoised to obtain all the seed points; The pavement crack point generation module is used to perform regional growth on the seed points to obtain the pavement crack points of the multiple scan line data.

6. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, Wherein, when the one or more programs are executed by the one or more processors, the one or more processors execute the pavement crack extraction method of point cloud echo intensity adaptive convolution according to any one of claims 1 to 4.

7. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to execute the pavement crack extraction method based on point cloud echo intensity adaptive convolution according to any one of claims 1 to 4.

Images