CN107633516B - Method and device for identifying road surface deformation diseases - Google Patents
Method and device for identifying road surface deformation diseases Download PDFInfo
- Publication number
- CN107633516B CN107633516B CN201710861318.2A CN201710861318A CN107633516B CN 107633516 B CN107633516 B CN 107633516B CN 201710861318 A CN201710861318 A CN 201710861318A CN 107633516 B CN107633516 B CN 107633516B
- Authority
- CN
- China
- Prior art keywords
- disease
- area
- deformation
- depth
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides a method and a device for identifying pavement deformation diseases, wherein the method comprises the following steps: s1, acquiring deformation depth information of the road surface to be detected according to the pre-acquired three-dimensional data of the road surface to be detected; s2, extracting the suspected disease edge through an edge detection algorithm according to the deformation depth information; s3, acquiring an initial disease positioning area according to the deformation depth information and the suspected disease edge, and positioning the disease area through area growth reduction treatment; s4, acquiring a disease attribute set of the disease area, and identifying the disease type of the disease area according to the disease attribute set. According to the method, the disease depth information and the deformation depth image are obtained, the disease area in the pavement is accurately extracted, and the integrity of the disease area is ensured; and the disease type of the disease area is accurately identified through the disease attribute, so that the pavement deformation disease is efficiently and accurately detected and identified.
Description
Technical Field
The invention relates to the technical field of pavement detection, in particular to a method and a device for identifying pavement deformation diseases.
Background
With the continuous improvement of economic level, the highway construction in China is rapidly developing. With the increasing traffic volume, the pursuit of driving comfort and driving safety is increasing day by day, the surface characteristics of the road directly affect the requirements of people on the two aspects, and the need of continuously improving the road service level to ensure the excellent surface characteristics of the road is needed.
During the use of the road, various road deformation diseases (such as ruts, pits, bags, subsidence and the like) can be caused due to the influence of various natural and non-natural factors. Therefore, it is very important to detect the health condition of the road quickly and accurately and provide the road surface condition analysis index for the maintenance of the road.
In the prior art, in order to detect the road health condition, the record can be manually detected on the spot, but the method needs to consume a large amount of manpower, financial resources and material resources, has the problems of safety, efficiency, precision and the like, and has large workload of post-processing, thereby being not suitable for the requirement of large-scale road detection.
In addition, a road surface rapid detection system based on a simulation photography technology and a simulation video technology can be used, the road surface damage image is synchronously acquired by mainly using a high-speed high-precision camera and a vehicle positioning system, and then the road surface damage image is processed by using a computer to obtain road surface disease information, but the road surface environment generally has strong noise (road surface material particle size noise, uneven illumination, shading shadow and the like) and the image distortion, trailing and fuzzy phenomena are caused by the installation mode of the camera or self distortion, so that the method has the defects of poor real-time performance, difficult recognition rate, difficult classification and the like.
Further, since the captured image is a planar figure, the processing method for planar two-dimensional image data is generally: preprocessing a target image such as gray processing, smoothing processing, sharpening processing and the like; and then, carrying out image segmentation, morphological processing and contour extraction on the diseases in the preprocessed road surface image, and finally carrying out accurate positioning output on the diseases by carrying out feature extraction and measurement on the diseases in the road surface image.
However, the processing method is greatly influenced by the quality of the acquired data, and the false detection rate is high in the process of identifying the diseases; in particular, for defects having no distinct features in the two-dimensional grayscale image (for example, partially shallow rut defects), the accuracy of the identification of the deformation defects based on the two-dimensional image data is low, and the depth information of the deformation defects cannot be acquired.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a method and a device for identifying road surface deformation diseases.
One aspect of the present invention provides a method for identifying a road surface deformation disease, including: s1, acquiring deformation depth information of the road surface to be detected according to the pre-acquired three-dimensional data of the road surface to be detected; s2, extracting the suspected disease edge through an edge detection algorithm according to the deformation depth information; s3, acquiring an initial disease positioning area according to the deformation depth information and the suspected disease edge, and positioning the disease area through area growth reduction treatment; s4, acquiring a disease attribute set of the disease area, and identifying the disease type of the disease area according to the disease attribute set.
Wherein the step S1 further includes: s11, carrying out abnormal value elimination processing, data calibration processing and filtering processing on the three-dimensional data to obtain a section control contour; s12, analyzing the profile characteristics of the section control profile to obtain a section standard profile corresponding to the section control profile; s13, making a difference between the section control contour and the section standard contour, and acquiring section elevation difference information of the actual elevation and the standard elevation of the section of the road surface to be detected; and S14, splicing the continuous multiple sections according to the section elevation difference information, and acquiring the deformation depth information of the road surface to be detected.
Wherein the step S3 further includes: s31, dividing the deformation depth information into a plurality of image sub-blocks, and acquiring depth attribute information corresponding to the image sub-blocks respectively; wherein the depth attribute information includes a depth average value, a depth value variance, and depth value distribution information; s32, evaluating confidence degrees of the image sub-blocks according to depth attribute information corresponding to the image sub-blocks and the suspected disease edges by combining a deformation disease knowledge base, and taking the image sub-blocks with higher confidence degrees as the primary positioning disease areas; s33, carrying out connected region marking on the initially positioned disease region to obtain region parameters of each connected region; wherein the region parameters comprise region length, region area, region position and region direction; and S34, performing edge extension on the connected region with the region parameters meeting the preset conditions to obtain the damaged region.
Wherein the step S4 further includes: s41, acquiring the effective length, the effective width, the length-width ratio and the disease position of the disease area, and acquiring the maximum depth, the average depth and the disease area of the disease area according to the effective length and the effective width; the disease attribute set comprises the effective length, the effective width, the length-width ratio, the disease position, the maximum depth, the average depth and the disease area of the disease area; and S42, acquiring the disease types of the diseases contained in the disease areas based on a deformation disease knowledge base according to the disease attribute set.
Wherein the step S34 further includes: s341, performing edge extension on a first communication region with the region length and the region area larger than a preset threshold value along the region direction of the first communication region; s342, if a second communication area exists in the extension area and the distance between the first communication area and the second communication area is smaller than a preset distance, acquiring a central connection line between the first communication area and the second communication area; and S343, combining the first communication area and the second communication area along the direction of the central connecting line, and taking the combined area as a new disease area.
Wherein the step S2 further includes: s21, obtaining the gradient component of each pixel point according to a preset edge detection operator and the deformation depth information; and S22, obtaining pixel points with gradient components larger than a preset gradient threshold value as suspected disease edge points, and obtaining the suspected disease edges according to the suspected disease edge points.
Wherein the step S42 further includes: s421, obtaining a classifier according to the deformation disease knowledge base; s422, acquiring the disease types of the diseases contained in the disease areas through the classifier based on the disease linear characteristics, the depth characteristics, the area array characteristics, the position characteristics and the deformation degree according to the disease attribute set; wherein the linear features comprise an effective length, an effective width, an aspect ratio; the depth features include a maximum depth and an average depth; the area array characteristics comprise disease areas; the location features include disease locations; the degree of deformation includes slight deformation, moderate deformation, and severe deformation.
Another aspect of the present invention provides an apparatus for identifying a road surface deformation type disease, including: the acquisition module is used for acquiring deformation depth information of the road surface to be detected according to the pre-acquired three-dimensional data of the road surface to be detected; the processing module is used for extracting suspected disease edges through an edge detection algorithm according to the deformation depth information; the positioning module is used for acquiring an initial positioning disease area according to the deformation depth information and the suspected disease edge, and positioning the disease area through area growth reduction treatment; and the identification module is used for acquiring the disease attribute set of the disease area and identifying the disease type of the disease area according to the disease attribute set.
Still another aspect of the present invention provides an apparatus for identifying a road surface deformation type disease, comprising: at least one processor; and at least one memory communicatively coupled to the processor, wherein: the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the method for identifying the road surface deformation diseases provided by the above aspect of the invention, for example, the method includes: s1, acquiring deformation depth information of the road surface to be detected according to the pre-acquired three-dimensional data of the road surface to be detected; s2, extracting the suspected disease edge through an edge detection algorithm according to the deformation depth information; s3, acquiring an initial disease positioning area according to the deformation depth information and the suspected disease edge, and positioning the disease area through area growth reduction treatment; s4, acquiring a disease attribute set of the disease area, and identifying the disease type of the disease area according to the disease attribute set.
Yet another aspect of the present invention provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method for identifying a road surface deformation-type fault provided by the above aspect of the present invention, for example, the method includes: s1, acquiring deformation depth information of the road surface to be detected according to the pre-acquired three-dimensional data of the road surface to be detected; s2, extracting the suspected disease edge through an edge detection algorithm according to the deformation depth information; s3, acquiring an initial disease positioning area according to the deformation depth information and the suspected disease edge, and positioning the disease area through area growth reduction treatment; s4, acquiring a disease attribute set of the disease area, and identifying the disease type of the disease area according to the disease attribute set.
According to the method and the device for identifying the road surface deformation diseases, the disease depth information and the deformation depth image are obtained, the disease area in the road surface is accurately extracted, and the integrity of the disease area is ensured; and the disease type of the disease area is accurately identified through the disease attribute, so that the pavement deformation disease is efficiently and accurately detected and identified.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for identifying a road surface deformation disease according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a deformation depth image (a), an initial positioning damaged area (b), a damaged area (c) and damaged feature extraction (d) of a pit groove damage in the method for identifying a road surface deformation type damage provided by the embodiment of the invention;
FIG. 3 is a schematic view of a cross-sectional profile of a pit defect in the method for identifying a road surface deformation defect according to the embodiment of the present invention;
fig. 4 is a schematic diagram of a cross-sectional profile of a hugging disease of the method for identifying pavement deformation diseases provided by the embodiment of the invention;
FIG. 5 is a schematic diagram of a method for identifying a road surface deformation type disease according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a device for identifying a road surface deformation disease according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an apparatus for identifying a road surface deformation disease according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, the three-dimensional modeling technology is widely applied to various fields, and is widely applied from macroscopic homeland survey, three-dimensional visualization, three-dimensional animation, high-precision three-dimensional modeling to three-dimensional printing. According to the principle of laser triangulation, the method based on the combination of line structure light and vision sensor measurement realizes synchronous measurement in the same posture and at the same time, namely, a complete section is required to be measured and sampled at one time, and the measurement of one section in the same posture is ensured. The embodiment of the invention identifies the pavement diseases based on the three-dimensional data of the pavement.
Fig. 1 is a schematic flow chart of a method for identifying a road surface deformation disease according to an embodiment of the present invention, as shown in fig. 1, including: s1, acquiring deformation depth information of the road surface to be detected according to the pre-acquired three-dimensional data of the road surface to be detected; s2, extracting the suspected disease edge through an edge detection algorithm according to the deformation depth information; s3, acquiring an initial disease positioning area according to the deformation depth information and the suspected disease edge, and positioning the disease area through area growth reduction treatment; s4, acquiring a disease attribute set of the disease area, and identifying the disease type of the disease area according to the disease attribute set.
The three-dimensional data is obtained by measuring the road surface to be detected through the line scanning three-dimensional measuring sensor. Specifically, the line scanning three-dimensional measurement sensor can measure and obtain the relative change condition of the elevation of the surface of the measured object, and the obtained three-dimensional data can reflect the elevation change information of the surface of the measured object. The line scanning three-dimensional measuring sensor can realize the synchronous measurement of the profile of the section at the same attitude and the same moment, and the acquisition mode comprises two modes: the three-dimensional measuring sensor is arranged on a fixed support, a measured object passes through a measuring area at a certain speed within the measuring range of the three-dimensional measuring sensor, and the three-dimensional profile data of the measured object is acquired in the moving process of the measured object; and secondly, the three-dimensional measuring sensor is arranged on a moving carrier, and data acquisition is carried out on the three-dimensional profile of the measured object in the moving process of the measuring carrier. In the embodiment of the present invention, the line scanning three-dimensional measurement sensor is disposed on the vehicle, and the vehicle runs on the road surface to be detected once to acquire three-dimensional data.
The deformation depth information reflects depth information of different positions of the whole road surface to be detected, for example, each point of the road surface to be detected and a depth value corresponding to each point are represented in a coordinate mode; the deformed depth image reflects the image of the depth information at different positions of the whole to-be-detected road surface, and the image can visually reflect the depth change condition of the whole to-be-detected road surface.
The edge is the most obvious place of gray level change on the image, the edge detection algorithm utilizes the characteristic to identify the points with obvious brightness change in the digital image, and the obvious change in the image attribute usually reflects the important events and changes of the attribute. The edge in the embodiment of the invention reflects the edge of the diseased area.
The disease attribute set comprises a plurality of disease attributes, and can reflect the characteristics of a disease area in shape and depth; the diseases in the disease area can be classified according to the disease attribute set.
In step S1, a line-scanning three-dimensional measurement sensor may be used to collect three-dimensional data of the road surface to be detected; and after the acquisition, processing the three-dimensional data, and further acquiring the deformation depth information and the deformation depth image of the road surface to be detected. Fig. 2 is a schematic diagram of a deformation depth image (a) of a pit defect in the method for identifying a road surface deformation type defect according to the embodiment of the present invention, and as shown in fig. 2, taking a pit defect as an example, a deeper position on a road surface to be detected has a deeper color, so as to distinguish depth values at different positions of the road surface to be detected.
In step S2, according to the deformation depth information obtained in step S1, the deformation depth information is solved by using an edge detection algorithm, and the obtained edge is a suspected disease edge; the suspected disease edge can reflect the disease area to a certain extent.
In step S3, first, an initial localized disease area is obtained based on the deformation depth information obtained in step S1 and the suspected disease edge obtained in step S2; and then the diseased area can be obtained through the treatment of area growing reduction. The area growth reduction is to extract the damaged areas by utilizing the topological relation among the damaged areas by utilizing the characteristics of the pavement deformation diseases, such as area aggregation and depth change continuity.
In step S4, acquiring a disease attribute set in the disease area according to the disease area acquired in step S3; the disease attribute set reflects characteristics such as the shape and depth of the disease area, and the disease category of the disease area can be effectively identified by the attribute set.
According to the method for identifying the road surface deformation diseases, the disease depth information and the deformation depth image are obtained, the disease area in the road surface is accurately extracted, and the integrity of the disease area is guaranteed; and the disease type of the disease area is accurately identified through the disease attribute, so that the pavement deformation disease is efficiently and accurately detected and identified.
On the basis of any of the above embodiments, the step S1 further includes: s11, carrying out abnormal value elimination processing, data calibration processing and filtering processing on the three-dimensional data to obtain a section control contour; s12, analyzing the profile characteristics of the section control profile to obtain a section standard profile corresponding to the section control profile; s13, making a difference between the section control contour and the section standard contour, and acquiring section elevation difference information of the actual elevation and the standard elevation of the section of the road surface to be detected; and S14, splicing the continuous multiple sections according to the section elevation difference information, and acquiring the deformation depth information of the road surface to be detected.
The three-dimensional data is composed of a plurality of continuous section profiles, and each section profile mainly comprises a section standard profile, a section control profile and a road texture; wherein, the standard profile of the section represents the normal road profile, which comprises the measurement attitude (the cross section inclination phenomenon of the vehicle-mounted three-dimensional system caused by roll and other factors) but does not comprise macroscopic and microscopic disease profile information (such as pit slot, track, subsidence, hugging, crack and the like); the section control contour is a contour which is attached to pavement data, contains macroscopic disease contour information (such as pits, ruts, subsidence, cuddles and the like) but does not contain microscopic disease information (such as cracks and the like); the road texture is the local fine fluctuation of the contour formed by the road material particles under normal conditions.
Wherein, the abnormal value elimination processing is to remove the obvious error value contained in the three-dimensional data; and the data calibration processing is to convert the image space elevation data into object space elevation data so as to accurately acquire the actual contour of the measured object.
The filtering may be mean filtering, gaussian filtering, etc., and taking mean filtering as an example, the mean filtering is a typical linear filtering algorithm, which means that a template is given to a target pixel on an image, the template includes neighboring pixels around the target pixel (8 surrounding pixels with the target pixel as a center form a filtering template, i.e., the target pixel itself is removed), and the original pixel value is replaced by an average value of all pixels in the template.
In step S11, preprocessing three-dimensional data acquired in advance, where the preprocessing includes outlier rejection processing and data calibration processing; fig. 3 is a schematic view of a cross-sectional profile of a pit defect in the method for identifying a road surface deformation defect according to the embodiment of the present invention, fig. 4 is a schematic view of a cross-sectional profile of a hugging defect in the method for identifying a road surface deformation defect according to the embodiment of the present invention, a cross-sectional control profile of a pit defect is shown in fig. 3, and a cross-sectional control profile of a hugging defect is shown in fig. 4.
In step S12, according to the section control profile obtained in step S11, since the section control profile reflects the real condition of the road surface, it is necessary to analyze the profile characteristics of the section control profile to obtain a section standard profile reflecting the condition of a normal road surface; the profile features may include features such as trend, curvature, and peak point of the profile control profile line. For example, the profile control profile is concave downward as shown in fig. 3, so that it can be determined to some extent that the profile control profile should be on the upper side of the downward peak point; however, as the profile control contour is upwardly convex as shown in fig. 4, it can be determined to some extent that the profile control contour should be below the upward peak point.
In step S13, according to the cross-section control contour and the cross-section standard contour obtained in step S12, the cross-section control contour includes contour information of the cross-section defect and the cross-section standard contour; therefore, using the standard profile SP of the cross sectionjSubtracting the profile control profile CPjObtaining the elevation difference information F of the sectionj＝{Fji1,2., n }, (n is the number of single cross-section measurement points).
In step S14, a plurality of continuous sections on the road surface to be detected are spliced together according to the section height difference information obtained in step S13, and deformation depth information F ═ F of the road surface to be detected is formedji1,2., m, i ═ 1,2.. n }; (wherein m is the number of splicing sections, and n is the number of single section measuring points); the deformed depth image is an image corresponding to the deformed depth information.
Through the steps, the depth information of the road surface to be detected can be effectively extracted, and the integrity is guaranteed.
On the basis of any of the above embodiments, the step S3 further includes: s31, dividing the deformation depth information into a plurality of image sub-blocks, and acquiring depth attribute information corresponding to the image sub-blocks respectively; wherein the depth attribute information includes a depth average value, a depth value variance, and depth value distribution information; s32, evaluating confidence degrees of the image sub-blocks according to depth attribute information corresponding to the image sub-blocks and the suspected disease edges by combining a deformation disease knowledge base, and taking the image sub-blocks with higher confidence degrees as the primary positioning disease areas; s33, carrying out connected region marking on the initially positioned disease region to obtain region parameters of each connected region; wherein the region parameters comprise region length, region area, region position and region direction; and S34, performing edge extension on the connected region with the region parameters meeting the preset conditions to obtain the damaged region.
In step S31, the deformation depth information or the deformation depth image of the road surface to be detected is reasonably divided into image sub-blocks (with the size sm sn) whose sizes do not overlap with each other, and SU ═ snxy|x＝1,2,...M,y＝1,2,...N}，SUxy＝{Fji|j∈Xx,i∈YyM/sm is the number of the image sub-blocks in the row direction; n is N/sn is the number of the image sub-blocks in the column direction; xx∈[(x-1)*sm+1x*sm]And Xx∈{1,2,...m}，Yy∈[(y-1)*sn+1y*sn]And Y isy∈{1,2,...n}。
After dividing into a plurality of image sub-blocks, obtaining attribute information of the depth values in the image sub-blocks by counting and analyzing the depth values in the image sub-blocks SU, wherein the attribute information of the depth values can include a depth average value, a depth value variance and depth value distribution information, and the distribution information can be positive and negative distribution information; for example, the depth value attribute information may be SUA ═ mean AVGxyVariance STDxyPositive and negative distribution information PMxy1,2., M, y ═ 1,2., N }, where M is the number of image sub-blocks in the row direction and N is the number of image sub-blocks in the column direction.
In step S32, the deformed disease knowledge base stores shape characteristics, depth characteristics, and the like of various diseases (such as ruts, bumps, pits, depressions, and the like) included in the deformed diseases, and the type of the diseases can be confirmed to some extent by comparing and matching the actual parameters with the knowledge base. Specifically, according to a deformation disease knowledge base, the confidence degrees of the image subblocks are evaluated by combining the image subblocks SU, the depth attribute information SUA and the suspected disease edge, the image subblocks with higher confidence degrees (higher confidence degrees indicate that the image subblocks are more likely to be a disease area) and the position information (such as coordinate values) of the image subblocks are obtained, initial disease positioning is realized, and the obtained image subblocks with higher confidence degrees are used as initial positioning disease areas; fig. 2 is a schematic view of a primary localized damaged area (b) of a pit defect in the method for identifying a road surface deformation type defect according to the embodiment of the present invention, and the primary localized damaged area is illustrated by taking the pit defect as an example.
In step S33, a connected region is marked for the primary localized damaged region based on the primary localized damaged region acquired in step S32, and the mark value is recorded as FR ═ { FR ═ji1, · m, | j ═ 1, 2; n (where m is the number of the spliced cross sections and n is the number of the measurement points of a single cross section), and counting each connected region UR in the connected region labeling image FRu(the number of connected regions with U ═ 1,2, …, U;. U is the total number of connected regions) and the region parameters include: region length URLuArea URA of the regionuRegional location URSuAnd region direction URDu. Wherein the length of the regionURLuThe length of the long side or diagonal line of the connecting area with the mark value of u; area of area URAuThe number of pixels of the connected region with the mark value of u; regional location URSuCoordinates of the center of gravity of the connected region; regional direction URDuIt can be obtained using, for example, a least squares fit method.
In step S34, for each region parameter (e.g., region length URL) based on the region parameters acquired in step S33uAnd area URAu) Performing edge extension (extending direction is according to region direction URD of geometric shape) on the disease region meeting the requirements of preset conditions (for example, the threshold is respectively larger than a preset threshold, wherein the threshold is obtained by a deformation disease knowledge base)uDetermining) to obtain a final disease area.
On the basis of any of the above embodiments, the step S4 further includes: s41, acquiring the effective length, the effective width, the length-width ratio and the disease position of the disease area, and acquiring the maximum depth, the average depth and the disease area of the disease area according to the effective length and the effective width; the disease attribute set comprises the effective length, the effective width, the length-width ratio, the disease position, the maximum depth, the average depth and the disease area of the disease area; and S42, acquiring the disease types of the diseases contained in the disease areas based on a deformation disease knowledge base according to the disease attribute set.
In step S41, after the damaged area is extracted, the damaged area DZ is usedk(k is 1,2, …, s, where s is the total number of diseases) to obtain the effective length L, effective width W, length-width ratio LW and disease position Loc (position coordinates of the longest connecting line vertex in the disease area), and calculating the maximum depth Hmax and average depth H of the disease areaavgAnd the Area of disease Area; obtaining a disease attribute set DZAk，(DZAk＝{L,W,LW,Loc,Hmax,HavgArea, k is 1,2, and s is the total number of diseases).
In step S42, the deformation disease knowledge base is used to compare and match the disease attribute set with the data in the knowledge base, so as to identify the disease type of the disease area.
On the basis of any of the above embodiments, the step S34 further includes: s341, performing edge extension on a first communication region with the region length and the region area larger than a preset threshold value along the region direction of the first communication region; s342, if a second communication area exists in the extension area and the distance between the first communication area and the second communication area is smaller than a preset distance, acquiring a central connection line between the first communication area and the second communication area; and S343, combining the first communication area and the second communication area along the direction of the central connecting line, and taking the combined area as a new disease area.
Specifically, the URL is specified for each region lengthuAnd area URAuPerforming edge extension (extending direction is according to region direction URD of geometric form of the region) on the disease region (namely, the first connected region) meeting the requirement of the threshold (the threshold is obtained by a deformation disease knowledge base)uDetermining), judging whether other disease marks exist in the extended area, if a second connected area exists and has a certain topological relation (namely the distance is short and is smaller than a preset distance), acquiring a central connecting line of the first connected area and the second connected area, and extending and combining the two disease areas (the first connected area and the second connected area) along the central connecting line; after multiple times of combination, if a larger disease area does not exist around a small disease area, the disease growth and reduction process is finished; the confidence of the generated disease area with a larger range is higher, and the disease area is reserved; eliminating the small-range disease areas which are not combined, wherein the confidence coefficient of the small-range disease areas is low; obtaining the final disease area DZk(k ═ 1,2, …, s, where s is the total number of diseases).
On the basis of any of the above embodiments, the step S2 further includes: s21, obtaining the gradient component of each pixel point according to a preset edge detection operator and the deformation depth information; and S22, obtaining pixel points with gradient components larger than a preset gradient threshold value as suspected disease edge points, and obtaining the suspected disease edges according to the suspected disease edge points.
In step S21, because the area of the deformed disease area is characterized by a large area, the embodiment of the present invention designs an edge detection operator at 11 × 11, and solves the suspected edge points of the deformed disease area by using a differential edge detection method on the road deformation depth information F to locate the disease area; the following description will take an edge detection operator of 11 × 11 as an example, where the edge detection operator is as follows:
according to the edge detection operator, calculating a gradient component as follows:
in the formula, f (j, i) represents the deformation depth value at the coordinate (j, i), and the magnitude of the gradient component of the pixel point (j, i) is:
G(j,i)≈|Gj|+|Gi|
in step S22, according to the gradient components obtained in step S21, if G (j, i) > Th, where Th is a preset gradient threshold; g (j, i) is a suspected disease edge point.
By carrying out statistics on the proportional relation between the gradient values of the edges of the deformed diseases and the gradient values of all pixels in a large quantity, Th can be set to be 80% of the maximum gradient value, and suspected disease edge points are obtained; all suspected disease edge points constitute suspected disease edges.
On the basis of any of the above embodiments, the step S42 further includes: s421, obtaining a classifier according to the deformation disease knowledge base; s422, acquiring the disease types of the diseases contained in the disease areas through the classifier based on the disease linear characteristics, the depth characteristics, the area array characteristics, the position characteristics and the deformation degree according to the disease attribute set; wherein the linear features comprise an effective length, an effective width, an aspect ratio; the depth features include a maximum depth and an average depth; the area array characteristics comprise disease areas; the location features include disease locations; the degree of deformation includes slight deformation, moderate deformation, and severe deformation.
Fig. 5 is a schematic diagram of a method for identifying a road surface deformation type disease according to an embodiment of the present invention, and as shown in fig. 5, a classifier is first designed in combination with a disease knowledge base, and the classifier is used to identify a type of a disease area based on a disease attribute characteristic; the disease attribute characteristics comprise disease linear characteristics, depth characteristics, area array characteristics, position characteristics and deformation degree; wherein the linear features include an effective length, an effective width, an aspect ratio; the depth characteristics comprise maximum depth and average depth of the diseases; the area array characteristics comprise disease area; the position characteristics comprise disease positions; the degree of deformation includes slight deformation, moderate deformation, and severe deformation.
The classifier classifies the diseases based on the disease attribute characteristics, for example, the following rules may be adopted: for a certain diseased area, the number of the disease areas is increased,
rule 1, it will be greater than threshold Th according to disease depth informationupThe 'upward type' disease is extracted as a hugging disease;
rule 2, the average depth (greater than threshold T1) is determined by the effective length (e.g., ruts have significant length characteristics), effective width (e.g., a certain proportion of wheel width), maximum depth of damage (greater than threshold T1max), and average depth (greater than threshold T1)mean) Aspect ratio (greater than threshold T)lw,TlwThe value of (d) is related to the sampling interval and resolution of the data), and the position of the disease accords with the characteristics of wheel track and the like, and the disease is extracted as a rut disease;
rule 3, according to the maximum depth of the disease (greater than threshold T2)max) Average depth (greater than threshold T2)mean) Incorporating area features (area threshold T)area) Extracting sinking diseases and pit slot diseases;
in addition, after the disease types (pit, sink, track and hug) are determined according to the classification result, the deformation disease knowledge base can be perfected according to the current disease area characteristics.
Fig. 6 is a schematic structural diagram of a device for identifying a road surface deformation disease according to an embodiment of the present invention, as shown in fig. 6, including: the acquiring module 601 is configured to acquire deformation depth information of a road surface to be detected according to three-dimensional data of the road surface to be detected, which is acquired in advance; a processing module 602, configured to extract a suspected disease edge through an edge detection algorithm according to the deformation depth information; a positioning module 603, configured to obtain an initial disease-positioning area according to the deformation depth information and the suspected disease edge, and position the disease area through area growth reduction processing; the identifying module 604 is configured to obtain a disease attribute set of the disease area, and identify a disease type of the disease area according to the disease attribute set.
The method comprises the following steps that a line scanning three-dimensional measuring sensor can be adopted to collect three-dimensional data of a road surface to be detected; after the acquisition, the acquisition module 601 processes the three-dimensional data to further acquire the deformation depth information and the deformation depth image of the road surface to be detected. Fig. 2 is a schematic diagram of a deformation depth image (a) of a pit defect in the method for identifying a road surface deformation type defect according to the embodiment of the present invention, and as shown in fig. 2, taking a pit defect as an example, a deeper position on a road surface to be detected has a deeper color, so as to distinguish depth values at different positions of the road surface to be detected.
The processing module 602, according to the deformation depth information obtained by the obtaining module 601, uses an edge detection algorithm to solve the deformation depth information, and the obtained edge is a suspected disease edge; the suspected disease edge can reflect the disease area to a certain extent.
The positioning module 603 first obtains an initial positioning disease area according to the deformation depth information obtained by the obtaining module 601 and the suspected disease edge obtained by the processing module 602; and then the diseased area can be obtained through the treatment of area growing reduction. The area growth reduction is to extract the damaged areas by utilizing the topological relation among the damaged areas by utilizing the characteristics of the pavement deformation diseases, such as area aggregation and depth change continuity.
The identification module 604 obtains a disease attribute set in the disease area according to the disease area obtained by the positioning module 603; the disease attribute set reflects characteristics such as the shape and depth of the disease area, and the disease category of the disease area can be effectively identified by the attribute set.
According to the device for identifying the road surface deformation diseases, the disease depth information and the deformation depth image are obtained, the disease area in the road surface is accurately extracted, and the integrity of the disease area is guaranteed; and the disease type of the disease area is accurately identified through the disease attribute, so that the pavement deformation disease is efficiently and accurately detected and identified.
On the basis of any of the above embodiments, the obtaining module 601 further includes: the preprocessing unit is used for carrying out abnormal value elimination processing, data calibration processing and filtering processing on the three-dimensional data to obtain a section control contour; the analysis unit is used for analyzing the profile characteristics of the section control profile to acquire a section standard profile corresponding to the section control profile; the acquisition unit is used for making a difference between the section control profile and the section standard profile and acquiring section elevation difference information of the actual section elevation and the standard section elevation of the road surface to be detected; and the splicing unit is used for splicing a plurality of continuous sections according to the section elevation difference information to acquire the deformation depth information of the road surface to be detected.
On the basis of any of the above embodiments, the positioning module 603 further includes: the dividing unit is used for dividing the deformation depth information into a plurality of image sub-blocks and acquiring depth attribute information corresponding to the image sub-blocks; wherein the depth attribute information includes a depth average value, a depth value variance, and depth value distribution information; the evaluation unit is used for evaluating the confidence degrees of the image subblocks according to the depth attribute information corresponding to the image subblocks and the suspected disease edge by combining a deformation disease knowledge base, and taking the image subblock with higher confidence degree as the primary positioning disease area; the marking unit is used for marking the communicated areas of the initially positioned disease areas to obtain the area parameters of each communicated area; wherein the region parameters comprise region length, region area, region position and region direction; and the extending unit is used for performing edge extension on the communicated area of which the area parameters meet the preset conditions to obtain the damaged area.
On the basis of any of the above embodiments, the identifying module 604 further includes: the set acquisition unit is used for acquiring the effective length, the effective width, the length-width ratio, the maximum depth, the average depth, the disease area and the disease position of the disease area; the disease attribute set comprises the effective length, the effective width, the length-width ratio, the disease position, the maximum depth, the average depth and the disease area of the disease area; and the type acquisition unit is used for acquiring the disease types of the diseases contained in the disease areas based on a deformation disease knowledge base according to the disease attribute set.
On the basis of any of the above embodiments, the extension unit further comprises: the extension subunit is used for performing edge extension on a first communication region with the region length and the region area larger than a preset threshold along the region direction of the first communication region; the connection subunit is configured to, if a second connected region exists in the extension region and a distance between the first connected region and the second connected region is smaller than a preset distance, obtain a central connection line between the first connected region and the second connected region; and the merging subunit is used for merging the first communication area and the second communication area along the direction of the central connecting line, and merging the obtained areas to serve as new disease areas.
On the basis of any of the above embodiments, the processing module 602 further includes: the gradient obtaining unit is used for obtaining the gradient component of each pixel point according to a preset edge detection operator and the deformation depth information; and the edge acquisition unit is used for acquiring pixel points with gradient components larger than a preset gradient threshold value as suspected disease edge points and acquiring the suspected disease edges according to the suspected disease edge points.
On the basis of any of the above embodiments, the type obtaining unit further includes: the classifier obtaining subunit is used for obtaining a classifier according to the deformation disease knowledge base; the type obtaining subunit is used for obtaining the disease type of the disease contained in the disease area through the classifier based on the disease linear feature, the depth feature, the area array feature, the position feature and the deformation degree according to the disease attribute set; wherein the linear features comprise an effective length, an effective width, an aspect ratio; the depth features include a maximum depth and an average depth; the area array characteristics comprise disease areas; the location features include disease locations; the degree of deformation includes slight deformation, moderate deformation, and severe deformation.
Fig. 7 is a schematic structural diagram of an apparatus for identifying a road surface deformation disease according to an embodiment of the present invention, and as shown in fig. 7, the apparatus includes: at least one processor 701; and at least one memory 702 communicatively coupled to the processor 701, wherein: the memory 702 stores program instructions executable by the processor 701, and the processor 701 calls the program instructions to be able to execute the method for identifying a road surface deformation type disease provided in the foregoing embodiments, for example, the method includes: s1, acquiring deformation depth information of the road surface to be detected according to the pre-acquired three-dimensional data of the road surface to be detected; s2, extracting the suspected disease edge through an edge detection algorithm according to the deformation depth information; s3, acquiring an initial disease positioning area according to the deformation depth information and the suspected disease edge, and positioning the disease area through area growth reduction treatment; s4, acquiring a disease attribute set of the disease area, and identifying the disease type of the disease area according to the disease attribute set.
An embodiment of the present invention further provides a non-transitory computer-readable storage medium, where the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable a computer to execute the method for identifying a road surface deformation disease provided in the corresponding embodiment, for example, the method includes: s1, acquiring deformation depth information of the road surface to be detected according to the pre-acquired three-dimensional data of the road surface to be detected; s2, extracting the suspected disease edge through an edge detection algorithm according to the deformation depth information; s3, acquiring an initial disease positioning area according to the deformation depth information and the suspected disease edge, and positioning the disease area through area growth reduction treatment; s4, acquiring a disease attribute set of the disease area, and identifying the disease type of the disease area according to the disease attribute set.
The above-described embodiments of the apparatus for identifying a road surface deformation type disease and the like are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute the various embodiments or some parts of the methods of the embodiments.
According to the method, the device and the equipment for identifying the road surface deformation diseases, provided by the embodiment of the invention, the elevation difference value of the three-dimensional road surface standard contour and the control contour is calculated to obtain the section deformation elevation information; splicing the sections along the driving direction to form a road surface deformation depth image; reasonably dividing the road surface deformation depth image into image sub-blocks with non-overlapping sizes, and performing statistical analysis on the depth values in each divided sub-block to obtain the mean value, variance and positive-negative distribution information of the depth values in the sub-blocks; the rapid and accurate extraction of the road surface deformation depth information is realized.
In the pavement deformation disease positioning process, the disease edges are extracted by utilizing differential edge detection, and the initial positioning of the diseases is realized by combining a deformation disease knowledge base and the depth information of the disease sub-blocks; the method is characterized in that the deformation disease has the characteristics of regional aggregation and depth change continuity, morphological processing is carried out based on the initially positioned disease target sub-block, regional growth reduction is carried out by using the topological relation of the morphological processing, a disease region with high confidence coefficient is obtained, extraction of the deformation disease region is further realized, and the integrity of the disease region is ensured.
A classifier is designed by combining a pavement deformation disease knowledge base, and extracted pavement deformation disease areas are classified by using disease linear characteristics, area array characteristics, position characteristics and deformation degrees, so that the deformation disease types are determined, and meanwhile, a three-dimensional pavement deformation disease knowledge base is perfected.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. A method for identifying pavement deformation diseases is characterized by comprising the following steps:
s1, acquiring deformation depth information of the road surface to be detected according to the pre-acquired three-dimensional data of the road surface to be detected;
s2, extracting the suspected disease edge through an edge detection algorithm according to the deformation depth information;
s3, acquiring an initial disease positioning area according to the deformation depth information and the suspected disease edge, and positioning the disease area through area growth reduction treatment;
s4, acquiring a disease attribute set of the disease area, and identifying the disease type of the disease area according to the disease attribute set;
the step S1 further includes:
s11, carrying out abnormal value elimination processing, data calibration processing and filtering processing on the three-dimensional data to obtain a section control contour;
s12, analyzing the profile characteristics of the section control profile to obtain a section standard profile corresponding to the section control profile;
s13, making a difference between the section control contour and the section standard contour, and acquiring section elevation difference information of the actual elevation and the standard elevation of the section of the road surface to be detected;
s14, splicing a plurality of continuous sections according to the section elevation difference information to obtain the deformation depth information of the road surface to be detected;
the step S2 further includes:
s21, obtaining the gradient component of each pixel point according to a preset edge detection operator and the deformation depth information;
s22, obtaining pixel points with gradient components larger than a preset gradient threshold value as suspected disease edge points, and obtaining the suspected disease edges according to the suspected disease edge points;
in step S21, using an edge detection operator of 11 × 11, to the road surface deformation depth information F, a differential edge detection method is used to solve suspected edge points of the deformation type diseases to locate the disease area; the edge detection operator is:
according to the edge detection operator, calculating a gradient component as follows:
in the formula, f (j, i) represents the deformation depth value at the coordinate (j, i), and the magnitude of the gradient component of the pixel point (j, i) is:
G(j,i)≈|Gj|+|Gil, |; in step S22, according to the gradient components obtained in step S21, if G (j, i) > Th, where Th is a preset gradient threshold; g (j, i) is a suspected disease edge point;
the step S3 further includes:
s31, dividing the deformation depth information into a plurality of image sub-blocks, and acquiring depth attribute information corresponding to the image sub-blocks respectively;
wherein the depth attribute information includes a depth average value, a depth value variance, and depth value distribution information;
s32, evaluating confidence degrees of the image sub-blocks according to depth attribute information corresponding to the image sub-blocks and the suspected disease edges by combining a deformation disease knowledge base, and taking the image sub-blocks with higher confidence degrees as the primary positioning disease areas;
s33, carrying out connected region marking on the initially positioned disease region to obtain region parameters of each connected region;
wherein the region parameters comprise region length, region area, region position and region direction;
and S34, performing edge extension on the connected region with the region parameters meeting the preset conditions to obtain the damaged region.
2. The method according to claim 1, wherein the step S4 further comprises:
s41, acquiring the effective length, the effective width, the length-width ratio and the disease position of the disease area, and acquiring the maximum depth, the average depth and the disease area of the disease area according to the effective length and the effective width;
the disease attribute set comprises the effective length, the effective width, the length-width ratio, the disease position, the maximum depth, the average depth and the disease area of the disease area;
and S42, acquiring the disease types of the diseases contained in the disease areas based on a deformation disease knowledge base according to the disease attribute set.
3. The method according to claim 1, wherein the step S34 further comprises:
s341, performing edge extension on a first communication region with the region length and the region area larger than a preset threshold value along the region direction of the first communication region;
s342, if a second communication area exists in the extension area and the distance between the first communication area and the second communication area is smaller than a preset distance, acquiring a central connection line between the first communication area and the second communication area;
and S343, combining the first communication area and the second communication area along the direction of the central connecting line, and taking the combined area as a new disease area.
4. The method according to claim 2, wherein the step S42 further comprises:
s421, obtaining a classifier according to the deformation disease knowledge base;
s422, acquiring the disease types of the diseases contained in the disease areas through the classifier based on the disease linear characteristics, the depth characteristics, the area array characteristics, the position characteristics and the deformation degree according to the disease attribute set;
wherein the linear features comprise an effective length, an effective width, an aspect ratio; the depth features include a maximum depth and an average depth; the area array characteristics comprise disease areas; the location features include disease locations; the degree of deformation includes slight deformation, moderate deformation, and severe deformation.
5. A device for identifying road surface deformation diseases is characterized by comprising:
the acquisition module is used for acquiring deformation depth information of the road surface to be detected according to the pre-acquired three-dimensional data of the road surface to be detected;
the processing module is used for extracting suspected disease edges through an edge detection algorithm according to the deformation depth information;
the positioning module is used for acquiring an initial positioning disease area according to the deformation depth information and the suspected disease edge, and positioning the disease area through area growth reduction treatment;
the identification module is used for acquiring a disease attribute set of the disease area and identifying the disease type of the disease area according to the disease attribute set;
wherein the obtaining module is further configured to perform operations comprising:
s11, carrying out abnormal value elimination processing, data calibration processing and filtering processing on the three-dimensional data to obtain a section control contour;
s12, analyzing the profile characteristics of the section control profile to obtain a section standard profile corresponding to the section control profile;
s13, making a difference between the section control contour and the section standard contour, and acquiring section elevation difference information of the actual elevation and the standard elevation of the section of the road surface to be detected;
s14, splicing a plurality of continuous sections according to the section elevation difference information to obtain the deformation depth information of the road surface to be detected;
the processing module is further configured to perform operations comprising:
s21, obtaining the gradient component of each pixel point according to a preset edge detection operator and the deformation depth information;
s22, obtaining pixel points with gradient components larger than a preset gradient threshold value as suspected disease edge points, and obtaining the suspected disease edges according to the suspected disease edge points;
in step S21, using an edge detection operator of 11 × 11, to the road surface deformation depth information F, a differential edge detection method is used to solve suspected edge points of the deformation type diseases to locate the disease area; the edge detection operator is:
according to the edge detection operator, calculating a gradient component as follows:
in the formula, f (j, i) represents the deformation depth value at the coordinate (j, i), and the magnitude of the gradient component of the pixel point (j, i) is:
G(j,i)≈|Gj|+|Gil, |; in step S22, according to the gradient components obtained in step S21, if G (j, i) > Th, where Th is a preset gradient threshold; g (j, i) is a suspected disease edge point;
the positioning module is further configured to perform operations comprising:
s31, dividing the deformation depth information into a plurality of image sub-blocks, and acquiring depth attribute information corresponding to the image sub-blocks respectively;
wherein the depth attribute information includes a depth average value, a depth value variance, and depth value distribution information;
s32, evaluating confidence degrees of the image sub-blocks according to depth attribute information corresponding to the image sub-blocks and the suspected disease edges by combining a deformation disease knowledge base, and taking the image sub-blocks with higher confidence degrees as the primary positioning disease areas;
s33, carrying out connected region marking on the initially positioned disease region to obtain region parameters of each connected region;
wherein the region parameters comprise region length, region area, region position and region direction;
and S34, performing edge extension on the connected region with the region parameters meeting the preset conditions to obtain the damaged region.
6. An apparatus for identifying road surface deformation diseases is characterized by comprising:
at least one processor;
and at least one memory communicatively coupled to the processor, wherein: the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1 to 4.
7. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710861318.2A CN107633516B (en) | 2017-09-21 | 2017-09-21 | Method and device for identifying road surface deformation diseases |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710861318.2A CN107633516B (en) | 2017-09-21 | 2017-09-21 | Method and device for identifying road surface deformation diseases |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107633516A CN107633516A (en) | 2018-01-26 |
| CN107633516B true CN107633516B (en) | 2020-04-07 |
Family
ID=61102089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710861318.2A Active CN107633516B (en) | 2017-09-21 | 2017-09-21 | Method and device for identifying road surface deformation diseases |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107633516B (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108710730B (en) * | 2018-04-28 | 2021-10-19 | 东南大学 | Rut cross section type identification and index extraction method based on multipoint detection data |
| CN110084844B (en) * | 2019-04-25 | 2023-03-28 | 中国民航大学 | Airport pavement crack detection method based on depth camera |
| CN110222569B (en) * | 2019-05-05 | 2021-04-23 | 北京三快在线科技有限公司 | Object detection method and device, electronic equipment and readable storage medium |
| CN110443881B (en) * | 2019-05-29 | 2023-07-07 | 重庆交通大学 | Bridge deck morphological change recognition bridge structure damage CNN-GRNN method |
| CN110211382A (en) * | 2019-06-11 | 2019-09-06 | 九江学院 | Automobile speed limit method for early warning and system |
| CN110473187B (en) * | 2019-08-08 | 2022-03-22 | 武汉光谷卓越科技股份有限公司 | Object-oriented line scanning three-dimensional pavement crack extraction method |
| CN110969103B (en) * | 2019-11-21 | 2021-05-11 | 同济大学 | Method for measuring length of highway pavement disease based on PTZ camera |
| CN112053376B (en) * | 2020-09-07 | 2023-10-20 | 南京大学 | Workpiece weld joint identification method based on depth information |
| CN112411324B (en) * | 2020-09-30 | 2022-03-29 | 武汉光谷卓越科技股份有限公司 | Line structure light road surface vehicle jumping detection method |
| CN112348798A (en) * | 2020-11-10 | 2021-02-09 | 江苏现代工程检测有限公司 | Automatic detection, analysis and evaluation method for asphalt pavement diseases |
| CN112465765B (en) * | 2020-11-24 | 2022-04-19 | 山东科技大学 | Road surface depth information model construction method based on vehicle-mounted mobile laser point cloud |
| CN113420621A (en) * | 2021-06-08 | 2021-09-21 | 广东省大湾区集成电路与系统应用研究院 | Pavement damage degree identification method, device, equipment and storage medium |
| CN113469990B (en) * | 2021-07-15 | 2024-01-05 | 绍兴文理学院 | Pavement disease detection method and device |
| CN114049294B (en) * | 2021-09-26 | 2023-04-25 | 武汉光谷卓越科技股份有限公司 | Road surface technical condition detection method and equipment based on three-dimensional contour |
| CN114004950B (en) * | 2021-10-29 | 2024-01-19 | 深圳大学 | BIM and LiDAR technology-based intelligent pavement disease identification and management method |
| CN114519695B (en) * | 2021-12-29 | 2024-09-27 | 郑州大学 | Asphalt pavement deformation disease judgment method |
| CN114486732B (en) * | 2021-12-30 | 2024-04-09 | 武汉光谷卓越科技股份有限公司 | Ceramic tile defect online detection method based on line scanning three-dimension |
| CN114708319B (en) * | 2022-05-25 | 2022-09-30 | 深圳思谋信息科技有限公司 | Method, device, equipment, storage medium and program product for locating diseased area |
| CN114663438A (en) * | 2022-05-26 | 2022-06-24 | 浙江银轮智能装备有限公司 | Track detection method, system, apparatus, storage medium and computer program product |
| CN115578430B (en) * | 2022-11-24 | 2023-04-07 | 深圳市城市交通规划设计研究中心股份有限公司 | Three-dimensional reconstruction method of road track disease, electronic equipment and storage medium |
| CN118015293A (en) * | 2024-02-29 | 2024-05-10 | 西南交通大学 | Pavement disease feature extraction method based on disease mask image |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104008553A (en) * | 2014-06-17 | 2014-08-27 | 武汉武大卓越科技有限责任公司 | Crack detection method with image gradient direction histogram and watershed method conflated |
| CN104021574A (en) * | 2014-07-04 | 2014-09-03 | 武汉武大卓越科技有限责任公司 | Method for automatically identifying pavement diseases |
| CN104792792A (en) * | 2015-04-27 | 2015-07-22 | 武汉武大卓越科技有限责任公司 | Stepwise-refinement pavement crack detection method |
| CN105113375A (en) * | 2015-05-15 | 2015-12-02 | 南京航空航天大学 | Pavement cracking detection system and method based on line structured light |
| CN105133471A (en) * | 2015-05-15 | 2015-12-09 | 南京航空航天大学 | Linear structured light pavement surface detection system-based pavement depth image production method |
| CN105809668A (en) * | 2016-01-15 | 2016-07-27 | 武汉武大卓越科技有限责任公司 | Object surface deformation feature extraction method based on line scanning three-dimensional point cloud |
| CN105839505A (en) * | 2016-03-18 | 2016-08-10 | 交通运输部科学研究院 | Three-dimensional visual detection method and detection device for road surface damage information |
| CN106296691A (en) * | 2016-08-11 | 2017-01-04 | 梁晓东 | Pavement disease recognition methods based on graphical analysis |
| CN106373134A (en) * | 2016-09-18 | 2017-02-01 | 武汉武大卓越科技有限责任公司 | Road index line detection method based on linear structured light three-dimensional measurement |
| CN106874882A (en) * | 2017-02-24 | 2017-06-20 | 广东诚泰交通科技发展有限公司 | Pavement disease edge detection method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9053372B2 (en) * | 2012-06-28 | 2015-06-09 | Honda Motor Co., Ltd. | Road marking detection and recognition |
-
2017
- 2017-09-21 CN CN201710861318.2A patent/CN107633516B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104008553A (en) * | 2014-06-17 | 2014-08-27 | 武汉武大卓越科技有限责任公司 | Crack detection method with image gradient direction histogram and watershed method conflated |
| CN104021574A (en) * | 2014-07-04 | 2014-09-03 | 武汉武大卓越科技有限责任公司 | Method for automatically identifying pavement diseases |
| CN104792792A (en) * | 2015-04-27 | 2015-07-22 | 武汉武大卓越科技有限责任公司 | Stepwise-refinement pavement crack detection method |
| CN105113375A (en) * | 2015-05-15 | 2015-12-02 | 南京航空航天大学 | Pavement cracking detection system and method based on line structured light |
| CN105133471A (en) * | 2015-05-15 | 2015-12-09 | 南京航空航天大学 | Linear structured light pavement surface detection system-based pavement depth image production method |
| CN105809668A (en) * | 2016-01-15 | 2016-07-27 | 武汉武大卓越科技有限责任公司 | Object surface deformation feature extraction method based on line scanning three-dimensional point cloud |
| CN105839505A (en) * | 2016-03-18 | 2016-08-10 | 交通运输部科学研究院 | Three-dimensional visual detection method and detection device for road surface damage information |
| CN106296691A (en) * | 2016-08-11 | 2017-01-04 | 梁晓东 | Pavement disease recognition methods based on graphical analysis |
| CN106373134A (en) * | 2016-09-18 | 2017-02-01 | 武汉武大卓越科技有限责任公司 | Road index line detection method based on linear structured light three-dimensional measurement |
| CN106874882A (en) * | 2017-02-24 | 2017-06-20 | 广东诚泰交通科技发展有限公司 | Pavement disease edge detection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107633516A (en) | 2018-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107633516B (en) | Method and device for identifying road surface deformation diseases | |
| CN107463918B (en) | Lane line extraction method based on fusion of laser point cloud and image data | |
| Oliveira et al. | Automatic road crack detection and characterization | |
| WO2019134252A1 (en) | Method and device for automated portrayal and accurate measurement of width of structural crack | |
| WO2017120897A1 (en) | Object surface deformation feature extraction method based on line scanning three-dimensional point cloud | |
| CN108319920B (en) | Road marking detection and parameter calculation method based on line scanning three-dimensional point cloud | |
| CN110210448B (en) | Intelligent face skin aging degree identification and evaluation method | |
| CN112149543B (en) | Building dust recognition system and method based on computer vision | |
| CN113240623B (en) | Pavement disease detection method and device | |
| CN107798293A (en) | A kind of crack on road detection means | |
| Yun et al. | Crack recognition and segmentation using morphological image-processing techniques for flexible pavements | |
| CN111126183A (en) | Method for detecting damage of building after earthquake based on near-ground image data | |
| CN112070756B (en) | Three-dimensional road surface disease measuring method based on unmanned aerial vehicle oblique photography | |
| Arjapure et al. | Deep learning model for pothole detection and area computation | |
| CN112652015A (en) | BIM-based pavement disease marking method and device | |
| Liang et al. | Research on concrete cracks recognition based on dual convolutional neural network | |
| CN114972177A (en) | Road disease identification management method and device and intelligent terminal | |
| CN104168462B (en) | Camera scene change detection method based on image angle point set feature | |
| CN113781537A (en) | Track elastic strip fastener defect identification method and device and computer equipment | |
| CN117422699B (en) | Highway detection method, highway detection device, computer equipment and storage medium | |
| CN115690081A (en) | Tree counting method, system, storage medium, computer equipment and terminal | |
| CN114299247A (en) | Rapid detection and problem troubleshooting method for road traffic sign lines | |
| CN114581805A (en) | Coating roller surface defect detection method adopting 3D line laser profile technology | |
| CN107301421A (en) | The recognition methods of vehicle color and device | |
| CN113362274B (en) | Rainfall monitoring and calculating method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Li Qingquan Inventor after: Zhang Dejin Inventor after: Cao Min Inventor after: Lin Hong Inventor after: Gui Rong Inventor before: Li Qingquan Inventor before: Zhang Dejin Inventor before: Cao Min Inventor before: Lin Hong Inventor before: Gui Rong |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 430223 No.6, 4th Road, Wuda Science Park, Donghu high tech Zone, Wuhan City, Hubei Province Patentee after: Wuhan Wuda excellence Technology Co.,Ltd. Address before: 430223 No.6, 4th Road, Wuda Science Park, Donghu high tech Zone, Wuhan City, Hubei Province Patentee before: WUHAN WUDA ZOYON SCIENCE AND TECHNOLOGY Co.,Ltd. Address after: 430223 No.6, 4th Road, Wuda Science Park, Donghu high tech Zone, Wuhan City, Hubei Province Patentee after: Wuhan Optical Valley excellence Technology Co.,Ltd. Address before: 430223 No.6, 4th Road, Wuda Science Park, Donghu high tech Zone, Wuhan City, Hubei Province Patentee before: Wuhan Wuda excellence Technology Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |