WO2023115754A1 - 基于精密三维的路面错台检测方法及装置 - Google Patents

基于精密三维的路面错台检测方法及装置 Download PDF

Info

Publication number
WO2023115754A1
WO2023115754A1 PCT/CN2022/085609 CN2022085609W WO2023115754A1 WO 2023115754 A1 WO2023115754 A1 WO 2023115754A1 CN 2022085609 W CN2022085609 W CN 2022085609W WO 2023115754 A1 WO2023115754 A1 WO 2023115754A1
Authority
WO
WIPO (PCT)
Prior art keywords
seam
road surface
target
suspected
binary image
Prior art date
Application number
PCT/CN2022/085609
Other languages
English (en)
French (fr)
Inventor
林红
曹民
卢毅
王新林
曲旋
李辉
胡秀文
Original Assignee
武汉光谷卓越科技股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 武汉光谷卓越科技股份有限公司 filed Critical 武汉光谷卓越科技股份有限公司
Priority to AU2022418482A priority Critical patent/AU2022418482A1/en
Publication of WO2023115754A1 publication Critical patent/WO2023115754A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G06T5/70—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30132—Masonry; Concrete

Definitions

  • the present application relates to the technical field of road surface detection, and in particular to a precise three-dimensional-based road surface misalignment detection method and device.
  • Pavement stagger refers to the difference in elevation between two adjacent cement slabs at the transverse joint in the cement concrete pavement. Staggering is an important factor affecting the flatness, service life and reflective cracks of cement concrete pavement after overlaying, and it is also an important index that must be considered in the evaluation of cement concrete pavement technical condition, maintenance and overlay design. Therefore, how to carry out accurate and efficient detection and evaluation of the wrong platform has become a problem of great concern to the highway management and maintenance department.
  • the commonly used detection methods for the amount of error include manual method and automatic detection method.
  • the manual method is realized by ruler, vernier caliper or level, which is slow, has low precision, and interferes with traffic; the automatic detection method will significantly affect the characteristics of the International Roughness Index (IRI) due to the existence of the wrong platform, such as laser profiler, ultrasonic profiler Instruments, etc., the profiler is expensive, and cannot accurately measure the misalignment (because there are only a small number of longitudinal profiles, the measurement results are easily affected by cracks, peeling, etc.).
  • IRI International Roughness Index
  • the present application provides a precise three-dimensional based road misalignment detection method and device, which are used to solve the defects of large measurement errors, low detection efficiency, and expensive equipment cost in the prior art, so as to reduce measurement errors and improve detection efficiency.
  • This application provides a precise three-dimensional based detection method for road misalignment, including:
  • the original seam target image and the representative position of the seam are obtained;
  • the road surface stagger information is obtained.
  • the denoising binary image of the suspected seam is obtained based on the suspected seam point, including:
  • the original seam target map and the representative position of the seam are obtained based on the row direction projection features of the target measuring point in the denoising binary image of the suspected seam, including:
  • the original seam target map and the seam representative position are obtained.
  • the original seam target map and the seam representative position are obtained based on the statistical characteristics of each row of suspected seam points, including:
  • the seam line is the line where the seam seed point is located.
  • the target seam is obtained through the seam extension operation.
  • Seam binary maps including:
  • the measurement points in the denoising binary image of the suspected seam which belong to the same connected region as the seam seed point, are used as supplementary seam points;
  • the fitting seam position in the column with missing seam in the extended seam binary image is used as the extended seam target point;
  • a target seam binary map is obtained.
  • the contour reference surface is obtained based on the road surface three-dimensional contour data, and the contour deviation between the measuring points in the road surface three-dimensional contour data and the contour reference surface includes:
  • the invalid measuring points are replaced to obtain new three-dimensional contour data of the road surface;
  • the suspected seam point is a measurement point corresponding to a contour deviation greater than a segmentation threshold.
  • the information on the wrong platform on a road surface is obtained based on the binary image of the target joint and the three-dimensional contour data of the road surface, including:
  • the road surface stagger information is obtained.
  • the representative elevations of the road surface on both sides of the front and rear sides of the seam are obtained based on the binary image of the target seam, including:
  • the average elevation of the road surface adjacent to the fitting seam is used as the representative elevation of the front side road surface, and the representative elevation set of the front side road surface is obtained;
  • the front side road surface is the road surface in the forward direction of the vehicle ;
  • the average elevation of the road surface adjacent to the fitting joint is used as the representative elevation of the rear road surface, and a set of representative elevations of the rear road surface is obtained.
  • the road surface stagger information is obtained based on the representative elevations of the road surfaces on both sides of the front and rear of the seam, including:
  • the full-width stagger value, the left and right wheel track stagger value, the maximum stagger value, the average value of the full-width stagger, the median value of the full-width stagger, and the weighted full-width stagger are obtained. at least one of the values;
  • the calculation method of the left and right wheel track belt stagger value is as follows:
  • the full-width stagger values of the corresponding columns of the left wheel track and the right wheel track are respectively selected as the left and right wheel track stagger values
  • the full-scale weighted stagger value is calculated based on the multiple columns of full-frame stagger values and the weights corresponding to each column of full-frame stagger values.
  • the present application also provides a precision three-dimensional based road misalignment detection device, including:
  • the first calculation module is used to obtain the three-dimensional contour data of the road surface, and obtain a contour reference surface based on the three-dimensional contour data of the road surface, and a contour deviation between the measurement points in the three-dimensional road surface contour data and the contour reference surface;
  • the second calculation module is used to obtain suspected seam points based on the contour deviation, and obtain a suspected seam denoising binary image based on the suspected seam points;
  • the third calculation module is used to obtain the original seam target map and the representative position of the seam based on the row direction projection feature of the target measuring point in the denoising binary image of the suspected seam;
  • the fourth calculation module is used to obtain a target seam binary image through a seam extension operation based on the suspected seam denoising binary image, the original seam target image, and the seam representative position;
  • the fifth calculation module is configured to obtain information on road staggering based on the binary image of the target joint and the three-dimensional contour data of the road.
  • the present application also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and operable on the processor.
  • the processor executes the program, it realizes any of the above-mentioned road staggering The steps of the detection method.
  • the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any one of the above-mentioned road surface error detection methods are realized.
  • the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of any one of the above-mentioned road surface misalignment detection methods are implemented.
  • the precision 3D-based pavement dislocation detection method and device obtaineds the 3D contour data of the road surface, calculates the contour reference surface and contour deviation, further determines the suspected seam points, obtains the target seam binary image, and finally obtains Wrong platform information on the road surface.
  • the entire process of calculating the information of road misalignment is completed automatically, without manual detection, and expensive equipment such as laser profilers and ultrasonic profilers are not required for pavement misalignment detection. Therefore, the method for detecting pavement misalignment provided by the present application can not only improve the detection efficiency of pavement misalignment, reduce the detection error of pavement misalignment, but also not require the use of expensive profilers, thereby reducing the cost of pavement misalignment detection.
  • Fig. 1 is one of the schematic flow charts of the road surface misalignment detection method provided by the present application
  • Fig. 2 is the binary image of the first original suspected seam point provided by the application
  • Fig. 3 is a seam positioning result diagram corresponding to Fig. 2 provided by the present application.
  • Fig. 4 is the binary image of the second original suspected seam point provided by the present application.
  • Fig. 5 is a seam positioning result diagram corresponding to Fig. 4 provided by the present application.
  • Fig. 6 is a schematic structural view of a road surface misalignment detection device provided by the present application.
  • FIG. 7 is a schematic structural diagram of an electronic device provided by the present application.
  • a method for detecting a road surface misalignment includes:
  • Step 110 acquiring road surface three-dimensional contour data, and based on the road surface three-dimensional contour data, obtaining a contour reference surface and a contour deviation between measuring points in the road surface three-dimensional contour data and the contour reference surface.
  • the three-dimensional contour data of the road surface may be three-dimensional contour data obtained by line scanning the road surface.
  • it may be based on a set of three-dimensional road surface data acquisition system composed of two line-scanning three-dimensional measurement sensors, and the acquired precise three-dimensional profile data of the road surface may be used as input.
  • the three-dimensional profile data of the road surface has been processed by three-dimensional modeling;
  • the line-scanning three-dimensional measurement sensor is composed of a three-dimensional camera, a laser, a controller, and an attitude measurement sensor.
  • the laser line is projected, and the line-scanning three-dimensional measurement unit can obtain the elevation data of the road cross-section in a single measurement;
  • the sampling interval of the line-scanning three-dimensional measurement unit in the cross-sectional direction is 1-3mm, such as 1mm, and the sampling interval in the driving direction is 1-5mm , such as 5mm, measuring width 2000-4000mm, such as 3600mm.
  • preprocessing may be performed on the three-dimensional contour data of the road surface, including processing abnormal values of measurement, obtaining contour reference surfaces, and obtaining contour deviations.
  • Step 120 Obtain suspected seam points based on the contour deviation, and obtain a denoised binary image of the suspected seam based on the suspected seam points.
  • Step 130 Based on the row-direction projection features of the target measuring points in the denoised binary image of the suspected seam, the original seam object image and the seam representative position are obtained.
  • the suspected seam point is the measuring point that may be the seam point after preliminary judgment.
  • the representative position of the seam is based on the distribution information of the row where the seam is located, and merges the seam rows whose row distance is smaller than the preset row spacing value into the same seam, corresponding to a representative location.
  • Step 140 based on the denoising binary image of the suspected seam, the original seam target image, and the seam representative position, through a seam extension operation, to obtain a target seam binary image.
  • seam extension can also be performed based on the original seam target map and the seam representative position, and the seam extension includes The connected region is extended and the missing region is extended, and finally the target seam binary map is obtained.
  • Step 150 based on the target seam binary image and the three-dimensional road profile data, obtain road stagger information.
  • the denoising binary image of suspected seams is obtained based on the suspected seams, including:
  • the binary map of suspected seam points based on the suspected seam points it may be: first mark the connected region on the original binary map of suspected seam points, and then use the connected region as a unit, according to the connected region The length, contour deviation amplitude, and connected region direction features are denoised, and a denoised binary map of suspected seams is obtained.
  • the original seam target map and the seam representative position are obtained based on the row direction projection feature of the target measuring point in the denoising binary image of the suspected seam, including:
  • the original seam target map and the seam representative position are obtained.
  • the statistical feature of each row of suspected seam points may be the number of each row of suspected seam points, and the ratio of the number of each row of suspected seam points to the total number of suspected seam points.
  • the statistical features of the suspected seam points based on the rows are obtained to obtain the original seam target map and the seam representative position, including:
  • the seam line is the line where the seam seed point is located.
  • seam target positioning includes obtaining seam seed points and seam representative positions.
  • the seam seed point acquisition method is: project the suspected seam denoising binary image along the row direction (road direction), and count the number of suspected seam points in each row. If the number of suspected seam points in the current row is greater than the preset If the value is set, the suspected seam point in the current row is marked as the seam seed point, and the row where the current behavior seam is located is recorded, and the binary map composed of the seam seed point is marked as the original seam target map.
  • the method for obtaining the seam representative position is: according to the distribution information of the row where the seam is located, merge the seam rows whose row distance is smaller than the preset row spacing value into the same seam, and record the average value of the row as the merged seam representative location.
  • the target seam binary image is obtained through a seam extension operation, include:
  • the measurement points in the denoising binary image of the suspected seam which belong to the same connected region as the seam seed point, are used as supplementary seam points;
  • the fitting seam position in the column with missing seam in the extended seam binary image is used as the extended seam target point;
  • a target seam binary map is obtained.
  • extension of the seam includes the extension of the connected region and the extension of the missing region.
  • the specific method of expanding the connected region is as follows: first, based on the seam seed points in the original seam target map, for each seam seed point, within the first target range, the denoised suspected seam binary map The points that belong to the same connected region as the current seam seed point are supplemented as seam points, and the expanded seam binary map is obtained.
  • the specific method of extending the missing area is: according to the seam representative position information, for each seam, with the seam representative position as the center, search for the seam points in the binary map of the expanded seam within the second target range, and It performs a linear fit, resulting in a fitted seam. If within the second target range, there is a column of missing seams in the expanded seam binary map, mark the position of the fitting seam in the corresponding column as the seam target point, and obtain the target seam binary map .
  • the obtaining a contour reference surface based on the three-dimensional contour data of the road surface, and the contour deviation between the measurement points in the three-dimensional road surface contour data and the contour reference surface include:
  • the invalid measuring points are replaced to obtain new three-dimensional contour data of the road surface;
  • the suspected seam point is a measurement point corresponding to a contour deviation greater than a segmentation threshold.
  • the measurement abnormal value of the contour reference surface can be processed, and the road surface three-dimensional contour data processed by the measurement abnormal value can be filtered (such as median filter, low-pass filter, mean value Filtering, full variation filtering), or frequency domain transformation (such as Fourier transform, wavelet transform) and other methods to obtain the contour reference surface.
  • filtered such as median filter, low-pass filter, mean value Filtering, full variation filtering
  • frequency domain transformation such as Fourier transform, wavelet transform
  • the contour deviation is obtained by measuring the difference between the three-dimensional contour data processed by the abnormal value and the contour reference plane.
  • the segmentation threshold is adaptively calculated according to the contour deviation near the measuring point. If the contour deviation value of the measuring point is greater than or equal to the segmentation threshold, the current measuring point is marked as a suspected seam point, and the original suspected seam point is obtained. Binary map.
  • the obtaining the road surface misalignment information based on the target seam binary image and the road surface three-dimensional contour data includes:
  • the road surface stagger information is obtained.
  • the representative elevations of the road surfaces on both sides before and after the seam are obtained, including:
  • the average elevation of the road surface adjacent to the fitting seam is used as the representative elevation of the front side road surface, and the representative elevation set of the front side road surface is obtained;
  • the front side road surface is the road surface in the forward direction of the vehicle , the rear side road is the road in the opposite direction of the vehicle;
  • the average elevation of the road surface adjacent to the fitting joint is used as the representative elevation of the rear road surface, and a set of representative elevations of the rear road surface is obtained.
  • the road surfaces on both sides before and after the joint represent the elevation, that is, the road surfaces on both sides before and after the fitting joint represent the elevation.
  • the representative elevations of the road surfaces on the front and rear sides of the joint include a representative elevation set of the road surface on the front side, and a representative elevation set of the road surface on the rear side.
  • the road surface stagger information is obtained based on the representative elevations of the road surfaces on the front and rear sides of the joint, including:
  • the full-width stagger value, the left and right wheel track stagger value, the maximum stagger value, the average value of the full-width stagger, the median value of the full-width stagger, and the weighted full-width stagger are obtained. at least one of the values.
  • the road surface misalignment information includes at least one of the full width misalignment value, the left and right wheel track misalignment value, the maximum misalignment value, the full width misalignment average value, the full width width misalignment median value and the full width weighted misalignment value .
  • the calculation method of the left and right wheel track belt stagger value is as follows:
  • the full-width stagger values of the corresponding columns of the left wheel track and the right wheel track are respectively selected as the left and right wheel track stagger values
  • the full-scale weighted stagger value is calculated based on the multiple columns of full-frame stagger values and the weights corresponding to each column of full-frame stagger values.
  • the representative elevations of the road surfaces on both sides before and after the joint are obtained, that is, for each joint, the representative elevations of the road surfaces on both sides of the joint are obtained column by column.
  • the specific method is: for each column of the joint, to fit the joint Take the location of the joint as the center, within the third target range, find the starting point and end point of the joint along the driving direction; above the starting point of the joint, take the average elevation of the road surface adjacent to the joint within the fourth target range as the representative of the front side road surface Elevation, get the representative elevation set ⁇ FZ 1 , FZ 2 ,...,FZ n ⁇ of the front side road surface; below the end point of the joint, take the average elevation of the road surface adjacent to the joint within the fifth target range as the representative elevation of the rear road surface ⁇ BZ 1 ,BZ 2 ,...,BZ n ⁇ , where n is the number of columns of the target seam binary map.
  • Calculation of stagger value calculate the stagger value for each seam separately. Calculation methods include the calculation of full-width misalignment, the calculation of left and right wheel track misalignment, the maximum misalignment, the average of full-width misalignment, the median of full-width width misalignment, and the calculation of full-width weighted misalignment.
  • Calculation of left and right wheel track misalignment values Combining the corresponding relationship between the column position of the 3D road surface data and the road width direction position, respectively select the full width of the left and right wheel track corresponding to the column position as the left and right wheel track misalignment value
  • j R ⁇ ), respectively, where L and R are the positions of the left and right wheel tracks respectively corresponding column number.
  • the calculation of the full-width weighted misalignment value is the weighted average of all values in the full-width misalignment value set ⁇ SS j
  • DIS j min(
  • ), j 1,2,...,n, x j is the distance position of column j in the width direction, x L , x R are respectively the distance positions of the left and right wheel tracks in the width direction;
  • Full frame weighted error calculation Calculate the full-frame weighted mis-station value S weight according to all the mis-station values in the column mis-station value set and the corresponding weight w i .
  • the staggered stage can be divided into various levels.
  • the three-dimensional contour data of the pavement can also be used to detect pavement cracks, pavement rutting and other indicators.
  • the method for detecting wrong platform on the road includes: data preprocessing, seam positioning, and information acquisition of wrong platform.
  • Data preprocessing including measurement outlier processing, contour reference surface acquisition, and contour deviation acquisition.
  • Seam positioning including segmentation of suspected seam points, coarse denoising of suspected seam points, seam target positioning, and seam extension.
  • Acquisition of staggered platform information including acquisition of representative elevations of road surfaces on both sides of the front and rear of the joint, calculation of staggered platform values, and acquisition of staggered platform attributes.
  • Data preprocessing including measurement outlier processing, contour reference surface acquisition, and contour deviation acquisition, specifically:
  • Measurement outlier processing using valid measurement points near zero-value measurement points (ie: invalid measurement points) to replace zero-value measurement points.
  • the contour reference surface is obtained, and the three-dimensional contour data processed by the measurement abnormal value are obtained by means of filtering method.
  • the contour deviation is obtained by measuring the difference between the three-dimensional contour data processed by the abnormal value and the contour reference surface.
  • Tex 2 is the mean value of the contour deviation corresponding to all points in the binary image of the current suspected seam point.
  • Seam target positioning including seam seed point acquisition and seam representative position acquisition.
  • the specific method of expanding the connected region is as follows: first, based on the seam seed points in the original seam target map, for each seam seed point, within the first target range (50mm), denoise the suspected seam. The points in the graph that belong to the same connected area as the current seam seed point are supplemented as seam points, and the expanded seam binary map is obtained.
  • the specific method of extending the missing area is, according to the seam representative position information, for each seam, with the seam representative position as the center, find the seam point in the binary image of the expanded seam within the second target range (300mm) , and perform linear fitting on it to get the fitted seam. If within a given range (row direction 500mm), there is a column with a missing seam in the expanded seam binary map, then the fitted seam in the corresponding column will be The position where the seam is located is marked as the seam target point, and the target seam binary map is obtained.
  • Acquisition of staggered platform information including acquisition of representative elevations of road surfaces on both sides of the front and rear of the joint, calculation of staggered platform values, and acquisition of staggered platform attributes.
  • the representative elevations of the road surfaces on both sides before and after the joint are obtained, and the representative elevations of the road surfaces on both sides before and after the joint are obtained column by column for each joint.
  • the third target range (row direction 500mm)
  • the side road surface represents the elevation
  • the front side road surface represents the elevation set ⁇ FZ 1 , FZ 2 ,...,FZ n ⁇ ; below the end point of the joint, take the average elevation of the road surface adjacent to the joint within the fifth target range (row direction 50mm)
  • Calculation of stagger value calculate stagger value for each seam separately.
  • Calculation methods include the calculation of full-width misalignment, the calculation of left and right wheel track misalignment, the maximum misalignment, the average of full-width misalignment, the median of full-width width misalignment, and the calculation of full-width weighted misalignment.
  • the calculation of the full-scale stagger value is to calculate the absolute difference between the representative elevation of the front road surface and the representative elevation of the rear road surface column by column, which is recorded as SS j , ⁇ SS j
  • the calculation of the left and right wheel track misalignment values combined with the corresponding relationship between the column position of the 3D road surface data and the width direction of the road surface, respectively select the full width of the left and right wheel track position corresponding to the column position as the left and right wheel track misalignment value
  • the calculation of the mean value of the full-width misalignment is the mean value of the full-width misalignment value, which is recorded as S Avg ,
  • the calculation of the median value of the full-width misalignment is the median value of the full-width misalignment, which is denoted as S Mid .
  • the calculation of the full-width weighted misalignment value is the weighted average of all values in the full-width misalignment value set ⁇ SS j
  • DIS j min(
  • ), j 1,2,...,n, x j is the distance position of the jth column in the width direction, x L , x R are respectively the distance positions of the left and right wheel tracks in the width direction;
  • Full frame weighted error calculation Calculate the full-frame weighted mis-station value S weight according to all the mis-station values in the column mis-station value set and the corresponding weight w i .
  • the misalignment is divided into various grades. Specifically, the misalignment value ⁇ 2.54mm is classified as mild misalignment, the misalignment value ⁇ 2.54mm and ⁇ 5.08mm is classified as moderate misalignment, and the misalignment value is classified as moderate The value ⁇ 5.08mm is classified as severe misalignment.
  • the binary image of the first original suspected seam point is shown in FIG. 2
  • the image of the seam positioning result corresponding to the first binary image of the original suspected seam point is shown in FIG. 3 .
  • the second original binary image of suspected seam points is shown in FIG. 4
  • the seam location result image corresponding to the second original binary image of suspected seam points is shown in FIG. 5 .
  • the average value of the full width of the joint is 2.07mm
  • the median value of the full width is 2.02mm
  • the value of the left wheel track is 1.84mm
  • the value of the right wheel track is 2.65mm
  • the maximum value is 4.13 mm.
  • the average value of the full-width misalignment of the upper seam is 3.21mm
  • the median value of the full-width misalignment is 3.23mm
  • the misalignment value of the left wheel trace is 3.65mm
  • the misalignment value of the right wheel trace is 4.55mm
  • the average value of the full-width misalignment of the lower seam is 1.33mm
  • the median value of the full-width misalignment is 0.77mm
  • the misalignment value of the left wheel track is 3.62mm
  • the misalignment value of the right wheel trace is 0.87mm
  • the precise three-dimensional contour data of the road surface can also be used to detect road surface cracks, road surface rutting and other indicators.
  • the road surface error detection method includes: obtaining the three-dimensional contour data of the road surface, and based on the three-dimensional contour data of the road surface, obtaining a contour reference surface, and measuring points and contours in the three-dimensional contour data of the road surface The contour deviation between the reference surfaces; based on the contour deviation, the suspected seam point is obtained, and based on the suspected seam point, the original seam target image and the seam representative position of the suspected seam denoising binary image are obtained; based on the Describe the row direction projection features of the target measuring points in the suspected seam denoising binary image, and obtain the original seam target image and the representative position of the seam; based on the suspected seam denoising binary image, the original seam object image , and the representative position of the seam, through the seam extension operation, the target seam binary map is obtained;
  • the road surface stagger information is obtained.
  • the pavement misalignment detection method provided in this application, after obtaining the three-dimensional contour data of the road surface, the contour reference surface and the contour deviation are calculated, and then the suspected seam points are further determined to obtain the target seam binary map, and finally the road surface error is obtained. station information.
  • the entire process of calculating the information of road misalignment is completed automatically, without manual detection, and expensive equipment such as laser profilers and ultrasonic profilers are not required for pavement misalignment detection. Therefore, the pavement misalignment detection method provided by the present application can improve the detection efficiency of pavement misalignment, reduce the detection error of road surface misalignment, and does not need to use expensive profilers, thereby reducing the cost of pavement misalignment detection.
  • the wrong platform detection method provided by this application has high measurement accuracy, which can effectively avoid the influence of road surface cracks and peeling on the detection results; the wrong platform detection method provided by this application is low in cost, and can share measurement equipment with road surface damage, road rutting and other detection indicators .
  • the road misalignment detection device described below and the road misalignment detection method described above can be referred to in correspondence.
  • the road surface misalignment detection device 600 includes: a first calculation module 610 , a second calculation module 620 , a third calculation module 630 , a fourth calculation module 640 and a fifth calculation module 650 .
  • the first calculation module 610 is used to acquire 3D road surface contour data, and obtain a contour reference surface and a contour deviation between measurement points in the road surface 3D contour data and the contour reference surface based on the road surface 3D contour data.
  • the second calculation module 620 is configured to obtain suspected seam points based on the contour deviation, and obtain a denoised binary map of suspected seams based on the suspected seam points.
  • the third calculation module 630 is configured to obtain the original seam target map and the representative position of the seam based on the row-direction projection features of the target measurement points in the denoised binary image of the suspected seam.
  • the fourth calculation module 640 is configured to obtain a target seam binary image through a seam extension operation based on the suspected seam denoising binary image, the original seam target image, and the seam representative position.
  • the fifth calculation module 650 is configured to obtain road surface misalignment information based on the target seam binary image and the road surface three-dimensional contour data.
  • the second calculation module 620 includes: a first binary image generation unit and a binary image processing unit.
  • the first binary image generating unit is configured to obtain an original binary image of suspected seam points based on the suspected seam points.
  • the binary image processing unit is used to take the connected area in the binary image of the original suspected seam point as a unit, and perform denoising according to the length of the connected area, the magnitude of the contour deviation, and the direction feature of the connected area, to obtain the Describe the suspected seam denoising binary image.
  • the third calculating module 630 includes: a suspicious point generating unit and a suspicious point processing unit.
  • the suspected point generating unit is used to project the target point in the suspected seam denoising binary image along the row direction to obtain each row of suspected seam points.
  • the suspected point processing unit is configured to obtain the original seam target map and the seam representative position based on the statistical characteristics of each row of suspected seam points.
  • the suspected point processing unit includes: a determination unit, a seam map generation unit, and a seam position calculation unit.
  • the determination unit is used to determine that the suspected seam points in the current row are seam seed points when the number of suspected seam points in the current row is greater than the preset number value;
  • the seam graph generation unit is used to obtain the original seam target graph based on the seam seed point;
  • the seam position calculation unit is used to use the sum of the seams whose line spacing is smaller than the preset line spacing value as the target seam line, and merge the target seam lines into the same seam, and average the lines of the target seam line value as the seam represents position;
  • the seam line is the line where the seam seed point is located.
  • the fourth calculation module 640 includes: a supplementary unit, an expansion unit, a fitting unit, an extension unit and a second binary image generation unit.
  • the supplementary unit is used to denoise the suspected seam in the binary image of the suspected seam within the first target range corresponding to the seam seed point, and the measurement points belonging to the same connected area as the seam seed point are used as supplementary joints. sewing point;
  • the expansion unit is used to obtain an expanded seam binary image based on the seam seed point and the supplementary seam point;
  • the fitting unit is used to search for seam points in the expanded seam binary image within the second target range corresponding to the seam representative position, and perform linear fitting on the searched seam points to obtain a fitted Seams;
  • the extension unit is used to use the fitted seam position in the column with missing seams in the expanded seam binary image as the extended seam target point within the third target range corresponding to the seam representative position;
  • the second binary image generating unit is configured to obtain a target seam binary image based on the seam seed point, the supplementary seam point and the extended seam target point.
  • the first calculation module 610 includes: a data acquisition unit, a data processing unit and a deviation calculation unit.
  • the data acquisition unit is used to replace the invalid measuring points based on valid measuring points near the invalid measuring points to obtain new road surface three-dimensional contour data when there are invalid measuring points in the three-dimensional road surface contour data;
  • the data processing unit is used to process the new road surface three-dimensional contour data based on a filtering method or a frequency domain change method to obtain the contour reference surface;
  • the deviation calculating unit is used for making a difference between the new road surface three-dimensional profile data and the profile reference surface to obtain the profile deviation.
  • the suspected seam point is a measurement point corresponding to a contour deviation greater than a segmentation threshold.
  • the fifth calculation module 650 includes: an elevation calculation unit and a platform error calculation unit.
  • the elevation calculation unit is used to obtain representative elevations of road surfaces on both sides of the front and rear sides of the seam based on the target seam binary image;
  • the staggering calculation unit is used to obtain the information of the staggering of the road surface based on representative elevations of the road surfaces on both sides before and after the joint.
  • the elevation calculation unit includes: a search unit, a first elevation determination unit and a second elevation determination unit.
  • the search unit is configured to search for a seam start point and a seam end point within a fourth target range based on the target seam binary image, with the fitting seam as the center;
  • the first elevation determination unit is used to, within the fifth target range corresponding to the starting point of the seam, take the average elevation of the road surface adjacent to the fitting seam as the representative elevation of the front road surface, and obtain a set of representative elevations of the front road surface;
  • the side road is the road in the forward direction of the vehicle;
  • the second elevation determination unit is configured to use the average elevation of the road surface adjacent to the fitted joint within the sixth target range corresponding to the end point of the joint as the representative elevation of the rear road surface to obtain a set of representative elevations of the rear road surface.
  • the stagger calculation unit is further used to: obtain the full width stagger value, the left and right wheel track zone stagger value, the maximum stagger value, and the full width stagger based on the representative elevations of the road surfaces on the front and rear sides of the joint. At least one of the channel average value, the full-width mis-channel value, and the full-width weighted channel error value.
  • the calculation method of the left and right wheel track belt stagger value is as follows:
  • the full-width stagger values of the corresponding columns of the left wheel track and the right wheel track are respectively selected as the left and right wheel track stagger values
  • the full-scale weighted stagger value is calculated based on the multiple columns of full-frame stagger values and the weights corresponding to each column of full-frame stagger values.
  • the first calculation module 610 is used to acquire 3D road surface contour data, and obtain a contour reference surface and a contour deviation between measurement points in the road surface 3D contour data and the contour reference surface based on the road surface 3D contour data.
  • the second calculation module 620 is configured to obtain suspected seam points based on the contour deviation, and obtain an original seam target map and seam representative positions based on the suspected seam points.
  • the third calculation module 630 is configured to obtain a target seam binary image based on the original seam target image and the seam representative position.
  • the fourth calculation module 640 is used to obtain road surface misalignment information based on the target seam binary image.
  • the second calculation module 620 includes: a first binary image generation unit and a seam calculation unit.
  • the first binary image generating unit is configured to obtain a binary image of suspected seam points based on the suspected seam points.
  • the seam calculation unit is used to project the binary image of the suspected seam points along the row direction to obtain each row of suspected seam points, and to obtain the original seam target map and the seam seam points based on each row of suspected seam points.
  • the seam represents the position.
  • the seam calculation unit includes: a seed point determination unit, a seam target map calculation unit, and a seam representative position calculation unit.
  • the seed point determination unit is configured to determine the suspected seam points in the current row as seam seed points when the number of suspected seam points in the current row is greater than a preset number value.
  • the seam target graph calculation unit is configured to obtain the original seam target graph based on the seam seed point.
  • the seam representative position calculation unit is used to use the sum of the seams whose line spacing is smaller than the preset line spacing value as the target seam line, and merge the target seam lines into the same seam, and combine the lines of the target seam line
  • the mean value serves as a representative position of the seam.
  • the seam line is the line where the seam seed point is located.
  • the third calculation module 630 includes: a supplementary seam point calculation unit, an expansion unit, a fitting unit, a seam target calculation unit and a second binary image generation unit.
  • the supplementary seam point calculation unit is used to, within the first target range corresponding to the seam seed point, calculate the measurement points in the binary image of the suspected seam point that belong to the same connected area as the seam seed point, as a supplementary seam point;
  • the expansion unit is used to obtain the expansion joint binary map based on the supplementary joint points;
  • the fitting unit is used to search for seam points in the expanded seam binary image within the second target range corresponding to the seam representative position, and perform linear fitting on the searched seam points to obtain a fitted Seams;
  • the seam target calculation unit is used to use the fitted seam position in the column with missing seams in the expanded seam binary image as the seam target within the third target range corresponding to the seam representative position point;
  • the second binary image generating unit is configured to obtain a target seam binary image based on the extended seam target point.
  • the first calculation module 610 includes: a denoising unit, a reference plane calculation unit and a deviation calculation unit.
  • the denoising unit is used to replace the invalid measuring points based on valid measuring points near the invalid measuring points to obtain new road surface three-dimensional contour data when there are invalid measuring points in the three-dimensional road surface contour data.
  • the reference surface calculation unit is configured to process the new road surface three-dimensional contour data based on a filtering method or a frequency domain variation method to obtain the contour reference surface.
  • the deviation calculation unit is used for making a difference between the new road surface three-dimensional profile data and the profile reference surface to obtain the profile deviation.
  • the suspected seam point is a measurement point corresponding to a contour deviation greater than a segmentation threshold.
  • the fourth calculation module 640 is further used to obtain the full-width misalignment value, the left and right wheel track misalignment value, the maximum misalignment value, the full-width width misalignment value, and the full-width misalignment value based on the target seam binary image.
  • the median value of width misalignment and the weighted misalignment value of full width is further used to obtain the full-width misalignment value, the left and right wheel track misalignment value, the maximum misalignment value, the full-width width misalignment value, and the full-width misalignment value based on the target seam binary image.
  • the median value of width misalignment and the weighted misalignment value of full width is the average value of width misalignment and the weighted misalignment value of full width.
  • the electronic device, computer program product, and storage medium provided by the present application are described below, and the electronic device, computer program product, and storage medium described below can be referred to in correspondence with the above-described road surface misalignment detection method.
  • FIG. 7 illustrates a schematic diagram of the physical structure of an electronic device.
  • the electronic device may include: a processor (processor) 710, a communication interface (Communications Interface) 720, a memory (memory) 730 and a communication bus 740, Wherein, the processor 710 , the communication interface 720 , and the memory 730 communicate with each other through the communication bus 740 .
  • the processor 710 can call the logic instructions in the memory 730 to execute the method for detecting a wrong platform on the road surface, and the method includes:
  • Step 110 acquiring road surface three-dimensional contour data, and obtaining a contour reference surface based on the road surface three-dimensional contour data, and the contour deviation between the measuring points in the road surface three-dimensional contour data and the contour reference surface;
  • Step 120 Obtain suspected seam points based on the contour deviation, and obtain the original seam target image and seam representative position of the suspected seam denoising binary image based on the suspected seam points;
  • Step 130 Obtain the original seam target map and the representative position of the seam based on the row direction projection features of the target measuring point in the denoised binary image of the suspected seam;
  • Step 140 based on the suspected seam denoising binary image, the original seam target image, and the seam representative position, obtain a target seam binary image through a seam extension operation;
  • Step 150 based on the target seam binary image and the three-dimensional road profile data, obtain road stagger information.
  • the above-mentioned logic instructions in the memory 730 may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as an independent product.
  • the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc., which can store program codes. .
  • the present application also provides a computer program product, the computer program product includes a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer can Carry out the method for detecting road surface misalignment provided by each of the above methods, the method includes:
  • Step 110 acquiring road surface three-dimensional contour data, and obtaining a contour reference surface based on the road surface three-dimensional contour data, and the contour deviation between the measuring points in the road surface three-dimensional contour data and the contour reference surface;
  • Step 120 Obtain suspected seam points based on the contour deviation, and obtain the original seam target image and seam representative position of the suspected seam denoising binary image based on the suspected seam points;
  • Step 130 Obtain the original seam target map and the representative position of the seam based on the row direction projection features of the target measuring point in the denoised binary image of the suspected seam;
  • Step 140 based on the suspected seam denoising binary image, the original seam target image, and the seam representative position, obtain a target seam binary image through a seam extension operation;
  • Step 150 based on the target seam binary image and the three-dimensional road profile data, obtain road stagger information.
  • the present application also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it is implemented to perform the method for detecting a wrong platform on a road surface provided by the above-mentioned methods, the method include:
  • Step 110 acquiring road surface three-dimensional contour data, and obtaining a contour reference surface based on the road surface three-dimensional contour data, and the contour deviation between the measuring points in the road surface three-dimensional contour data and the contour reference surface;
  • Step 120 Obtain suspected seam points based on the contour deviation, and obtain the original seam target image and seam representative position of the suspected seam denoising binary image based on the suspected seam points;
  • Step 130 Obtain the original seam target map and the representative position of the seam based on the row direction projection features of the target measuring point in the denoised binary image of the suspected seam;
  • Step 140 based on the suspected seam denoising binary image, the original seam target image, and the seam representative position, obtain a target seam binary image through a seam extension operation;
  • Step 150 based on the target seam binary image and the three-dimensional road profile data, obtain road stagger information.
  • the device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network elements. Part or all of the modules can be selected according to actual needs to realize the purpose of the solution of this embodiment. It can be understood and implemented by those skilled in the art without any creative efforts.
  • each implementation can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware.
  • the essence of the above technical solution or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic discs, optical discs, etc., including several instructions to make a computer device (which may be a personal computer, server, or network device, etc.) execute the methods described in various embodiments or some parts of the embodiments.

Abstract

本申请提供一种基于精密三维的路面错台检测方法及装置，该方法包括：获取路面三维轮廓数据，并基于路面三维轮廓数据，得到轮廓参考面，以及路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差；基于轮廓偏差得到疑似接缝点，并基于疑似接缝点，得到疑似接缝去噪二值图；基于疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置；基于疑似接缝去噪二值图、原始接缝目标图，以及接缝代表位置，通过接缝延伸操作，得到目标接缝二值图；基于目标接缝二值图和路面三维轮廓数据，得到路面错台信息。本申请提供的基于精密三维的路面错台检测方法及装置，可以实现降低测量误差，提高检测效率。

Description

基于精密三维的路面错台检测方法及装置
相关申请的交叉引用
本申请要求于2021年12月21日提交的申请号为202111572820.4，名称为“基于精密三维的路面错台检测方法及装置”的中国专利申请的优先权，其通过引用方式全部并入本文。
技术领域
本申请涉及路面检测技术领域，尤其涉及一种基于精密三维的路面错台检测方法及装置。
背景技术
路面错台是指水泥混凝土路面中横向接缝处相邻两块水泥板的高程差。错台是影响水泥混凝土路面平整度、寿命以及加铺后反射裂缝的重要因素，也是水泥混凝土路面技术状况评定，养护、加铺设计时必须考虑的一个重要指标。因此，如何对错台进行准确、高效的检测和评价，成为公路管理养护部门十分关注的问题。
目前，常用的错台量的检测方法有人工法和自动检测法。人工法利用直尺、游标卡尺或水准仪等实现，速度慢，精度低，且干扰交通；自动检测法利用错台的存在会显著影响国际平整度指标(IRI)的特性，有激光断面仪、超声波断面仪等，断面仪价格昂贵，并且不能对错台进行准确测量(由于只有少量纵向轮廓，测量结果易受裂缝、剥落等影响)。
综上所述，现有错台检测技术存在测量误差大、检测效率低、设备造价昂贵等问题。
发明内容
本申请提供一种基于精密三维的路面错台检测方法及装置，用以解决现有技术中测量误差大、检测效率低、设备造价昂贵的缺陷，实现降低测量误差，提高检测效率。
本申请提供一种基于精密三维的路面错台检测方法，包括：
获取路面三维轮廓数据，并基于所述路面三维轮廓数据，得到轮廓参考 面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差；
基于所述轮廓偏差得到疑似接缝点，并基于所述疑似接缝点，得到疑似接缝去噪二值图；
基于所述疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置；
基于所述疑似接缝去噪二值图、所述原始接缝目标图，以及所述接缝代表位置，通过接缝延伸操作，得到目标接缝二值图；
基于所述目标接缝二值图和所述路面三维轮廓数据，得到路面错台信息。
根据本申请提供的路面错台检测方法，所述基于所述疑似接缝点，得到疑似接缝去噪二值图，包括：
基于所述疑似接缝点得到原始疑似接缝点二值图；
以所述原始疑似接缝点二值图中连通区域为单位，依据所述连通区域的长度、所述轮廓偏差的幅值、连通区域方向特征进行去噪，得到所述疑似接缝去噪二值图。
根据本申请提供的路面错台检测方法，所述基于所述疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置，包括：
将所述疑似接缝去噪二值图中目标点沿行方向投影，得到各行疑似接缝点；
基于所述各行疑似接缝点的统计特征，得到所述原始接缝目标图以及所述接缝代表位置。
根据本申请提供的路面错台检测方法，所述基于所述各行疑似接缝点的统计特征，得到所述原始接缝目标图以及所述接缝代表位置，包括：
在当前行中的疑似接缝点数量大于预设数量值的情况下，确定当前行中的疑似接缝点为接缝种子点；
基于所述接缝种子点，得到所述原始接缝目标图；
将行间距小于预设行距值的接缝和作为目标接缝行，并将所述目标接缝行合并为同一接缝，且将所述目标接缝行的行平均值作为所述接缝代表位置；
其中，所述接缝行为所述接缝种子点所在行。
根据本申请提供的路面错台检测方法，所述基于所述疑似接缝去噪二值 图、所述原始接缝目标图，以及所述接缝代表位置，通过接缝延伸操作，得到目标接缝二值图，包括：
在所述接缝种子点对应的第一目标范围内，将所述疑似接缝去噪二值图中，与所述接缝种子点属于相同连通区域的测点，作为补充接缝点；
基于所述接缝种子点和所述补充接缝点，得到扩展接缝二值图；
在所述接缝代表位置对应的第二目标范围内，搜索所述扩展接缝二值图中的接缝点，并对搜索到的接缝点进行线性拟合，得到拟合接缝；
在所述接缝代表位置对应的第三目标范围内，将所述扩展接缝二值图中，存在缺失接缝的列中的拟合接缝位置作为延伸接缝目标点；
基于所述接缝种子点、所述补充接缝点和所述延伸接缝目标点，得到目标接缝二值图。
根据本申请提供的路面错台检测方法，所述基于所述路面三维轮廓数据，得到轮廓参考面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差，包括：
在所述路面三维轮廓数据中存在无效测点的情况下，基于所述无效测点附近的有效测点，替代所述无效测点，得到新的路面三维轮廓数据；
基于滤波方式或者频域变化方式，对所述新的路面三维轮廓数据进行处理，得到所述轮廓参考面；
将所述新的路面三维轮廓数据，与所述轮廓参考面作差，得到所述轮廓偏差；
其中，所述疑似接缝点，为对应轮廓偏差大于分割阈值对应的测点。
根据本申请提供的路面错台检测方法，所述基于所述目标接缝二值图和所述路面三维轮廓数据，得到路面错台信息，包括：
基于所述目标接缝二值图，得到接缝前后两侧路面代表高程；
基于所述接缝前后两侧路面代表高程，得到所述路面错台信息。
根据本申请提供的路面错台检测方法，所述基于所述目标接缝二值图，得到接缝前后两侧路面代表高程，包括：
基于所述目标接缝二值图，以拟合接缝为中心，在第四目标范围内，搜索接缝起点和接缝终点；
在所述接缝起点对应的第五目标范围内，邻近所述拟合接缝的路面平均 高程作为前侧路面代表高程，得到前侧路面代表高程集合；所述前侧路面为车辆前进方向路面；
在所述接缝终点对应的第六目标范围内，邻近所述拟合接缝的路面平均高程作为后侧路面代表高程，得到后侧路面代表高程集合。
根据本申请提供的路面错台检测方法，所述基于所述接缝前后两侧路面代表高程，得到所述路面错台信息，包括：
所述基于所述接缝前后两侧路面代表高程，得到全幅错台值、左右轮迹带错台值、最大错台值、全幅宽错台均值、全幅宽错台中值以及全幅宽加权错台值中的至少一个；
其中，所述全幅错台值的计算方式如下：
逐列分别计算前侧路面代表高程与后侧路面代表高程的绝对差值，得到多列全幅错台值；列方向与路面的幅宽方向对应，行方向与列方向垂直；
所述左右轮迹带错台值的计算方式如下：
基于所述路面三维轮廓数据的列向位置与路面幅宽方向位置的对应关系，分别选取左轮迹带和右轮迹带对应列的全幅错台值作为左右轮迹带错台值；
所述全幅宽加权错台值的计算方式如下：
基于所述多列全幅错台值中，计算各列全幅错台值与左轮迹带和右轮迹带对应列，在路面幅宽方向的最小距离，
基于所述路面幅宽方向的最小距离，以及在路面幅宽方向，所述左轮迹带和所述右轮迹带的距离，计算得到各列全幅错台值对应的权重；
基于所述多列全幅错台值，以及所述各列全幅错台值对应的权重，计算得到所述全幅加权错台值。
本申请还提供一种基于精密三维的路面错台检测装置，包括：
第一计算模块，用于获取路面三维轮廓数据，并基于所述路面三维轮廓数据，得到轮廓参考面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差；
第二计算模块，用于基于所述轮廓偏差得到疑似接缝点，并基于所述疑似接缝点，得到疑似接缝去噪二值图；
第三计算模块，用于基于所述疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置；
第四计算模块，用于基于所述疑似接缝去噪二值图、所述原始接缝目标图，以及所述接缝代表位置，通过接缝延伸操作，得到目标接缝二值图；
第五计算模块，用于基于所述目标接缝二值图和所述路面三维轮廓数据，得到路面错台信息。
本申请还提供一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现如上述任一种所述路面错台检测方法的步骤。
本申请还提供一种非暂态计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现如上述任一种所述路面错台检测方法的步骤。
本申请还提供一种计算机程序产品，包括计算机程序，所述计算机程序被处理器执行时实现如上述任一种所述路面错台检测方法的步骤。
本申请提供的基于精密三维的路面错台检测方法及装置，通过获取路面三维轮廓数据，计算得到轮廓参考面以及轮廓偏差，再进一步确定疑似接缝点，得到目标接缝二值图，最后得到路面错台信息。整个计算路面错台信息的过程都是自动完成，不需要通过人工进行检测，也不需要激光断面仪、超声波断面仪等昂贵设备进行路面错台检测。因此，本申请提供的路面错台检测方法，既可以提高路面错台的检测效率，降低路面错台的检测误差，还不需要使用昂贵的断面仪，进而可以降低路面错台检测的成本。
附图说明
为了更清楚地说明本申请或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请提供的路面错台检测方法的流程示意图之一；
图2是本申请提供第一原始疑似接缝点二值图；
图3是本申请提供的图2对应的接缝定位结果图；
图4是本申请提供的第二原始疑似接缝点二值图；
图5是本申请提供的图4对应的接缝定位结果图；
图6是本申请提供的路面错台检测装置的结构示意图；
图7是本申请提供的电子设备的结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合本申请中的附图，对本申请中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
下面结合图1-图7描述本申请的基于精密三维的路面错台检测方法及装置。
如图1所示，本申请提供的一种路面错台检测方法，包括：
步骤110、获取路面三维轮廓数据，并基于所述路面三维轮廓数据，得到轮廓参考面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差。
可以理解的是，路面三维轮廓数据，可以是对路面进行线扫描所获取三维轮廓数据。
本实施例中，可以基于一套由2个线扫描三维测量传感器组成的三维路面数据采集系统，所获取的精密路面三维轮廓数据作为输入。
其中，所述路面三维轮廓数据已经过三维建模处理；所述线扫描三维测量传感器由三维相机、激光器、控制器、姿态测量传感器组成，所述线扫描三维测量传感器中激光器沿道路幅宽方向投射激光线，线扫描三维测量单元单次测量可获取道路横断面高程数据；所述线扫描三维测量单元在横断面方向的采样间距1-3mm，例如1mm，在行车方向的采样间距1-5mm，例如5mm，测量幅宽2000-4000mm，例如3600mm。
进一步，在获取路面三维轮廓数据之后，可以先对路面三维轮廓数据进行预处理，包括测量异常值处理、轮廓参考面获取、轮廓偏差获取。
步骤120、基于所述轮廓偏差得到疑似接缝点，并基于所述疑似接缝点，得到疑似接缝去噪二值图。
步骤130、基于所述疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置。
可以理解的是，疑似接缝点是经过初步判断，确定可能是接缝点的测点。 接缝代表位置，是依据接缝所在行的分布信息，将行距离小于预设行距值的接缝行合并为同一接缝，对应的一个代表位置。
步骤140、基于所述疑似接缝去噪二值图、所述原始接缝目标图，以及所述接缝代表位置，通过接缝延伸操作，得到目标接缝二值图。
可以理解的是，在得到所述原始接缝目标图以及所述接缝代表位置之后，还可以基于所述原始接缝目标图以及所述接缝代表位置，进行接缝延伸，接缝延伸包括连通区域扩展和缺失区域延伸，最后得到目标接缝二值图。
步骤150、基于所述目标接缝二值图和所述路面三维轮廓数据，得到路面错台信息。
可以理解的是，基于所述目标接缝二值图，得到路面错台信息，可以先基于接缝二值图，获取接缝前后两侧路面代表高程，再计算得到路面错台值。
在一些实施例中，所述基于所述疑似接缝点，得到疑似接缝去噪二值图，包括：
基于所述疑似接缝点得到原始疑似接缝点二值图；
以所述原始疑似接缝点二值图中连通区域为单位，依据所述连通区域的长度、所述轮廓偏差的幅值、连通区域方向特征进行去噪，得到所述疑似接缝去噪二值图。
可以理解的是，基于所述疑似接缝点得到疑似接缝点二值图，可以是：对原始疑似接缝点二值图先进行连通区域标记，再以连通区域为单位，依据连通区域的长度、轮廓偏差幅值、连通区域方向特征进行去噪，得到去噪的疑似接缝二值图。
在一些实施例中，基于所述疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置，包括：
将所述疑似接缝去噪二值图中目标点沿行方向投影，得到各行疑似接缝点；
基于所述各行疑似接缝点的统计特征，得到所述原始接缝目标图以及所述接缝代表位置。
其中，各行疑似接缝点的统计特征可以是各行疑似接缝点的数量，以及各行疑似接缝点的数量占疑似接缝点总数量的比例。
在一些实施例中，所述基于所述各行疑似接缝点的统计特征，得到所述 原始接缝目标图以及所述接缝代表位置，包括：
在当前行中的疑似接缝点数量大于预设数量值的情况下，确定当前行中的疑似接缝点为接缝种子点；
基于所述接缝种子点，得到所述原始接缝目标图；
将行间距小于预设行距值的接缝和作为目标接缝行，并将所述目标接缝行合并为同一接缝，且将所述目标接缝行的行平均值作为所述接缝代表位置；
其中，所述接缝行为所述接缝种子点所在行。
可以理解的是，接缝目标定位，包括获取接缝种子点、获取接缝代表位置。
接缝种子点获取方法为：对疑似接缝去噪二值图沿行方向(道路方向)投影，并统计各行的疑似接缝点个数，若当前行中的疑似接缝点个数大于预设数量值，则将当前行中的疑似接缝点标记为接缝种子点，并记录当前行为接缝所在的行，将接缝种子点组成的二值图记为原始接缝目标图。
接缝代表位置获取方法为：依据接缝所在行的分布信息，将行距离小于预设行距值的接缝行合并为同一接缝，并将行均值记录为合并后的接缝代表位置。
在一些实施例中，所述基于所述疑似接缝去噪二值图、所述原始接缝目标图，以及所述接缝代表位置，通过接缝延伸操作，得到目标接缝二值图，包括：
在所述接缝种子点对应的第一目标范围内，将所述疑似接缝去噪二值图中，与所述接缝种子点属于相同连通区域的测点，作为补充接缝点；
基于所述接缝种子点和所述补充接缝点，得到扩展接缝二值图；
在所述接缝代表位置对应的第二目标范围内，搜索所述扩展接缝二值图中的接缝点，并对搜索到的接缝点进行线性拟合，得到拟合接缝；
在所述接缝代表位置对应的第三目标范围内，将所述扩展接缝二值图中，存在缺失接缝的列中的拟合接缝位置作为延伸接缝目标点；
基于所述接缝种子点、所述补充接缝点和所述延伸接缝目标点，得到目标接缝二值图。
可以理解的是，接缝延伸包括连通区域扩展和缺失区域延伸。
连通区域扩展的具体方法为：先以原始接缝目标图中的接缝种子点为基 础，对每个接缝种子点，在第一目标范围内，将去噪的疑似接缝二值图中与当前接缝种子点同属于相同连通区域的点补充为接缝点，得到扩展接缝二值图。
缺失区域延伸的具体方法为：依据接缝代表位置信息，对每条接缝，以接缝代表位置为中心，在第二目标范围内寻找扩展接缝二值图中的接缝点，并对其进行线性拟合，得到拟合接缝。若在第二目标范围内，在扩展接缝二值图中存在缺失接缝的列，则将对应列中，拟合接缝所在的位置标记为接缝目标点，得到目标接缝二值图。
在一些实施例中，所述基于所述路面三维轮廓数据，得到轮廓参考面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差，包括：
在所述路面三维轮廓数据中存在无效测点的情况下，基于所述无效测点附近的有效测点，替代所述无效测点，得到新的路面三维轮廓数据；
基于滤波方式或者频域变化方式，对所述新的路面三维轮廓数据进行处理，得到所述轮廓参考面；
将所述新的路面三维轮廓数据，与所述轮廓参考面作差，得到所述轮廓偏差；
其中，所述疑似接缝点，为对应轮廓偏差大于分割阈值对应的测点。
可以理解的是，在获取了轮廓参考面后，可以对轮廓参考面的测量异常值进行处理，对测量异常值处理后的路面三维轮廓数据，通过滤波(例如中值滤波、低通滤波、均值滤波、全变分滤波)，或者频域变换(例如傅里叶变换、小波变换)等方法获取轮廓参考面。
轮廓偏差是通过测量异常值处理后的三维轮廓数据与轮廓参考面作差得到。
对各测点，依据测点附近的轮廓偏差情况，自适应计算分割阈值，若测点的轮廓偏差值大于等于分割阈值，则将当前测点点标记为疑似接缝点，得到原始疑似接缝点二值图。
在一些实施例中，所述基于所述目标接缝二值图和所述路面三维轮廓数据，得到路面错台信息，包括：
基于所述目标接缝二值图，得到接缝前后两侧路面代表高程；
基于所述接缝前后两侧路面代表高程，得到所述路面错台信息。
进一步，所述基于所述目标接缝二值图，得到接缝前后两侧路面代表高程，包括：
基于所述目标接缝二值图，以拟合接缝为中心，在第四目标范围内，搜索接缝起点和接缝终点；
在所述接缝起点对应的第五目标范围内，邻近所述拟合接缝的路面平均高程作为前侧路面代表高程，得到前侧路面代表高程集合；所述前侧路面为车辆前进方向路面，后侧路面为车辆前进相反方向的路面；
在所述接缝终点对应的第六目标范围内，邻近所述拟合接缝的路面平均高程作为后侧路面代表高程，得到后侧路面代表高程集合。
可以理解的是，接缝前后两侧路面代表高程，也即是拟合接缝前后两侧路面代表高程。具体地，接缝前后两侧路面代表高程包括前侧路面代表高程集合，以及后侧路面代表高程集合。
在一些实施例中，所述基于所述接缝前后两侧路面代表高程，得到所述路面错台信息，包括：
所述基于所述接缝前后两侧路面代表高程，得到全幅错台值、左右轮迹带错台值、最大错台值、全幅宽错台均值、全幅宽错台中值以及全幅宽加权错台值中的至少一个。
可以理解的是，路面错台信息包括全幅错台值、左右轮迹带错台值、最大错台值、全幅宽错台均值、全幅宽错台中值以及全幅宽加权错台值中的至少一个。
其中，所述全幅错台值的计算方式如下：
逐列分别计算前侧路面代表高程与后侧路面代表高程的绝对差值，得到多列全幅错台值；列方向与路面的幅宽方向对应，行方向与列方向垂直；
所述左右轮迹带错台值的计算方式如下：
基于所述路面三维轮廓数据的列向位置与路面幅宽方向位置的对应关系，分别选取左轮迹带和右轮迹带对应列的全幅错台值作为左右轮迹带错台值；
所述全幅宽加权错台值的计算方式如下：
基于所述多列全幅错台值中，计算各列全幅错台值与左轮迹带和右轮迹带对应列，在路面幅宽方向的最小距离，
基于所述路面幅宽方向的最小距离，以及在路面幅宽方向，所述左轮迹 带和所述右轮迹带的距离，计算得到各列全幅错台值对应的权重；
基于所述多列全幅错台值，以及所述各列全幅错台值对应的权重，计算得到所述全幅加权错台值。
可以理解的是，接缝前后两侧路面代表高程获取，即：对每条接缝分别逐列获取接缝前后两侧路面代表高程，具体方法为：对接缝的每列，以拟合接缝所在的位置为中心，在第三目标范围内，沿行车方向寻找接缝的起点和终点；在接缝起点的上方，取第四目标范围内邻近接缝的路面平均高程作为前侧路面代表高程，得到前侧路面代表高程集合{FZ 1,FZ 2,…,FZ n}；在接缝终点的下方，取第五目标范围内邻近接缝的路面平均高程作为后侧路面代表高程{BZ 1,BZ 2,…,BZ n}，其中n为目标接缝二值图的列个数。
错台值计算：即对每条接缝分别计算错台值。计算方法包括全幅错台值计算、左右轮迹带错台值计算、最大错台值计算、全幅宽错台均值计算、全幅宽错台中值计算、全幅宽加权错台值计算。
全幅错台值计算：为逐列分别计算前侧路面代表高程与后侧路面代表高程的绝对差值，记为SS j,{SS j|SS j＝abs(FZ j-BZ j),j＝1,2,…,n}。
左右轮迹带错台值计算：结合三维路面数据的列向位置与路面幅宽方向位置的对应关系，分别选取左右轮迹带对应列位置所对应的全幅错台值作为左右轮迹带错台值，分别记为S Left(S Left＝{SS j|j＝L})、S Right(S Right＝{SS j|j＝R})，其中L、R分别为左、右轮迹带位置对应的列序号。
最大错台值计算：为全幅错台值中的最大值，记为S Max，S Max＝max{SS 1,SS 2,…,SS n}。
全幅宽错台均值计算：为全幅错台值的均值，记为S Avg，
Figure PCTCN2022085609-appb-000001
全幅宽错台中值计算：为全幅错台值的中值，记为S Mid。
全幅宽加权错台值计算，为全幅错台值集合{SS j|SS j＝abs(FZ j-BZ j),j＝1,2,…,n}中所有值的加权平均，具体计算步骤如下：
自适应权重计算。依据全幅错台值中各列与左轮迹、右轮迹带所在列在幅宽方向的最小距离DIS i和左右轮迹带在幅宽方向的距离，计算自身权重w j，计算公式如下：
Figure PCTCN2022085609-appb-000002
其中，DIS j＝min(|x j-x L|,|x j-x R|)，j＝1,2,…,n，x j为第j列在幅宽方向的距离位置，x L、x R分别为左右轮迹带在幅宽方向的距离位置；
全幅加权错台值计算。依据列错台值集合中所有错台值，以及对应的权重w i，计算全幅加权错台值S weight。
Figure PCTCN2022085609-appb-000003
错台属性获取，包括错台里程位置信息获取、错台严重程度获取。所述错台里程位置信息获取，利用计算单元所在的测量里程信息，结合计算单元内部的错台相对位置信息，计算错台里程信息；所述错台严重程度获取，结合错台值大小和客户应用需求，将错台划分多种等级。
路面三维轮廓数据，在结合特定数据处理方法的基础上，还可用于路面裂缝、路面车辙等指标的检测。
在另一些实施例中，路面错台检测方法包括：数据预处理、接缝定位、错台信息获取。
数据预处理，包括测量异常值处理、轮廓参考面获取、轮廓偏差获取。
接缝定位，包括疑似接缝点分割、疑似接缝点粗去噪、接缝目标定位、接缝延伸。
错台信息获取，包括接缝前后两侧路面代表高程获取、错台值计算、错台属性获取。
数据预处理，包括测量异常值处理、轮廓参考面获取、轮廓偏差获取，具体的：
测量异常值处理，利用零值测点(即：无效测点)附近的有效测点替换零值测点。
轮廓参考面获取，对测量异常值处理后的三维轮廓数据，通过均值滤波方法获取。
轮廓偏差获取，通过测量异常值处理后的三维轮廓数据与轮廓参考面作差得到。
疑似接缝点分割，对各测点，依据测点附近的轮廓偏差均值Tex 1，自适应计算分割阈值T 1(T 1＝2*Tex 1)，若测点的轮廓偏差值大于等于分割阈值T 1，则将当前点标记为疑似接缝点，得到原始疑似接缝点二值图。
疑似接缝点粗去噪，对原始疑似接缝点二值图先进行连通区域标记，再以连通区域为单位，依据连通区域的长度阈值LenT 1(LenT 1＝40mm)和LenT 2(LenT 2＝400mm)、轮廓偏差阈值T 2(T 2＝1.3*Tex 2)、水平方向夹角阈值AngleT(AngleT＝30°)进行去噪，得到疑似接缝去噪二值图。
其中Tex 2为当前疑似接缝点二值图中所有点对应的轮廓偏差均值。
接缝目标定位，包括接缝种子点获取、接缝代表位置获取。
接缝种子点获取方法为：对疑似接缝去噪二值图沿行方向(道路方向)投影，并统计各行的疑似接缝点个数，若当前行中的疑似接缝点个数大于T 2(T 2＝n*0.2)，则将当前行中的疑似接缝点标记为接缝种子点，并记录当前行为接缝所在的行，将接缝种子点组成的二值图记为原始接缝目标图。
接缝代表位置获取方法为：依据接缝所在行的分布信息，将行距离小于T 3(T 3＝500mm)的接缝行合并为同一接缝，并将行均值记录为合并后的接缝代表位置；
接缝延伸，包括连通区域扩展和缺失区域延伸。
连通区域扩展的具体方法为：先以原始接缝目标图中的接缝种子点为基础，对每个接缝种子点，在第一目标范围内(50mm)，将疑似接缝去噪二值图中与当前接缝种子点同属于相同连通区域的点补充为接缝点，得到扩展接缝二值图。
缺失区域延伸的具体方法为，依据接缝代表位置信息，对每条接缝，以接缝代表位置为中心，在第二目标范围内(300mm)寻找扩展接缝二值图中的接缝点，并对其进行线性拟合，得到拟合接缝，若在给定范围内(行向500mm)，在扩展接缝二值图中存在缺失接缝的列，则将对应列中拟合接缝所在的位置标记为接缝目标点，得到目标接缝二值图。
错台信息获取，包括接缝前后两侧路面代表高程获取、错台值计算、错台属性获取。
接缝前后两侧路面代表高程获取，对每条接缝分别逐列获取接缝前后两侧路面代表高程，具体方法为：对接缝的每列，以拟合接缝所在的位置为中心，在第三目标范围内(行向500mm)，沿行车方向寻找接缝的起点和终点；在接缝起点的上方，取第四目标范围内(行向50mm)邻近接缝的路面平均高程作为前侧路面代表高程，得到前侧路面代表高程集合{FZ 1,FZ 2,…,FZ n}；在接 缝终点的下方，取第五目标范围内(行向50mm)邻近接缝的路面平均高程作为后侧路面代表高程{BZ 1,BZ 2,…,BZ n},其中n为二值图的列个数(n＝3600)。
错台值计算，对每条接缝分别计算错台值。计算方法包括全幅错台值计算、左右轮迹带错台值计算、最大错台值计算、全幅宽错台均值计算、全幅宽错台中值计算、全幅宽加权错台值计算。
全幅错台值计算，为逐列分别计算前侧路面代表高程与后侧路面代表高程的绝对差值，记为SS j,{SS j|SS j＝abs(FZ j-BZ j),j＝1,2,…,n}。
左右轮迹带错台值计算，结合三维路面数据的列向位置与路面幅宽方向位置的对应关系，分别选取左右轮迹带对应列位置所对应的全幅错台值作为左右轮迹带错台值,分别记为S Left(S Left＝{SS j|j＝L})、S Right(S Right＝{SS j|j＝R})，其中L、R分别为左、右轮迹带位置对应的列序号(L＝1100、R＝2700)。
最大错台值计算,为全幅错台值中的最大值，S Max，S Max＝max{SS 1,SS 2,…,SS n}。
全幅宽错台均值计算，为全幅错台值的均值，记为S Avg，
Figure PCTCN2022085609-appb-000004
全幅宽错台中值计算，为全幅错台值的中值，记为S Mid。
全幅宽加权错台值计算，为全幅错台值集合{SS j|SS j＝abs(FZ j-BZ j),j＝1,2,…,n}中所有值的加权平均，具体计算步骤如下：
自适应权重计算。依据全幅错台值中各列与左轮迹、右轮迹带所在列在幅宽方向的最小距离DIS i和左右轮迹带在幅宽方向的距离，计算自身权重w j，计算公式如下：
Figure PCTCN2022085609-appb-000005
其中，DIS j＝min(|x j-x L|,|x j-x R|)，j＝1,2,…,n，x j为第j列在幅宽方向的距离位置，x L、x R分别为左右轮迹带在幅宽方向的距离位置；
全幅加权错台值计算。依据列错台值集合中所有错台值，以及对应的权重w i，计算全幅加权错台值S weight。
Figure PCTCN2022085609-appb-000006
错台属性获取，包括错台里程位置信息获取、错台严重程度获取。所述错台里程位置信息获取，利用计算单元所在的测量里程信息，结合计算单元内部的错台相对位置信息，计算错台里程信息；所述错台严重程度获取，结合错台值大小和客户应用需求，将错台划分多种等级，具体的，将错台值＜2.54mm的划分为轻度错台，错台值≥2.54mm且≤5.08mm的划分为中度错台， 将错台值≥5.08mm的划分为重度错台。
在上述实施例中，第一原始疑似接缝点二值图如图2所示，第一原始疑似接缝点二值图对应的接缝定位结果图如图3所示。
第二原始疑似接缝点二值图如图4所示，第二原始疑似接缝点二值图对应的接缝定位结果图如图5所示。
图2～3中，接缝的全幅错台均值为2.07mm，全幅宽错台中值为2.02mm，左轮迹带错台值1.84mm，右轮迹带错台值2.65mm，最大错台值4.13mm。
图4～5中，上部接缝的全幅错台均值为3.21mm，全幅宽错台中值为3.23mm，左轮迹带错台值3.65mm，右轮迹带错台值4.55mm，最大错台值7.27mm。
图4～5中，下部接缝的全幅错台均值为1.33mm，全幅宽错台中值为0.77mm，左轮迹带错台值3.62mm，右轮迹带错台值0.87mm，最大错台值14.07mm。
所述路面精密三维轮廓数据，在结合特定数据处理方法的基础上，还可用于路面裂缝、路面车辙等指标的检测。
综上所述，本申请提供的路面错台检测方法，包括：获取路面三维轮廓数据，并基于所述路面三维轮廓数据，得到轮廓参考面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差；基于所述轮廓偏差得到疑似接缝点，并基于所述疑似接缝点，得到疑似接缝去噪二值图原始接缝目标图以及接缝代表位置；基于所述疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置；基于所述疑似接缝去噪二值图、所述原始接缝目标图，以及所述接缝代表位置，通过接缝延伸操作，得到目标接缝二值图；
基于所述目标接缝二值图和所述路面三维轮廓数据，得到路面错台信息。
在本申请提供的路面错台检测方法中，在获取了路面三维轮廓数据后，计算得到轮廓参考面以及轮廓偏差，再进一步确定疑似接缝点，得到目标接缝二值图，最后得到路面错台信息。整个计算路面错台信息的过程都是自动完成，不需要通过人工进行检测，也不需要激光断面仪、超声波断面仪等昂贵设备进行路面错台检测。因此，本申请提供的路面错台检测方法，既可以提高路面错台的检测效率，降低路面错台的检测误差，还不需要使用昂贵的 断面仪，进而可以降低路面错台检测的成本。
本申请提供的错台检测方法测量精度高，可有效避免路面裂缝、剥落等对检测结果的影响；本申请提供的错台检测方法造价低，可与路面破损、路面车辙等检测指标共用测量设备。
下面对本申请提供的路面错台检测装置进行描述，下文描述的路面错台检测装置与上文描述的路面错台检测方法可相互对应参照。
如图6所示，本申请提供的路面错台检测装置600，包括：第一计算模块610、第二计算模块620、第三计算模块630、第四计算模块640和第五计算模块650。
第一计算模块610用于获取路面三维轮廓数据，并基于所述路面三维轮廓数据，得到轮廓参考面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差。
第二计算模块620用于基于所述轮廓偏差得到疑似接缝点，并基于所述疑似接缝点，得到疑似接缝去噪二值图。
第三计算模块630用于基于所述疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置。
第四计算模块640用于基于所述疑似接缝去噪二值图、所述原始接缝目标图，以及所述接缝代表位置，通过接缝延伸操作，得到目标接缝二值图。
第五计算模块650用于基于所述目标接缝二值图和所述路面三维轮廓数据，得到路面错台信息。
在一些实施例中，第二计算模块620包括：第一二值图生成单元和二值图处理单元。
第一二值图生成单元用于基于所述疑似接缝点得到原始疑似接缝点二值图。
二值图处理单元用于以所述原始疑似接缝点二值图中连通区域为单位，依据所述连通区域的长度、所述轮廓偏差的幅值、连通区域方向特征进行去噪，得到所述疑似接缝去噪二值图。
在一些实施例中，第三计算模块630包括：疑似点生成单元和疑似点处理单元。
疑似点生成单元用于将所述疑似接缝去噪二值图中目标点沿行方向投影， 得到各行疑似接缝点。
疑似点处理单元用于基于所述各行疑似接缝点的统计特征，得到所述原始接缝目标图以及所述接缝代表位置。
在一些实施例中，疑似点处理单元包括：确定单元、接缝图生成单元和接缝位置计算单元。
确定单元用于在当前行中的疑似接缝点数量大于预设数量值的情况下，确定当前行中的疑似接缝点为接缝种子点；
接缝图生成单元用于基于所述接缝种子点，得到所述原始接缝目标图；
接缝位置计算单元用于将行间距小于预设行距值的接缝和作为目标接缝行，并将所述目标接缝行合并为同一接缝，且将所述目标接缝行的行平均值作为所述接缝代表位置；
其中，所述接缝行为所述接缝种子点所在行。
在一些实施例中，第四计算模块640包括：补充单元、扩展单元、拟合单元、延伸单元和第二二值图生成单元。
补充单元用于在所述接缝种子点对应的第一目标范围内，将所述疑似接缝去噪二值图中，与所述接缝种子点属于相同连通区域的测点，作为补充接缝点；
扩展单元用于基于所述接缝种子点和所述补充接缝点，得到扩展接缝二值图；
拟合单元用于在所述接缝代表位置对应的第二目标范围内，搜索所述扩展接缝二值图中的接缝点，并对搜索到的接缝点进行线性拟合，得到拟合接缝；
延伸单元用于在所述接缝代表位置对应的第三目标范围内，将所述扩展接缝二值图中，存在缺失接缝的列中的拟合接缝位置作为延伸接缝目标点；
第二二值图生成单元用于基于所述接缝种子点、所述补充接缝点和所述延伸接缝目标点，得到目标接缝二值图。
在一些实施例中，第一计算模块610包括：数据获取单元、数据处理单元和偏差计算单元。
数据获取单元用于在所述路面三维轮廓数据中存在无效测点的情况下，基于所述无效测点附近的有效测点，替代所述无效测点，得到新的路面三维 轮廓数据；
数据处理单元用于基于滤波方式或者频域变化方式，对所述新的路面三维轮廓数据进行处理，得到所述轮廓参考面；
偏差计算单元用于将所述新的路面三维轮廓数据，与所述轮廓参考面作差，得到所述轮廓偏差。
其中，所述疑似接缝点，为对应轮廓偏差大于分割阈值对应的测点。
在一些实施例中，第五计算模块650包括：高程计算单元和错台计算单元。
高程计算单元用于基于所述目标接缝二值图，得到接缝前后两侧路面代表高程；
错台计算单元用于基于所述接缝前后两侧路面代表高程，得到所述路面错台信息。
在一些实施例中，高程计算单元包括：搜索单元、第一高程确定单元和第二高程确定单元。
搜索单元用于基于所述目标接缝二值图，以拟合接缝为中心，在第四目标范围内，搜索接缝起点和接缝终点；
第一高程确定单元用于在所述接缝起点对应的第五目标范围内，邻近所述拟合接缝的路面平均高程作为前侧路面代表高程，得到前侧路面代表高程集合；所述前侧路面为车辆前进方向路面；
第二高程确定单元用于在所述接缝终点对应的第六目标范围内，邻近所述拟合接缝的路面平均高程作为后侧路面代表高程，得到后侧路面代表高程集合。
在一些实施例中，错台计算单元进一步用于：所述基于所述接缝前后两侧路面代表高程，得到全幅错台值、左右轮迹带错台值、最大错台值、全幅宽错台均值、全幅宽错台中值以及全幅宽加权错台值中的至少一个。
其中，所述全幅错台值的计算方式如下：
逐列分别计算前侧路面代表高程与后侧路面代表高程的绝对差值，得到多列全幅错台值；列方向与路面的幅宽方向对应，行方向与列方向垂直；
所述左右轮迹带错台值的计算方式如下：
基于所述路面三维轮廓数据的列向位置与路面幅宽方向位置的对应关系， 分别选取左轮迹带和右轮迹带对应列的全幅错台值作为左右轮迹带错台值；
所述全幅宽加权错台值的计算方式如下：
基于所述多列全幅错台值中，计算各列全幅错台值与左轮迹带和右轮迹带对应列，在路面幅宽方向的最小距离，
基于所述路面幅宽方向的最小距离，以及在路面幅宽方向，所述左轮迹带和所述右轮迹带的距离，计算得到各列全幅错台值对应的权重；
基于所述多列全幅错台值，以及所述各列全幅错台值对应的权重，计算得到所述全幅加权错台值。
第一计算模块610用于获取路面三维轮廓数据，并基于所述路面三维轮廓数据，得到轮廓参考面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差。
第二计算模块620用于基于所述轮廓偏差得到疑似接缝点，并基于所述疑似接缝点，得到原始接缝目标图以及接缝代表位置。
第三计算模块630用于基于所述原始接缝目标图以及所述接缝代表位置，得到目标接缝二值图。
第四计算模块640用于基于所述目标接缝二值图，得到路面错台信息。
在一些实施例中，第二计算模块620包括：第一二值图生成单元和接缝计算单元。
第一二值图生成单元用于基于所述疑似接缝点得到疑似接缝点二值图。
接缝计算单元用于将所述疑似接缝点二值图沿行方向投影，得到各行疑似接缝点，并基于所述各行疑似接缝点，得到所述原始接缝目标图以及所述接缝代表位置。
在一些实施例中，接缝计算单元包括：种子点确定单元、接缝目标图计算单元和接缝代表位置计算单元。
种子点确定单元用于在当前行中的疑似接缝点数量大于预设数量值的情况下，确定当前行中的疑似接缝点为接缝种子点。
接缝目标图计算单元用于基于所述接缝种子点，得到所述原始接缝目标图。
接缝代表位置计算单元用于将行间距小于预设行距值的接缝和作为目标接缝行，并将所述目标接缝行合并为同一接缝，且将所述目标接缝行的行平 均值作为所述接缝代表位置。
其中，所述接缝行为所述接缝种子点所在行。
在一些实施例中，第三计算模块630包括：补充接缝点计算单元、扩展单元、拟合单元、接缝目标计算单元和第二二值图生成单元。
补充接缝点计算单元用于在所述接缝种子点对应的第一目标范围内，将所述疑似接缝点二值图中，与所述接缝种子点属于相同连通区域的测点，作为补充接缝点；
扩展单元用于基于所述补充接缝点，得到扩展接缝二值图；
拟合单元用于在所述接缝代表位置对应的第二目标范围内，搜索所述扩展接缝二值图中的接缝点，并对搜索到的接缝点进行线性拟合，得到拟合接缝；
接缝目标计算单元用于在所述接缝代表位置对应的第三目标范围内，将所述扩展接缝二值图中，存在缺失接缝的列中的拟合接缝位置作为接缝目标点；
第二二值图生成单元用于基于所述延伸接缝目标点，得到目标接缝二值图。
在一些实施例中，第一计算模块610包括：去噪单元、参考面计算单元和偏差计算单元。
去噪单元用于在所述路面三维轮廓数据中存在无效测点的情况下，基于所述无效测点附近的有效测点，替代所述无效测点，得到新的路面三维轮廓数据。
参考面计算单元用于基于滤波方式或者频域变化方式，对所述新的路面三维轮廓数据进行处理，得到所述轮廓参考面。
偏差计算单元用于将所述新的路面三维轮廓数据，与所述轮廓参考面作差，得到所述轮廓偏差。
其中，所述疑似接缝点，为对应轮廓偏差大于分割阈值对应的测点。
在一些实施例中，第四计算模块640进一步用于基于所述目标接缝二值图，得到全幅错台值、左右轮迹带错台值、最大错台值、全幅宽错台均值、全幅宽错台中值以及全幅宽加权错台值。
下面对本申请提供的电子设备、计算机程序产品及存储介质进行描述， 下文描述的电子设备、计算机程序产品及存储介质与上文描述的路面错台检测方法可相互对应参照。
图7示例了一种电子设备的实体结构示意图，如图7所示，该电子设备可以包括：处理器(processor)710、通信接口(Communications Interface)720、存储器(memory)730和通信总线740，其中，处理器710，通信接口720，存储器730通过通信总线740完成相互间的通信。处理器710可以调用存储器730中的逻辑指令，以执行路面错台检测方法，该方法包括：
步骤110、获取路面三维轮廓数据，并基于所述路面三维轮廓数据，得到轮廓参考面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差；
步骤120、基于所述轮廓偏差得到疑似接缝点，并基于所述疑似接缝点，得到疑似接缝去噪二值图原始接缝目标图以及接缝代表位置；
步骤130、基于所述疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置；
步骤140、基于所述疑似接缝去噪二值图、所述原始接缝目标图，以及所述接缝代表位置，通过接缝延伸操作，得到目标接缝二值图；
步骤150、基于所述目标接缝二值图和所述路面三维轮廓数据，得到路面错台信息。
此外，上述的存储器730中的逻辑指令可以通过软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
另一方面，本申请还提供一种计算机程序产品，所述计算机程序产品包括计算机程序，计算机程序可存储在非暂态计算机可读存储介质上，所述计算机程序被处理器执行时，计算机能够执行上述各方法所提供的路面错台检 测方法，该方法包括：
步骤110、获取路面三维轮廓数据，并基于所述路面三维轮廓数据，得到轮廓参考面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差；
步骤120、基于所述轮廓偏差得到疑似接缝点，并基于所述疑似接缝点，得到疑似接缝去噪二值图原始接缝目标图以及接缝代表位置；
步骤130、基于所述疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置；
步骤140、基于所述疑似接缝去噪二值图、所述原始接缝目标图，以及所述接缝代表位置，通过接缝延伸操作，得到目标接缝二值图；
步骤150、基于所述目标接缝二值图和所述路面三维轮廓数据，得到路面错台信息。
又一方面，本申请还提供一种非暂态计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现以执行上述各方法提供的路面错台检测方法，该方法包括：
步骤110、获取路面三维轮廓数据，并基于所述路面三维轮廓数据，得到轮廓参考面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差；
步骤120、基于所述轮廓偏差得到疑似接缝点，并基于所述疑似接缝点，得到疑似接缝去噪二值图原始接缝目标图以及接缝代表位置；
步骤130、基于所述疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置；
步骤140、基于所述疑似接缝去噪二值图、所述原始接缝目标图，以及所述接缝代表位置，通过接缝延伸操作，得到目标接缝二值图；
步骤150、基于所述目标接缝二值图和所述路面三维轮廓数据，得到路面错台信息。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例 方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (10)

  1. 一种基于精密三维的路面错台检测方法，包括：
    获取路面三维轮廓数据，并基于所述路面三维轮廓数据，得到轮廓参考面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差；
    基于所述轮廓偏差得到疑似接缝点，并基于所述疑似接缝点，得到疑似接缝去噪二值图；
    基于所述疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置；
    基于所述疑似接缝去噪二值图、所述原始接缝目标图，以及所述接缝代表位置，通过接缝延伸操作，得到目标接缝二值图；
    基于所述目标接缝二值图和所述路面三维轮廓数据，得到路面错台信息。
  2. 根据权利要求1所述的路面错台检测方法，其特征在于，所述基于所述疑似接缝点，得到疑似接缝去噪二值图，包括：
    基于所述疑似接缝点得到原始疑似接缝点二值图；
    以所述原始疑似接缝点二值图中连通区域为单位，依据所述连通区域的长度、所述轮廓偏差的幅值、连通区域方向特征进行去噪，得到所述疑似接缝去噪二值图。
  3. 根据权利要求2所述的基于精密三维的路面错台检测方法，其特征在于，所述基于所述疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置，包括：
    将所述疑似接缝去噪二值图中目标点沿行方向投影，得到各行疑似接缝点；
    基于所述各行疑似接缝点的统计特征，得到所述原始接缝目标图以及所述接缝代表位置。
  4. 根据权利要求3所述的基于精密三维的路面错台检测方法，其特征在于，所述基于所述各行疑似接缝点的统计特征，得到所述原始接缝目标图以及所述接缝代表位置，包括：
    在当前行中的疑似接缝点数量大于预设数量值的情况下，确定当前行中的疑似接缝点为接缝种子点；
    基于所述接缝种子点，得到所述原始接缝目标图；
    将行间距小于预设行距值的接缝和作为目标接缝行，并将所述目标接缝行合并为同一接缝，且将所述目标接缝行的行平均值作为所述接缝代表位置；
    其中，所述接缝行为所述接缝种子点所在行。
  5. 根据权利要求1所述的基于精密三维的路面错台检测方法，其特征在于，所述基于所述疑似接缝去噪二值图、所述原始接缝目标图，以及所述接缝代表位置，通过接缝延伸操作，得到目标接缝二值图，包括：
    在所述接缝种子点对应的第一目标范围内，将所述疑似接缝去噪二值图中，与所述接缝种子点属于相同连通区域的测点，作为补充接缝点；
    基于所述接缝种子点和所述补充接缝点，得到扩展接缝二值图；
    在所述接缝代表位置对应的第二目标范围内，搜索所述扩展接缝二值图中的接缝点，并对搜索到的接缝点进行线性拟合，得到拟合接缝；
    在所述接缝代表位置对应的第三目标范围内，将所述扩展接缝二值图中，存在缺失接缝的列中的拟合接缝位置作为延伸接缝目标点；
    基于所述接缝种子点、所述补充接缝点和所述延伸接缝目标点，得到目标接缝二值图。
  6. 根据权利要求1所述的基于精密三维的路面错台检测方法，其特征在于，所述基于所述路面三维轮廓数据，得到轮廓参考面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差，包括：
    在所述路面三维轮廓数据中存在无效测点的情况下，基于所述无效测点附近的有效测点，替代所述无效测点，得到新的路面三维轮廓数据；
    基于滤波方式或者频域变化方式，对所述新的路面三维轮廓数据进行处理，得到所述轮廓参考面；
    将所述新的路面三维轮廓数据，与所述轮廓参考面作差，得到所述轮廓偏差；
    其中，所述疑似接缝点，为对应轮廓偏差大于分割阈值对应的测点。
  7. 根据权利要求1-6任一项所述的基于精密三维的路面错台检测方法，其特征在于，所述基于所述目标接缝二值图和所述路面三维轮廓数据，得到路面错台信息，包括：
    基于所述目标接缝二值图，得到接缝前后两侧路面代表高程；
    基于所述接缝前后两侧路面代表高程，得到所述路面错台信息。
  8. 根据权利要求7所述的基于精密三维的路面错台检测方法，其特征在于，所述基于所述目标接缝二值图，得到接缝前后两侧路面代表高程，包括：
    基于所述目标接缝二值图，以拟合接缝为中心，在第四目标范围内，搜索接缝起点和接缝终点；
    在所述接缝起点对应的第五目标范围内，邻近所述拟合接缝的路面平均高程作为前侧路面代表高程，得到前侧路面代表高程集合；所述前侧路面为车辆前进方向路面；
    在所述接缝终点对应的第六目标范围内，邻近所述拟合接缝的路面平均高程作为后侧路面代表高程，得到后侧路面代表高程集合。
  9. 根据权利要求7所述的基于精密三维的路面错台检测方法，其特征在于，所述基于所述接缝前后两侧路面代表高程，得到所述路面错台信息，包括：
    所述基于所述接缝前后两侧路面代表高程，得到全幅错台值、左右轮迹带错台值、最大错台值、全幅宽错台均值、全幅宽错台中值以及全幅宽加权错台值中的至少一个；
    其中，所述全幅错台值的计算方式如下：
    逐列分别计算前侧路面代表高程与后侧路面代表高程的绝对差值，得到多列全幅错台值；列方向与路面的幅宽方向对应，行方向与列方向垂直；
    所述左右轮迹带错台值的计算方式如下：
    基于所述路面三维轮廓数据的列向位置与路面幅宽方向位置的对应关系，分别选取左轮迹带和右轮迹带对应列的全幅错台值作为左右轮迹带错台值；
    所述全幅宽加权错台值的计算方式如下：
    基于所述多列全幅错台值中，计算各列全幅错台值与左轮迹带和右轮迹带对应列，在路面幅宽方向的最小距离，
    基于所述路面幅宽方向的最小距离，以及在路面幅宽方向，所述左轮迹带和所述右轮迹带的距离，计算得到各列全幅错台值对应的权重；
    基于所述多列全幅错台值，以及所述各列全幅错台值对应的权重，计算得到所述全幅加权错台值。
  10. 一种基于精密三维的路面错台检测装置，包括：
    第一计算模块，用于获取路面三维轮廓数据，并基于所述路面三维轮廓数据，得到轮廓参考面，以及所述路面三维轮廓数据中的测点与轮廓参考面之间的轮廓偏差；
    第二计算模块，用于基于所述轮廓偏差得到疑似接缝点，并基于所述疑似接缝点，得到疑似接缝去噪二值图；
    第三计算模块，用于基于所述疑似接缝去噪二值图中目标测点的行方向投影特征，得到原始接缝目标图以及接缝代表位置；
    第四计算模块，用于基于所述疑似接缝去噪二值图、所述原始接缝目标图，以及所述接缝代表位置，通过接缝延伸操作，得到目标接缝二值图；
    第五计算模块，用于基于所述目标接缝二值图和所述路面三维轮廓数据，得到路面错台信息。
PCT/CN2022/085609 2021-12-21 2022-04-07 基于精密三维的路面错台检测方法及装置 WO2023115754A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2022418482A AU2022418482A1 (en) 2021-12-21 2022-04-07 Precision three-dimensional pavement faulting measurement method and apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111572820.4A CN114511495A (zh) 2021-12-21 2021-12-21 基于精密三维的路面错台检测方法及装置
CN202111572820.4 2021-12-21

Publications (1)

Publication Number Publication Date
WO2023115754A1 true WO2023115754A1 (zh) 2023-06-29

Family

ID=81548687

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/085609 WO2023115754A1 (zh) 2021-12-21 2022-04-07 基于精密三维的路面错台检测方法及装置

Country Status (3)

Country Link
CN (1) CN114511495A (zh)
AU (1) AU2022418482A1 (zh)
WO (1) WO2023115754A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101845788A (zh) * 2010-04-09 2010-09-29 同济大学 基于结构光视觉的水泥混凝土路面错台检测装置及方法
US20130155061A1 (en) * 2011-12-16 2013-06-20 University Of Southern California Autonomous pavement condition assessment
CN108319920A (zh) * 2018-02-05 2018-07-24 武汉武大卓越科技有限责任公司 一种基于线扫描三维点云的路面标线检测及参数计算方法
CN111968079A (zh) * 2020-07-28 2020-11-20 武汉武大卓越科技有限责任公司 基于断面局部极值及分段稀疏的三维路面裂缝提取方法
CN113701678A (zh) * 2021-09-18 2021-11-26 武汉光谷卓越科技股份有限公司 一种基于线扫描三维的路面平整度检测方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101845788A (zh) * 2010-04-09 2010-09-29 同济大学 基于结构光视觉的水泥混凝土路面错台检测装置及方法
US20130155061A1 (en) * 2011-12-16 2013-06-20 University Of Southern California Autonomous pavement condition assessment
CN108319920A (zh) * 2018-02-05 2018-07-24 武汉武大卓越科技有限责任公司 一种基于线扫描三维点云的路面标线检测及参数计算方法
CN111968079A (zh) * 2020-07-28 2020-11-20 武汉武大卓越科技有限责任公司 基于断面局部极值及分段稀疏的三维路面裂缝提取方法
CN113701678A (zh) * 2021-09-18 2021-11-26 武汉光谷卓越科技股份有限公司 一种基于线扫描三维的路面平整度检测方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
YING HONG, TAN ZHIMING: "Cement Concrete Pavement Faulting Detection and Recognization Based on Binocular Vision", JOURNAL OF TONGJI UNIVERSITY(NATURAL SCIENCE), vol. 39, no. 2, 15 February 2011 (2011-02-15), pages 247 - 252, XP093074056, ISSN: 0253-374X, DOI: 10.3969/j.issn.0253-374x.2011.02.017 *

Also Published As

Publication number Publication date
CN114511495A (zh) 2022-05-17
AU2022418482A1 (en) 2023-11-23

Similar Documents

Publication Publication Date Title
US10755132B2 (en) Methods for extracting surface deformation feature of object based on linear scanning three-dimensional point cloud
CN112433203B (zh) 一种基于毫米波雷达数据的车道线形检测方法
CN108319920B (zh) 一种基于线扫描三维点云的路面标线检测及参数计算方法
CN105809668B (zh) 基于线扫描三维点云的物体表面变形特征提取方法
CN116071387B (zh) 基于机器视觉的枕轨生产质量检测方法
CN104776810B (zh) 一种基于3d线激光设备的坑槽三维指标提取计算方法
CN107830839B (zh) 地面三维激光扫描数据处理方法及装置
CN107869958B (zh) 一种用于地铁检测及测量的3d扫描方法
CN110530278B (zh) 利用多线结构光测量间隙面差的方法
CN110736999B (zh) 基于激光雷达的铁路道岔检测方法
CN110276752B (zh) 基于android系统的混凝土表面裂缝特征的APP检测方法
CN108921164A (zh) 一种基于三维点云分割的接触网定位器坡度检测方法
CN105387801A (zh) 一种地铁隧道管片错台量检测方法
Firoozi Yeganeh et al. Automated rutting measurement using an inexpensive RGB-D sensor fusion approach
CN111968079B (zh) 基于断面局部极值及分段稀疏的三维路面裂缝提取方法
CN115112044A (zh) 一种基于多线结构光点云数据的轮对尺寸测量方法
Ong et al. A hybrid method for pavement crack width measurement
WO2023115754A1 (zh) 基于精密三维的路面错台检测方法及装置
CN102012964A (zh) 激光扫描的采样数据的处理方法和装置
CN112950562A (zh) 一种基于线结构光的扣件检测算法
CN113093217A (zh) 多线激光扫描隧道三维重构方法
CN116543037B (zh) Crtsiii型无砟轨道板承轨台中心提取方法
CN109115127A (zh) 一种基于贝塞尔曲线的亚像素峰值点提取算法
CN111455787B (zh) 一种基于路面三维数字化的路面检测系统
CN112033385A (zh) 一种基于海量点云数据的桥墩位姿测量方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22909092

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2022418482

Country of ref document: AU

Ref document number: AU2022418482

Country of ref document: AU

ENP Entry into the national phase

Ref document number: 2022418482

Country of ref document: AU

Date of ref document: 20220407

Kind code of ref document: A