CN113469940A - Fastener looseness detection method based on three-dimensional point cloud and two-dimensional image processing technology - Google Patents
Fastener looseness detection method based on three-dimensional point cloud and two-dimensional image processing technology Download PDFInfo
- Publication number
- CN113469940A CN113469940A CN202110579074.5A CN202110579074A CN113469940A CN 113469940 A CN113469940 A CN 113469940A CN 202110579074 A CN202110579074 A CN 202110579074A CN 113469940 A CN113469940 A CN 113469940A
- Authority
- CN
- China
- Prior art keywords
- fastener
- point
- point cloud
- dimensional
- points
- 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.)
- Granted
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/30164—Workpiece; Machine component
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
- G06T2219/20—Indexing scheme for editing of 3D models
- G06T2219/2004—Aligning objects, relative positioning of parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
- G06T2219/20—Indexing scheme for editing of 3D models
- G06T2219/2016—Rotation, translation, scaling
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Graphics (AREA)
- Architecture (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of rail transit engineering detection, and particularly relates to a fastener looseness detection method based on a three-dimensional point cloud combined two-dimensional image processing technology.
Description
Technical Field
The invention belongs to the technical field of contact network rail transit engineering detection, and particularly relates to a fastener looseness detection method based on a three-dimensional point cloud and two-dimensional image processing technology.
Background
The middle connection part is also called a steel rail fastener, the steel rail fastener is a fastening device part of a steel rail and a sleeper with a rigid fastening piece, and the 70-type buckle plate type fastener for fastening 50, 43(kg/m) and other steel rails on a concrete sleeper line in China comprises a bolt spike, a nut, a flat washer, a Hotan washer, a rigid buckle plate, an iron seat, an insulating buffer gasket, an under-rail rubber mat, an insulating buffer gasket, insulating antirust paint, sulfur anchor and other parts. The rail fasteners are used for fastening rails and rail fittings of off-machine components, and are divided into two categories, namely sleeper line fasteners and concrete sleeper line (other types of concrete off-machine component lines) fasteners according to the types of sleepers.
At present, in the technical scheme of a track detection device, methods for detecting fastener looseness include an angle comparison method based on a two-dimensional image, a detection method based on infrared thermal imaging and by acquiring contact stress between a fastener and a steel rail, a fastener bolt floating detection method based on three-dimensional point cloud, and the like. Compared with the method for detecting the loosening of the fastener from the two-dimensional image, the method for detecting the floating of the fastener bolt based on the three-dimensional point cloud has higher precision of identifying the loosening of the fastener from the three-dimensional point cloud, in the prior art, the three-dimensional point cloud is converted into a two-dimensional depth image, then the fastener is extracted by setting a gray threshold range, then whether the fastener is loosened or not is judged according to the height information of the bolt, but the method is only suitable for keeping a fixed distance between the point cloud acquisition equipment and the fastener and has no interference data, the fastener can be directly extracted by setting a threshold value through coordinate position information, and the loosening of the fastener is usually the loosening of the nut below the bolt without pressing the elastic strip, so that the loosening of the bolt of the fastener can not accurately reflect whether the fastener is loosened or not only by detecting the loosening of the bolt of the fastener, but can not automatically complete the recognition, positioning and interference filtering of the fasteners in the three-dimensional point cloud and realize the accurate positioning of the key measuring points of the elastic strips and the reference points of the insulating blocks.
Compared with the method, the method has the advantages that the identification, positioning and interference information filtering of the fastener is automatically completed in the three-dimensional point cloud, and the accurate positioning of the key measuring point of the elastic strip and the reference point of the insulating block is realized, so that the looseness of the fastener is accurately measured.
Disclosure of Invention
In order to overcome the problems and the defects in the prior art, the invention aims to provide a fastener looseness detection method which can automatically complete the identification, positioning and interference signal filtering of a fastener in three-dimensional point cloud, and realize the accurate positioning of a key measuring point of an elastic strip and a reference point of an insulating block so as to achieve the accurate measurement of fastener looseness.
The fastener looseness detection method based on the combination of the three-dimensional point cloud and the two-dimensional image processing technology comprises the following steps:
positioning the steel rail: setting a threshold range (z) according to height information in the three-dimensional point cloud of the track acquired by the three-dimensional acquisition systemrailmin～zrailmax) Filtering the track three-dimensional point cloud through a threshold range, setting the threshold range by the height information, wherein the threshold range is a priori threshold value depending on the distance between the three-dimensional acquisition equipment and the track surface, then density clustering is carried out on the filtered three-dimensional point clouds of the track, the coordinates of external cubes of the point clouds of the left steel rail and the right steel rail are respectively obtained, the density clustering specifically comprises the steps of judging a threshold value by setting a distance, carrying out distance calculation on all the three-dimensional point clouds in the three-dimensional point clouds, dividing the three-dimensional point clouds with the distance falling into a threshold value range into a cluster, applying a clustering method to a mature technology of three-dimensional inside, determining that a fastener is always positioned in the external cube coordinates of the point clouds of the left steel rail and the right steel rail according to the position relation of the fastener and the steel rail, the purpose of acquiring the coordinates of the external cube is to perform a preliminary division on the area where the fastener is located, and the coordinates of two diagonal points of the external cube are set as (x).min，ymin，zmin) And (x)max，ymax，zmax)；
A fastener positioning step: because the fasteners are located at the two sides of the rail surface within the distance T from the rail surface by xmin-T～xmax-TIntercepting three-dimensional point clouds including fasteners from external cubic coordinates of the left and right steel rail point clouds obtained in the steel rail positioning step, namely fastener point clouds, wherein T is the distance between two sides of a rail surface and the rail surface; according to the height range (h) of the fastenermin～hmax) Filtering the fastener point cloud to obtain a three-dimensional point cloud of the fastener outline, namely a fastener set point cloud and a height range (h)min～hmax) According to the distance between the installed three-dimensional acquisition equipment and the fastener, the range is only a larger and rough range as the threshold range set for the height information in the steel rail positioning step, finally, the fastener template matching is carried out in the fastener set point cloud through a standard fastener generation matching model, and all three-dimensional point coordinate point sets s of the fastener template are used0Translating, rotating and changing into three-dimensional point coordinate point set s 'corresponding to matched fastener'0；
Normally, the distance between the fastener and the steel rail is within 150mm, therefore, in the fastener positioning step, the T distance can be set to be generally between 100 and 200mm, and is preferably 150 mm.
In the step of positioning the fastener, performing fastener matching in a fastener set point cloud based on a point cloud template matching algorithm of a Fast Point Feature Histogram (FPFH) descriptor, specifically comprising the following steps:
step 1, selecting n sampling points from a cloud P to be registered, wherein the distance between the sampling points is greater than a preset minimum distance threshold value d, so that the sampled points can have different FPFH (field programmable gate hopping) characteristics;
step 2, one or more points with similar FPFH characteristics to the sampling points in the point cloud P are searched in the target point cloud Q, and one point is randomly selected from the similar points to serve as a one-to-one corresponding point of the point cloud P in the target point cloud Q;
step 3, calculating a rigid body transformation matrix between corresponding points, and then judging the performance of the current registration transformation by solving a distance error sum function after the corresponding points are transformed;
the translational and rotational change processing is specifically a three-dimensional point coordinate point set s of a fastener template matched with a fastener in a three-dimensional point cloud0By translational and rotational variation matrices matrix0(tx,ty,tz1, alpha, beta, lambda) is subjected to translational and rotational change processing to obtain a three-dimensional point coordinate point set s 'of a fastener, corresponding to and matched with the fastener template, in the three-dimensional point cloud of the fastener area'0Wherein (t)x，ty，tzAnd 1) is a translation parameter, and (alpha, beta, lambda) bits are rotation parameters, and a translation rotation change matrix is derived from the output of a template matching algorithm, so that the translation parameter and the rotation parameter are values obtained through the algorithm.
More specifically, the three-dimensional point coordinates (x) of the fastener template are first mapped by translation parameters0，y0，z0) The translation processing obtains translation position coordinates
Three-dimensional point coordinates (x) of fastener template0，y0，z0) The three-dimensional point coordinates of the fastener template are manually selected or input in a three-dimensional coordinate system according to the proportion of the structure, the shape, the size and the like of the fastener template, so that the three-dimensional point coordinates of the fastener template can be transformed into an original coordinate system through a transformation matrix and can be directly used in the three-dimensional point coordinate system.
And then rotating the translation position coordinate through the rotation parameters (alpha, beta, lambda) to obtain a position coordinate (x ') after translation and rotation'0，y′0，z′0) The point set of all three-dimensional point coordinates of the fastener template after translational rotation processing is the position coordinate point set of the fastener in the three-dimensional point cloud, which is recorded as s'0，
Positioning the key points of the elastic strips: according to the point of each fastenerExtracting a current fastener point cloud s from the fastener set point cloud by cloud horizontal distribution range1(ii) a Calculating the current fastener point cloud s1And corresponding point cloud s'0The spatial distance between the point(s) and the point(s) is eliminated1Points with intermediate space distance not meeting threshold value constitute point cloud s2(ii) a A point cloud s0And point cloud s2Generating a two-dimensional image template model0And a two-dimensional image in plan view0Template model of two-dimensional image0And a two-dimensional image in plan view0Image template matching and two-dimensional image template model extraction0To look down two-dimensional image0And transforming the two-dimensional image template model0The key point area of the elastic strip is mapped to the matched overlook two-dimensional image through the transformation matrix0Obtaining a two-dimensional image of the overlook view at the corresponding position0The key point area is obtained by manually marking the key point area in the template according to the prior threshold or experience, the key point coordinates in the acquired data can be accurately found by simultaneously rotating and translating the key point area and the template through the transformation matrix, secondary accurate registration is completed, and the overlook two-dimensional image is obtained0The area of the key measuring point of the elastic strip; from a point cloud s2Extracting the height average value of the area of the key point of the elastic strip to obtain the relative height h of the key point of the elastic strip1。
In the step of positioning the key points of the elastic strips, a KD-tree structure is adopted to quickly traverse the calculation point set s1Zhonghe Point set s'0The distance dis between the points in and recording the set of points s1Of each point is from the point set s'0The minimum distance dis of the points inminTo reject the minimum distance disminPoints greater than a distance threshold m, a set of points s1The remaining points in the set constitute a point set s2And the distance threshold m is a determination threshold.
In the step of positioning the key points of the elastic strips, a point set s is set0Generating a two-dimensional overlook image and establishing a two-dimensional image template model0Then, recording the area a of the selected key measuring point0In template model0Position (x) ina0min～xa0max，ya0min～ya0max)；
Then set the points s2Generating a two-dimensional image of an overhead view0Will image0And model0Matching image templates, and obtaining a two-dimensional transformation matrix according to template matching1For the area a of the key measuring point0A is obtained by conversion operation0' region, a0' region, i.e. region of key measurement points, is set of points s2The position of (1);
direct computation of a set of points s2In (A) of0' height average of area, relative height h of key measuring point can be obtained1。
The region of the key measurement point is located in a portion of a spring strip component of the fastener of which the spring strip is one of the components, and the key point is located in the spring strip of the fastener.
Positioning a fastener reference point: longitudinally expanding the key point area of the elastic strip to obtain a point cloud s2The point cloud of the area is intercepted, the area is divided into i parts by adopting a density clustering method, and the average height h of each part is respectively obtainediaveTaking the lowest average height h'iaveAverage height h as reference point of insulating block2；
In the step of positioning the fastener reference point, the size of the longitudinally expanded key point area is a1[xa0min～xa0max，(ya0min-n)～(ya0max+n)]And n is a fixed length selected in the template according to the prior threshold.
A fastener looseness judging step, namely directly calculating the overlook two-dimensional image obtained in the fastener key measuring point positioning step0Height average h of fastener key point area in1H is to be1H in the step of locating the fastener reference point2Calculating difference to obtain height difference delta h between the key point area and the reference point areaMeasuringComparison of Δ hMeasuringA standard value Δ h of the distanceStandard of meritWhether the difference is greater than the threshold value U or not, so as to judge whether the fastener is loosened or not and determine the standard value delta hStandard of meritCritical point area distance insulation for standard fastenersThe distance of the blocks is determined according to the standard design value of the fastener; the threshold U is an acceptable fastener loosening range, and is set according to the operating environment.
Corresponding to the method, the invention also provides computer equipment, which comprises: one or more processors, a memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform the method described above.
And, a non-transitory machine-readable storage medium storing executable instructions that, when executed, cause the machine to perform the above-described method.
Has the advantages that:
1. according to the technical scheme provided by the invention, the three-dimensional point cloud data is roughly divided and the area where the fastener as a target is located is extracted in an external quadrilateral coordinate acquisition mode according to the classical track and component data as a prior threshold, the point cloud containing the fastener is quickly and directly acquired from the acquired object data by adopting a single index, all invalid data are eliminated, the processing and identification computation amount is greatly reduced, and the subsequent matching and identification processing can be more efficient and faster.
2. Furthermore, the method uses a three-dimensional template matching method for point cloud containing fasteners, uses a fastener standard template as reference, automatically finds out the position of each fastener from the collected point cloud data of the whole track, then uses a overlook two-dimensional graph of the fastener standard template to perform secondary precise configuration on the detected fasteners, and finds out the relative position of a key point area such as a spring strip and the like and the fasteners, so as to accurately obtain the height of the key point area, thereby rapidly completing the detection of the looseness of the fasteners in a height threshold value judging mode.
3. After fastener point cloud is obtained through template matching, the outline of a fastener is identified by adopting a point cloud template matching algorithm based on a Fast Point Feature Histogram (FPFH) descriptor to obtain an accurate fastener template, then a spring strip serving as a classic key point in the fastener is taken as an object, the actual height is calculated to obtain the actual height of the spring strip in a detected track, planar point cloud data serving as a reference point is separated from the point cloud data of the spring strip through two-dimensional processing to obtain the actual height of the spring strip, meanwhile, the relative height of the spring strip in the fastener model serving as the template in the point cloud is correspondingly calculated, the actual height of the spring strip in the detected track and the relative height of the spring strip in the fastener model serving as a reference standard are subjected to height difference calculation, the height difference calculation result is taken as data for judging whether the fastener is loosened, and the method of combining three-dimensional template matching with two-dimensional image data is utilized, the fastener region, the elastic strip key point region and the insulation block reference point region are automatically extracted from the point cloud data of the whole rail surface and two sides, and the influence of the position, direction, height and other changes of the fastener is avoided.
Drawings
The foregoing and following detailed description of the invention will be apparent when read in conjunction with the following drawings, in which:
FIG. 1 is a logic diagram of the present invention;
FIG. 2 is a schematic diagram of a three-dimensional point cloud of a track acquired by a three-dimensional acquisition system;
FIG. 3 is a schematic diagram of filtering a three-dimensional point cloud of a track through a threshold range of altitude information;
FIG. 4 is a schematic diagram of external cubic coordinates for obtaining point clouds of left and right steel rails;
FIG. 5 is a schematic view of a three-dimensional point cloud including fasteners;
FIG. 6 is a schematic three-dimensional point cloud of a fastener region;
FIG. 7 is a set of coordinates of all three-dimensional points s of a fastener template0A schematic diagram;
FIG. 8 is a three-dimensional point coordinate point set s 'of a fastener correspondingly matched with a three-dimensional point cloud of a track'0A schematic diagram;
FIG. 9 is a three-dimensional point coordinate point set s'0Extracting a range schematic diagram;
FIG. 10 is a diagram of a point set s according to an embodiment of the present invention2A schematic diagram of (a);
FIG. 11 is a two-dimensional image template model0Key point region schematic diagram of (1);
FIG. 12 is a schematic diagram of the longitudinal expansion of the region of key measurement points;
FIG. 13 is a graph of data height differences for the standard region points and the keypoint region;
Detailed Description
The technical solutions for achieving the objects of the present invention are further illustrated by the following specific examples, and it should be noted that the technical solutions claimed in the present invention include, but are not limited to, the following examples.
Example 1
As a specific embodiment of the present invention, this embodiment discloses a fastener looseness detection method based on a three-dimensional point cloud combined with a two-dimensional image processing technology, as shown in fig. 1, including a steel rail positioning step, a fastener positioning step, a spring bar key point positioning step, a fastener reference point positioning step and a fastener looseness judging step, using a fastener standard template to find each fastener position in the whole track point cloud data automatically by using a three-dimensional template matching method, then using a top view two-dimensional diagram of a template fastener to perform secondary precise configuration on the detected fastener, finding the relative position between a spring bar key point region and a fastener, obtaining the height of the spring bar key point region, then using the relative height difference between an insulation block reference point and a key point on the spring bar, separating the insulation block reference point plane point cloud data from the point cloud data, obtaining the relative height of the insulation block reference point, and finally, judging whether the fastener is loosened or not by utilizing the relative height difference between the key point on the elastic strip and the reference point of the insulating block, and more accurately judging whether the fastener is loosened or not by selectively using the key point of the elastic strip and the reference point of the insulating block.
Specifically, in the rail positioning step, as shown in fig. 2, a threshold range (z) is set according to height information in a three-dimensional point cloud of a track acquired by a three-dimensional acquisition system through the three-dimensional point cloud of the track acquired by the three-dimensional acquisition systemrailmin～zrailmax) As shown in fig. 3, the track three-dimensional point cloud is filtered through a threshold range, and the height information setting threshold range depends on the distance between the three-dimensional acquisition equipment and the track surface and is a prior threshold; then as shown in the figure4, density clustering is carried out on the filtered three-dimensional point clouds of the track, external cubic coordinates of the point clouds of the left and right steel rails are respectively obtained, the density clustering is a mature technology that a clustering method is applied to three-dimensional interior by setting a distance judgment threshold value, distance calculation is carried out on all the three-dimensional point clouds in pairs, the distance falling into the range of the threshold value is divided into a cluster, the position relation of a fastener and the steel rail determines that the fastener is always positioned in the external cubic coordinates of the point clouds of the left and right steel rails, namely the external cubic coordinates are obtained for the purpose of carrying out primary division on the area where the fastener is positioned, and the diagonal two-point coordinates of the external cube are set as (xmin，ymin，zmin) And (x)max，ymax，zmax) It should be noted that the X, Y, Z directions of the front, back, left, right, upper, lower and coordinate points referred to in the description of the present invention are all relative position-limited descriptions for easier understanding of the technical solution, and are not absolute orientation limitations.
And then, in the fastener positioning step, setting T as the distance between two sides of the rail surface and the rail surface, because the fasteners are positioned in the distance between two sides of the rail surface and the rail surface T, and normally, the distance between the fasteners and the rail is within 150mm, therefore, the distance T can be generally set to be between 100 and 200mm, preferably can be directly set to be 150mm, and then is xmin-T～xmax-TThe three-dimensional point cloud containing fasteners as shown in fig. 5 is intercepted from the circumscribed cubic coordinates of the left and right rail point clouds obtained in the rail positioning step.
Then referring again to FIG. 6, depending on the height range (h) of the fastenermin～hmax) Filtering the three-dimensional point cloud containing the fasteners to obtain the three-dimensional point cloud of the fastener area, the height range (h)min～hmax) Depending on the distance between the installed three-dimensional acquisition equipment and the fastener, which is only a large and rough range as the threshold range set for the height information in the rail positioning step, the fastener template matching is finally performed in the three-dimensional point cloud of the fastener region by the standard fastener generation matching model, and all three-dimensional point coordinate point sets of the fastener template as shown in fig. 7 are collecteds0The translation and rotation change processing is carried out to obtain a three-dimensional point coordinate point set s 'of the fastener correspondingly matched with the three-dimensional point cloud of the track as shown in figure 8'0。
Positioning the key points of the elastic strips, namely extracting the current fastener point cloud s from the fastener set point cloud according to the point cloud horizontal distribution range of each fastener1According to the range (X ') of the three-dimensional point cloud position coordinates of the fastener matched in the fastener positioning step on the X axis and the Y axis, as shown in FIG. 9'0min～x′0max) And (y'0min～y′0max) Extracting three-dimensional point clouds falling into the range from all the three-dimensional point clouds of the track acquired by the three-dimensional acquisition system to form a point set s1And gather s 'by points'0From the set of points s according to a set decision threshold for reference1Points which do not meet the requirement of the judgment threshold are removed to form a point set s shown in figure 102(ii) a Set of points s0And set of points s2Generating a two-dimensional image template model0And a two-dimensional image in plan view0Template model of two-dimensional image0And a two-dimensional image in plan view0Matching image templates and modeling two-dimensional image templates0The key point area in (1) is transformed to a matched overlook two-dimensional image through a transformation matrix based on a two-dimensional image matching algorithm0The corresponding positions in the image are shown in fig. 11, the key point areas are obtained by manually marking the key point areas in the template according to the prior threshold or experience, the key point coordinates in the acquired data can be accurately found by simultaneously transforming the matrix to rotate and translate, the secondary accurate registration is completed, and the overlook two-dimensional image is obtained0Calculating the height average value of the key measuring points in the area to obtain the relative height h of the key measuring points1。
In the fastener looseness judging step, as shown in fig. 12, the overlook two-dimensional image obtained in the fastener key measuring point positioning step is0The region of the key measuring point of the elastic strip is longitudinally expanded, the longitudinally expanded key measuring point region is divided into i parts by adopting density-based method clustering (such as DBSCAN clustering method), and the average height h of each part is respectively obtainediaveThe lowest average height portion is the fastener reference point region, which has an average height h'iaveI.e. the average height h of the reference point area of the insulating block2And whether the cable is loosened or not can be judged through the height difference between the key measuring point and the insulating block.
Specifically, the fastener looseness judging step is to directly calculate the overlook two-dimensional image obtained in the fastener key measuring point positioning step0Height average h of fastener key point area in1H is to be1H in the step of locating the fastener reference point2Calculating difference to obtain height difference delta h between the key point area and the reference point areaMeasuringComparison of Δ hMeasuringA standard value Δ h of the distanceStandard of meritWhether the difference is greater than the threshold value U or not, so as to judge whether the fastener is loosened or not and determine the standard value delta hStandard of meritDetermining the distance between the key point area of the standard fastener and the insulating block according to the standard design value of the fastener; the threshold U is an acceptable fastener loosening range, and is set according to the operating environment.
Example 2
As a preferred embodiment of the present invention, this embodiment discloses a fastener looseness detection method based on a three-dimensional point cloud combined with a two-dimensional image processing technology, as shown in fig. 1, including a steel rail positioning step, a fastener key measuring point positioning step, a fastener reference point positioning step, and a fastener looseness determining step, specifically:
in the rail positioning step, as shown in fig. 2, a threshold value range Z is set according to height information in a three-dimensional point cloud of the track acquired by a three-dimensional acquisition system through the three-dimensional point cloud of the track acquired by the three-dimensional acquisition systemrailmin～ZrailmaxAs shown in fig. 3, the track three-dimensional point cloud is filtered through a threshold range, and the height information setting threshold range depends on the distance between the three-dimensional acquisition equipment and the track surface and is a prior threshold; then, as shown in fig. 4, density clustering is carried out on the filtered three-dimensional point clouds of the track, external cubic coordinates of the point clouds of the left and right steel rails are respectively obtained, specifically, the density clustering is to calculate the distance between every two three-dimensional point clouds in the three-dimensional point clouds by setting a distance judgment threshold value, and the distance is calculatedDividing the point of the point cloud of the left and right steel rails into a cluster, wherein the clustering method is a mature technology for applying a clustering method to three dimensions, the position relation of the fasteners and the steel rails determines that the fasteners are always positioned in external cubic coordinates of the point cloud of the left and right steel rails, namely the external cubic coordinates are obtained for the purpose of carrying out primary division on the area where the fasteners are positioned, and the coordinates of two opposite angles of the external cubic are set as (x) two-point coordinatesmin，ymin，zmin) And (x)max，ymax，zmax) It should be noted that the X, Y, Z directions of the front, back, left, right, upper, lower and coordinate points referred to in the description of the present invention are all relative position-limited descriptions for easier understanding of the technical solution, and are not absolute orientation limitations.
And then, in the fastener positioning step, setting T as the distance between two sides of the rail surface and the rail surface, because the fasteners are positioned in the distance between two sides of the rail surface and the rail surface T, and normally, the distance between the fasteners and the rail is within 150mm, therefore, the distance T can be generally set to be between 100 and 200mm, preferably can be directly set to be 150mm, and then is xmin-T～xmax-TThe three-dimensional point cloud containing fasteners as shown in fig. 5 is intercepted from the circumscribed cubic coordinates of the left and right rail point clouds obtained in the rail positioning step.
Then referring again to FIG. 6, depending on the height range (h) of the fastenermin～hmax) Filtering the three-dimensional point cloud containing the fasteners to obtain the three-dimensional point cloud of the fastener area, the height range (h)min～hmax) Depending on the distance between the installed three-dimensional acquisition equipment and the fastener, which is only a large and rough range as the threshold range set for the height information in the rail positioning step, the fastener template matching is finally performed in the three-dimensional point cloud of the fastener region by the standard fastener generation matching model, and the set s of all three-dimensional point coordinates of the fastener template as shown in fig. 7 is used0The translation and rotation change processing is carried out to obtain a three-dimensional point coordinate point set s 'of the fastener correspondingly matched with the three-dimensional point cloud of the track as shown in figure 8'0More specifically, the point cloud template matching algorithm based on the FPFH descriptor is used for carrying out the fastener in the three-dimensional point cloud containing the fastenerMatching:
further, in the step of locating the fastener, performing fastener matching in the fastener set point cloud based on a point cloud template matching algorithm of a Fast Point Feature Histogram (FPFH) descriptor, specifically, the method includes the following steps:
step 1, selecting n sampling points from a cloud P to be registered, wherein the distance between the sampling points is greater than a preset minimum distance threshold value d, so that the sampled points can have different FPFH (field programmable gate hopping) characteristics;
step 2, one or more points with similar FPFH characteristics to the sampling points in the point cloud P are searched in the target point cloud Q, and one point is randomly selected from the similar points to serve as a one-to-one corresponding point of the point cloud P in the target point cloud Q;
step 3, calculating a rigid body transformation matrix between corresponding points, and then judging the performance of the current registration transformation by solving a distance error sum function after the corresponding points are transformed;
the translational and rotational change processing is specifically a three-dimensional point coordinate point set s of a fastener template matched with a fastener in a three-dimensional point cloud0By translational and rotational variation matrices matrix0(tx,ty,tz1, alpha, beta, lambda) is subjected to translational and rotational change processing to obtain a three-dimensional point coordinate point set s 'of a fastener, corresponding to and matched with the fastener template, in the three-dimensional point cloud of the fastener area'0Wherein (t)x，ty，tzAnd 1) is a translation parameter, and (alpha, beta, lambda) bits are rotation parameters, and a translation rotation change matrix is derived from the output of a template matching algorithm, so that the translation parameter and the rotation parameter are values obtained through the algorithm.
More specifically, the three-dimensional point coordinates (x) of the fastener template are first mapped by translation parameters0，y0，z0) The translation processing obtains translation position coordinates
Three-dimensional point coordinates (x) of fastener template0，y0，z0) Manually selecting or selecting in a three-dimensional coordinate system according to the structure, shape, size and other proportions of the fastener templateThe three-dimensional point coordinates of the input template can be transformed into an original coordinate system through a transformation matrix and can be directly used in the three-dimensional point coordinate system.
And then rotating the translation position coordinate through the rotation parameters (alpha, beta, lambda) to obtain a position coordinate (x ') after translation and rotation'0，y′0，z′0) The point set of all three-dimensional point coordinates of the fastener template after translational rotation processing is the position coordinate point set of the fastener in the three-dimensional point cloud, which is recorded as s'0，
Positioning key measuring points of the fastener, as shown in fig. 9, according to the ranges (X ') of the three-dimensional point cloud position coordinates of the fastener matched in the fastener positioning step on the X axis and the Y axis'0min～x′0max) And (y'0min～y′0max) Extracting three-dimensional point clouds falling into the range from all the three-dimensional point clouds of the track acquired by the three-dimensional acquisition system to form a point set s1And gather s 'by points'0From the set of points s according to a set decision threshold for reference1Points which do not meet the requirement of the judgment threshold are removed to form a point set s shown in figure 102Particularly, a KD-tree structure is adopted to quickly traverse a computation point set s1Zhonghe Point set s'0The distance dis between the points in and recording the set of points s1Of each point is from the point set s'0The minimum distance dis of the points inminTo reject the minimum distance disminPoints greater than a distance threshold m, a set of points s1The remaining points in the set constitute a point set s2And the distance threshold m is a determination threshold.
Then set the points s0And set of points s2Generating a two-dimensional image template model0And a two-dimensional image in plan view0Set points s0Generating a two-dimensional overlook image and establishing a two-dimensional image template model0Then, recording the area a of the selected key measuring point0In template model0Position (x) ina0min～xa0max，ya0min～ya0max)；
Then set the points s2Generating a two-dimensional image of an overhead view0Will image0And model0Matching image templates, and obtaining a two-dimensional transformation matrix according to template matching1For the area a of the key measuring point0A is obtained by conversion operation0' region, a0' region, i.e. region of key measurement points, is set of points s2The position of (1); that is, a two-dimensional image template model is applied0And a two-dimensional image in plan view0Matching image templates and modeling two-dimensional image templates0The key point area in (1) is transformed to a matched overlook two-dimensional image through a transformation matrix based on a two-dimensional image matching algorithm0The corresponding positions in the image are shown in fig. 11, the key point areas are obtained by manually marking the key point areas in the template according to the prior threshold or experience, the key point coordinates in the acquired data can be accurately found by simultaneously transforming the matrix to rotate and translate, the secondary accurate registration is completed, and the overlook two-dimensional image is obtained0The region of the key measuring point of the elastic strip in the middle is directly calculated to obtain a point set s2In (A) of0' height average of area, relative height h of key measuring point can be obtained1。
And preferably the region of critical measurement points is located in a portion of the fastener in which the spring strip is one of the component parts of the fastener, the critical points being located in the spring strip of the fastener.
The fastener reference point positioning step, as shown in fig. 12, is to obtain the overlook two-dimensional image in the fastener key measuring point positioning step0The area of the key measuring point of the elastic strip is longitudinally expanded, and the size of the longitudinally expanded key point area is a1[xa0min～xa0max，(ya0min-n)～(ya0max+n)]And n is a fixed length selected in the template according to the prior threshold. Dividing the longitudinally expanded key measuring point region into i parts by adopting density-based method clustering (DBSCAN), and respectively calculating the average height h of each partiaveThe lowest average height portion is the fastener reference point region, which has an average height h'iaveI.e. the average height h of the reference point area of the insulating block2And whether the cable is loosened or not can be judged through the height difference between the key measuring point and the insulating block.
Specifically, the fastener looseness judging step is to directly calculate the overlook two-dimensional image obtained in the fastener key measuring point positioning step0Height average h of fastener key point area in1H is to be1H in the step of locating the fastener reference point2Calculating difference to obtain height difference delta h between the key point area and the reference point areaMeasuringCompare Δ h, as in FIG. 13MeasuringA standard value Δ h of the distanceStandard of meritWhether the difference is greater than the threshold value U or not, so as to judge whether the fastener is loosened or not and determine the standard value delta hStandard of meritDetermining the distance between the key point area of the standard fastener and the insulating block according to the standard design value of the fastener; the threshold U is an acceptable fastener loosening range, and is set according to the operating environment.
Claims (10)
1. The fastener looseness detection method based on the combination of the three-dimensional point cloud and the two-dimensional image processing technology is characterized by comprising the following steps of:
positioning the steel rail: obtaining three-dimensional point cloud from a three-dimensional acquisition system, and calculating a threshold height range (z) of the point cloud according to the rail heightrailmin～zrailmax) Screening steel rail point clouds and carrying out density clustering on the steel rail point clouds to obtain an external cube of the steel rail point clouds;
a fastener positioning step: with xmin-T～xmax-TThe point cloud containing the fastener is intercepted from the external cube, wherein T is the transverse distance between the outer side of the fastener and the rail surface; according to the height range (h) of the fastenermin～hmax) Screening the point cloud containing the fasteners to obtain a fastener set point cloud; then the fastener set point cloud and the template point cloud s generated by the standard fastener are processed0Performing template matching and obtaining the template point cloud s0To the translation and rotation transformation matrix of each fastener, and point cloud s of the template0The translation and the rotation are carried out,recording the point cloud after translation and rotation as s'0；
Positioning the key points of the elastic strips: extracting the current fastener point cloud s from the fastener set point cloud according to the point cloud horizontal distribution range of each fastener1(ii) a Calculating the current fastener point cloud s1And corresponding point cloud s'0The spatial distance between the point(s) and the point(s) is eliminated1Points with intermediate space distance not meeting threshold value constitute point cloud s2(ii) a A point cloud s0And point cloud s2Generating a two-dimensional image template model0And a two-dimensional image in plan view0Template model of two-dimensional image0And a two-dimensional image in plan view0Image template matching and two-dimensional image template model extraction0To look down two-dimensional image0And transforming the two-dimensional image template model0The key point area of the elastic strip is mapped to the matched overlook two-dimensional image through the transformation matrix0Obtaining a two-dimensional image of the overlook view at the corresponding position0The key point area of the elastic strip; from a point cloud s2Extracting the height average value of the area of the key point of the elastic strip to obtain the relative height h of the key point of the elastic strip1；
Positioning a fastener reference point: longitudinally expanding the key point area of the elastic strip to obtain a point cloud s2The point cloud of the area is intercepted, the area is divided into i parts by adopting a density clustering method, and the average height h of each part is respectively obtainediaveTaking the lowest average height h'iaveAverage height h as reference point of insulating block2；
Judging the loosening of the fastener: relative height h of spring strip key point1Average height h from reference point of insulating block2Making difference to obtain the height difference delta h between the key point of the elastic bar and the reference point of the insulating blockMeasuringAccording to Δ hMeasuringAnd judging whether the fastener is loosened or not if the threshold value is exceeded.
2. The fastener looseness detection method based on the combination of the three-dimensional point cloud and the two-dimensional image processing technology as claimed in claim 1, wherein: in the fastener positioning step, the T distance may be set to be generally 100 to 200mm, preferably 150 mm.
3. The method for detecting fastener looseness based on the combination of the three-dimensional point cloud and the two-dimensional image processing technology as claimed in claim 1, wherein in the fastener positioning step, the fastener matching is performed in the fastener set point cloud based on a point cloud template matching algorithm of a Fast Point Feature Histogram (FPFH) descriptor, and specifically, the method comprises the following steps:
step 1, selecting n sampling points from a cloud P to be registered, wherein the distance between the sampling points is greater than a preset minimum distance threshold value d;
step 2, one or more points with similar FPFH characteristics to the sampling points in the point cloud P are searched in the target point cloud Q, and one point is randomly selected from the similar points to serve as a one-to-one corresponding point of the point cloud P in the target point cloud Q;
step 3, calculating a rigid body transformation matrix between corresponding points, and then judging the performance of the current registration transformation by solving a distance error sum function after the corresponding points are transformed;
the translational and rotational change processing is specifically a three-dimensional point coordinate point set s of a fastener template matched with a fastener in a three-dimensional point cloud0By translational and rotational variation matrices matrix0(tx,ty,tz1, alpha, beta, lambda) is subjected to translational and rotational change processing to obtain a three-dimensional point coordinate point set s 'of a fastener, corresponding to and matched with the fastener template, in the three-dimensional point cloud of the fastener area'0Wherein (t)x，ty，tzAnd 1) is a translation parameter, and the (alpha, beta, lambda) position is a rotation parameter.
4. The fastener looseness detection method based on the combination of the three-dimensional point cloud and the two-dimensional image processing technology, as claimed in claim 3, wherein:
firstly, the three-dimensional point coordinate (x) of the fastener template is determined by translation parameters0，y0，z0) The translation processing obtains translation position coordinates
And then rotating the translation position coordinate through the rotation parameters (alpha, beta, lambda) to obtain a position coordinate (x ') after translation and rotation'0，y′0，z′0) The point set of all three-dimensional point coordinates of the fastener template after translational rotation processing is the position coordinate point set of the fastener in the three-dimensional point cloud, which is recorded as s'0，
5. The fastener looseness detection method based on the combination of the three-dimensional point cloud and the two-dimensional image processing technology as claimed in claim 1, wherein: in the step of positioning the key points of the elastic strips, a KD-tree structure is adopted to quickly traverse the calculation point set s1Zhonghe Point set s'0The distance dis between the points in and recording the set of points s1Of each point is from the point set s'0The minimum distance dis of the points inminTo reject the minimum distance disminPoints greater than a distance threshold m, a set of points s1The remaining points in the set constitute a point set s2And the distance threshold m is a determination threshold.
6. The fastener looseness detection method based on the combination of the three-dimensional point cloud and the two-dimensional image processing technology, as claimed in claim 5, wherein: in the step of positioning the key points of the elastic strips, a point set s is set0Generating a two-dimensional overlook image and establishing a two-dimensional image template model0Then, recording the area a of the selected key measuring point0In template model0Position (x) ina0min～xa0max，ya0min～ya0max)；
Then set the points s2Generating a two-dimensional image of an overhead view0Will image0And model0Matching image templates, and obtaining a two-dimensional transformation matrix according to template matching1For the area a of the key measuring point0Transformation transportCalculating to obtain a0' region, a0' region, i.e. region of key measurement points, is set of points s2The position of (1);
direct computation of a set of points s2In (A) of0' height average of area, relative height h of key measuring point can be obtained1。
7. The fastener looseness detection method based on the combination of the three-dimensional point cloud and the two-dimensional image processing technology, as claimed in claim 6, wherein: the region of the key measurement point is located in a portion of a spring strip component of the fastener of which the spring strip is one of the components, and the key point is located in the spring strip of the fastener.
8. The fastener looseness detection method based on the combination of the three-dimensional point cloud and the two-dimensional image processing technology as claimed in claim 1, wherein: in the step of positioning the fastener reference point, the size of the longitudinally expanded key point area is a1[xa0min～xa0max，(ya0min-n)～(ya0max+n)]And n is a fixed length selected in the template according to the prior threshold.
9. A computer device, characterized by: comprising one or more processors, a memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-8 above.
10. A non-transitory machine-readable storage medium, characterized in that: stored with executable instructions that, when executed, cause the machine to perform the method of any of the preceding claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110579074.5A CN113469940B (en) | 2021-05-26 | 2021-05-26 | Fastener loosening detection method based on three-dimensional point cloud and two-dimensional image processing technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110579074.5A CN113469940B (en) | 2021-05-26 | 2021-05-26 | Fastener loosening detection method based on three-dimensional point cloud and two-dimensional image processing technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113469940A true CN113469940A (en) | 2021-10-01 |
| CN113469940B CN113469940B (en) | 2023-08-04 |
Family
ID=77871348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110579074.5A Active CN113469940B (en) | 2021-05-26 | 2021-05-26 | Fastener loosening detection method based on three-dimensional point cloud and two-dimensional image processing technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113469940B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114354618A (en) * | 2021-12-16 | 2022-04-15 | 浙江大华技术股份有限公司 | Method and device for detecting welding seam |
| CN115100109A (en) * | 2022-05-19 | 2022-09-23 | 南昌工程学院 | Method for detecting tightness state of rail elastic strip fastener |
| CN115830019A (en) * | 2023-02-14 | 2023-03-21 | 南京慧然科技有限公司 | Three-dimensional point cloud calibration processing method and device for steel rail detection |
| CN117635520A (en) * | 2023-03-20 | 2024-03-01 | 南昌工程学院 | Elastic strip fastener tightness detection method by fusing two-dimensional image and three-dimensional point cloud |
| CN117830199A (en) * | 2023-04-14 | 2024-04-05 | 南昌工程学院 | Comprehensive detection method for defects of track elastic strip fastener by fusing image and point cloud |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009210276A (en) * | 2008-02-29 | 2009-09-17 | Mitsubishi Heavy Ind Ltd | System and method for detecting loosening of fastening implement |
| CN106192634A (en) * | 2016-08-31 | 2016-12-07 | 武汉汉宁轨道交通技术有限公司 | A kind of railroad track elastic bar fastener condition automatic detection device and method |
| US20170372127A1 (en) * | 2016-06-24 | 2017-12-28 | Skusub LLC | System and Method for Part Identification Using 3D Imaging |
| CN108797241A (en) * | 2018-06-05 | 2018-11-13 | 成都精工华耀科技有限公司 | A kind of rail clip nut loosening detection method compared based on height |
| CN108830891A (en) * | 2018-06-05 | 2018-11-16 | 成都精工华耀科技有限公司 | A kind of rail splice fastener loosening detection method |
| CN110634122A (en) * | 2018-06-05 | 2019-12-31 | 成都精工华耀科技有限公司 | Fastener elastic strip displacement detection method |
| US20210027475A1 (en) * | 2018-03-23 | 2021-01-28 | University Of Kansas | Vision-based fastener loosening detection |
| CN112365461A (en) * | 2020-11-06 | 2021-02-12 | 北京格灵深瞳信息技术有限公司 | Fastener loosening identification method, system, terminal and storage medium |
-
2021
- 2021-05-26 CN CN202110579074.5A patent/CN113469940B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009210276A (en) * | 2008-02-29 | 2009-09-17 | Mitsubishi Heavy Ind Ltd | System and method for detecting loosening of fastening implement |
| US20170372127A1 (en) * | 2016-06-24 | 2017-12-28 | Skusub LLC | System and Method for Part Identification Using 3D Imaging |
| CN106192634A (en) * | 2016-08-31 | 2016-12-07 | 武汉汉宁轨道交通技术有限公司 | A kind of railroad track elastic bar fastener condition automatic detection device and method |
| US20210027475A1 (en) * | 2018-03-23 | 2021-01-28 | University Of Kansas | Vision-based fastener loosening detection |
| CN108797241A (en) * | 2018-06-05 | 2018-11-13 | 成都精工华耀科技有限公司 | A kind of rail clip nut loosening detection method compared based on height |
| CN108830891A (en) * | 2018-06-05 | 2018-11-16 | 成都精工华耀科技有限公司 | A kind of rail splice fastener loosening detection method |
| CN110634122A (en) * | 2018-06-05 | 2019-12-31 | 成都精工华耀科技有限公司 | Fastener elastic strip displacement detection method |
| CN112365461A (en) * | 2020-11-06 | 2021-02-12 | 北京格灵深瞳信息技术有限公司 | Fastener loosening identification method, system, terminal and storage medium |
Non-Patent Citations (5)
| Title |
|---|
| HAO CUI等: "Real-Time Geometric Parameter Measurement of High-Speed Railway Fastener Based on Point Cloud from Structured Light Sensors", 《SENSORS》, vol. 18, no. 11, pages 1 - 19 * |
| HAO SUN等: "Looseness Detection of Rail Fasteners Using MEMS Sensor and Power Spectrum Entropy", 《2018 IEEE 1ST INTERNATIONAL CONFERENCE ON MICRO/NANO SENSORS FOR AI, HEALTHCARE AND ROBOTICS(NSENS)》, pages 25 - 29 * |
| 代先星: "高速铁路扣件缺陷三维检测***集成与识别算法", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》, no. 2020, pages 033 - 3 * |
| 杨佳烁: "基于3D成像技术的铁路扣件检测研究与应用", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》, no. 2020, pages 033 - 112 * |
| 肖俊 等: "密度聚类与PCA的点云数据处理技术在高铁轨道检测中的应用", 《铁道标准设计》, vol. 64, no. 8, pages 37 - 42 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114354618A (en) * | 2021-12-16 | 2022-04-15 | 浙江大华技术股份有限公司 | Method and device for detecting welding seam |
| CN115100109A (en) * | 2022-05-19 | 2022-09-23 | 南昌工程学院 | Method for detecting tightness state of rail elastic strip fastener |
| CN115100109B (en) * | 2022-05-19 | 2023-04-18 | 南昌工程学院 | Method for detecting tightness state of rail elastic strip fastener |
| CN115830019A (en) * | 2023-02-14 | 2023-03-21 | 南京慧然科技有限公司 | Three-dimensional point cloud calibration processing method and device for steel rail detection |
| CN117635520A (en) * | 2023-03-20 | 2024-03-01 | 南昌工程学院 | Elastic strip fastener tightness detection method by fusing two-dimensional image and three-dimensional point cloud |
| CN117830199A (en) * | 2023-04-14 | 2024-04-05 | 南昌工程学院 | Comprehensive detection method for defects of track elastic strip fastener by fusing image and point cloud |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113469940B (en) | 2023-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113469940B (en) | Fastener loosening detection method based on three-dimensional point cloud and two-dimensional image processing technology | |
| CN108107444B (en) | Transformer substation foreign matter identification method based on laser data | |
| CN108489403B (en) | Rapid and fine evaluation method for joint attitude of surface mine slope rock mass based on three-dimensional laser scanning | |
| CN109050535B (en) | Rapid terrain condition identification method based on vehicle attitude | |
| CN112529844B (en) | Rock mass structural plane identification and information extraction method based on three-dimensional laser scanning | |
| CN112465948A (en) | Vehicle-mounted laser pavement point cloud rarefying method capable of retaining spatial features | |
| CN111179321B (en) | Point cloud registration method based on template matching | |
| CN103727930A (en) | Edge-matching-based relative pose calibration method of laser range finder and camera | |
| CN102750449B (en) | Point cloud linear feature extraction method based on substep three-dimensional space and feature dimension mapping | |
| CN102798362A (en) | Point cloud data-based method for estimating working allowance of casting | |
| CN111508073A (en) | Method for extracting roof contour line of three-dimensional building model | |
| CN113487722A (en) | Automatic concrete member detection method based on three-dimensional laser scanning method | |
| CN108830317B (en) | Rapid and fine evaluation method for joint attitude of surface mine slope rock mass based on digital photogrammetry | |
| CN108931206A (en) | Method for distinguishing is known for rail profile outlier detection and effective profile | |
| CN111968224A (en) | Ship 3D scanning point cloud data processing method | |
| CN115690184A (en) | Tunnel face displacement measurement method based on three-dimensional laser scanning | |
| CN115018249A (en) | Subway station construction quality evaluation method based on laser scanning technology | |
| CN116727691B (en) | Metal 3D printing method and system based on digital management | |
| CN112232248A (en) | Method and device for extracting plane features of multi-line LiDAR point cloud data | |
| CN112561989A (en) | Method for identifying hoisting object in construction scene | |
| CN112330604A (en) | Method for generating vectorized road model from point cloud data | |
| CN116681912A (en) | Rail gauge detection method and device for railway turnout | |
| CN101625763B (en) | Method for measuring similarity of spatial color histogram | |
| CN112833815B (en) | Laser-based house measurement and wall flatness detection method | |
| CN116385356A (en) | Method and system for extracting regular hexagonal hole features based on laser vision |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |