CN113155027A - Tunnel rock wall feature identification method - Google Patents
Tunnel rock wall feature identification method Download PDFInfo
- Publication number
- CN113155027A CN113155027A CN202110458537.2A CN202110458537A CN113155027A CN 113155027 A CN113155027 A CN 113155027A CN 202110458537 A CN202110458537 A CN 202110458537A CN 113155027 A CN113155027 A CN 113155027A
- Authority
- CN
- China
- Prior art keywords
- point
- point cloud
- rock wall
- cloud data
- tunnel
- 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
- 239000011435 rock Substances 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 title claims abstract description 66
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 55
- 239000010959 steel Substances 0.000 claims abstract description 55
- 239000013598 vector Substances 0.000 claims abstract description 35
- 238000005507 spraying Methods 0.000 claims abstract description 22
- 239000007921 spray Substances 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000001914 filtration Methods 0.000 claims description 66
- 238000010606 normalization Methods 0.000 claims description 12
- 238000013461 design Methods 0.000 claims description 8
- 230000000717 retained effect Effects 0.000 claims description 2
- 238000010845 search algorithm Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 3
- 238000010276 construction Methods 0.000 description 11
- 238000005259 measurement Methods 0.000 description 6
- 238000005422 blasting Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000005553 drilling Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 239000002002 slurry Substances 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a tunnel rock wall feature identification method, which is used for solving the problems of strong subjectivity and poor tunnel rock wall spraying effect of the existing artificial identification arch center. The method comprises the following steps: the method comprises the steps that a laser scanner is used for conducting three-dimensional scanning on a tunnel rock wall, and point cloud data containing tunnel rock wall feature information are obtained; processing the point cloud data by using a normal difference algorithm to obtain normal difference values of all point clouds to form a linear difference characteristic vector; dividing the line difference characteristic vectors into different clustering categories by using an European clustering method to realize the identification of the tunnel rock wall characteristic objects; and acquiring the three-dimensional coordinates of the identified tunnel rock wall features. The method realizes the classification of the tunnel rock wall steel arch and the accurate determination of the spatial position, and can guide the subsequent automatic guniting operation. The method can feed back to the upper computer of the wet spraying trolley, and is convenient for developers to make path planning of the boom frame and the spray gun of the wet spraying trolley according to the identified three-dimensional coordinates of the steel arch, thereby realizing subsequent automatic guniting operation.
Description
Technology neighborhood
The invention relates to the technical field of tunnel engineering construction, in particular to a tunnel rock wall feature identification method.
Background
The tunnel drilling and blasting construction adopts controlled blasting as an excavation method, after earth and stones are dug in a tunnel according to the designed size, the exposed rock wall of the tunnel is subjected to primary support, the stability of surrounding rocks is kept as much as possible, and a stable cavern is formed. In the tunnel drilling and blasting construction process, the existing primary support means mainly comprise bolting, laying a reinforcing mesh and erecting an arch frame. After the tunnel exposed rock wall is initially supported, an operator controls the wet spraying machine to perform spraying operation through a handle, the position of an arch frame is usually determined by artificial observation, and the handle is controlled to move an arm support and a spray gun to an area between two adjacent arch frames to perform concrete spraying operation. On the other hand, the covering thickness of the concrete on the surface of the steel arch frame is too large, and the concrete needs to be manually shoveled in the later period, so that the subsequent construction process cannot be carried out on time. Therefore, how to accurately identify the position of the tunnel rock wall steel arch has important significance for ensuring the spraying quality, saving the spraying construction time and ensuring the good connection of the subsequent construction procedures.
At present, a three-dimensional laser scanning technology is used as a novel measurement technology, and is applied more and more widely in tunnel construction due to high measurement precision and high scanning speed. And carrying out panoramic scanning on the tunnel profile through a laser scanner to obtain three-dimensional point cloud data containing tunnel rock mass features. Based on three-dimensional point cloud data, most of research focuses on tunnel overbreak and underbreak measurement, and less focuses on tunnel rock wall feature identification to assist in the research of spraying operation. Therefore, the invention provides a tunnel rock mass feature identification method by using three-dimensional point cloud data, and subsequent automatic guniting operation is guided by accurately identifying the position coordinates of the primary support steel arch.
Disclosure of Invention
Aiming at the technical problems of strong subjectivity of the existing artificial identification arch and poor spraying effect of the tunnel rock wall, the invention provides a tunnel rock wall feature identification method, which realizes the classification and the accurate determination of the spatial position of the tunnel rock wall steel arch through point cloud data acquisition, non-target object elimination and steel arch point cloud identification, and can guide the subsequent automatic slurry spraying operation.
In order to achieve the purpose, the technical scheme of the invention is realized as follows: a tunnel rock wall feature identification method comprises the following steps:
the method comprises the following steps: the method comprises the steps that a laser scanner is used for conducting three-dimensional scanning on a tunnel rock wall, and point cloud data containing tunnel rock wall feature information are obtained;
step two: processing the point cloud data by using a normal difference algorithm to obtain normal difference values of all point clouds to form a linear difference characteristic vector;
step three: dividing the line difference characteristic vectors into different clustering categories by using an European clustering method to realize the identification of the tunnel rock wall characteristic objects;
step four: and acquiring the three-dimensional coordinates of the identified tunnel rock wall feature according to the tunnel rock wall feature identified in the third step.
Further, the tunnel rock wall feature is a steel arch; the identified three-dimensional coordinates of the steel arch are fed back to the upper computer of the wet spraying trolley, and the path planning of the boom and the spray gun of the wet spraying machine can be formulated, so that the automatic guniting operation is realized. The wet spraying trolley can be guided by identifying the steel arch on the rock wall of the tunnel, and automatic guniting is realized.
Further, the laser scanner in the first step is arranged at a position 10-15 m away from the tunnel rock wall steel arch, and a spherical prism target is placed at a position 5-10 m away from the laser scanner; the total station is erected in the tunnel to measure and absolutely position the laser scanner, and the earth absolute coordinate of the laser scanner in the tunnel is obtained. The point cloud data can be converted into a geodetic coordinate system according to the geodetic absolute coordinates, and the point cloud data can be conveniently processed.
Further, the types of point cloud data in the first step include an X coordinate, a Y coordinate, a Z coordinate, and a reflection intensity value of the point. And filtering the point cloud data according to the reflection intensity value.
Further, filtering the point cloud data in the first step to remove non-target objects, and then processing the point cloud data by using a normal difference algorithm; the method for filtering the point cloud data comprises the following steps:
step 1, designing a filtering threshold radius and calculating the distance from a central axis coordinate to point cloud data according to the central axis coordinate of the tunnel and the design radius of the primary support of the tunnelDistance of passageFiltering out point cloud number by comparison with filtering threshold radiusAccordingly, point cloud data after primary filtering is obtained; and filtering invalid point cloud data by primary filtering according to the distance and the filtering threshold radius.
Step 2, counting the reflection intensity values of all points in the point cloud data subjected to the primary filtering to obtain the reflection intensity range [ arch ] of the point cloud data corresponding to the surface of the steel arch frames,archl];
Step 3, according to the threshold value range [ archs,archl]Performing secondary point cloud filtering on the point cloud data after primary filtering: if the reflection intensity value of the point cloud data after the primary filtering is within the threshold range [ arch ]s,archl]Keeping the point cloud data after primary filtering; otherwise, the point cloud data of the concrete surface of the tunnel rock wall are removed, and the point cloud data after secondary filtering is obtained.
Further, the implementation method of the step 1 is as follows:
step 1.1, according to the central axis coordinate P of the tunnelc=(xc,yc,zc) Calculating distance to point cloud data P ═ (x, y, z):
step 1.2, calculating the radius R of a filtering threshold value according to the design radius R of the primary support of the tunnel1And a radius R2Respectively as follows:
wherein, both alpha and beta are filtering scale factors;
step 1.3, comparing the distance between the central axis coordinate of the tunnel and the point cloud data of the rock wall of the tunnelAnd a filtering threshold radius R1Radius R2If distanceThe point cloud data is retained; otherwise, the point cloud data is removed.
Further, the method for implementing the normal difference algorithm includes:
step 4, setting a first neighborhood radius r for estimating a normal vector of a point cloud in a tunnel rock wall1And a second neighborhood radius r2And r is1>r2;
And 5, utilizing the first neighborhood radius r for each point in the point cloud data after the secondary filtering1Calculate the normal vector n of each point1;
And 6, utilizing the radius r of a second neighborhood for each point in the point cloud data after the secondary filtering2Calculate the normal vector n of each point2;
Step 7, calculating and normalizing a normal difference value delta n of the same point under different neighborhood radiuses for each point in the point cloud data after secondary filtering to obtain a normal difference value of each point after normalization;
and 8, filtering the normal difference values of all the point clouds after normalization according to a preset normal difference threshold value to obtain the normal difference characteristic vector of the point clouds after filtering. The normal line difference algorithm can filter the point cloud data again, and the subsequent Euclidean clustering method can identify the point cloud corresponding to the steel arch conveniently.
Further, the normal vector n of each point is calculated in the step 51The method comprises the following steps:
s5.1, searching the first neighborhood radius r according to the coordinate of each point1All neighborhood points in the range form a neighborhood point cloud set M1;
S5.2, calculating a neighborhood point cloud set M1Center point coordinate center of1The coordinates of (a):
wherein ,set M for neighborhood point clouds1Point of (2) center point coordinatesi=(xi,yi,zi) Set M for neighborhood point clouds1The three-dimensional coordinates of the ith point in the point, M is a neighborhood point cloud set M1The number of inner point clouds, i ═ 1, 2.., m;
Further, the solution vector n in step 6 is solved2The method comprises the following steps:
s6.1, searching a second neighborhood radius r according to the coordinate of each point2All neighborhood points in the range form a neighborhood point cloud set M2;
S6.2, calculating a neighborhood point cloud set M2Center point coordinate center of2The coordinates of (a):
wherein ,set M for neighborhood point clouds2Point of (2) center point coordinatesj=(xj,yj,zj) Set M for neighborhood point clouds2The three-dimensional coordinates of the jth point in the neighborhood cloud set M is n2The number of inner point clouds, j ═ 1, 2.., n;
Further, the normal differential value Δ n isSaid normal differential value beingWhere | | represents the norm of the normal difference value Δ n.
Further, the method for filtering the normal difference values of all the point clouds after normalization in step 8 includes: according to a preset normal differential threshold value delta nthresholdIf the normal line difference value delta n of the point cloud after normalizationnormalize>=ΔnthresholdIf yes, the normal differential value is reserved; otherwise, the normal differential value is removed; and vectors formed by the normal differential values of all the point clouds after filtering are normal differential feature vectors.
Further, the method for implementing the euclidean clustering method comprises the following steps:
step (3.1): according to the normal differential value of the filtered point cloud, randomly selecting the normal differential value corresponding to p points as an initialization clustering center ClustertRespectively finding k normal differential values to each initialized Cluster center through a neighbor search algorithmtThe closest point; wherein t is 1,2, p;
step (3.2): according to a given distance threshold dthresholdCalculating k normal differential values to corresponding initialized Cluster centerstIf the distance of the normal line difference value is less than a set threshold dthresholdThen cluster to cluster set Qt;
Step (3.3): if the cluster set QtIf the number of the internal point clouds is not increased any more, finishing the clustering process; otherwise, the initialized cluster center point needs to be updated, and the cluster set Q is selectedtAs a cluster center, the step S5.5.3 is repeated until the cluster set Q is reachedtUntil the number of point clouds no longer increases. And clustering the point cloud data by using the European clustering method to obtain different clustering categories.
Further, the method for acquiring the three-dimensional coordinates in the fourth step comprises the following steps: collecting Q according to clustered clusterstAcquiring point cloud data sets corresponding to different steel arches, namely, different clustering categories correspond to different steel arches, and each clustering set QtThree comprising steel arch frameDimensional coordinate information.
Compared with the prior art, the invention has the beneficial effects that: according to the three-dimensional coordinates and the reflection intensity of the point cloud, the rapid filtering of the point cloud data of the steel arch on the rock wall of the tunnel is realized by utilizing the threshold filtering radius and the reflection intensity range of the steel arch; by extracting the normal line difference characteristics from the filtered point cloud data of the steel arch of the tunnel rock wall, the position of the steel arch of the tunnel rock wall can be accurately identified. In addition, the three-dimensional coordinates of the tunnel rock wall steel arch identified by the invention can be fed back to the wet spraying trolley upper computer, so that developers can conveniently make path planning of a boom and a spray gun of the wet spraying machine according to the identified three-dimensional coordinates of the steel arch, and the subsequent automatic guniting operation is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart of the present invention.
Fig. 2 is a diagram illustrating the recognition effect of the steel arch of the tunnel rock wall in the embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the protection scope of the present invention.
As shown in fig. 1, a method for identifying a feature of a tunnel rock wall includes the following steps:
s1, a laser scanner is placed at a distance of 15m from the tunnel wall steel arch, and a spherical prism target is placed at a distance of 6m from the laser scanner.
The laser scanner is used for measuring point cloud data of a tunnel rock wall, a spherical prism is used as a target, the target is looked at through the total station, an azimuth angle and a distance between the current survey station and the target are determined, and positioning is achieved.
And S2, erecting a total station in the tunnel to measure and absolutely position the laser scanner before the measurement operation of the laser scanner, so as to acquire the geodetic absolute coordinates of the laser scanner in the tunnel.
The method comprises the steps of sighting a spherical prism near a laser scanner through a total station, determining an azimuth angle and a distance between a current measuring point and a target, and performing coordinate conversion by combining a known coordinate, the azimuth angle and the distance of a target point to realize absolute positioning, namely acquiring an absolute coordinate of the laser scanner near the measuring point. The function of acquiring the geodetic absolute coordinates is to convert the point cloud data acquired by the laser scanner into a geodetic coordinate system.
And S3, performing three-dimensional panoramic scanning on the tunnel rock wall through the laser scanner to obtain point cloud data containing tunnel rock wall steel arch information.
The types of the point cloud data acquired in step S3 are an X coordinate, a Y coordinate, a Z coordinate, and a reflection intensity value of the point.
And S4, filtering the acquired original point cloud data according to the axle wire coordinate of the tunnel and the design radius of the primary support of the tunnel, and removing non-target objects such as air pipes, construction trolleys, field personnel and the like in the tunnel.
The specific implementation steps of the method for filtering point cloud data are as follows:
s4.1, calculating a radius R of a filtering threshold value according to the axle wire coordinate of the tunnel and the design radius R of the primary support of the tunnel provided by the tunnel construction party1Radius R2And the distance between the central axis coordinate and the original point cloud dataDistance of passageComparison with a Filter threshold radiusFiltering point cloud data, wherein the point cloud data are used for eliminating non-target objects such as air pipes, construction trolleys and field personnel outside the rock wall of the tunnel to obtain point cloud data after primary filtering; the method comprises the following specific steps:
s4.1.1, according to the central axis coordinate P of the tunnelc=(xc,yc,zc) And (3) calculating the distance between the central axis coordinate of the tunnel and the original point cloud data of the tunnel rock wall with the original point cloud data P being (x, y, z):
s4.1.2, calculating the radius R of the filtering threshold value according to the design radius R of the tunnel preliminary bracing and a certain scale factor1And a radius R2Respectively as follows:
wherein alpha and beta are both filtering scale factors, alpha is usually set to be 0.7-0.9, and beta is usually set to be 1.1-1.3.
S4.1.3, by comparing the distance between the central axis coordinates of the tunnel and the original point cloud data of the tunnel rock wallAnd a filtering threshold radius R1Radius R2If, ifThe original point cloud data is reserved; otherwise, the point cloud data is regarded as invalid point cloud data and is removed.
S4.2, counting the reflection intensity values of all points in the point cloud data after primary filtering, and counting the reflection intensity range [ wall ] of the tunnel rock wall, namely the tunnel concrete wall surface corresponding to the point cloud data according to the principle that the reflection intensities of the laser on the surfaces of different objects are differents,walll]The reflection intensity range of the point cloud data corresponding to the surface of the steel arch frame [ archs,archl]。
Counting the reflection intensity range of the tunnel rock walls,walll]The method is used for distinguishing the difference of point cloud intensity between non-target objects and target objects. The method comprises the steps of drawing intensity distribution of point cloud data after primary filtering, selecting point cloud data corresponding to a steel arch frame in a man-machine interaction mode, and determining intensity lower limit arch corresponding to the arch frame point cloud datasUpper limit of archlThereby obtaining a reflection intensity range [ archs,archl]。
S4.3, according to the threshold range [ arch ] of the reflection intensity of the surface of the steel arch frames,archl]Carrying out secondary point cloud filtering: if the reflection intensity value of the point cloud data is between [ archs,archl]If yes, point cloud data are reserved; and otherwise, the object is regarded as a non-target object, point cloud data of the concrete surface of the tunnel rock wall are removed, and point cloud data of the steel arch of the tunnel rock wall after secondary filtering are obtained.
S5, according to the point cloud data of the tunnel rock wall steel arch after secondary filtering, recognizing the tunnel rock wall steel arch by using a normal differential algorithm, and acquiring the three-dimensional coordinates of the recognized tunnel rock wall steel arch, wherein the specific steps are as follows:
s5.1, setting a larger neighborhood radius r for estimating a point cloud normal vector in a tunnel rock wall1Smaller neighborhood radius r2Larger neighborhood radius r1The radius r of a small neighborhood is usually set to be 30-402The setting is 10-20.
S5.2, for each point in the point cloud data after the secondary filtering, utilizing a larger neighborhood radius r1Calculate the normal vector n of each point1The method comprises the following specific steps:
s5.2.1, according to the coordinate of each point and the radius r of a larger neighborhood1Search neighborhood radius r1All neighborhood points in the range form a neighborhood point cloud set M1;
S5.2.2, according to the point cloud collection M1Calculating a neighborhood point cloud set M1Center point coordinate center of1:
wherein ,set M for neighborhood point clouds1Point of (2) center point coordinatesi=(xi,yi,zi) Set M for neighborhood point clouds1The three-dimensional coordinates of the ith point in the point, M is a neighborhood point cloud set M1The number of inner point clouds, i ═ 1, 2.
S5.2.3 knowing the coordinates center of all points and the center point in the neighborhood of the point cloud1Solution vector n1Convertible to looking for a normal vector n1And (3) enabling the distribution of projection points of all neighborhood points in the direction to be most concentrated, namely solving a minimization problem:
solving the minimization problem by using a least square method to obtain a normal vector n1。
S5.3, for each point in the point cloud data after the secondary filtering, utilizing the smaller neighborhood radius r2Calculate the normal vector n of each point2The method comprises the following specific steps:
s5.3.1, according to the coordinates of each point and the radius r of the smaller neighborhood2Searching all neighborhood points in the neighborhood radius range to form a neighborhood point cloud set M2。
S5.3.2, collecting M point clouds according to the neighborhood point2Calculating a neighborhood point cloud set M2Center point coordinate center of2:
wherein ,set M for neighborhood point clouds2Point of (2) center point coordinatesj=(xj,yj,zj) Set M for neighborhood point clouds2The three-dimensional coordinates of the jth point in the neighborhood, n is the set M of the point2The number of inner point clouds, j ═ 1, 2.
S5.3.3 knowing the coordinates center of all points and the center point in the neighborhood of the point cloud2Solution vector n2Convertible to seeking a normal n2So that all neighborhood points are in the direction n2The distribution of the projection points on the surface is most concentrated:
s5.4, calculating normal difference value delta n of the same point under different neighborhood radiuses for each point in the point cloud data after secondary filtering, and normalizing to obtain the normal difference value delta n of each point after normalizationnormalize:
Wherein, | | | represents the norm of the normal difference value Δ n, i.e., the magnitude of the normal difference value Δ n, and is used for normalization processing.
S5.5, according to a preset normal differential threshold value delta nthresholdFiltering the normal differential values of all the point clouds after normalization to obtain the normal differential values of the point clouds after filtering, and identifying the point clouds corresponding to the steel arch by using an Euclidean clustering method, which comprises the following specific steps:
s5.5.1, according to the preset normal differential threshold value delta nthresholdIf the normal line difference value delta n of the point cloud after normalizationnormalize>=ΔnthresholdIf yes, the corresponding normal differential value is reserved; otherwise, the corresponding normal differential value is eliminated.
S5.5.2, randomly selecting the normal difference value corresponding to p points in the space as the Cluster center of initialization according to the normal difference value of the filtered point cloudtRespectively finding k normal differences by a neighbor search algorithmScore to each initialized Cluster center ClustertThe closest point. Wherein t is 1,2, p.
S5.5.3, according to a given distance threshold dthresholdCalculating k normal differential values to corresponding initialized Cluster centerstIf the distance of the k normal differential values is less than a set threshold dthresholdThen cluster to cluster set Qt,t=1,2,···,p;
S5.5.4 if the set Q of clusterstIf the number of the internal point clouds is not increased any more, finishing the clustering process; otherwise, the initialized cluster center point needs to be updated, and the cluster set Q is selectedtAs a cluster center, the step S5.5.3 is repeated until the cluster set Q is reachedtUntil the number of point clouds no longer increases.
S5.5.5, collecting the point clouds Q according to the clusterstAnd acquiring point cloud data sets corresponding to different steel arches, namely, different clustering types correspond to different steel arches, and each clustering set comprises three-dimensional coordinate information of the steel arch.
Calculating the distance d from each filtered normal differential value to the residual normal differential value in the normal differential feature vector; according to a given distance threshold dthresholdThe normal difference feature vectors are divided into different cluster categories, i.e. different steel arches, by the distance d, and the different cluster categories are distinguished by different colors. And searching and identifying the three-dimensional coordinates of the steel arch according to indexes of different clustering categories. Visualization of the steel arch recognition result, different colors are adopted to distinguish the clustered arch information, and field operators can conveniently and visually check the information, as shown in fig. 2.
And S6, feeding back the identified three-dimensional coordinates of the tunnel rock wall steel arch to the wet spraying trolley upper computer, and making a path plan of a boom and a spray gun of the wet spraying machine by an operator according to the identified three-dimensional coordinates of the steel arch to realize subsequent automatic guniting operation.
The method comprises the following steps: placing a laser scanner at a position 10-15 m away from a tunnel rock wall steel arch frame, and placing a spherical prism target at a position 5-10 m away from the scanner; before the measurement operation of the laser scanner, erecting a total station to carry out measurement and absolute positioning on the total station; performing three-dimensional panoramic scanning on the tunnel rock wall by using a scanner to obtain point cloud data containing tunnel rock wall steel arch information; filtering the original point cloud data according to the central axis coordinate of the tunnel and the design radius of the primary support of the tunnel, and removing non-target objects such as air pipes, construction trolleys, field personnel and the like in the tunnel; according to the filtered point cloud data of the tunnel rock wall steel arch, recognizing the tunnel rock wall steel arch by using a normal differential algorithm, and acquiring a three-dimensional coordinate of the tunnel rock wall steel arch; and feeding back the three-dimensional coordinates of the identified tunnel rock wall steel arch to an upper computer of the wet spraying trolley, and developing personnel can make path planning of an arm support and a spray gun of the wet spraying machine according to the three-dimensional coordinates of the identified steel arch so as to realize subsequent automatic guniting operation.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (13)
1. A tunnel rock wall feature identification method is characterized by comprising the following steps:
the method comprises the following steps: the method comprises the steps that a laser scanner is used for conducting three-dimensional scanning on a tunnel rock wall, and point cloud data containing tunnel rock wall feature information are obtained;
step two: processing the point cloud data by using a normal difference algorithm to obtain normal difference values of all point clouds to form a linear difference characteristic vector;
step three: dividing the line difference characteristic vectors into different clustering categories by using an European clustering method to realize the identification of the tunnel rock wall characteristic objects;
step four: and acquiring the three-dimensional coordinates of the identified tunnel rock wall feature according to the tunnel rock wall feature identified in the third step.
2. The method for identifying tunnel rock wall features of claim 1, wherein the tunnel rock wall features are steel arches; the identified three-dimensional coordinates of the steel arch are fed back to the upper computer of the wet spraying trolley, and the path planning of the boom and the spray gun of the wet spraying machine can be formulated, so that the automatic guniting operation is realized.
3. The method for identifying the characteristic objects of the tunnel rock wall as claimed in claim 2, wherein the laser scanner in the first step is arranged at a position 10-15 m away from the steel arch of the tunnel rock wall, and a spherical prism target is placed at a position 5-10 m away from the laser scanner; the total station is erected in the tunnel to measure and absolutely position the laser scanner, and the earth absolute coordinate of the laser scanner in the tunnel is obtained.
4. The tunnel rock wall feature identification method according to claim 2 or 3, wherein the type of point cloud data in the first step comprises X coordinate, Y coordinate, Z coordinate and reflection intensity value of the point.
5. The tunnel rock wall feature identification method according to claim 4, wherein the point cloud data in the first step is filtered to remove non-target objects and then processed by using a normal difference algorithm; the method for filtering the point cloud data comprises the following steps:
step 1, designing a filtering threshold radius and calculating the distance from a central axis coordinate to point cloud data according to the central axis coordinate of the tunnel and the design radius of the primary support of the tunnelDistance of passageComparing the filtered point cloud data with the filtering threshold radius to filter the point cloud data to obtain point cloud data after primary filtering;
step 2, counting the reflection intensity values of all points in the point cloud data subjected to the primary filtering to obtain the reflection intensity range [ arch ] of the point cloud data corresponding to the surface of the steel arch frames,archl];
Step 3, according to the threshold value range [ archs,archl]Performing secondary point cloud filtering on the point cloud data after primary filtering: if the reflection intensity value of the point cloud data after the primary filtering is within the threshold range [ arch ]s,archl]Keeping the point cloud data after primary filtering; otherwise, the point cloud data of the concrete surface of the tunnel rock wall are removed, and the point cloud data after secondary filtering is obtained.
6. The method for identifying the features of the tunnel rock wall as claimed in claim 4, wherein the implementation method of the step 1 is as follows:
step 1.1, according to the central axis coordinate P of the tunnelc=(xc,yc,zc) Calculating distance to point cloud data P ═ (x, y, z):
step 1.2, calculating the radius R of a filtering threshold value according to the design radius R of the primary support of the tunnel1And a radius R2Respectively as follows:
wherein, both alpha and beta are filtering scale factors;
7. The tunnel rock wall feature identification method according to claim 5 or 6, wherein the normal difference algorithm is implemented by:
step 4, setting a first neighborhood radius r for estimating a normal vector of a point cloud in a tunnel rock wall1And a second neighborhood radius r2And r is1>r2;
And 5, utilizing the first neighborhood radius r for each point in the point cloud data after the secondary filtering1Calculate the normal vector n of each point1;
And 6, utilizing the radius r of a second neighborhood for each point in the point cloud data after the secondary filtering2Calculate the normal vector n of each point2;
Step 7, calculating and normalizing a normal difference value delta n of the same point under different neighborhood radiuses for each point in the point cloud data after secondary filtering to obtain a normal difference value of each point after normalization;
and 8, filtering the normal difference values of all the point clouds after normalization according to a preset normal difference threshold value to obtain the normal difference characteristic vector of the point clouds after filtering.
8. The method for identifying tunnel rock wall features of claim 7, wherein the normal vector n of each point is calculated in the step 51The method comprises the following steps:
s5.1, searching the first neighborhood radius r according to the coordinate of each point1All neighborhood points in the range form a neighborhood point cloud set M1;
S5.2, calculating a neighborhood point cloud set M1Center point coordinate center of1The coordinates of (a):
wherein ,set M for neighborhood point clouds1Point of (2) center point coordinatesi=(xi,yi,zi) Set M for neighborhood point clouds1The three-dimensional coordinates of the ith point in the point, M is a neighborhood point cloud set M1The number of inner point clouds, i ═ 1, 2.., m;
9. The method of identifying tunnel rock wall features of claim 7, wherein the solution vector n in step 6 is determined2The method comprises the following steps:
s6.1, searching a second neighborhood radius r according to the coordinate of each point2All neighborhood points in the range form a neighborhood point cloud set M2;
S6.2, calculating a neighborhood point cloud set M2Center point coordinate center of2The coordinates of (a):
wherein ,set M for neighborhood point clouds2Point of (2) center point coordinatesj=(xj,yj,zj) Set M for neighborhood point clouds2The three-dimensional coordinates of the jth point in the neighborhood cloud set M is n2The number of inner point clouds, j ═ 1, 2.., n;
11. The method for identifying the tunnel rock wall features of claim 10, wherein the step 8 of filtering the normal differential values of all the point clouds after normalization comprises the following steps: according to a preset normal differential threshold value delta nthresholdIf the normal line difference value delta n of the point cloud after normalizationnormalize>=ΔnthresholdIf yes, the normal differential value is reserved; otherwise, the normal differential value is removed; and vectors formed by the normal differential values of all the point clouds after filtering are normal differential feature vectors.
12. The method for identifying the features of the tunnel rock wall according to claim 1 or 11, wherein the Euclidean clustering method is implemented by the following steps:
step (3.1): according to the normal differential value of the filtered point cloud, randomly selecting the normal differential value corresponding to p points as an initialization clustering center ClustertRespectively finding k normal differential values to each initialized Cluster center through a neighbor search algorithmtThe closest point; wherein t is 1,2, …, p;
step (3.2): according to a given distance threshold dthresholdCalculating k normal differential values to corresponding initialized Cluster centerstIf the distance of the normal line difference value is less than a set threshold dthresholdThen cluster to cluster set Qt;
Step (3.3): if the cluster set QtIf the number of the internal point clouds is not increased any more, finishing the clustering process; otherwise, the initialized cluster center point needs to be updated, and the cluster set Q is selectedtAs cluster center, and the step S5.5.3 is repeated until the cluster setQtUntil the number of point clouds no longer increases.
13. The method for identifying the features of the tunnel rock wall as claimed in claim 12, wherein the method for acquiring the three-dimensional coordinates in the fourth step is as follows: collecting Q according to clustered clusterstAcquiring point cloud data sets corresponding to different steel arches, namely, different clustering categories correspond to different steel arches, and each clustering set QtAnd the three-dimensional coordinate information of the steel arch is contained.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110458537.2A CN113155027B (en) | 2021-04-27 | 2021-04-27 | Tunnel rock wall feature identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110458537.2A CN113155027B (en) | 2021-04-27 | 2021-04-27 | Tunnel rock wall feature identification method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113155027A true CN113155027A (en) | 2021-07-23 |
CN113155027B CN113155027B (en) | 2023-05-26 |
Family
ID=76871260
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110458537.2A Active CN113155027B (en) | 2021-04-27 | 2021-04-27 | Tunnel rock wall feature identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113155027B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113884010A (en) * | 2021-12-07 | 2022-01-04 | 湖南联智科技股份有限公司 | Tunnel steel frame detection method |
WO2023015407A1 (en) * | 2021-08-09 | 2023-02-16 | 深圳市速腾聚创科技有限公司 | Method for identifying artifact point, terminal device, and computer-readable storage medium |
CN117974866A (en) * | 2024-03-29 | 2024-05-03 | 奇翼软件技术(大连)有限公司 | Space virtual entity dynamic updating method based on virtual simulation teaching |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105910556A (en) * | 2016-04-13 | 2016-08-31 | 中国农业大学 | Leaf area vertical distribution information extraction method |
CN110415259A (en) * | 2019-07-30 | 2019-11-05 | 南京林业大学 | A kind of shade tree point cloud recognition methods based on laser reflection intensity |
CN110866449A (en) * | 2019-10-21 | 2020-03-06 | 北京京东尚科信息技术有限公司 | Method and device for identifying target object in road |
CN111027484A (en) * | 2019-12-11 | 2020-04-17 | 中南大学 | Tunnel steel arch identification method based on three-dimensional imaging |
CN111369600A (en) * | 2020-02-12 | 2020-07-03 | 苏州大学 | Laser radar point cloud data registration method based on reference object |
CN111553292A (en) * | 2020-04-30 | 2020-08-18 | 南京工业大学 | Rock mass structural plane identification and occurrence classification method based on point cloud data |
CN111915662A (en) * | 2019-05-07 | 2020-11-10 | 北京京东尚科信息技术有限公司 | Three-dimensional laser point cloud data preprocessing method and device |
US10929694B1 (en) * | 2020-01-22 | 2021-02-23 | Tsinghua University | Lane detection method and system based on vision and lidar multi-level fusion |
-
2021
- 2021-04-27 CN CN202110458537.2A patent/CN113155027B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105910556A (en) * | 2016-04-13 | 2016-08-31 | 中国农业大学 | Leaf area vertical distribution information extraction method |
CN111915662A (en) * | 2019-05-07 | 2020-11-10 | 北京京东尚科信息技术有限公司 | Three-dimensional laser point cloud data preprocessing method and device |
CN110415259A (en) * | 2019-07-30 | 2019-11-05 | 南京林业大学 | A kind of shade tree point cloud recognition methods based on laser reflection intensity |
CN110866449A (en) * | 2019-10-21 | 2020-03-06 | 北京京东尚科信息技术有限公司 | Method and device for identifying target object in road |
CN111027484A (en) * | 2019-12-11 | 2020-04-17 | 中南大学 | Tunnel steel arch identification method based on three-dimensional imaging |
US10929694B1 (en) * | 2020-01-22 | 2021-02-23 | Tsinghua University | Lane detection method and system based on vision and lidar multi-level fusion |
CN111369600A (en) * | 2020-02-12 | 2020-07-03 | 苏州大学 | Laser radar point cloud data registration method based on reference object |
CN111553292A (en) * | 2020-04-30 | 2020-08-18 | 南京工业大学 | Rock mass structural plane identification and occurrence classification method based on point cloud data |
Non-Patent Citations (2)
Title |
---|
刘春晓等: "基于散乱点云特征提取算法研究", 《测绘与空间地理信息》 * |
陈向阳等: "欧式聚类算法支持下的点云数据分割", 《测绘通报》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023015407A1 (en) * | 2021-08-09 | 2023-02-16 | 深圳市速腾聚创科技有限公司 | Method for identifying artifact point, terminal device, and computer-readable storage medium |
CN113884010A (en) * | 2021-12-07 | 2022-01-04 | 湖南联智科技股份有限公司 | Tunnel steel frame detection method |
CN117974866A (en) * | 2024-03-29 | 2024-05-03 | 奇翼软件技术(大连)有限公司 | Space virtual entity dynamic updating method based on virtual simulation teaching |
Also Published As
Publication number | Publication date |
---|---|
CN113155027B (en) | 2023-05-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113155027A (en) | Tunnel rock wall feature identification method | |
CN110986878B (en) | Method for automatically extracting rail section based on mobile measurement system | |
CN108107444B (en) | Transformer substation foreign matter identification method based on laser data | |
CN111830528A (en) | Tower characteristic point automatic identification and inclination parameter automatic measurement method based on laser point cloud | |
CN109214994B (en) | Tunnel dense point cloud noise elimination method based on double control points | |
CN109934855A (en) | A kind of livewire work scene power components three-dimensional rebuilding method based on cloud | |
CN112396641B (en) | Point cloud global registration method based on congruent two-baseline matching | |
CN109285163B (en) | Laser point cloud based lane line left and right contour line interactive extraction method | |
CN112529044B (en) | Method for extracting and classifying railway contact network based on vehicle-mounted LiDAR | |
CN110986877B (en) | Railway engineering clearance detection method based on high-precision vehicle-mounted laser mobile measurement system | |
CN113255677B (en) | Method, equipment and medium for rapidly extracting rock mass structural plane and occurrence information | |
CN111815611A (en) | Round hole feature extraction method for rivet hole measurement point cloud data | |
CN111915517A (en) | Global positioning method for RGB-D camera in indoor illumination adverse environment | |
CN114419445A (en) | Tunnel surrounding rock information identification and extraction method based on three-dimensional laser scanning | |
CN114998212A (en) | Method and system for positioning steel belt drill hole of mine roadway roof based on laser scanner | |
CN115877400A (en) | Tunnel roof support steel belt drilling positioning method based on radar and vision fusion | |
CN117197677A (en) | Tropical rain forest arbor-shrub separation method based on laser radar point cloud data | |
CN116563377A (en) | Mars rock measurement method based on hemispherical projection model | |
CN116465327A (en) | Bridge line shape measurement method based on vehicle-mounted three-dimensional laser scanning | |
CN117854060B (en) | Tunnel rock body planar crack identification method and system based on deep learning | |
CN115854895A (en) | Non-contact stumpage breast diameter measurement method based on target stumpage form | |
CN117115390A (en) | Three-dimensional model layout method of power transformation equipment in transformer substation | |
CN115657049A (en) | Tunnel vehicle-mounted laser radar positioning and deviation rectifying method and system | |
CN114998395A (en) | Effective embankment three-dimensional data change detection method and system | |
CN108921896B (en) | Downward vision compass integrating dotted line characteristics |
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 |