CN109900338A - A kind of road surface pit slot volume measuring method and device - Google Patents
A kind of road surface pit slot volume measuring method and device Download PDFInfo
- Publication number
- CN109900338A CN109900338A CN201811589420.2A CN201811589420A CN109900338A CN 109900338 A CN109900338 A CN 109900338A CN 201811589420 A CN201811589420 A CN 201811589420A CN 109900338 A CN109900338 A CN 109900338A
- Authority
- CN
- China
- Prior art keywords
- pit slot
- dimensional
- dimensional point
- point cloud
- road
- 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
Landscapes
- Image Processing (AREA)
- Road Repair (AREA)
Abstract
The invention discloses a kind of road surface pit slot volume measuring method and devices, and road surface three-dimensional point cloud is split, and obtain pit slot area three-dimensional point cloud；The road pit slot area three-dimensional Dian Yunxiang plane domain is projected, the two-dimensional surface in pit slot region is obtained；Triangle segmentation is carried out to the two-dimensional surface in pit slot region, obtains the pit slot two-dimensional surface of multiple triangles；The pit slot two-dimensional surface of multiple triangles is obtained into multiple triangular prisms into three-dimensional space with the direction back projection perpendicular to road plane domain；The volume for calculating each triangular prism obtains the volume in pit slot region after summation；Volume measuring method provided by the invention, for the problem that the feature of pit slot point cloud misclosure, solves open pit slot cubing for the first time, three-dimensional point cloud precise restoration pit slot original physical form, error is smaller during algorithm process, therefore cubing accuracy with higher.
Description
Technical field
The present invention relates to road surface pit slot measurement method and devices, and in particular to a kind of road surface pit slot volume measuring method and dress
It sets.
Background technique
Road pit slot refers to due to road surface aging, sleet corrodes and vehicle be lost caused by road surface locally gather materials forfeiture and
The hollow of formation, this is the more serious pavement disease of one kind that road maintenance faces.Road pit slot not only causes to run to driving
It winnows with a dustpan uncomfortable, but also there are security risks, in the case that especially measurement is run at high speed on a highway, pit slot may cause
Serious traffic accident.
In the daily inspection management of highway and regularly in road surface pit slot information gathering process, it is several to obtain accurate pit slot
What information has valuable help to road upkeep construction operation.In future, the automation of maintenance of surface system inevitable trend, intelligence
Change, to improve efficiency, reduces maintenance cost, the pit slot volume road maintenance data important as one, are Intelligent curving equipments
The emphasis of concern.Accurate pit slot volume measuring method obtains road pit slot information to accurate, mentions for Intelligent road to maintain equipment
For precisely filling up volume foundation, there is important application value.
The existing some road surface pit slot automatic measurement techniques in market at present, can only detect the area and depth information of pit slot.
Due to the arbitrariness of pit slot shape, misclosure and scrambling, the three-D volumes information of pit slot, market can not be accurately obtained
On also carry out the volume of measurement road pit slot without good method.The accurate acquisition of road pit slot volume is automated in plant maintenance
And road fill up automatically in have a clear superiority.
Summary of the invention
The purpose of the present invention is to provide a kind of road surface pit slot volume measuring method and devices, to solve in the prior art
Measurement method and device the problem of can not obtaining accurate pit slot volume.
In order to realize above-mentioned task, the invention adopts the following technical scheme:
A kind of road surface pit slot volume measuring method, the road surface include road road plane domain and pit slot region, described
Method execute according to the following steps:
Step 1, the direction to be parallel to the road plane domain acquire road surface three-dimensional point cloud；
Step 2 is split the road surface three-dimensional point cloud, obtains pit slot area three-dimensional point cloud；
Step 3 projects the road pit slot area three-dimensional Dian Yunxiang plane domain direction, obtains the two of pit slot region
Dimensional plane；
Step 4 carries out triangle segmentation to the two-dimensional surface in the pit slot region, obtains the pit slot two dimension of multiple triangles
Plane；
Step 5, by the pit slot two-dimensional surface of multiple triangles with the direction perpendicular to the road plane domain
Back projection obtains multiple triangular prisms into three-dimensional space；
The height on three sides of the triangular prism is respectively three tops in the pit slot two-dimensional surface of the triangle obtained in step 4
Put the depth value of corresponding three three-dimensional points in the pit slot area three-dimensional point cloud before projecting in step 3；
Step 6, the volume for calculating each triangular prism, obtain the volume in pit slot region after summation.
Further, the step 2 specifically includes:
Step 21 carries out pretreatment operation to the road surface three-dimensional point cloud, obtains pretreated three-dimensional point cloud, described
Pretreatment operation include the down-sampled operation successively executed and filtering operation；
Step 22, according to the depth value size of three-dimensional point each in three-dimensional point cloud after pretreatment, by the depth value of three-dimensional point
Less than all three-dimensional point deletions of depth threshold, the three-dimensional point cloud of non-road plane domain is obtained, the depth threshold is pre- place
After reason twice of all three-dimensional point depth value average values in three-dimensional point cloud；
Step 23, in the three-dimensional point cloud of the non-road plane domain, using the maximum three-dimensional point of depth value as seed
Point obtains initial pit slot area three-dimensional point cloud using the method for region growing；
Step 24, using the method for Edge Search to all three-dimensional points in the initial pit slot area three-dimensional point cloud at
Reason obtains multiple three-dimensional point composition pit slot edges of regions；
Step 25, by three-dimensional point set all within the pit slot edges of regions, obtain the pit slot area three-dimensional
Point cloud.
Further, down-sampled operation is that voxel grid filters in the step 21.
Further, in the step 22, according to the depth value size of three-dimensional point each in three-dimensional point cloud after pretreatment,
The depth value of three-dimensional point is less than to all three-dimensional point deletions of depth threshold using RANSAC algorithm, obtains non-road plane domain
Three-dimensional point cloud.
Further, the method using Edge Search is to all three-dimensionals in the initial pit slot area three-dimensional point cloud
When point is handled, using a vertex of the initial pit slot area three-dimensional point cloud as three boundary points of starting, boundary point is utilized
Maximum angular principle successively obtains multiple three-dimensional point composition pit slot edges of regions.
Further, triangle point is carried out using two-dimensional surface of the Delaunay Triangulation Algorithm to the pit slot region
It cuts, obtains the pit slot two-dimensional surface of multiple triangles.
Further, triangle point is being carried out using two-dimensional surface of the Delaunay Triangulation Algorithm to the pit slot region
After cutting, after obtaining multiple triangle two-dimensional surfaces, three vertex and the pit slot area are deleted from multiple triangle two-dimensional surfaces
After the triangle two-dimensional surface of domain coincident, the two-dimentional pit slot plane of multiple triangles is obtained.
A kind of road surface pit slot volume measurement device, for realizing the road surface pit slot volume measuring method, the dress
It sets and obtains module, pit slot three-dimensional point cloud segmentation module and pit slot volume calculation module including road surface three-dimensional point cloud；
The road surface three-dimensional point cloud obtains module and connect with the pit slot three-dimensional point cloud segmentation module, for parallel
In the direction of the road plane domain, road surface three-dimensional point cloud is acquired；
The pit slot three-dimensional point cloud segmentation module and the pit slot volume calculation module, for the road surface three
Dimension point cloud is split, and obtains the pit slot area three-dimensional point cloud；
The pit slot volume calculation module is used to project the road pit slot area three-dimensional Dian Yunxiang plane domain,
Obtain the two-dimensional surface in pit slot region；
It is also used to carry out triangle segmentation to the two-dimensional surface in the pit slot region, obtains the pit slot two dimension of multiple triangles
Plane；
It is also used to the pit slot two-dimensional surface of multiple triangles with the direction perpendicular to the road plane domain
Back projection obtains multiple triangular prisms into three-dimensional space；
It is also used to calculate the volume of each triangular prism, the volume in pit slot region is obtained after summation.
Further, pit slot three-dimensional point cloud segmentation module and pit slot volume calculation module are that intelligent mobile is set
It is standby.
Further, the Intelligent mobile equipment is mobile phone.
The present invention has following technical effect that compared with prior art
1, pit slot volume measuring method in road surface provided by the invention is adopted when being split to pit slot region by filtering drop
The methods of sample eliminates mistake and redundant points cloud, simplifies the quantity of three-dimensional point in three-dimensional point cloud, effectively increases pit slot region point
Cut speed；
2, road surface pit slot volume measuring method and device provided by the invention utilize depth when being split to pit slot region
It spends threshold value and removes road plane domain, can quickly the approximate region of pit slot be split by retaining non-road plane domain, be reduced
The complexity of dividing method, improves splitting speed；
3, road surface pit slot volume measuring method and device provided by the invention are adopted first when being split to pit slot region
Initial pit slot region is obtained with Area generation method, reuses the method for Edge Search on this basis to obtain complete pit slot
The edge in region improves the integrality and accuracy of pit slot segmentation；
4, road surface pit slot volume measuring method and device provided by the invention utilize side when being split to pit slot region
Boundary's point maximum angular principle successively obtains multiple three-dimensional point composition pit slot edges of regions, further increases the accurate of pit slot segmentation
Property, good data basis is provided for the accurate calculating of pit slot volume；
5, road surface pit slot volume measuring method and device provided by the invention first will when calculating pit slot volume
Three-dimensional point cloud is mapped on two-dimensional surface, and back mapping returns in three-dimensional space again after being split to two-dimensional surface, compared to straight
Connect that the complexity being split to three-dimensional point cloud is low, the real-time of calculation method is high；
6, road surface pit slot volume measuring method and device provided by the invention are when calculating pit slot volume, using height
Precision three-dimensional point cloud measures pit slot three-D volumes, three-dimensional point cloud precise restoration pit slot original physical form, in algorithm process
Error is smaller in the process, therefore cubing accuracy with higher；
7, road surface pit slot volume measuring method and device provided by the invention are when calculating pit slot volume, for hole
The feature of slot point cloud misclosure, solves the problems, such as open pit slot cubing for the first time.
Detailed description of the invention
Fig. 1 is the flow chart of pit slot volume measuring method in road surface provided by the invention；
Fig. 2 is in one embodiment of the present of invention for rebuilding the left and right camera image when three-dimensional point cloud of road surface；
Fig. 3 is the road surface three-dimensional point cloud acquired in one embodiment of the present of invention；
Fig. 4 is the pit slot area three-dimensional point cloud for dividing acquisition in one embodiment of the present of invention；
Fig. 5 is the two-dimensional image that pit slot region is obtained in one embodiment of the present of invention；
Fig. 6 is the two-dimensional image in the pit slot region after the segmentation of one embodiment of the present of invention intermediate cam；
Fig. 7 is the image that a triangular prism is obtained in one embodiment of the present of invention；
Fig. 8 is the simulation pit slot image provided in one embodiment of the present of invention；
Fig. 9 is the road surface pit slot volume measurement device structure chart provided in one embodiment of the present of invention.
Specific embodiment
Three-dimensional point cloud: being made of multiple three-dimensional points, and each three-dimensional point has abscissa value, ordinate value and depth value,
Generally using the left camera lens of camera as coordinate origin, abscissa value, ordinate value and depth value are all positive values.
Boundary point maximum angular principle: in multiple neighbor points of a certain boundary point, boundary point is deposited with any one neighbor point
In angle (angle does not include other neighbor points), therefore there can be multiple angles, and difference pair between maximum two angles
Two point of proximity answered must be boundary point.
Delaunay Triangulation Algorithm: if a triangulation T of point set V only includes the side Delaunay, this three
Angle subdivision is known as Delaunay Triangulation, wherein two ends of Delaunay while for there are a circles by Delaunay
Point, circle is interior without any other point in point set V, can be divided into point set or image using Delaunay Triangulation Algorithm
Multiple triangles.
Embodiment one
A kind of road surface pit slot volume measuring method, the road surface include road road plane domain and pit slot region, such as Fig. 1
Shown, measurement method executes according to the following steps:
Step 1, the direction to be parallel to the road plane domain acquire road surface three-dimensional point cloud；
The road surface region containing recess is obtained using three-dimensional imaging devices such as binocular solid cameras first in this step
Three-dimensional point cloud, using the three-dimensional point cloud as the input of the measurement method provided in the present embodiment.
Notice that imaging device face plane is shot when shooting, and covers complete pit slot depressed range.
In the present embodiment, to the left and right camera image of binocular camera as shown in Figure 2, carry out what three-dimensional reconstruction acquired
Road surface three-dimensional point cloud is as shown in Figure 3.
Step 2 is split the road surface three-dimensional point cloud, obtains the pit slot area three-dimensional point cloud；
In this step, when being split to three-dimensional point cloud, existing method have Euclidean algorithm, kdTree algorithm with
And OcTree algorithm, but several algorithms are when facing road surface three-dimensional point cloud above, and since road surface itself is uneven, Er Qie
It therefore can include a large amount of noise in collected three-dimensional point cloud, when being split using dividing method in the prior art, meeting
It is not high to there is segmentation accuracy rate, causes road surface pit slot cubing inaccurate.
Optionally, the step 2 specifically includes:
Step 21 carries out pretreatment operation to the road surface three-dimensional point cloud, obtains pretreated three-dimensional point cloud, described
Pretreatment operation include the down-sampled operation successively executed and filtering operation；
Since the data volume that collected three-dimensional point cloud includes is larger, and contain noise, if directly handled, meeting
There is splitting speed is slow and segmentation effect is poor phenomenon, therefore in this step, three-dimensional point cloud is carried out after dimensionality reduction again first
Filtering.
Optionally, the step 21 executes according to the following steps:
Step 211, the method that the three-dimensional point cloud is filtered using voxel grid carry out it is down-sampled, obtain it is down-sampled after
Three-dimensional point cloud；
It is down-sampled to three-dimensional point cloud progress first, it is down-sampled to three-dimensional point cloud progress using the method for voxel grid filtering,
To reduce amount of redundant data, points cloud processing speed is improved, when filtering can keep details in the depth direction, reduce depth direction
Loss of detail.
Detailed process are as follows: a three-dimensional voxel grid is created by the three-dimensional point cloud of input, voxel grid is equivalent to space
The set of three-dimensional cube, then in each voxel, with the center of gravity of all the points in voxel come other points in approximate display voxel,
All the points finally just indicate that all the points cloud is dropped after all handling by voxel grid with a focus point in this way in the voxel grid
Sampled point cloud obtains the expression that accurate sampled point corresponds to curved surface.
Step 212, to it is described it is down-sampled after three-dimensional point cloud carry out straight-through filtering, filtered three-dimensional point is led directly in acquisition
Cloud；
In this step, the three-dimensional point cloud after down-sampled is filtered, using the method for straight-through filtering, particular by
Three-dimensional point cloud depth direction data area is set, such as between 0.8-1.2m, the point cloud except this range all will be as interference
Point removal.
Step 213 leads directly to filtered three-dimensional point cloud and carries out statistical filtering to described, the three-dimensional point that obtains that treated
Cloud.
In this step, to filtered three-dimensional point cloud is led directly to using statistical filtering method, each neighborhood of a point is carried out
One statistical analysis, and some non-compliant clouds are removed, reduce isolated redundant points cloud, neighbour of the statistical filtering to each point
Domain carries out a statistical analysis, and trims those points for not meeting established standards.Specifically, it uses in the present embodiment dilute
Outlier removing method is dredged, based on the calculating in input three-dimensional point cloud to the range distribution of point to neighbor point.To each three
Tie up point, calculate the average distance that it arrives itself all neighbor point, it is obtaining the result is that a Gaussian Profile, shape by mean value and
Standard deviation determines that three-dimensional point of the average distance except critical field (being defined by global distance average and variance) is to peel off
Point, and got rid of from three-dimensional point cloud.
Pit slot volume measuring method in road surface provided by the invention is gone when being split to pit slot region using depth threshold
Except road plane domain, can quickly the approximate region of pit slot be split by retaining non-road plane domain, reduce dividing method
Complexity, improve splitting speed.
Step 22, according to the depth value size of three-dimensional point each in three-dimensional point cloud after pretreatment, by the depth value of three-dimensional point
Less than all three-dimensional point deletions of depth threshold, the three-dimensional point cloud of non-road plane domain is obtained, the depth threshold is pre- place
After reason twice of all three-dimensional point depth value average values in three-dimensional point cloud；
In this step, plane domain acquisition, plane domain three are parallel to when obtaining due to three-dimensional point cloud
Depth value should be the same in dimension point cloud, by this feature, plane three-dimensional point cloud can be found.
It preferably, will using RANSAC algorithm according to the depth value size of three-dimensional point each in three-dimensional point cloud after pretreatment
The depth value of three-dimensional point is less than all three-dimensional point deletions of depth threshold, obtains the three-dimensional point cloud of non-road plane domain.
In this step, when extracting road plane using RANSAC algorithm, depth threshold is set, depth threshold is according to road
The thickness setting of plane, such as it to be partitioned into the road plane of 2mm depth, it will be in measurement method provided in this embodiment
Road plane nearby all the points in 2mm depth as road plane three-dimensional point, the step for be equivalent to three-dimensional point cloud in depth side
It is cut upwards, road plane is reamed.
It in this step, (include pit slot point by other non-flat portion point clouds while extracting planar point cloud
Cloud) it splits.Under normal circumstances, the interference due to noise and without matching error point cloud point can not propose complete at this time
Accurate pit slot not partial dot cloud, needs further to handle.
Therefore, before executing the step 23, first to the three-dimensional point cloud of the non-road plane domain using system
The mode of meter filtering carries out secondary filtering, obtains the three-dimensional point cloud of filtered non-road plane domain, will be described filtered
The three-dimensional point cloud of non-road plane domain is input in the step 23.
In this step, when secondary filtering again by the way of statistical filtering, filtering parameter is set, useless model is removed
Lesser isolated point cloud is enclosed, the three-dimensional point sum for including in certain distance by setting each cloud, if it is less than setting
Minimum three-dimensional point sum threshold value, then it is assumed that be isolated point cloud, if it is greater than the maximum three-dimensional point sum threshold value of setting, be considered as
Invalid three-dimensional point cloud.Such as three-dimensional point quantity around some three-dimensional point in 5 centimetres is counted, if statistical result is less than 500
It is a, then all three-dimensional points in 5 centimetres around the three-dimensional point and three-dimensional point are considered as isolated point cloud, if statistical result is greater than
50000 are considered as the Null Spot cloud cluster more than theoretical pit slot data volume, will also remove, in Fig. 3, beside maximum pit slot region
These small pit slot regions are removed in this step there are also some small pit slot regions, these small pit slot regions are just
It is isolated point cloud.
Step 23, in the three-dimensional point cloud of the non-road plane domain, using the maximum three-dimensional point of depth value as seed
Point obtains initial pit slot area three-dimensional point cloud using the method for region growing；
In this step, according to it is down-sampled when the depth threshold that sets as the distance threshold in the method for region growing,
Using the maximum three-dimensional point of depth value as starting point, the point within the scope of distance threshold is searched, is risen with what the point iteration newly searched was newly
Point, continues to search for, and is partitioned into pit slot edges of regions three-dimensional point until searching, and obtains initial pit slot area three-dimensional point cloud.
In order to improve the accuracy rate of segmentation, therefore initial pit slot area three-dimensional point cloud is carried out again in the present embodiment
Edge Search, to obtain the edge in complete pit slot region.
Step 24, using the method for Edge Search to all three-dimensional points in the initial pit slot area three-dimensional point cloud at
Reason obtains multiple three-dimensional point composition pit slot edges of regions；
In this step, the method for Edge Search can be depth threshold detection, method of gradient difference value threshold test etc.,
But these methods, since the edge of pit slot has gradient, are adopted when in face of pit slot region in road surface in the prior art
The edge that pit slot region good can not be all found with the method for existing threshold test leads to the inaccurate of pit slot region segmentation
Really, so that the calculating inaccuracy of pit slot volume.
Therefore a kind of iterative edge searching method constantly approached is provided in the present embodiment, by the initial pit slot area
One vertex of domain three-dimensional point cloud successively obtains multiple three-dimensional points using boundary point maximum angular principle and forms as start boundary point
Pit slot edges of regions.
Specifically, it executes according to the following steps:
Step I, boundary three-dimensional point set is emptied；
Step II, multiple neighbouring three-dimensional points around start boundary point are found using k nearest neighbor algorithm；
In this step, specifically using the start boundary point as the centre of sphere, using distance threshold as the radius of ball, selection is established
Sphere selects described three-dimensional point all in sphere as neighbouring three-dimensional point, obtains multiple neighbouring three-dimensional points, the distance
Threshold value is after secondary filtering twice of all three-dimensional point depth value average values in three-dimensional point cloud；
Step III, the angle each between neighbouring three-dimensional point and the start boundary point is calculated, multiple angle values are obtained；
Step IV, all angle values are arranged according to size descending, calculate the differential seat angle between two neighboring angle value,
Obtain multiple differential seat angles；
Step V, select maximum angle poor from all differential seat angles, the corresponding two angle values of maximum angle difference is corresponding
Two neighbouring three-dimensional points as two boundary three-dimensional points；
If step VI, boundary three-dimensional point set is combined into sky at this time, VIII is thened follow the steps；Otherwise VII is executed；
Step VII, the two boundary three-dimensional points obtained in judgment step V whether have one in the boundary three-dimensional point set
In conjunction；
If having one in the boundary three-dimensional point set, by another not side in the three-dimensional point set of boundary
After boundary's three-dimensional point is as new start boundary point, executed in step IX after placing into boundary three-dimensional point set；
If two boundary three-dimensional points, all in the boundary three-dimensional point set, selection is apart from start boundary point apart from most
A remote point is as new start boundary point；
Otherwise, two boundary three-dimensional points are put into the three-dimensional point set of boundary first, then calculate separately two boundary three-dimensionals
Angle value between point and the start boundary point, the maximum boundary three-dimensional point of selected angle value is as new start boundary point
Afterwards, step IX is executed；
Step IX, using new start boundary point as input, repeat step II to step IX, until this obtain it is new
Start boundary point is execution step behind a vertex of the initial pit slot area three-dimensional point cloud chosen when executing step II for the first time
X；
In the present embodiment, multiple three-dimensional points are successively obtained using boundary point maximum angular principle and form pit slot edges of regions,
The accuracy of pit slot segmentation is further increased, provides good data basis for the accurate calculating of pit slot volume.
Step X, it from all boundary three-dimensional points in the three-dimensional point set of boundary are extracted in initial pit slot area three-dimensional point cloud, obtains
Multiple three-dimensional points form pit slot edges of regions.
In step X, from being extracted in initial pit slot area three-dimensional point cloud in the three-dimensional point set of boundary after all boundary three-dimensional points,
Multiple boundary three-dimensional points at this time are sparse boundary three-dimensional points, directly obtain pit slot area three-dimensional point by sparse boundary three-dimensional point
If cloud, pit slot area three-dimensional point cloud can have noise, that is, divide the situation of inaccuracy, therefore in the present embodiment to all
Boundary three-dimensional point carries out denseization, obtains multiple three-dimensional point composition pit slot edges of regions.
In this step, denseization being carried out to all boundary three-dimensional points, the method for denseization can be the methods of interpolation,
But in the present embodiment, in order to improve the accuracy rate of denseization, enable the pit slot region after segmentation more complete and
Accurately, boundary denseization is that sparse boundary point is evolved into dense point cloud, and the boundary point on sparse line is also added
Into boundary point cloud.
Specifically, denseization is carried out to all boundary three-dimensional points according to the following steps in the present embodiment:
Step A, two adjacent boundary three-dimensional points are found from all boundary three-dimensional points respectively as endpoint and terminal；
Step B, using endpoint as the centre of sphere, using distance threshold as the radius of ball, selection sphere is established, will be owned in selection sphere
Three-dimensional point is used as neighbouring boundary three-dimensional point, obtains multiple neighbouring boundary three-dimensional points；
Distance threshold in this step is identical as the distance threshold in step II.
Step C, all neighbouring boundary three-dimensional points are calculated to the distance between the straight line being made of endpoint and terminal, are obtained more
The distance value of a neighbouring boundary three-dimensional point；
Step D, using the corresponding neighbouring boundary three-dimensional point of the distance value for being less than dense distance threshold as dense boundary three-dimensional point,
Multiple dense boundary three-dimensional points are obtained, dense distance threshold is the density value of three-dimensional point cloud after secondary filtering；
Step E, step A to step E is repeated until all boundary three-dimensional points are used as endpoint mistake, the multiple dense sides of acquisition
Boundary's three-dimensional point；
Step F, by all dense boundary three-dimensional points in conjunction with all boundary three-dimensional points, multiple three-dimensional point composition pit slots are obtained
Edges of regions.
Step 25, by three-dimensional point set all within pit slot edges of regions, obtain pit slot area three-dimensional point cloud.
Therefore, pit slot edges of regions is being made of dense boundary point and all boundary three-dimensional points of obtaining in step F
Edge takes out all three-dimensional points within the edge, including the edge, has obtained pit slot area three-dimensional point cloud.
In the present embodiment, to road surface three-dimensional point cloud as shown in Figure 3, pit slot point cloud in the road surface three-dimensional point cloud in Fig. 3
The sub-fraction in the three-dimensional point cloud of road surface is accounted for, but it can be seen that untreated three dimensional point cloud is in Fig. 3
It is very large, using the method for the Edge Search and edge denseization that are provided in the present embodiment, obtain as shown in Figure 4
Pit slot region, the edge in the pit slot region are to be made of dense three-dimensional boundaries point and three-dimensional boundaries point.
Pit slot volume measuring method in road surface provided by the invention is raw using region first when being split to pit slot region
Initial pit slot region is obtained at method, reuses the method for Edge Search on this basis to obtain the side in complete pit slot region
Edge, improves the integrality and accuracy of pit slot segmentation, and provides the method to denseization of sparse edge, to obtain
More accurate pit slot region.
If after being directly split to pit slot area three-dimensional point cloud, the volume of each section after dividing is asked to be added,
Data volume will lead to greatly very much that the measurement method speed of service is excessively slow, and entire measurement method does not have real-time, therefore in the present embodiment
In, first three-dimensional point cloud is projected to two-dimensional surface, Calculation Plane area yet further obtains volume.
Step 3 projects the road pit slot area three-dimensional Dian Yunxiang plane domain, and the two dimension for obtaining pit slot region is flat
Face；
In this step, the pit slot area three-dimensional point cloud being partitioned into is mapped to the two dimension of the X-Y using road plane as benchmark
Plane, coordinate origin are projection of the left camera photocentre of binocular camera in the plane of road.
In the present embodiment, coordinate of the three-dimensional point A in space is (x1, y1, z1), and coordinate of the three-dimensional point B in space is
(x2, y2, z2), coordinate of the three-dimensional point C in space is (x3, y3, z3), carries out projecting to be equivalent to road plane domain removing z-axis
Coordinate then obtains three two-dimensional points, and point A is (x1, y1) in the coordinate of two-dimensional surface, and vertex B is in the coordinate of two-dimensional surface
(x2, y2), vertex C are (x3, y3) in the coordinate of two-dimensional surface.
In the present embodiment, the two-dimensional image in the pit slot region of acquisition is as shown in Figure 5.
Step 4 carries out triangle segmentation to the two-dimensional surface in the pit slot region, obtains the pit slot two dimension of multiple triangles
Plane；
Optionally, triangle segmentation is carried out using two-dimensional surface of the Delaunay Triangulation Algorithm to the pit slot region,
Obtain the pit slot two-dimensional surface of multiple triangles.
In this step, the two-dimensional surface gridding in pit slot region is made the smallest using Delaunay Triangulation Algorithm
Interior angle maximizes, and does not ensure that the triangle finally obtained all in hollow projection.When spill is presented in hollow, such as Fig. 6 institute
Show, all black region is inside pit slot, and is divided on the outside of pit slot edge that there is also some using Delaunay Triangulation Algorithm
Triangle is not belonging to the triangle to be calculated.
Therefore, in order to eliminate this triangle in pit slot areas outside, to guarantee the accuracy of pit slot volume calculating,
After carrying out triangle segmentation using two-dimensional surface of the Delaunay Triangulation Algorithm to the pit slot region, multiple triangles are obtained
After two-dimensional surface, the triangle two that three vertex are overlapped with the pit slot edges of regions is deleted from multiple triangle two-dimensional surfaces
After dimensional plane, the two-dimentional pit slot plane of multiple triangles is obtained.
In the present embodiment, three vertex of triangle belong to boundary point；Three vertex of triangle under normal circumstances
At least one belongs to inside hollow, theoretically has this principle that can exclude all outer triangles, but in order to
Prevent the not complete enough of dense border points extraction；Two vertex of triangle belong to more than ten times boundary points of boundary point and distance,
Then judging this triangle also is outer triangle, removes all outer triangles, obtains the pit slot two-dimensional surface of multiple triangles.
Step 5, by the pit slot two-dimensional surface of multiple triangles with the direction back projection perpendicular to road plane domain to three-dimensional
In space, multiple triangular prisms are obtained；
The height on three sides of triangular prism be respectively in the pit slot two-dimensional surface of the triangle obtained in step 4 three vertex exist
The depth value of corresponding three three-dimensional points in pit slot area three-dimensional point cloud before being projected in step 3；
In the present embodiment, three vertex of triangle are respectively A, B and C, wherein coordinate of the vertex A in two-dimensional surface
For (x1, y1), vertex B is (x2, y2) in the coordinate of two-dimensional surface, and vertex C is (x3, y3) in the coordinate of two-dimensional surface, by this
After three vertex carry out back projection, so that these three vertex are provided with spatial information, i.e. depth value, this depth value is exactly three
When in no projection to two-dimensional surface, the depth value of corresponding three-dimensional point, i.e., wherein coordinate of the vertex A in space is on vertex
(x1, y1, z1), coordinate of the vertex B in space are (x2, y2, z2), and coordinate of the vertex C in space is (x3, y3, z3).
Step 6, the volume for calculating each triangular prism, obtain the volume in pit slot region after summation.
In this step, as shown in fig. 7, being partitioned into a triangle using step 4, one is obtained after back projection
Triangular prism, the vertex of triangular prism top surface three are respectively A, B and C, and coordinate of the vertex A in space is (x1, y1, z1), and vertex B exists
The coordinate in space is (x2, y2, z2), and coordinate of the vertex C in space is (x3, y3, z3), on the diagram as can be seen that the triangular prism
It is not a regular triangular prism, top surface is an inclined-plane, and bottom surface is road plane, therefore in the present embodiment, is used
This triangular prism is divided into a standard triangular prism and a tetrahedron by the method for segmentation triangular prism, by seeking standard respectively
The volume of triangular prism and tetrahedral volume are added the total volume for obtaining triangular prism.
In this step, when segmentation, the height z nearest apart from road plane is taken to be divided as the height h of standard triangular prism
It cuts, as shown in phantom in Figure 7, in this example, selects height h=z1 of the depth value of vertex A as triangular prism.
Wherein divide the area for obtaining the triangle in step 4 are as follows:
S=(1/2) | (x2-x1) * (y3-y1)-(x3-x1) * (y2-y1) |
The volume v of standard triangular prismp=S*h.
Secondly, calculating the tetrahedron volume on standard triangular prism, in this step, it is known that three dimensions of three three-dimensional points
According to, and the three-dimensional data by doing secondary surface also available other two vertex of tetrahedron, it can be obtained tetrahedral face
Product vt。
The then volume of a triangular prism are as follows: vi=vp+vt。
After the volume for calculating all triangular prisms by above method, a pit slot volume is obtained, but more than passing through
The pit slot volume that method obtains not is final exact value, due to when pit slot is divided, in step 22 by the depth of three-dimensional point
Angle value is less than all three-dimensional point deletions of depth threshold, obtains the three-dimensional point cloud of non-road plane domain, mentions with certain thickness
It when taking road plane, is equivalent to the thickness of the road surface road skiving Liao Yige plane, therefore the pit slot volume obtained can lack the part,
Therefore in order to obtain accurate pit slot volume, in the present embodiment, using the area of the multiple triangles obtained in step 4 as
Multiple standard triangular prism volumes are sought again using twice in step 22 of all three-dimensional point depth value average values as height in bottom
Afterwards, summation obtains pit slot and compensates volume, this part pit slot on the pit slot volume machine obtained in above-mentioned steps is compensated volume, is obtained
Final accurately pit slot Domain Volume.
It is calculated using volume of the volume measuring method provided in the present embodiment to simulation pit slot as shown in Figure 8,
Wherein the unit of each reference axis is m, verifies the validity of volume measuring method, and theoretically the volume of the hemisphere is
2.094395102393195m3, using the step 3- step 6 provided in the present embodiment, the volume that calculating obtains the hemisphere is
2.072184805179722m3, since calculation method of physical volume in the present embodiment is using interior approximatioss, in the hope of body
Product can be less than normal, but has met the calculating requirement in practical operation to pit slot volume, therefore road surface pit slot provided by the invention
Calculation method of physical volume error is smaller, and accuracy is higher.
In addition pit slot volume measuring method in road surface provided by the invention is not only applicable to the measurement of pit slot volume on road surface, can
Suitable for measuring the recessed pit slot volume for having pit slot all planes.
Embodiment two
As shown in figure 9, disclosing a kind of road surface pit slot volume measurement device, in the present embodiment for realizing embodiment one
In road surface pit slot volume measuring method, device include road surface three-dimensional point cloud obtain module, pit slot three-dimensional point cloud segmentation module with
And pit slot volume calculation module；
Road surface three-dimensional point cloud obtains module and connect with pit slot three-dimensional point cloud segmentation module, for be parallel to road plane domain
Direction, acquire road surface three-dimensional point cloud；
Pit slot three-dimensional point cloud divides module and pit slot volume calculation module, is split, obtains for road pavement three-dimensional point cloud
Obtain pit slot area three-dimensional point cloud；
Pit slot volume calculation module obtains pit slot area for projecting the road pit slot area three-dimensional Dian Yunxiang plane domain
The two-dimensional surface in domain；
It is also used to carry out triangle segmentation to the two-dimensional surface in pit slot region, obtains the pit slot two-dimensional surface of multiple triangles；
It is also used to the pit slot two-dimensional surface of multiple triangles with the direction back projection perpendicular to road plane domain to three-dimensional
In space, multiple triangular prisms are obtained；
It is also used to calculate the volume of each triangular prism, the volume in pit slot region is obtained after summation.
Optionally, at the beginning of pit slot three-dimensional point cloud segmentation module includes pit slot three-dimensional point cloud preprocessing module, pit slot three-dimensional point cloud
Step segmentation module and pit slot three-dimensional point cloud divide module again；
Pit slot three-dimensional point cloud preprocessing module is connect with pit slot three-dimensional point cloud primary segmentation module, is used for road pavement three-dimensional point
Cloud carries out pretreatment operation, obtains pretreated three-dimensional point cloud, pretreatment operation include the down-sampled operation that successively executes with
And filtering operation；
Pit slot three-dimensional point cloud primary segmentation module is divided module with pit slot three-dimensional point cloud again and is connect, after according to pretreatment
The depth value size of each three-dimensional point in three-dimensional point cloud deletes all three-dimensional points that the depth value of three-dimensional point is less than depth threshold
It removes, obtains the three-dimensional point cloud of non-road plane domain, depth threshold is that all three-dimensional point depth values are flat in three-dimensional point cloud after pre-processing
Twice of mean value；
Pit slot three-dimensional point cloud is divided module again and is used in the three-dimensional point cloud of non-road plane domain, by depth value maximum three
Dimension point is used as seed point, obtains initial pit slot area three-dimensional point cloud using the method for region growing；
It is also used to using a vertex of initial pit slot area three-dimensional point cloud as starting three-dimensional point, using the side of Edge Search
Method handles all three-dimensional points in initial pit slot area three-dimensional point cloud, obtains multiple three-dimensional point composition pit slot edges of regions；
It is also used to three-dimensional point set all within pit slot edges of regions obtaining pit slot area three-dimensional point cloud.
Optionally, pit slot three-dimensional point cloud segmentation module and pit slot volume calculation module are Intelligent mobile equipment.
In the present embodiment, in order to acquire road surface pit slot three-dimensional point cloud in real time, and hole can be handled in real time
Pit slot three-dimensional point cloud is divided module and pit slot volume calculates mould by slot three-dimensional point cloud to be split to it and the calculating of volume
Block is arranged on Intelligent mobile equipment, and Intelligent mobile equipment can be moveable the hardware devices such as computer, mobile phone.
Preferably, Intelligent mobile equipment is mobile phone.
For more convenient acquisition road surface pit slot volume, Intelligent mobile equipment is mobile phone, and maintenance of surface personnel can be straight
It connects and is attached with its mobile phone and road surface three-dimensional point cloud acquisition module (equipment such as binocular camera), three-dimensional point cloud acquisition module is adopted
The road surface three-dimensional point cloud collected is transmitted in mobile phone, is handled using cell phone application, and pit slot volume is obtained.
Claims (10)
1. a kind of road surface pit slot volume measuring method, which is characterized in that the road surface includes road road plane domain and pit slot
Region, the method execute according to the following steps:
Step 1, the direction to be parallel to the road plane domain acquire road surface three-dimensional point cloud；
Step 2 is split the road surface three-dimensional point cloud, obtains pit slot area three-dimensional point cloud；
Step 3 projects the road pit slot area three-dimensional Dian Yunxiang plane domain direction, and the two dimension for obtaining pit slot region is flat
Face；
Step 4 carries out triangle segmentation to the two-dimensional surface in the pit slot region, and the pit slot two dimension for obtaining multiple triangles is flat
Face；
Step 5 throws the pit slot two-dimensional surface of multiple triangles so that the direction perpendicular to the road plane domain is counter
Shadow obtains multiple triangular prisms into three-dimensional space；
The height on three sides of the triangular prism be respectively in the pit slot two-dimensional surface of the triangle obtained in step 4 three vertex exist
The depth value of corresponding three three-dimensional points in pit slot area three-dimensional point cloud before being projected in step 3；
Step 6, the volume for calculating each triangular prism, obtain the volume in pit slot region after summation.
2. pit slot volume measuring method in road surface as described in claim 1, which is characterized in that the step 2 specifically includes:
Step 21 carries out pretreatment operation to the road surface three-dimensional point cloud, obtains pretreated three-dimensional point cloud, described is pre-
Processing operation includes the down-sampled operation successively executed and filtering operation；
Step 22, according to the depth value size of three-dimensional point each in three-dimensional point cloud after pretreatment, the depth value of three-dimensional point is less than
All three-dimensional point deletions of depth threshold, obtain the three-dimensional point cloud of non-road plane domain, and the depth threshold is after pre-processing
Twice of all three-dimensional point depth value average values in three-dimensional point cloud；
Step 23, in the three-dimensional point cloud of the non-road plane domain, using the maximum three-dimensional point of depth value as seed point, adopt
Initial pit slot area three-dimensional point cloud is obtained with the method for region growing；
Step 24 is handled all three-dimensional points in the initial pit slot area three-dimensional point cloud using the method for Edge Search,
Obtain multiple three-dimensional point composition pit slot edges of regions；
Step 25, by three-dimensional point set all within the pit slot edges of regions, obtain the pit slot area three-dimensional point cloud.
3. pit slot volume measuring method in road surface as claimed in claim 2, which is characterized in that down-sampled behaviour in the step 21
It is filtered as voxel grid.
4. pit slot volume measuring method in road surface as claimed in claim 2, which is characterized in that in the step 22, according to pre-
After processing in three-dimensional point cloud each three-dimensional point depth value size, using RANSAC algorithm by the depth value of three-dimensional point be less than depth
All three-dimensional point deletions of threshold value, obtain the three-dimensional point cloud of non-road plane domain.
5. pit slot volume measuring method in road surface as claimed in claim 2, which is characterized in that the side using Edge Search
When method handles all three-dimensional points in the initial pit slot area three-dimensional point cloud, by the initial pit slot area three-dimensional point cloud
A vertex as three boundary points of starting, successively obtain multiple three-dimensional points using boundary point maximum angular principle and form pit slot region
Edge.
6. pit slot volume measuring method in road surface as claimed in claim 5, which is characterized in that use Delaunay Triangulation Algorithm
Triangle segmentation is carried out to the two-dimensional surface in the pit slot region, obtains the pit slot two-dimensional surface of multiple triangles.
7. pit slot volume measuring method in road surface as claimed in claim 6, which is characterized in that using the trigonometric ratio side Delaunay
After method carries out triangle segmentation to the two-dimensional surface in the pit slot region, after obtaining multiple triangle two-dimensional surfaces, from multiple three
After deleting the triangle two-dimensional surface that three vertex are overlapped with the pit slot edges of regions in angular two-dimensional surface, multiple three are obtained
Angular two-dimentional pit slot plane.
8. a kind of road surface pit slot volume measurement device, which is characterized in that for realizing any one of claim 1-7 claim
The road surface pit slot volume measuring method, the device include that road surface three-dimensional point cloud obtains module, pit slot three-dimensional point cloud point
Cut module and pit slot volume calculation module；
The road surface three-dimensional point cloud obtains module and connect with the pit slot three-dimensional point cloud segmentation module, for be parallel to
The direction of road plane domain is stated, road surface three-dimensional point cloud is acquired；
The pit slot three-dimensional point cloud segmentation module and the pit slot volume calculation module, for the road surface three-dimensional point
Cloud is split, and obtains the pit slot area three-dimensional point cloud；
The pit slot volume calculation module is obtained for projecting the road pit slot area three-dimensional Dian Yunxiang plane domain
The two-dimensional surface in pit slot region；
It is also used to carry out triangle segmentation to the two-dimensional surface in the pit slot region, the pit slot two dimension for obtaining multiple triangles is flat
Face；
It is also used to throw the pit slot two-dimensional surface of multiple triangles with the direction perpendicular to the road plane domain is counter
Shadow obtains multiple triangular prisms into three-dimensional space；
It is also used to calculate the volume of each triangular prism, the volume in pit slot region is obtained after summation.
9. pit slot volume measurement device in road surface as claimed in claim 8, which is characterized in that the pit slot three-dimensional point cloud segmentation
Module and pit slot volume calculation module are Intelligent mobile equipment.
10. pit slot volume measurement device in road surface as claimed in claim 9, which is characterized in that the Intelligent mobile equipment is
Mobile phone.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811589420.2A CN109900338B (en) | 2018-12-25 | 2018-12-25 | Method and device for measuring volume of pavement pit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811589420.2A CN109900338B (en) | 2018-12-25 | 2018-12-25 | Method and device for measuring volume of pavement pit |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109900338A true CN109900338A (en) | 2019-06-18 |
| CN109900338B CN109900338B (en) | 2020-09-01 |
Family
ID=66943444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811589420.2A Active CN109900338B (en) | 2018-12-25 | 2018-12-25 | Method and device for measuring volume of pavement pit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109900338B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112883757A (en) * | 2019-11-29 | 2021-06-01 | 北京航空航天大学 | Method for generating tracking attitude result |
| CN113074631A (en) * | 2021-03-11 | 2021-07-06 | 中国水利水电第七工程局有限公司 | Method for measuring rock-fill dam pit test volume through handheld three-dimensional laser scanning |
| CN113362385A (en) * | 2021-06-21 | 2021-09-07 | 山东产研信息与人工智能融合研究院有限公司 | Cargo volume measuring method and device based on depth image |
| CN113538557A (en) * | 2020-04-15 | 2021-10-22 | 深圳市光鉴科技有限公司 | Box volume measuring device based on three-dimensional vision |
| CN113888622A (en) * | 2021-10-14 | 2022-01-04 | 吉旗（成都）科技有限公司 | Method and device for determining cargo volume in carriage, electronic equipment and storage medium |
| CN114049618A (en) * | 2022-01-12 | 2022-02-15 | 河北工业大学 | Graph-point-graph transformation-based pavement three-dimensional disease PCI calculation method |
| CN116823832A (en) * | 2023-08-29 | 2023-09-29 | 武汉精一微仪器有限公司 | Solder paste defect detection method based on three-dimensional point cloud |
| US11983820B2 (en) | 2019-07-29 | 2024-05-14 | Zhejiang Sensetime Technology Development Co., Ltd | Information processing method and device, positioning method and device, electronic device and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011032207A1 (en) * | 2009-09-15 | 2011-03-24 | The University Of Sydney | A method and system for multiple dataset gaussian process modeling |
| CN103745474A (en) * | 2014-01-21 | 2014-04-23 | 南京理工大学 | Image registration method based on inertial sensor and camera |
| CN103886593A (en) * | 2014-03-07 | 2014-06-25 | 华侨大学 | Method for detecting hook face circular hole based on three-dimensional point cloud |
| CN104237086A (en) * | 2014-10-18 | 2014-12-24 | 山东理工大学 | Device and method for detecting dynamic light scattering variable-angle fiber-optic probe |
| CN104422391A (en) * | 2013-09-10 | 2015-03-18 | 上海瑷皑电子科技有限公司 | Sensing type object volume identifying technology |
| CN104457575A (en) * | 2014-12-18 | 2015-03-25 | 郑州长河电子工程有限公司 | Monitoring system and method for barn storage amount |
| CN104776810A (en) * | 2015-03-24 | 2015-07-15 | 长安大学 | Pit slot three-dimensional index extracting and calculating method based on 3D line laser equipment |
| CN107747906A (en) * | 2017-11-09 | 2018-03-02 | 中国电建集团成都勘测设计研究院有限公司 | A kind of volume measuring method of testing pits for rolling earth-rock dam |
-
2018
- 2018-12-25 CN CN201811589420.2A patent/CN109900338B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011032207A1 (en) * | 2009-09-15 | 2011-03-24 | The University Of Sydney | A method and system for multiple dataset gaussian process modeling |
| CN104422391A (en) * | 2013-09-10 | 2015-03-18 | 上海瑷皑电子科技有限公司 | Sensing type object volume identifying technology |
| CN103745474A (en) * | 2014-01-21 | 2014-04-23 | 南京理工大学 | Image registration method based on inertial sensor and camera |
| CN103886593A (en) * | 2014-03-07 | 2014-06-25 | 华侨大学 | Method for detecting hook face circular hole based on three-dimensional point cloud |
| CN104237086A (en) * | 2014-10-18 | 2014-12-24 | 山东理工大学 | Device and method for detecting dynamic light scattering variable-angle fiber-optic probe |
| CN104457575A (en) * | 2014-12-18 | 2015-03-25 | 郑州长河电子工程有限公司 | Monitoring system and method for barn storage amount |
| CN104776810A (en) * | 2015-03-24 | 2015-07-15 | 长安大学 | Pit slot three-dimensional index extracting and calculating method based on 3D line laser equipment |
| CN107747906A (en) * | 2017-11-09 | 2018-03-02 | 中国电建集团成都勘测设计研究院有限公司 | A kind of volume measuring method of testing pits for rolling earth-rock dam |
Non-Patent Citations (1)
| Title |
|---|
| 岳建平 等: "《安全监测技术与应用》", 31 August 2018, 武汉大学出版社 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11983820B2 (en) | 2019-07-29 | 2024-05-14 | Zhejiang Sensetime Technology Development Co., Ltd | Information processing method and device, positioning method and device, electronic device and storage medium |
| CN112883757A (en) * | 2019-11-29 | 2021-06-01 | 北京航空航天大学 | Method for generating tracking attitude result |
| CN113538557A (en) * | 2020-04-15 | 2021-10-22 | 深圳市光鉴科技有限公司 | Box volume measuring device based on three-dimensional vision |
| CN113538557B (en) * | 2020-04-15 | 2024-05-03 | 深圳市光鉴科技有限公司 | Box volume measuring device based on three-dimensional vision |
| CN113074631A (en) * | 2021-03-11 | 2021-07-06 | 中国水利水电第七工程局有限公司 | Method for measuring rock-fill dam pit test volume through handheld three-dimensional laser scanning |
| CN113362385A (en) * | 2021-06-21 | 2021-09-07 | 山东产研信息与人工智能融合研究院有限公司 | Cargo volume measuring method and device based on depth image |
| CN113888622A (en) * | 2021-10-14 | 2022-01-04 | 吉旗（成都）科技有限公司 | Method and device for determining cargo volume in carriage, electronic equipment and storage medium |
| CN114049618A (en) * | 2022-01-12 | 2022-02-15 | 河北工业大学 | Graph-point-graph transformation-based pavement three-dimensional disease PCI calculation method |
| CN114049618B (en) * | 2022-01-12 | 2022-03-22 | 河北工业大学 | Graph-point-graph transformation-based pavement three-dimensional disease PCI calculation method |
| CN116823832A (en) * | 2023-08-29 | 2023-09-29 | 武汉精一微仪器有限公司 | Solder paste defect detection method based on three-dimensional point cloud |
| CN116823832B (en) * | 2023-08-29 | 2023-12-12 | 武汉精一微仪器有限公司 | Solder paste defect detection method based on three-dimensional point cloud |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109900338B (en) | 2020-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109900338A (en) | A kind of road surface pit slot volume measuring method and device | |
| CN109816664A (en) | A kind of three-dimensional point cloud dividing method and device | |
| CN110717983B (en) | Building elevation three-dimensional reconstruction method based on knapsack type three-dimensional laser point cloud data | |
| CN106529469B (en) | Unmanned aerial vehicle-mounted LiDAR point cloud filtering method based on self-adaptive gradient | |
| CN110264567A (en) | A kind of real-time three-dimensional modeling method based on mark point | |
| CN101581575B (en) | Three-dimensional rebuilding method based on laser and camera data fusion | |
| CN109242862B (en) | Real-time digital surface model generation method | |
| CN107301648B (en) | Redundant point cloud removing method based on overlapping area boundary angle | |
| CN106970375A (en) | A kind of method that building information is automatically extracted in airborne laser radar point cloud | |
| CN108090960A (en) | A kind of Object reconstruction method based on geometrical constraint | |
| CN112418245B (en) | Electromagnetic emission point positioning method based on urban environment physical model | |
| CN110276732B (en) | Mountain area point cloud cavity repairing method considering topographic characteristic line elements | |
| CN111724433A (en) | Crop phenotype parameter extraction method and system based on multi-view vision | |
| CN116310192A (en) | Urban building three-dimensional model monomer reconstruction method based on point cloud | |
| CN107657659A (en) | The Manhattan construction method for automatic modeling of scanning three-dimensional point cloud is fitted based on cuboid | |
| CN108919295A (en) | Airborne LiDAR point cloud road information extracting method and device | |
| CN111598780B (en) | Terrain adaptive interpolation filtering method suitable for airborne LiDAR point cloud | |
| CN107767453A (en) | A kind of building LIDAR point cloud reconstruction and optimization methods of rule-based constraint | |
| CN108765568A (en) | A kind of multi-level building quick three-dimensional reconstructing method based on laser radar point cloud | |
| CN110070567A (en) | A kind of ground laser point cloud method for registering | |
| CN109191484B (en) | A method of the rapidly extracting planar chip from airborne laser radar point cloud | |
| CN112365543B (en) | Geological structure surface extraction method and device based on optical image | |
| CN113763529B (en) | Substation modeling method based on three-dimensional scanning | |
| CN111895907B (en) | Electricity tower point cloud extraction method, system and equipment | |
| CN116051980B (en) | Building identification method, system, electronic equipment and medium based on oblique photography |
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 |