CN110084116A - Pavement detection method, apparatus, computer equipment and storage medium - Google Patents
Pavement detection method, apparatus, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110084116A CN110084116A CN201910220802.6A CN201910220802A CN110084116A CN 110084116 A CN110084116 A CN 110084116A CN 201910220802 A CN201910220802 A CN 201910220802A CN 110084116 A CN110084116 A CN 110084116A
- Authority
- CN
- China
- Prior art keywords
- grid
- ground point
- value
- point cloud
- dimentional
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Length Measuring Devices With Unspecified Measuring Means (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Traffic Control Systems (AREA)
- Road Repair (AREA)
Abstract
This application involves a kind of pavement detection method, apparatus, computer equipment and storage mediums.The described method includes: obtaining the ground point cloud on road surface to be detected；Grating map is constructed according to the ground point cloud, determines the two-dimentional ground point that each grid is covered in the grating map；The height value for obtaining the two-dimentional ground point that each grid is covered determines the flatness on the road surface to be detected according to the height value of the two-dimentional ground point of each grid covering.The higher pavement detection of precision can be realized using this method.
Description
Technical field
This application involves unmanned technical fields, more particularly to a kind of pavement detection method, apparatus, computer equipment
And storage medium.
Background technique
With the development in unmanned field, there is road surface road conditions detection technique, road surface road conditions detection module is automatic
Most basic and important one of module is driven, road surface road conditions detection technique can provide road conditions to automatic driving vehicle and guide.
However, current road surface road conditions detection method, is carried out, camera data based on camera (camera) data
It is larger by light intensity effect, lead to not obtain the higher pavement detection result of precision.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of pavement detection result that can obtain degree of precision
Pavement detection method, apparatus, computer equipment and storage medium.
A kind of pavement detection method, which comprises
Obtain the ground point cloud on road surface to be detected；
Grating map is constructed according to the ground point cloud, determines that each grid is covered two-dimensionally in the grating map
Millet cake；
The height value for obtaining the two-dimentional ground point that each grid is covered, according to the two dimension of each grid covering
The height value of ground point determines the flatness on the road surface to be detected.
The ground point cloud for obtaining road surface to be detected includes: in one of the embodiments,
Obtain the point cloud data on the road surface to be detected of acquisition device acquisition；The acquisition device is laser radar；
The ground point cloud on the road surface to be detected is extracted from the point cloud data.
The ground point cloud that the road surface to be detected is extracted from the point cloud data in one of the embodiments,
Include:
From the point cloud data according to apart from acquisition device from closely to the remote point cloud for obtaining preset quantity；
The ground point cloud in the point cloud of the preset quantity is determined according to the height of the acquisition device；
Straight line fitting, which is carried out, according to the ground point cloud of the determination determines the ground point cloud in the point cloud data.
It is described in one of the embodiments, that grating map is constructed according to the ground point cloud, determine the grating map
In the two-dimentional ground point that is covered of each grid, comprising:
According to the three-dimensional information of the ground point cloud to be detected, convert the ground point cloud to be detected to two-dimensionally
Millet cake；
It uses grid size for two dimension ground point described in the grid map combining of the first preset value, obtains grating map.
The height value of the two-dimentional ground point for obtaining each grid covering in one of the embodiments, according to
The height value of the two-dimentional ground point of each grid covering determines the flatness on the ground to be detected, comprising:
Obtain the height value of the two-dimentional ground point of each grid covering；
The height value of the two-dimentional ground point of each grid covering is counted, the statistics of each grid is obtained
Value；
The template that side length is the second preset value is constructed centered on each grid, according to each grid in the template
Statistical value determine the flatness of each grid；
The average value or intermediate value for obtaining the flatness of each grid, by the average value of the flatness of each grid
Or flatness of the intermediate value as the road surface to be detected.
The height value of the two-dimentional ground point for obtaining each grid covering in one of the embodiments,；To institute
The height value for stating the two-dimentional ground point of each grid covering is counted, and the statistical value of each grid is obtained, comprising:
The two-dimentional ground point of each grid covering is traversed, the ground point of each grid covering is obtained
Maximum height value or height value mean value or minimum height values；
By the maximum height value of the two-dimentional ground point of each grid covering or height value mean value or minimum height values, make
For the statistical value of corresponding each grid.
The height value of the two-dimentional ground point to each grid covering counts in one of the embodiments,
Analysis, after obtaining the statistical value of each grid, further includes: be that empty grid carries out interpolation processing to statistical value.
Described in one of the embodiments, is that empty grid carries out interpolation processing to statistical value, comprising:
By the statistical value be empty grid centered on building side length be third preset value template；
The mean value for obtaining the statistical value of each grid in the template of the building, using the mean value of the statistical value as described in
Statistical value is the interpolation of empty grid.
The pavement detection method in one of the embodiments, further include:
According to the height value of the two-dimentional ground point of each grid covering, melt pit detection is carried out to the ground to be detected
Or fault detection.
A kind of road surface checking device, described device include:
Ground point cloud obtains module, for obtaining ground point cloud to be detected；
Grating map constructs module, for constructing grating map according to the ground point cloud, determines in the grating map
The two-dimentional ground point that each grid is covered；
Module is tested and analyzed, for obtaining the height value for the two-dimentional ground point that each grid is covered, according to described
The height value of the two-dimentional ground point of each grid covering determines the flatness on the road surface to be detected, by the road surface to be detected
Flatness is as testing result.
Ground point cloud acquisition module includes: in one of the embodiments,
Acquisition unit, the point cloud data on the road surface to be detected for obtaining acquisition device acquisition；The acquisition device is sharp
Optical radar；
Extraction unit, for extracting the ground point cloud on the road surface to be detected from the point cloud data.
Extraction unit be also used to from the point cloud data according to apart from acquisition device from closely to the remote preset quantity that obtains
Point cloud determines the ground point cloud in the point cloud of the preset quantity according to the height of the acquisition device, according to the determination
Ground point cloud carries out straight line fitting and determines the ground point cloud in the point cloud data.
Grating map building module includes: in one of the embodiments,
Projecting cell, for the three-dimensional information according to the ground point cloud to be detected, by the ground point to be detected
Cloud is converted into two-dimentional ground point；
Grid division unit, for using grid size for two dimension ground point described in the grid map combining of the first preset value,
Obtain grating map.
Testing and analyzing module in one of the embodiments, includes:
Data capture unit, the height value of the two-dimentional ground point for obtaining each grid covering；
Statistic unit, the height value for the two-dimentional ground point to each grid covering are counted, are obtained described
The statistical value of each grid；
First computing unit, for constructing the template that side length is the second preset value centered on each grid, according to
The statistical value of each grid determines the flatness of each grid in the template；
Second computing unit, the average value or intermediate value of the flatness for obtaining each grid, by each grid
Flatness of the average value or intermediate value of the flatness of lattice as the road surface to be detected.
Statistic unit is also used to the two-dimentional ground point progress time to each grid covering in one of the embodiments,
It goes through, the maximum height value or height value mean value or minimum height values of the two-dimentional ground point of each grid covering is obtained, by institute
The maximum height value or height value mean value or minimum height values for stating the two-dimentional ground point of each grid covering, as corresponding described
The statistical value of each grid.
Module is tested and analyzed in one of the embodiments, further include: interpolation process unit, for being empty to statistical value
Grid carries out interpolation processing.
Interpolation process unit constructs centered on being also used to the grid by the statistical value for sky in one of the embodiments,
Side length is the template of third preset value；The mean value for obtaining the statistical value of each grid in the template of the building, by the statistics
Interpolation of the mean value of value as the grid that the statistical value is sky.
Road surface checking device may also include that in one of the embodiments,
Melt pit detection module, the height value of the two-dimentional ground point for being covered according to each grid, to described to be checked
Geodetic face carries out melt pit detection；
Fault detection module, the height value of the two-dimentional ground point for being covered according to each grid, to described to be checked
Geodetic face carries out fault detection.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes above-mentioned pavement detection step when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
Above-mentioned pavement detection step is realized when row.
Above-mentioned pavement detection method, apparatus, computer equipment and storage medium are obtained by acquiring ground point cloud data
The three-dimensional modeling data for reflecting road surface to be detected constructs grating map according to ground point cloud, determines each grid in grating map
The two-dimentional ground point covered is analyzed and processed by the height value of the two-dimentional ground point covered to each grid, is obtained
The flatness on road surface to be detected, because point cloud data is not influenced by light, acquisition data are accurate, then the flatness precision that detects
Height realizes the higher pavement detection of precision.
Detailed description of the invention
Fig. 1 is the applied environment figure of road surface detection method in one embodiment；
Fig. 2 is the flow diagram of road surface detection method in one embodiment；
Fig. 3 is the schematic diagram of straight line fitting in one embodiment；
Fig. 4 is the flow diagram of ground point cloud obtaining step in one embodiment；
Fig. 5 is the flow diagram of grating map construction step in one embodiment；
Fig. 6 is the flow diagram that step is tested and analyzed in one embodiment；
Fig. 7 a is the grating map for not carrying out interpolation in one embodiment；
Fig. 7 b is the grating map in one embodiment after interpolation processing；
Fig. 8 a is the grating map constructed in another embodiment；
Fig. 8 b is the grating map in another embodiment after interpolation processing；
Fig. 9 is the flow diagram of road surface detection method in another embodiment；
Figure 10 is the top view of two-dimentional ground point in one embodiment；
Figure 11 is the structural block diagram of road surface checking device in one embodiment；
Figure 12 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Fig. 1 is the applied environment figure of road surface detection method in one embodiment.The embodiment of the present application provides a kind of road surface inspection
Survey method can be applied in application environment as shown in Figure 1.Wherein, it is provided with computer equipment 100 in moving trolley and adopts
Acquisition means 102.Acquisition device 102 can be laser radar, can emit laser and be scanned, obtain the point cloud data of ambient enviroment.
As shown in Figure 1, acquisition device 102 emits on laser to road surface, all scanned objects such as scanning to ground and barrier
Point cloud data, wherein ground may include the road surface characteristics such as puddle.Then acquisition device 102 is by all scanned objects
Point cloud data is transferred to computer equipment 100.
Wherein, acquisition device 102 can be also depth camera, for acquiring the depth image of ambient enviroment, the depth map
Point cloud chart picture is converted to as may be processed.
Wherein, computer equipment 100 can be car-mounted terminal or terminal console or mobile terminal, and mobile terminal specifically may be used
To be mobile phone, tablet computer, laptop, wearable device, personal digital assistant etc..Computer equipment 100 can also be used
The server cluster of independent server either multiple servers composition is realized.
Fig. 2 is a kind of flow diagram of pavement detection method in one embodiment.As shown in Fig. 2, providing a kind of road
Face detection method is applied to be illustrated for the computer equipment in Fig. 1 in this way, comprising the following steps:
Step 202, the ground point cloud on road surface to be detected is obtained.
Wherein, ground point cloud can refer to the point cloud data of the above ground portion extracted from vehicle-periphery point cloud data.
Specifically, the point cloud data that acquisition device 102 acquires vehicle-periphery is transferred in computer equipment 100, is counted
The point cloud data for calculating the vehicle-periphery of 100 pairs of machine equipment acquisitions carries out ground point detection, extracts ground point cloud.
Optionally, the process for obtaining ground point cloud may also is that acquisition device 102 acquires the depth map of vehicle-periphery
As being transferred to computer equipment 100, the depth image that computer equipment 100 will acquire carries out the point cloud for being converted to ambient enviroment
Then data carry out ground point detection to the point cloud data of the vehicle-periphery of acquisition, extract ground point cloud.
Optionally, the method for above-mentioned ground point detection can be line-fit (straight line fitting) algorithm, can also be point net
(point cloud segmentation) algorithm, also may be based on the detection algorithm of deep learning.
Wherein, with reference in the applied environment figure of road surface detection method and one embodiment of Fig. 3 in one embodiment of Fig. 1
The schematic diagram of straight line fitting, the method that ground point detection is carried out according to line-fit (straight line fitting) algorithm are as follows: according to laser thunder
Up to the height from wheel tire and ground face contact, judge that two clouds close to moving trolley as ground point cloud, are identified；
According to identified ground point cloud and the other clouds detected, straight line fitting and phase extension processing are carried out, judgement detects
Other clouds whether be ground point cloud.Repetitive operation detects all ground point clouds.
Wherein, the detection algorithm based on deep learning can be acquisition ground point cloud in advance, according to ground gathered in advance
Point cloud and the point cloud data on road surface to be detected carry out Characteristic Contrast, obtain ground point cloud.
Step 204, grating map is constructed according to the ground point cloud, determines that each grid is covered in the grating map
Two-dimentional ground point.
Wherein, the ground point cloud that two-dimentional ground point can refer to three-dimensional state projects to the point of the two-dimensional state formed in plane,
The two dimension ground point includes two-dimensional coordinate information and elevation information.Grating map can refer to comprising ground to be detected elevation information and
The map of location information.
Specifically, computer equipment 100 projects to the ground point cloud of three-dimensional state in plane, obtains two-dimentional ground point,
It is the grid of the first preset value that the plane comprising two-dimentional ground point, which is divided into size, again, obtains grating map.It wherein, will be three-dimensional
The ground point cloud of state retains the height value of the Z-direction of the ground point cloud of three-dimensional state when being converted to two-dimentional ground point, makees
For the height value of two-dimentional ground point.
Step 206, the height value for obtaining the two-dimentional ground point that each grid is covered, covers according to each grid
The height value of the two-dimentional ground point of lid determines the flatness on the road surface to be detected.
Wherein, the two-dimentional ground point number of each grid covering can be zero, or one or more.
Specifically, computer equipment 100 obtains the system of each grid according to the height value of ground point two-dimentional in each grid
Evaluation, according to the statistical value of each grid to the carry out flatness detection on road surface to be detected.Wherein, flatness detection can include:
Using a certain grid as center grid, according to the statistical value of grid in the center grates periphery preset range, the center grates are calculated
The variance of the statistical value of grid in the preset range of periphery, variance is bigger, then flatness is lower.Optionally, also settable preset areas
Each grid is center grid in domain, traverses each center grates, repetitive operation, and the periphery for calculating each center grates is pre-
The mean value or intermediate value or maximum value or minimum value for determining the statistical value of grid in range, further according to the mean value or intermediate value or maximum value
Or variance is calculated in minimum value, the flatness as institute's predeterminable area.
In above-mentioned pavement detection method, by acquiring ground point cloud data, the threedimensional model for reflecting road surface to be detected is obtained
Data construct grating map according to ground point cloud, the two-dimentional ground point that each grid is covered in grating map are determined, by right
The height value for the two-dimentional ground point that each grid is covered is analyzed and processed, and has obtained the flatness on road surface to be detected, because of point
Cloud data are not influenced by light, and acquisition data are accurate, then the flatness precision detected is high, realize the higher road surface inspection of precision
It surveys.
Fig. 4 is the flow diagram of ground point cloud obtaining step in one embodiment.As shown in figure 4, in one embodiment
In, step 202 the following steps are included:
Step 402, the point cloud data on the road surface to be detected of acquisition device acquisition is obtained；The acquisition device is laser thunder
It reaches.Wherein, the point cloud data on road surface to be detected refers to the reflection vehicle that acquisition device 102 acquires or computer equipment 100 is converted
The three-dimensional point cloud model data of ambient enviroment.
Step 404, the ground point cloud on the road surface to be detected is extracted from the point cloud data.
Specifically, computer equipment 100 carries out ground point detection, obtains the ground on road surface to be detected according to the point cloud data
Millet cake cloud.
In above-mentioned ground point cloud obtaining step, by acquiring the point cloud data of vehicle-periphery, then from the point cloud data
Middle extraction ground point cloud realizes effective acquisition of point cloud in road surface to be detected, compared to being more susceptible to light shadow in data acquisition
Loud camera (camera) data, point cloud data can more steadily reflect the practical three-dimensional model information on road surface to be detected, make
It is higher to obtain pavement detection result accuracy.
In one embodiment, the ground point cloud on the road surface to be detected is extracted from the point cloud data, comprising: from institute
State in point cloud data according to apart from acquisition device from closely to the remote point cloud for obtaining preset quantity；According to the height of the acquisition device
Determine the ground point cloud in the point cloud of the preset quantity；According to the progress straight line fitting determination of the ground point cloud of the determination
Ground point cloud in point cloud data.
Wherein, which acquires a frame point cloud data, and each cloud is to be with acquisition device in the frame point cloud data
The point cloud that the coordinate system that origin is established generates.
Specifically, referring to Fig.1, acquisition device 102 is first acquired away from two nearest clouds.As the first point Yun He
2 clouds, using the vertical range between the contact point and acquisition device 102 on tire and ground as height reference value, respectively with
The height value of some clouds and the height value of second point cloud are compared, if the difference of the height value of height reference value and first cloud
In pre-set interval, then first cloud is ground point cloud, if the difference of the height value of height reference value and second point cloud is default
In section, then second point cloud is ground point cloud.Successively according to apart from acquisition device 102 from closely to the remote point for obtaining preset quantity
Cloud repeats judgement operation, is ground point cloud until there are two clouds, respectively the first ground point cloud and the second ground point
Cloud.Straight line fitting is carried out according to the first ground point cloud and the second ground point cloud, judges whether the point cloud of subsequent acquisition is ground
Point cloud.
In above-mentioned ground point detecting step, by the method for straight line fitting, effective extraction of ground point cloud is realized.
Fig. 5 is the flow diagram of grating map construction step in one embodiment.As shown in figure 5, in one embodiment
In, step 204 the following steps are included:
Step 502, according to the three-dimensional information of the ground point cloud to be detected, the ground point cloud to be detected is converted
For two-dimentional ground point.
Wherein, ground point cloud includes three-dimensional coordinate information, and two-dimentional ground point includes two-dimensional coordinate information and elevation information.
Step 504, use grid size for two dimension ground point described in the grid map combining of the first preset value, with obtaining grid
Figure.
Wherein, size is that the grid of the first preset value can refer to the grid that side length is preset value, such as with size is 0.3m*
The grid of 0.3m.
In the construction step of above-mentioned grating map, to be formed by projecting the ground point cloud of three-dimensional state comprising height value
Two-dimentional ground point, and setting grid cover two-dimentional ground point, obtain grating map, wherein each grid includes the two of its covering
Tie up the height value of ground point.In the present embodiment, the building of grating map is convenient for being detected according to the information that each grid includes
Analysis.
Fig. 6 is the flow diagram that step is tested and analyzed in one embodiment.As shown in fig. 6, in one embodiment, step
Rapid 206 the following steps are included:
Step 602, the height value of the two-dimentional ground point of each grid covering is obtained.
Step 604, the height value of the two-dimentional ground point of each grid covering is counted, obtains each grid
The statistical value of lattice.
Wherein, the statistical value of grid can according to the height value of two-dimentional ground point that is covered of the grid be calculated should
The assignment of grid.
Step 606, the template that side length is the second preset value is constructed centered on each grid, according in the template
The statistical value of each grid determines the flatness of each grid.
Wherein, the flatness of grid can be the flatness in road surface region under world coordinate system corresponding to the reflection grid.
Step 608, the average value or intermediate value for obtaining the flatness of each grid, by the flatness of each grid
Flatness as the road surface to be detected of average value or intermediate value.
Wherein, the flatness on road surface to be detected is the testing result on road surface to be detected.
In above-mentioned detection and analysis step, the height value of the two-dimentional ground point covered by each grid determines road surface to be detected
Flatness, realize effective detection of surface evenness to be detected, wherein the height for the two-dimentional ground point for covering each grid
Angle value is counted, and statistical value is assigned to the grid, then analyze by the statistical value to each grid, so that road surface is examined
The testing result of survey is more nearly actual conditions.
In one embodiment, the height value of the two-dimentional ground point for obtaining each grid covering, to described each
The height value of the two-dimentional ground point of grid covering is counted, and the statistical value of each grid is obtained, comprising: to described each
The two-dimentional ground point of grid covering is traversed, and the maximum height value or height of the two-dimentional ground point of each grid covering are obtained
Angle value mean value；By the maximum height value or height value mean value of the two-dimentional ground point of each grid covering, as corresponding institute
State the statistical value of each grid.
For example, two-dimentional ground point 1 and two-dimentional ground point 2 are covered in a certain grid, wherein the height of two-dimentional ground point 1
Angle value is 1.1, and the height value of two-dimentional ground point 2 is 1.3, can use statistical value of the maximum height value 1.3 as the grid, also can use
Statistical value of the height value mean value 1.2 as the grid.
It optionally, can also be by the minimum height values for the two-dimentional ground point that each grid covers or height value mean value or minimum height
Angle value, the statistical value as corresponding each grid.
In the step of above-mentioned acquisition each grid statistical value, by the height for the two-dimentional ground point for being covered each grid
Value determines that the statistical value of each grid, the elevation information that the two-dimentional ground point that each grid is covered is included are transformed into its correspondence
Grid on so that being believed without traversing all two-dimentional ground points during testing and analyzing according to the height that each grid is included
Breath is analyzed.
In one embodiment, the height value of the two-dimentional ground point to each grid covering is for statistical analysis,
After obtaining the statistical value of each grid, further includes: be that empty grid carries out interpolation processing to statistical value.
Wherein, interpolation processing refers to be that empty grid carries out assignment to statistical value.
For example, being the grating map for not carrying out interpolation in one embodiment with reference to Fig. 7 a and Fig. 7 b, Fig. 7 a, Fig. 7 b is one
Grating map in embodiment after interpolation processing puts the sparse grid of cloud by interpolation processing it can be seen from Fig. 7 a and Fig. 7 b
Map becomes the dense grating map of a cloud.
In one embodiment, described is that empty grid carries out interpolation processing to statistical value, comprising: with the statistical value is sky
Grid centered on building side length be third preset value template；Obtain the statistical value of each grid in the template of the building
Mean value is the interpolation of empty grid using the mean value of the statistical value as the statistical value.
For example, referring to Fig. 8 a, Fig. 8 a is the grating map for not carrying out interpolation processing in another embodiment, and Fig. 8 b is another
Grating map in a embodiment after interpolation processing, the grid at A, in surrounding's grid of the template covering of 3*3, there are two grid
Lattice have a statistical value, and respectively 1.5 and 1.7, therefore 1.6 are assigned a value of to A point.
Optionally, the intermediate value or maximum value or minimum value that the statistical value of each grid in constructed template can be obtained, by this
The interpolation of intermediate value or maximum value or minimum value as the grid that the statistical value is sky.
Above-mentioned is the step of empty grid carries out interpolation to statistical value, according to the adjacent cells for statistical value being empty grid
Statistical value, determine the interpolation of the grid, statistical value, which is originally used for empty grid, new assignment, can by the assignment of the grid
For testing and analyzing, test and analyze that available data are more, so that the result tested and analyzed is more accurate.
In another embodiment, the pavement detection method further include: according to the two-dimentional ground of each grid covering
The height value of point carries out melt pit detection or fault detection to the ground to be detected.
Optionally, according to the height value of the two-dimentional ground point of each grid covering, the statistical value of each grid is determined.Traversal
Each grid, if the statistical value of the grid is sky, it is determined that the region under the corresponding world coordinate system of the grid belongs to fault zone
Domain, if the difference of the statistical value of the grid and height reference value is greater than preset value, it is determined that the corresponding world coordinate system of the grid
Under region belong to melt pit region.It is that region decision under the empty corresponding world coordinate system of continuous grid is by multiple statistical values
Fault region.It is world coordinate system corresponding greater than the continuous grid of preset value with the difference of height reference value by multiple statistical values
Under region decision be fault region.Wherein, melt pit region refers to that the ground region for low-lying feature occur, fault region are to point out
The ground region of existing slight crack feature.
Optionally, it according to the height value of the two-dimentional ground point of grid each in the region of default size covering, determines default
The statistical value of each grid in the region of size.Each grid in the region of default size is scanned line by line or by column, is counted
The mean value or intermediate value or minimum value or maximum value for calculating the statistical value of the grid in region of the default size, preset size as this
Region height value.If the difference of the statistical value of the height value in the region of the default size grid adjacent with boundary line is greater than
Preset value, it is determined that the region under the corresponding world coordinate system in region of the default size is melt pit region.
Above-mentioned melt pit detecting step and fault detection step, according to each grid covering two-dimentional ground point height value into
The detection of row melt pit and fault detection, realize multi-functional pavement detection.
Fig. 9 is the flow diagram of another road surface detection method, as shown in figure 9, in another embodiment, another road surface
Detection method includes the following steps:
Step 902, by ground point algorithm, ground point detection is carried out to the point cloud data of acquisition, extracts ground point cloud.
Specifically, referring to Figure 1 and Figure 3, Fig. 3 is the schematic diagram of straight line fitting.Acquisition device 102 in the present embodiment is more
Line laser radar, as shown in Figure 1, multi-line laser radar can emit multi-thread laser scanning ambient enviroment from the near to the remote, root simultaneously
Three-dimensional modeling is carried out according to the laser point cloud data of ambient enviroment.Then ground point detection is carried out.Firstly, according to laser radar from vehicle
The height of tire judges that two clouds close to moving trolley as ground point cloud, are marked as the first color；According to being labeled as
The ground point cloud of first color and the other clouds detected carry out straight line fitting and phase extension processing, judge to detect
Whether other clouds are ground point cloud.Wherein, ground point cloud is labeled as the first color, and obstacle tag is the second color.For example,
First color can be green, and the second color can be red.Repetitive operation goes out all ground points according to the first dithering of label
Cloud.
Step 904, grating map is constructed according to ground point cloud.
Wherein, ground point cloud includes three-dimensional location information (x, y, z), wherein x-y plane is the water where laser radar
Plane, z-axis are the long axis perpendicular to x-y plane direction.
Specifically, computer equipment 100 projects to ground point cloud in x-y plane, and 0, Figure 10 is an implementation referring to Fig.1
The top view of two-dimentional ground point in example, wherein the ground point cloud of three-dimensional state is converted into two-dimentional ground point.By x-y plane point
It is cut into the grid that size is r*r, wherein r is the first preset value, can be set according to actual conditions.It is building referring to Fig. 8 a, Fig. 8 a
Good grating map, wherein grid size 0.1m*0.1m is covered with two-dimentional ground point in grid.
It step 906, is that empty grid carries out interpolation processing to statistical value in the grating map built.
Wherein, the statistical value of grid is that sky refers to that the grid is not covered with two-dimentional ground point, i.e., without obtaining two-dimentional ground
The height value of point.
Wherein, after building grating map, can there are grid be covered with two-dimentional ground point, some grids are not covered with
The case where two-dimentional ground point, needs to carry out interpolation to the grid for being not covered with two-dimentional ground point at this time, to obtain continuous grid
Trrellis diagram.
Bilinear interpolation is used in the present embodiment, interpolation is carried out to the grid for being not covered with two-dimentional ground point, for distance
It is covered with the farther away grid of grid of two-dimentional ground point, even if the statistical value of the grid is sky, also without interpolation.For example, ginseng
It is the grating map after interpolation processing according to Fig. 8 b, Fig. 8 b, is empty grid for statistical value, constructs the template of 3*3；With the grid
Centered on, in the template of this 3*3, surrounding grid is covered, if the statistical value non-empty of surrounding grid, calculates these grid
The average value of the statistical value of lattice, the statistical value as the center grates.In Fig. 8 b, the grid at A, the template covering of 3*3
In surrounding grid, there is a statistical value there are two grid, respectively 1.5 and 1.7, therefore 1.6 are assigned a value of to A point.The grid at B,
The grid of the template covering of 3*3 does not have statistical value, therefore is assigned a value of sky to grid at B.
Step 908, the flatness on road surface to be detected is determined according to the height value of ground point two-dimentional in grid.
Specifically, as shown in Figure 8 b, using C point as center grid, the template of a 5*5 is constructed, according within the scope of the template
All grids statistical value calculate variance, further according to variance calculate average value, using the average value as the flatness on road surface.
It step 910, be the region decision where empty grid by statistical value is fault region according to the grating map.
Step 912, according to the grating map, by statistical value where the grid in the contiguous range of two-dimentional spot height
Region decision be melt pit region.
Wherein, contiguous range can refer to the range of pre-set interval size, which examines according to step 602 and step 604
The height value that the two-dimentional ground point measured includes determines.
In above-mentioned pavement detection method, by extraction ground point cloud, then grating map is constructed, and carry out to grating map
Analysis processing has obtained flatness, tomography judgement and the melt pit judgement on road surface, has realized effective pavement detection.
It should be understood that although each step in the flow chart of Fig. 2,4,5,6,9 is successively shown according to the instruction of arrow
Show, but these steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein, this
There is no stringent sequences to limit for the execution of a little steps, these steps can execute in other order.Moreover, Fig. 2,4,5,6,
At least part step in 9 may include that perhaps these sub-steps of multiple stages or stage be not necessarily for multiple sub-steps
It is to execute completion in synchronization, but can execute at different times, the execution sequence in these sub-steps or stage
It is not necessarily and successively carries out, but can be at least part wheel of the sub-step or stage of other steps or other steps
Stream alternately executes.
In one embodiment, as shown in figure 11, a kind of road surface checking device is provided, comprising: ground point cloud obtains mould
Block 1102, grating map building module 1104 and detection and analysis module 1106, in which:
Ground point cloud obtains module 1102, for obtaining ground point cloud to be detected；
Grating map constructs module 1104, for constructing grating map according to the ground point cloud, with determining the grid
The two-dimentional ground point that each grid is covered in figure；
Module 1106 is tested and analyzed, for obtaining the height value for the two-dimentional ground point that each grid is covered, according to
The height value of the two-dimentional ground point of each grid covering determines the flatness on the road surface to be detected.
Wherein, ground point cloud acquisition module 1102 includes:
Acquisition unit, the point cloud data on the road surface to be detected for obtaining acquisition；
Extraction unit, for extracting the ground point cloud on the road surface to be detected from the point cloud data.
Extraction unit be also used to from the point cloud data according to apart from acquisition device from closely to the remote preset quantity that obtains
Point cloud determines the ground point cloud in the point cloud of the preset quantity according to the height of the acquisition device, according to the determination
Ground point cloud carries out straight line fitting and determines the ground point cloud in the point cloud data.
Wherein, grating map building module 1104 includes:
Projecting cell, for the three-dimensional information according to the ground point cloud to be detected, by the ground point to be detected
Cloud is converted into two-dimentional ground point；
Grid division unit, for using grid size for two dimension ground point described in the grid map combining of the first preset value,
Obtain grating map.
Wherein, testing and analyzing module 1106 includes:
Data capture unit, the height value of the two-dimentional ground point for obtaining each grid covering；
Statistic unit, the height value for the two-dimentional ground point to each grid covering are counted, are obtained described
The statistical value of each grid；
First computing unit, for constructing the template that side length is the second preset value centered on each grid, according to
The statistical value of each grid determines the flatness of each grid in the template；
Second computing unit, the average value or intermediate value of the flatness for obtaining each grid, by each grid
Flatness of the average value or intermediate value of the flatness of lattice as the road surface to be detected.
Statistic unit is also used to traverse the two-dimentional ground point of each grid covering, obtains each grid
The maximum height value or height value mean value or minimum height values of the two-dimentional ground point of covering, by the two dimension of each grid covering
The maximum height value or height value mean value or minimum height values of ground point, the statistical value as corresponding each grid.
Test and analyze module 1106 further include: interpolation process unit, for being that empty grid carries out at interpolation to statistical value
Reason.
Interpolation process unit be also used to by the statistical value be empty grid centered on building side length be third preset value
Template；The mean value for obtaining the statistical value of each grid in the template of the building, using the mean value of the statistical value as the system
Evaluation is the interpolation of empty grid.
Road surface checking device may also include that
Melt pit detection module, the height value of the two-dimentional ground point for being covered according to each grid, to described to be checked
Geodetic face carries out melt pit detection；
Fault detection module, the height value of the two-dimentional ground point for being covered according to each grid, to described to be checked
Geodetic face carries out fault detection.
Specific about road surface checking device limits the restriction that may refer to above for pavement detection method, herein not
It repeats again.Modules in above-mentioned road surface checking device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure is shown in Fig.12.The computer equipment includes the processor connected by system bus, memory, network interface, shows
Display screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment
Memory includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer
Program.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The meter
The network interface for calculating machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor
To realize a kind of pavement detection method.The display screen of the computer equipment can be liquid crystal display or electric ink is shown
Screen, the input unit of the computer equipment can be the touch layer covered on display screen, be also possible on computer equipment shell
Key, trace ball or the Trackpad of setting can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Figure 12, only part relevant to application scheme
The block diagram of structure, does not constitute the restriction for the computer equipment being applied thereon to application scheme, and specific computer is set
Standby may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor realize above-mentioned pavement detection step when executing computer program.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes above-mentioned pavement detection step when being executed by processor.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (11)
1. a kind of pavement detection method, which comprises
Obtain the ground point cloud on road surface to be detected；
Grating map is constructed according to the ground point cloud, determines the two-dimentional ground that each grid is covered in the grating map
Point；
The height value for obtaining the two-dimentional ground point that each grid is covered, according to the two-dimentional ground of each grid covering
The height value of point determines the flatness on the road surface to be detected.
2. pavement detection method according to claim 1, which is characterized in that the ground point cloud for obtaining road surface to be detected
Include:
Obtain the point cloud data on the road surface to be detected of acquisition device acquisition；The acquisition device is laser radar；
The ground point cloud on the road surface to be detected is extracted from the point cloud data.
3. pavement detection method according to claim 2, which is characterized in that it is described from the point cloud data extract described in
The ground point cloud on road surface to be detected, comprising:
From the point cloud data according to apart from acquisition device from closely to the remote point cloud for obtaining preset quantity；
The ground point cloud in the point cloud of the preset quantity is determined according to the height of the acquisition device；
Straight line fitting, which is carried out, according to the ground point cloud of the determination determines the ground point cloud in the point cloud data.
4. pavement detection method according to claim 1, which is characterized in that described to construct grid according to the ground point cloud
Map determines the two-dimentional ground point that each grid is covered in the grating map, comprising:
According to the three-dimensional information of the ground point cloud to be detected, two-dimentional ground is converted by the ground point cloud to be detected
Point；
It uses grid size for two dimension ground point described in the grid map combining of the first preset value, obtains grating map.
5. pavement detection method according to claim 1, which is characterized in that described to obtain the two of each grid covering
The height value for tieing up ground point determines the ground to be detected according to the height value of the two-dimentional ground point of each grid covering
Flatness, comprising:
Obtain the height value of the two-dimentional ground point of each grid covering；
The height value of the two-dimentional ground point of each grid covering is counted, the statistical value of each grid is obtained；
The template that side length is the second preset value is constructed centered on each grid, according to the system of each grid in the template
Evaluation determines the flatness of each grid；
The average value or intermediate value for obtaining the flatness of each grid, by the average value of the flatness of each grid or in
It is worth the flatness as the road surface to be detected.
6. pavement detection method according to claim 5, which is characterized in that described to obtain the two of each grid covering
Tie up the height value of ground point；The height value of the two-dimentional ground point of each grid covering is counted, is obtained described each
The statistical value of grid, comprising:
The two-dimentional ground point of each grid covering is traversed, the two-dimentional ground point of each grid covering is obtained
Maximum height value or height value mean value or minimum height values；
By the maximum height value of the two-dimentional ground point of each grid covering or height value mean value or minimum height values, as right
The statistical value for each grid answered.
7. pavement detection method according to claim 5, which is characterized in that the two dimension to each grid covering
The height value of ground point is for statistical analysis, after obtaining the statistical value of each grid, further includes: is empty to statistical value
Grid carries out interpolation processing.
8. pavement detection method according to claim 7, which is characterized in that described to be that empty grid carries out to statistical value slotting
Value processing, comprising:
By the statistical value be empty grid centered on building side length be third preset value template；
The mean value for obtaining the statistical value of each grid in the template of the building, using the mean value of the statistical value as the statistics
Value is the interpolation of empty grid.
9. pavement detection method according to claim 1, which is characterized in that the pavement detection method further include:
According to the height value of the two-dimentional ground point of each grid covering, melt pit detection is carried out to the ground to be detected or is broken
Layer detection.
10. a kind of road surface checking device, which is characterized in that described device includes:
Ground point cloud obtains module, for obtaining ground point cloud to be detected；
Grating map constructs module, for constructing grating map according to the ground point cloud, determines each in the grating map
The two-dimentional ground point that grid is covered；
Module is tested and analyzed, for obtaining the height value for the two-dimentional ground point that each grid is covered, according to described each
The height value of the two-dimentional ground point of grid covering determines the flatness on the road surface to be detected, by the smooth of the road surface to be detected
Degree is used as testing result.
11. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 9 the method when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910220802.6A CN110084116B (en) | 2019-03-22 | 2019-03-22 | Road surface detection method, road surface detection device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910220802.6A CN110084116B (en) | 2019-03-22 | 2019-03-22 | Road surface detection method, road surface detection device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110084116A true CN110084116A (en) | 2019-08-02 |
| CN110084116B CN110084116B (en) | 2022-02-01 |
Family
ID=67413442
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910220802.6A Active CN110084116B (en) | 2019-03-22 | 2019-03-22 | Road surface detection method, road surface detection device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084116B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110487245A (en) * | 2019-08-16 | 2019-11-22 | 中国民用航空总局第二研究所 | Civil airport glide-path localizer protection zone place real-time monitoring analyzing system and its method |
| CN111123278A (en) * | 2019-12-30 | 2020-05-08 | 科沃斯机器人股份有限公司 | Partitioning method, device and storage medium |
| CN111208530A (en) * | 2020-01-15 | 2020-05-29 | 北京四维图新科技股份有限公司 | Positioning layer generation method and device, high-precision map and high-precision map equipment |
| CN111208533A (en) * | 2020-01-09 | 2020-05-29 | 上海工程技术大学 | Real-time ground detection method based on laser radar |
| CN111239757A (en) * | 2020-03-12 | 2020-06-05 | 湖南大学 | Automatic extraction method and system for road surface characteristic parameters |
| CN111932943A (en) * | 2020-10-15 | 2020-11-13 | 深圳市速腾聚创科技有限公司 | Dynamic target detection method and device, storage medium and roadbed monitoring equipment |
| CN111999741A (en) * | 2020-01-17 | 2020-11-27 | 青岛慧拓智能机器有限公司 | Method and device for detecting roadside laser radar target |
| CN112129266A (en) * | 2020-09-28 | 2020-12-25 | 北京嘀嘀无限科技发展有限公司 | Method, apparatus, device and computer readable storage medium for processing map |
| CN112199991A (en) * | 2020-08-27 | 2021-01-08 | 广州中国科学院软件应用技术研究所 | Simulation point cloud filtering method and system applied to vehicle-road cooperative roadside sensing |
| CN112348781A (en) * | 2020-10-26 | 2021-02-09 | 广东博智林机器人有限公司 | Method, device and equipment for detecting height of reference plane and storage medium |
| WO2021053679A2 (en) | 2019-09-22 | 2021-03-25 | Vayavision Sensing Ltd. | Methods and systems for autonomous driving of vehicles |
| WO2021098161A1 (en) * | 2019-11-20 | 2021-05-27 | 中铁四局集团第一工程有限公司 | Pavement flatness measurement method and system |
| CN113129255A (en) * | 2019-12-31 | 2021-07-16 | 杭州海康机器人技术有限公司 | Method, computing device, system and storage medium for detecting package |
| WO2021189479A1 (en) * | 2020-03-27 | 2021-09-30 | 深圳市速腾聚创科技有限公司 | Pose correction method and device for roadbed sensor, and roadbed sensor |
| CN113970295A (en) * | 2021-09-28 | 2022-01-25 | 湖南三一中益机械有限公司 | Paving thickness measuring method and device and paver |
| CN114322856A (en) * | 2021-12-16 | 2022-04-12 | 青岛慧拓智能机器有限公司 | Mining area pavement flatness detection method and device, storage medium and equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127771A (en) * | 2016-06-28 | 2016-11-16 | 上海数联空间科技有限公司 | Tunnel orthography system and method is obtained based on laser radar LIDAR cloud data |
| CN106199558A (en) * | 2016-08-18 | 2016-12-07 | 宁波傲视智绘光电科技有限公司 | Barrier method for quick |
| CN106650640A (en) * | 2016-12-05 | 2017-05-10 | 浙江大学 | Negative obstacle detection method based on local structure feature of laser radar point cloud |
| CN107092020A (en) * | 2017-04-19 | 2017-08-25 | 北京大学 | Merge the surface evenness monitoring method of unmanned plane LiDAR and high score image |
-
2019
- 2019-03-22 CN CN201910220802.6A patent/CN110084116B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127771A (en) * | 2016-06-28 | 2016-11-16 | 上海数联空间科技有限公司 | Tunnel orthography system and method is obtained based on laser radar LIDAR cloud data |
| CN106199558A (en) * | 2016-08-18 | 2016-12-07 | 宁波傲视智绘光电科技有限公司 | Barrier method for quick |
| CN106650640A (en) * | 2016-12-05 | 2017-05-10 | 浙江大学 | Negative obstacle detection method based on local structure feature of laser radar point cloud |
| CN107092020A (en) * | 2017-04-19 | 2017-08-25 | 北京大学 | Merge the surface evenness monitoring method of unmanned plane LiDAR and high score image |
Non-Patent Citations (1)
| Title |
|---|
| 杜跃武: "《平原地区县乡公路改建与养护》", 31 October 2004 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110487245A (en) * | 2019-08-16 | 2019-11-22 | 中国民用航空总局第二研究所 | Civil airport glide-path localizer protection zone place real-time monitoring analyzing system and its method |
| WO2021053679A2 (en) | 2019-09-22 | 2021-03-25 | Vayavision Sensing Ltd. | Methods and systems for autonomous driving of vehicles |
| EP4031426A4 (en) * | 2019-09-22 | 2023-08-30 | Vayavision Sensing Ltd. | Methods and systems for autonomous driving of vehicles |
| WO2021098161A1 (en) * | 2019-11-20 | 2021-05-27 | 中铁四局集团第一工程有限公司 | Pavement flatness measurement method and system |
| CN111123278A (en) * | 2019-12-30 | 2020-05-08 | 科沃斯机器人股份有限公司 | Partitioning method, device and storage medium |
| CN111123278B (en) * | 2019-12-30 | 2022-07-12 | 科沃斯机器人股份有限公司 | Partitioning method, partitioning equipment and storage medium |
| CN113129255A (en) * | 2019-12-31 | 2021-07-16 | 杭州海康机器人技术有限公司 | Method, computing device, system and storage medium for detecting package |
| CN111208533A (en) * | 2020-01-09 | 2020-05-29 | 上海工程技术大学 | Real-time ground detection method based on laser radar |
| CN111208530B (en) * | 2020-01-15 | 2022-06-17 | 北京四维图新科技股份有限公司 | Positioning layer generation method and device, high-precision map and high-precision map equipment |
| CN111208530A (en) * | 2020-01-15 | 2020-05-29 | 北京四维图新科技股份有限公司 | Positioning layer generation method and device, high-precision map and high-precision map equipment |
| CN111999741A (en) * | 2020-01-17 | 2020-11-27 | 青岛慧拓智能机器有限公司 | Method and device for detecting roadside laser radar target |
| CN111999741B (en) * | 2020-01-17 | 2023-03-14 | 青岛慧拓智能机器有限公司 | Method and device for detecting roadside laser radar target |
| CN111239757B (en) * | 2020-03-12 | 2022-04-19 | 湖南大学 | Automatic extraction method and system for road surface characteristic parameters |
| CN111239757A (en) * | 2020-03-12 | 2020-06-05 | 湖南大学 | Automatic extraction method and system for road surface characteristic parameters |
| WO2021189479A1 (en) * | 2020-03-27 | 2021-09-30 | 深圳市速腾聚创科技有限公司 | Pose correction method and device for roadbed sensor, and roadbed sensor |
| CN112199991A (en) * | 2020-08-27 | 2021-01-08 | 广州中国科学院软件应用技术研究所 | Simulation point cloud filtering method and system applied to vehicle-road cooperative roadside sensing |
| CN112199991B (en) * | 2020-08-27 | 2024-04-30 | 广州中国科学院软件应用技术研究所 | Simulation point cloud filtering method and system applied to vehicle-road cooperation road side perception |
| CN112129266A (en) * | 2020-09-28 | 2020-12-25 | 北京嘀嘀无限科技发展有限公司 | Method, apparatus, device and computer readable storage medium for processing map |
| CN111932943B (en) * | 2020-10-15 | 2021-05-14 | 深圳市速腾聚创科技有限公司 | Dynamic target detection method and device, storage medium and roadbed monitoring equipment |
| CN111932943A (en) * | 2020-10-15 | 2020-11-13 | 深圳市速腾聚创科技有限公司 | Dynamic target detection method and device, storage medium and roadbed monitoring equipment |
| CN112348781A (en) * | 2020-10-26 | 2021-02-09 | 广东博智林机器人有限公司 | Method, device and equipment for detecting height of reference plane and storage medium |
| CN113970295A (en) * | 2021-09-28 | 2022-01-25 | 湖南三一中益机械有限公司 | Paving thickness measuring method and device and paver |
| CN113970295B (en) * | 2021-09-28 | 2024-04-16 | 湖南三一中益机械有限公司 | Spreading thickness measuring method and device and spreading machine |
| CN114322856A (en) * | 2021-12-16 | 2022-04-12 | 青岛慧拓智能机器有限公司 | Mining area pavement flatness detection method and device, storage medium and equipment |
| CN114322856B (en) * | 2021-12-16 | 2023-09-15 | 青岛慧拓智能机器有限公司 | Mining area pavement evenness detection method, device, storage medium and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110084116B (en) | 2022-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084116A (en) | Pavement detection method, apparatus, computer equipment and storage medium | |
| Dai et al. | Comparison of image-based and time-of-flight-based technologies for three-dimensional reconstruction of infrastructure | |
| CN111815707B (en) | Point cloud determining method, point cloud screening method, point cloud determining device, point cloud screening device and computer equipment | |
| EP2304688B1 (en) | Automated building outline detection | |
| CN108885791A (en) | ground detection method, related device and computer readable storage medium | |
| JP7156515B2 (en) | Point cloud annotation device, method and program | |
| WO2019126972A1 (en) | Deformation information extraction method using insar, terminal, and storage medium | |
| US20160133007A1 (en) | Crack data collection apparatus and server apparatus to collect crack data | |
| JP2016090548A (en) | Crack information collection method and crack information collection program | |
| CN109141384A (en) | Acquisition and preprocess method to data before the detection after subway tunnel completion | |
| CN111462073B (en) | Quality inspection method and device for point cloud density of airborne laser radar | |
| CN115203778A (en) | Tunnel overbreak and underexcavation detection method and device, terminal equipment and storage medium | |
| CN105023270A (en) | Proactive 3D stereoscopic panorama visual sensor for monitoring underground infrastructure structure | |
| Lang et al. | Pavement cracking detection and classification based on 3d image using multiscale clustering model | |
| CN114565722A (en) | Three-dimensional model monomer realization method | |
| JP2015005143A (en) | Data analyzer, data analysis method, and program | |
| CN108875184B (en) | Shale organic carbon content prediction method and device based on digital outcrop model | |
| CN117269940B (en) | Point cloud data generation method and perception capability verification method of laser radar | |
| CN114549440A (en) | Method and device for detecting dynamic geometric parameters of contact network and electronic equipment | |
| CN113446932A (en) | Non-contact crack measuring method and system | |
| Zhao et al. | Intelligent segmentation method for blurred cracks and 3D mapping of width nephograms in concrete dams using UAV photogrammetry | |
| CN116049945A (en) | Tunnel construction engineering quantity measuring method, device, equipment and storage medium | |
| JP6546898B2 (en) | Three-dimensional space identification apparatus, method, and program | |
| CN114524097B (en) | Survey unmanned aerial vehicle survey device for survey and drawing geographic information | |
| Xi et al. | Automatic spacing inspection of rebar spacers on reinforcement skeletons using vision-based deep learning and computational geometry |
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 |