CN111485475A - Pavement pit recognition method and device - Google Patents
Pavement pit recognition method and device Download PDFInfo
- Publication number
- CN111485475A CN111485475A CN202010328827.0A CN202010328827A CN111485475A CN 111485475 A CN111485475 A CN 111485475A CN 202010328827 A CN202010328827 A CN 202010328827A CN 111485475 A CN111485475 A CN 111485475A
- Authority
- CN
- China
- Prior art keywords
- image
- pit
- camera
- gray
- processing unit
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000007906 compression Methods 0.000 claims description 4
- 230000006835 compression Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 description 9
- 230000000007 visual effect Effects 0.000 description 4
- 238000009434 installation Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 239000010426 asphalt Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E01—CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
- E01C—CONSTRUCTION OF, OR SURFACES FOR, ROADS, SPORTS GROUNDS, OR THE LIKE; MACHINES OR AUXILIARY TOOLS FOR CONSTRUCTION OR REPAIR
- E01C23/00—Auxiliary devices or arrangements for constructing, repairing, reconditioning, or taking-up road or like surfaces
- E01C23/01—Devices or auxiliary means for setting-out or checking the configuration of new surfacing, e.g. templates, screed or reference line supports; Applications of apparatus for measuring, indicating, or recording the surface configuration of existing surfacing, e.g. profilographs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Road Repair (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention specifically discloses a pavement pit recognition method, which comprises the following steps: step S1: an image acquisition unit is used for acquiring a road surface gray level image and a corresponding color image and sending the road surface gray level image and the corresponding color image to an image processing unit; step S2: preprocessing the collected gray level image by using the image processing unit; step S3: extracting the pit edge by using the image processing unit, calculating relevant parameters such as pit area, maximum pit depth, pit volume and the like by using camera calibration parameters, and modeling to obtain a pit three-dimensional image; the invention also specifically discloses a pavement pit recognition device, which comprises a detection vehicle body, an image acquisition unit, an image processing unit and a GPS (global positioning system) positioner; the device and the identification method thereof can be used for positioning the pit slot in daily road patrol work of a highway management department, and can also be used for identifying the pit slot and calculating parameters in the road surface repairing process, thereby improving the operation efficiency.
Description
Technical Field
The invention belongs to the technical field of road detection, and particularly relates to a method and a device for identifying a road pit.
Background
Pavement pit refers to the road surface and gathers materials and lose and the hole that forms on the surface of the road surface, and pit belongs to asphalt pavement and is more common and influence one of great diseases, and pit disease on the road surface can lead to current vehicle to jolt, influences people and uses travelling comfort and security, can influence the life of vehicle in the long term, threatens life safety. Therefore, the method for detecting the road surface pit and the device for designing the road surface pit and the groove have important significance.
The current road surface pit detection technology can be roughly divided into two types. One is a two-dimensional road surface pit detection method based on a single camera, and the method has the defects that the depth information of the road surface pit cannot be obtained; the other type is a road surface pit parameter three-dimensional detection method using line laser or binocular stereo vision, wherein the line laser method acquires road surface three-dimensional data by using a triangulation principle through a vehicle-mounted camera and a line laser transmitter. The method has complex camera registration and is easy to generate larger errors.
Therefore, a method and a device for detecting the pavement pit with low cost and high precision capable of acquiring three-dimensional information of the pit are needed.
Disclosure of Invention
The invention aims to provide a method and a device for identifying a pavement pit, which solve the problems of incomplete pavement information acquisition, high cost and complex operation in the prior art.
The invention adopts the technical scheme for solving the technical problems that:
a pavement pit recognition method comprises the following steps:
step S1: an image acquisition unit is used for acquiring a gray level image and a corresponding color image of a road surface and sending the gray level image and the corresponding color image to an image processing unit;
step S2: utilizing an image processing unit to carry out restoration pretreatment on the acquired gray level image;
step S3: and extracting the pit edge by using the image processing unit, calculating relevant parameters such as the pit area, the maximum pit depth, the pit volume and the like by using the camera calibration parameters, and modeling to obtain a three-dimensional pit image. The specific process comprises the following steps:
s301: converting a gray value in the collected gray image into an actual distance value, and converting a pixel coordinate of the gray image with an actual coordinate;
s302: determining the threshold value of pit division, converting the gray image into a binary image through the threshold value to obtain the pit edge, namely
Then, the surface area of the pit was calculated
Volume of pit
In the above formula, lpRepresenting a real length value represented by each pixel, x and y respectively representing an abscissa and an ordinate in an image coordinate system, p (x, y) representing a binary pit image indicating whether a point at a (x, y) position is a pit or not, and d (x, y) representing a depth value of the pit at the (x, y) position; and screening the maximum gray value, namely the maximum depth of the corresponding pit, and subtracting the ground reference value from the maximum gray value to obtain the maximum depth of the pit.
Preferably, in step S1, the image capturing unit uses a Kinect camera, before the Kinect camera captures the grayscale image of the road surface and the corresponding color image, the Kinect camera captures a checkered color image and the grayscale image, and performs camera parameter calibration according to the captured image to obtain calibration parameters, including:
calibrating checkerboard color images and gray level images shot by the Kinect camera by adopting a Zhang Zhenyou 2D checkerboard calibration method to obtain internal parameters of the Kinect camera, wherein the internal parameters comprise a depth camera focal length fxAnd fyCenter point coordinate c of depth cameraxAnd cy。
Preferably, in step S2, the preprocessing the acquired grayscale image by the image processing unit includes:
repairing the collected gray level image by adopting a median filtering method and a hole removing algorithm to obtain a repaired gray level image; wherein, the hole removing algorithm adopts a fast marching method.
Preferably, in step S301, the conversion method specifically includes:
if the installation height of the Kinect camera plane and the reference ground is H, and the gray value of the gray image at any position is g, the distance Z between any position of the pit slot and the video camera is × 25.5.5 + g (floor (H/25.5)), wherein the floor represents the downward rounding, and the conversion from the gray image coordinate to the actual coordinate can be completed through the following two formulas
Where x and y represent the abscissa and ordinate in the image coordinate system, respectively, and X, Y represent the numerical values in the actual coordinate system, respectively.
Preferably, in step S302, the threshold is 10 mm.
A pavement pit slot recognition device is characterized by comprising a detection vehicle body, wherein an image processing unit is arranged in the vehicle body of the detection vehicle body, a horizontally arranged fixed flat plate extends out of the rear end of the detection vehicle body, vertical baffles are respectively arranged on two sides of the fixed flat plate, a buffer structure is fixed on the fixed flat plate, an image acquisition unit is arranged on the fixed buffer structure, a GPS (global positioning system) positioner is further arranged on the detection vehicle body, and the GPS positioner is connected with the image processing unit;
wherein the content of the first and second substances,
the image acquisition unit is used for acquiring image data of a road surface of the detection road;
the GPS positioner is used for acquiring the position parameters of the pavement pit slot;
and the image processing unit is used for analyzing and processing the acquired road surface pit image data.
Preferably, the image acquisition unit is fixed in on the fixed flat board through fixed buffer structure, fixed buffer structure includes L type fixed plate, the horizontal part of L type fixed plate is fixed in on the fixed flat board through fastening screw, the vertical part of L type fixed plate passes through spherical hinge and camera fixing device swing joint, camera fixing device upper surface is provided with the spirit level, the last one side of keeping away from the vertical part of L type fixed plate of camera fixing device is provided with the slip track that is used for installing the image acquisition unit, still be provided with two sets of stop device in the slip track, install respectively at the both ends that the image acquisition unit is located the slip track camera, fix the image acquisition unit at current position.
Preferably, stop device includes L type canned paragraph, perpendicular movable section and horizontal movable section, all be provided with the mounting groove on L type canned paragraph's the vertical part and the horizontal part, be provided with the annular fixed slot round the periphery of mounting groove between the outer wall of mounting groove internal surface and L type canned paragraph, the one end that is close to L type canned paragraph on perpendicular movable section and the horizontal movable section is provided with respectively with mounting groove matched with adaptation groove to and insert the hollow post of annular in the annular fixed slot, be provided with compression spring in the mounting groove.
Preferably, the image processing unit is a Kinect camera, and a camera shooting end of the Kinect camera is arranged downwards towards the fixed flat plate; the image processing unit is a computer.
Compared with the prior art, the invention has the beneficial effects that: the device and the method have the characteristics of low cost, simplicity in operation and accuracy in calculation, can be used for identifying the pit slot and calculating parameters in the automatic pavement repair process, and can also be used for positioning the pit slot in daily road patrol of a highway management department, so that the corresponding working efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic view of a pavement pit recognition apparatus provided in the present invention;
FIG. 2 is a schematic diagram of a Kinect camera fixed by a fixed buffer structure;
FIG. 3 is a schematic view of a fixed cushioning structure;
FIG. 4 is a side view of the fixed cushioning structure;
FIG. 5 is a cross-sectional view of the spacing device;
FIG. 6 is an installation view of the stop device;
FIG. 7 is a flow chart of a method for identifying a pavement pit provided by the present invention;
FIG. 8 is a depth image taken by a Kinect camera;
fig. 9 illustrates the pit edge identified by the present invention;
fig. 10 is a three-dimensional image of a pit obtained by a modeling algorithm in the present invention.
The device comprises a detection vehicle body 1, a 2-Kinect camera, a 3-L type fixing plate, a 4-computer, a 5-camera fixing device, a 501-sliding track, a 6-limiting device, a 601-L type fixing section, a 602-horizontal moving section, a 603-vertical moving section, a 604-compression spring, a 605-annular hollow column, a 7-spherical hinge and an 8-level meter.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a pavement pit recognition device, which comprises a detection vehicle body 1, wherein an image processing unit 4 is arranged in the vehicle body of the detection vehicle body 1, a horizontally arranged fixed flat plate extends out of the rear end of the detection vehicle body, vertical baffles are respectively arranged on two sides of the fixed flat plate, a fixed buffer structure is arranged on the fixed flat plate, an image acquisition unit is arranged on the fixed buffer structure, an acquisition element of the image acquisition unit is a Kinect camera 2, a GPS (global positioning system) positioner is also arranged on the detection vehicle body 1, and the GPS positioner is connected with the image processing unit.
The image acquisition unit is used for acquiring image data of a road surface of a detection road; the GPS positioner is used for acquiring the position parameters of the pavement pit slot; and the image processing unit is used for carrying out image analysis and processing on the acquired road surface pit image data. Each unit of the detection vehicle body, which is mainly used for road surface detection, provides a mechanical carrying platform and a stable power supply.
Preferably, the image processing unit is a computer.
As a further improvement of the present invention, as shown in fig. 2-4, the Kinect camera 2 is fixed on the fixed flat plate by a fixed buffer structure, the fixed buffer structure includes an L-type fixed plate 3, a horizontal portion of the L-type fixed plate 3 is fixed on the fixed flat plate by fastening screws, a vertical portion of the L-type fixed plate 3 is movably connected with a camera fixing device 5 by a spherical hinge 7, a level 8 is disposed on an upper surface of the camera fixing device 5, a sliding rail 501 for mounting the Kinect camera 2 is disposed on one side of the camera fixing device 5 away from the vertical portion of the L-type fixed plate 3, and two sets of position-limiting devices 6 are further disposed in the sliding rail 501 and respectively mounted at two ends of a portion of the Kinect camera 2 located in the sliding rail 502 to fix the Kinect camera 2 at the current position.
In this embodiment, as shown in fig. 5 to 6, the position-limiting device 6 includes L-type fixed sections 601, vertical movable sections 603, and horizontal movable sections 602, wherein each of the vertical part and the horizontal part of the L-type fixed section 601 is provided with a mounting groove, an annular fixing groove is provided between the inner surface of the mounting groove and the outer wall of the L-type fixed section 601 around the periphery of the mounting groove, an adapting groove matched with the mounting groove is provided at one end of each of the vertical movable section 603 and the horizontal movable section 602 close to the L-type fixed section 601, and an annular hollow column 605 is inserted into the annular fixing groove, and a compression spring 604 is provided in the mounting groove.
When the Kinect camera 2 is installed, the method comprises the following steps:
firstly, a base of the Kinect camera 2 is inserted into a sliding rail 501 of a camera fixing device 5 in parallel, the left and right directions of the Kinect camera 2 in the sliding rail 501 are adjusted to appropriate positions, and after the positions are determined, two groups of limiting devices 6 are respectively compressed from two ends of the sliding rail into the sliding rail 501 to fix the Kinect camera 2 at the positions.
Then, the camera fixing device 5 rotates around the L-shaped fixing plate 3 through the spherical hinge 7 to adjust the parallelism between the plane of the Kinect camera 2 and the ground, the parallelism between the Kinect camera 2 and the ground can be adjusted to be optimal through the level gauge 8 in the adjusting process, and the angle of the camera is guaranteed not to change in the driving process of the vehicle.
The invention also provides a pavement pit recognition method, as shown in fig. 7, comprising the following steps:
step S1: an image acquisition unit is used for acquiring a gray level image and a corresponding color image of a road surface and sending the gray level image and the corresponding color image to an image processing unit; the gray value of the gray image is 0-255, the gray value corresponds to the distance between the Kinect camera plane and the shot object, the larger the gray value is, the farther the distance is represented, and in the example, the pit depth is larger;
step S2: preprocessing the acquired gray level image by using an image processing unit: the gray level image acquired by the Kinect camera has many defects, mainly comprises holes and noise, and is repaired by adopting a median filtering method and a fast marching method to obtain a repaired gray level image;
step S3: and extracting the pit edge by using the image processing unit, calculating relevant parameters such as the pit area, the maximum pit depth, the pit volume and the like, and modeling to obtain a three-dimensional pit image. The specific process comprises the following steps:
s301: converting a gray value in the collected gray image into an actual distance value, and converting a pixel coordinate of the gray image with an actual coordinate; wherein, the conversion mode specifically includes:
if the installation height of the Kinect camera plane and the reference ground is H, and the gray value of the gray image at any position is g, the distance Z between any position of the pit slot and the video camera is × 25.5.5 + g (floor (H/25.5)), wherein the floor represents the downward rounding, and the conversion from the gray image coordinate to the actual coordinate can be completed through the following two formulas
Wherein x and y respectively represent an abscissa and an ordinate in an image coordinate system, and X, Y respectively represent numerical values in an actual coordinate system;
s302: determining a threshold value of pit slot segmentation, wherein the threshold value is 10mm, the depth value is larger than the threshold value and is considered as a pit slot, and the depth value is smaller than the threshold value and is considered as a road surface; then converting the gray level image into a binary image through a threshold value to obtain the pit edge, namely
Then, the surface area of the pit was calculated
Volume of pit
In the above formula, lpRepresenting a real length value represented by each pixel, x and y respectively representing an abscissa and an ordinate in an image coordinate system, p (x, y) representing a binary pit image indicating whether a point at a (x, y) position is a pit or not, and d (x, y) representing a depth value of the pit at the (x, y) position; and screening the maximum gray value, namely the maximum depth of the corresponding pit, and subtracting the ground reference value from the maximum gray value to obtain the maximum depth of the pit.
Wherein lpThe calculation process of (2) is as follows:
the Kinect horizontal visual field and the vertical visual field are respectively 70 degrees and 60 degrees, the size of a depth image is 512 × 424 pixels, h represents the height of a camera from the ground, B represents a ground plane shot by the Kinect depth camera, A represents a shooting point of the depth camera, the included angle between the A point and the long side of a B plane is α to 70 degrees, represents the horizontal visual field, and the included angle between the A point and the short side of the B plane is β to 60 degrees, represents the vertical visual field, and the area represented by B is mathematically:
substituting α ° 70 ° and β ° 60 ° into the above formula yields B4 × tan35 ° × tan30 ° h2. The length value l represented by each pixelpExpressed as the ratio of true size to image pixel:
when the volume and the surface area are calculated specifically, the height value of a specific image is taken in, and l can be calculatedp。
It should be noted that in this embodiment, the operation process of the Kinect camera is to continuously acquire a road color image and a gray scale image at fixed intervals.
Preferably, in step S1, the image capturing unit uses a Kinect camera, and before the Kinect camera captures the grayscale image of the road surface and the corresponding color image, the Kinect camera is used to capture checkered color images and grayscale images, and camera parameter calibration is performed according to the captured images to obtain calibration parameters. The method specifically comprises the following steps:
calibrating checkerboard color images and gray level images shot by the Kinect camera by adopting a Zhang Zhenyou 2D checkerboard calibration method to obtain internal parameters of the Kinect camera, wherein the internal parameters comprise a depth camera focal length fxAnd fyCenter point coordinate c of depth cameraxAnd cy。
In this embodiment, as shown in fig. 8, the collected grayscale image is written in matlab according to the automatic road pit and slot identification algorithm. The maximum depth, perimeter, surface area, volume are calculated. The image edge shown in fig. 9 and the three-dimensional image of the pit shown in fig. 10 are obtained by utilizing the steps of the pit recognition algorithm, and the parameter values of the pit can be visually represented from the image. The matlab is used for compiling the area and volume calculation formula to obtain the surface area and the volume of the pit, the perimeter can be obtained by extracting and calculating the binary edge image, and the maximum depth can be obtained by using the calculation method. Specific data are the theoretical calculation data shown in the following table. In this example, the pit and groove data are actually measured and compared with the theoretical calculation, and the specific comparison result is shown in the following table.
| Parameter(s) | Actual measurement data | Theoretical calculation data | Relative error |
| Maximum depth (cm) | 10.00 | 9.90 | 1.818％ |
| Circumference (cm) | 103 | 105.7 | 2.621％ |
| Surface area (cm)2) | 820.58 | 837.56 | 2.069％ |
| Volume (cm)3) | 5160.00 | 5295.30 | 2.616％ |
It can be seen from the above table that the identification method of the present invention is not only convenient for calculation, but also has errors of the measured results of about 1% to 2%, and the errors are relatively negligible, which indicates that the identification method of the present invention can accurately calculate the pit parameters. The device and the method have the characteristics of low cost, simple operation and accurate calculation, can be used for identifying the pit slot and calculating parameters in the automatic pavement repairing process, and can also be used for positioning the pit slot in daily road patrol of a highway management department, thereby improving the efficiency of corresponding work.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the present invention in any way. Any simple modification, change and equivalent changes of the above embodiments according to the technical essence of the invention are still within the protection scope of the technical solution of the invention.
Claims (10)
1. A pavement pit recognition method is characterized by comprising the following steps:
step S1: an image acquisition unit is used for acquiring a gray level image and a corresponding color image of a road surface and sending the gray level image and the corresponding color image to an image processing unit;
step S2: restoring and preprocessing the collected gray level image by using the image processing unit;
step S3: the image processing unit is used for extracting the pit edge, the camera calibration parameters are used for calculating relevant parameters such as pit area, pit maximum depth and pit volume, and modeling is carried out to obtain a pit three-dimensional image, and the specific process is as follows:
s301: converting a gray value in the collected gray image into an actual distance value, and converting a pixel coordinate of the gray image with an actual coordinate;
s302: determining the threshold value of pit division, converting the gray image into a binary image through the threshold value to obtain the pit edge, namely
Then, the surface area of the pit was calculated
Volume of pit
In the above formula, lpRepresenting a real length value represented by each pixel, x and y respectively representing an abscissa and an ordinate in an image coordinate system, p (x, y) representing a binary pit image indicating whether a point at a (x, y) position is a pit or not, and d (x, y) representing a depth value of the pit at the (x, y) position; and screening the maximum gray value, namely the maximum depth of the corresponding pit, and subtracting the ground reference value from the maximum gray value to obtain the maximum depth of the pit.
2. The method as claimed in claim 1, wherein in step S1, the image capturing unit uses a Kinect camera, and before capturing the gray image of the road surface and the corresponding color image by the Kinect camera, the Kinect camera is used to capture checkered color image and gray image, and the camera parameters are calibrated according to the captured image to obtain calibration parameters.
3. The method for identifying the pavement pit slot as claimed in claim 2, wherein the step of capturing a checkerboard color image and a gray image by using the Kinect camera for calibration to obtain calibration parameters comprises:
calibrating checkerboard color images and gray level images shot by the Kinect camera by adopting a Zhang Zhenyou 2D checkerboard calibration method to obtain internal parameters of the Kinect camera, wherein the internal parameters comprise a depth camera focal length fxAnd fyCenter point coordinate c of depth cameraxAnd cy。
4. The method of claim 2, wherein in step S2, the pre-processing procedure of repairing the captured grayscale image by the image processing unit includes:
repairing the collected gray level image by adopting a median filtering method and a hole removing algorithm to obtain a repaired gray level image; wherein, the hole removing algorithm adopts a fast marching method.
5. The method for identifying a pavement pit according to claim 2, wherein in step S301, the conversion method specifically comprises:
if the mounting height of the Kinect camera plane and the reference ground is H, and the gray value of the gray image at any position is g, the distance Z between any position of the pit and the video camera is (floor (H/25.5)) × 25.5.5 + g, wherein floor represents rounding, and the method can be completed by the following two formulasConversion of gray scale image coordinates to actual coordinates
Where x and y represent the abscissa and ordinate in the image coordinate system, respectively, and X, Y represent the numerical values in the actual coordinate system, respectively.
6. A pavement pit recognition method according to claim 5, wherein in step S302, said threshold value is 10 mm.
7. A pavement pit recognition device based on the pavement pit recognition method of any one of claims 1-6, comprising a detection vehicle body, wherein an image processing unit is arranged in the vehicle body of the detection vehicle body, a horizontally arranged fixed flat plate extends out of the rear end of the detection vehicle body, vertical baffles are respectively arranged on two sides of the fixed flat plate, a fixed buffer structure is arranged on the fixed flat plate, an image acquisition unit is arranged on the fixed buffer structure, a GPS (global positioning system) positioner is further arranged on the detection vehicle body, and the GPS positioner is connected with the image processing unit;
wherein the content of the first and second substances,
the image acquisition unit is used for acquiring image data of a road surface of the detection road;
the GPS positioner is used for acquiring the position parameters of the pavement pit slot;
and the image processing unit is used for analyzing and processing the acquired road surface pit image data.
8. The device as claimed in claim 7, wherein the image capturing unit is fixed on the fixing plate by a fixing buffer structure, the fixing buffer structure comprises an L-type fixing plate, the horizontal portion of the L-type fixing plate is fixed on the fixing plate by fastening screws, the vertical portion of the L-type fixing plate is movably connected with the camera fixing device by a spherical hinge, the level gauge is disposed on the upper surface of the camera fixing device, a sliding rail for mounting the image capturing unit is disposed on the side of the camera fixing device away from the vertical portion of the L-type fixing plate, and two sets of position limiting devices are disposed in the sliding rail and respectively mounted at two ends of the camera of the image capturing unit located in the sliding rail for fixing the camera of the image capturing unit at the current position.
9. The pavement pit recognition device of claim 8, wherein the position-limiting device comprises L-type fixed sections, a vertical movable section and a horizontal movable section, wherein each of the L-type fixed sections has a mounting groove formed on its vertical portion and horizontal portion, an annular fixing groove is formed between the inner surface of the mounting groove and the outer wall of the L-type fixed section around the periphery of the mounting groove, and the ends of the vertical movable section and the horizontal movable section near the L-type fixed section are respectively provided with an adapting groove matched with the mounting groove and an annular hollow column inserted into the annular fixing groove, and a compression spring is disposed in the mounting groove.
10. The device for identifying pavement pits as claimed in claim 8, wherein the image processing unit is a Kinect camera, and a camera end of the Kinect camera is arranged downward towards the fixed flat plate; the image processing unit is a computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010328827.0A CN111485475B (en) | 2020-04-23 | 2020-04-23 | Pavement pit recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010328827.0A CN111485475B (en) | 2020-04-23 | 2020-04-23 | Pavement pit recognition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111485475A true CN111485475A (en) | 2020-08-04 |
| CN111485475B CN111485475B (en) | 2021-12-28 |
Family
ID=71813113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010328827.0A Expired - Fee Related CN111485475B (en) | 2020-04-23 | 2020-04-23 | Pavement pit recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111485475B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112560707A (en) * | 2020-12-18 | 2021-03-26 | 中国民用航空总局第二研究所 | Mobile road surface detection method and system based on laser light source |
| CN113486854A (en) * | 2021-07-29 | 2021-10-08 | 北京超维世纪科技有限公司 | Recognition detection algorithm for realizing industrial inspection robot based on depth camera |
| CN113516127A (en) * | 2021-09-14 | 2021-10-19 | 南通辑兴紧固件科技有限公司 | Artificial intelligence-based smart city highway maintenance method and system |
| CN113658144A (en) * | 2021-08-20 | 2021-11-16 | 中国公路工程咨询集团有限公司 | Method, device, equipment and medium for determining pavement disease geometric information |
| CN114775386A (en) * | 2022-04-18 | 2022-07-22 | 中电建路桥集团有限公司 | Pit slot identification and segmentation method based on machine vision |
| CN115424232A (en) * | 2022-11-04 | 2022-12-02 | 深圳市城市交通规划设计研究中心股份有限公司 | Method for identifying and evaluating pavement pit, electronic equipment and storage medium |
| CN117496189A (en) * | 2024-01-02 | 2024-02-02 | 中国石油大学(华东) | Rectangular tray hole identification method and system based on depth camera |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103266552A (en) * | 2013-05-09 | 2013-08-28 | 江苏科技大学 | Depth image based pavement detection system |
| CN105133471A (en) * | 2015-05-15 | 2015-12-09 | 南京航空航天大学 | Linear structured light pavement surface detection system-based pavement depth image production method |
| CN206556605U (en) * | 2017-01-25 | 2017-10-13 | 东南大学 | The image scanning of carrying Kinect a kind of and three-dimensional modeling equipment platform |
| CN108149554A (en) * | 2017-12-28 | 2018-06-12 | 长安大学 | A kind of road surface pit slot recognition methods and its device |
| US20200057895A1 (en) * | 2018-08-20 | 2020-02-20 | Hyundai Motor Company | Road surface detecting apparatus and method for detecting road surface |
-
2020
- 2020-04-23 CN CN202010328827.0A patent/CN111485475B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103266552A (en) * | 2013-05-09 | 2013-08-28 | 江苏科技大学 | Depth image based pavement detection system |
| CN105133471A (en) * | 2015-05-15 | 2015-12-09 | 南京航空航天大学 | Linear structured light pavement surface detection system-based pavement depth image production method |
| CN206556605U (en) * | 2017-01-25 | 2017-10-13 | 东南大学 | The image scanning of carrying Kinect a kind of and three-dimensional modeling equipment platform |
| CN108149554A (en) * | 2017-12-28 | 2018-06-12 | 长安大学 | A kind of road surface pit slot recognition methods and its device |
| US20200057895A1 (en) * | 2018-08-20 | 2020-02-20 | Hyundai Motor Company | Road surface detecting apparatus and method for detecting road surface |
Non-Patent Citations (1)
| Title |
|---|
| 常丽园: "基于Kinect的坑槽修补检测系统研究", 《工程科技II辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112560707A (en) * | 2020-12-18 | 2021-03-26 | 中国民用航空总局第二研究所 | Mobile road surface detection method and system based on laser light source |
| CN112560707B (en) * | 2020-12-18 | 2022-10-21 | 中国民用航空总局第二研究所 | Mobile road surface detection method and system based on laser light source |
| CN113486854A (en) * | 2021-07-29 | 2021-10-08 | 北京超维世纪科技有限公司 | Recognition detection algorithm for realizing industrial inspection robot based on depth camera |
| CN113658144A (en) * | 2021-08-20 | 2021-11-16 | 中国公路工程咨询集团有限公司 | Method, device, equipment and medium for determining pavement disease geometric information |
| CN113516127A (en) * | 2021-09-14 | 2021-10-19 | 南通辑兴紧固件科技有限公司 | Artificial intelligence-based smart city highway maintenance method and system |
| CN113516127B (en) * | 2021-09-14 | 2021-12-07 | 南通辑兴紧固件科技有限公司 | Artificial intelligence-based smart city highway maintenance method and system |
| CN114775386A (en) * | 2022-04-18 | 2022-07-22 | 中电建路桥集团有限公司 | Pit slot identification and segmentation method based on machine vision |
| CN115424232A (en) * | 2022-11-04 | 2022-12-02 | 深圳市城市交通规划设计研究中心股份有限公司 | Method for identifying and evaluating pavement pit, electronic equipment and storage medium |
| CN117496189A (en) * | 2024-01-02 | 2024-02-02 | 中国石油大学(华东) | Rectangular tray hole identification method and system based on depth camera |
| CN117496189B (en) * | 2024-01-02 | 2024-03-22 | 中国石油大学(华东) | Rectangular tray hole identification method and system based on depth camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111485475B (en) | 2021-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111485475B (en) | Pavement pit recognition method and device | |
| CN111855664B (en) | Adjustable three-dimensional tunnel defect detection system | |
| CN106053475B (en) | Tunnel defect tunneling boring dynamic device for fast detecting based on active panoramic vision | |
| CN106978774B (en) | A kind of road surface pit slot automatic testing method | |
| CN112418103B (en) | Bridge crane hoisting safety anti-collision system and method based on dynamic binocular vision | |
| CN110031829B (en) | Target accurate distance measurement method based on monocular vision | |
| CN110174059B (en) | Monocular image-based pantograph height and pull-out value measuring method | |
| CN113221682B (en) | Bridge vehicle load space-time distribution fine-grained identification method based on computer vision | |
| CN110567680B (en) | Track fastener looseness detection method based on angle comparison | |
| CN112950532B (en) | Train pantograph state detection method | |
| CN107798293A (en) | A kind of crack on road detection means | |
| CN113808096B (en) | Non-contact bolt loosening detection method and system | |
| CN110700056B (en) | Asphalt pavement disease monitoring system and monitoring method | |
| CN113554697A (en) | Cabin section profile accurate measurement method based on line laser | |
| CN115797338B (en) | Panoramic pavement multi-performance index calculation method and system based on binocular vision | |
| CN104239904A (en) | Non-contact detection method for external outline of railway vehicle | |
| CN111879264A (en) | Flatness measurement and evaluation system based on line structured light | |
| CN112288717A (en) | Method for detecting foreign matters on side part of motor train unit train | |
| CN112288802A (en) | Laser measurement light spot center positioning method for crane track | |
| CN104236866B (en) | Car headlamp error information detection correcting method based on direction of traffic | |
| CN112964195B (en) | Power supply rail geometric parameter comprehensive detection method and system based on laser triangulation method | |
| CN113607058B (en) | Straight blade size detection method and system based on machine vision | |
| CN113191239A (en) | Vehicle overall dimension dynamic detection system based on computer vision | |
| CN112950562A (en) | Fastener detection algorithm based on line structured light | |
| CN108108706B (en) | Method and system for optimizing sliding window in target detection |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20211228 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |