CN105891220B - A kind of pavement marker line defect detection device and its detection method - Google Patents
A kind of pavement marker line defect detection device and its detection method Download PDFInfo
- Publication number
- CN105891220B CN105891220B CN201610390149.4A CN201610390149A CN105891220B CN 105891220 B CN105891220 B CN 105891220B CN 201610390149 A CN201610390149 A CN 201610390149A CN 105891220 B CN105891220 B CN 105891220B
- Authority
- CN
- China
- Prior art keywords
- detection
- marker line
- pavement marker
- image information
- information
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8861—Determining coordinates of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/8874—Taking dimensions of defect into account
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/888—Marking defects
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of pavement marker line defect detection device and its detection methods, comprising: image information collecting unit is fixedly installed on the left and right sides of detection vehicle tailstock lower part, to obtain the pavement image information of detection vehicle present position and generate picture；Image information processing unit, input terminal are electrically connected with the output end of image information collecting unit, to the area of acquisition pavement marker line and the data information of shape after identifying the pavement marker line of road surface image information in picture and handling；Image information detection unit, input terminal are electrically connected with the output end of image information processing unit, to detect the defect and breakage of pavement marker line；Locating information acquisition unit, to obtain the geographical location information of pavement marker line.The present invention compared to the prior art, using the integrated of detection vehicle and detection device, reduces the security risk in detection process, also avoid complex road surface is influenced by vehicle and pedestrian, and the accuracy of detection is high, improves operating efficiency and quality.
Description
Technical field
The present invention relates to a kind of pavement marker line defect detection device and its detection methods.
Background technique
Modern Traffic system is very flourishing, but due to traffic safety problem, people are to road traffic environment
Demand is also higher and higher.Wherein, pavement marker line is the pith for guiding safe driving of vehicle, passes through pattern, symbol, text
Etc. being directly passed to driver, the accurate visual information of pedestrian.On the one hand effective pavement marker line can reduce traffic accident,
Ensure smooth traffic environment；Another aspect pavement marker line is also a part of road landscape cosmetic treatment.But use one
After the section time, the defects of pavement marker line will appear damaged, visibility retrogression of nature, its traffic direction-pointing function and road beauty are influenced
It sees, therefore, from road maintenance, the defect breakage of road pavement markings is needed to carry out periodic detection.
Existing traditional detection method is artificial situ visualization evaluation or hand dipping acquisition, the disadvantage is that it is time-consuming and laborious,
And the accuracy of data is vulnerable to interference from human factor, while there are security risks for collection in worksite operation.
Existing novel detection method is to detect pavement marker line using NI Vision Builder for Automated Inspection, but this means are chiefly used in vehicle
Navigation system.The disadvantage is that being interfered in complex road surface vulnerable to the non-detections information such as vehicle, pedestrian, and cannot be to detected
Pavement marker line is accurately positioned.
Summary of the invention
In order to solve the above-mentioned technical problems, the present invention provides a kind of pavement marker line defect detection device and its detection sides
Method.
In order to achieve the above object, technical scheme is as follows:
The present invention provides a kind of pavement marker line defect detection device, comprising:
Image information collecting unit is fixedly installed on the left and right sides of detection vehicle tailstock lower part, to obtain detection vehicle
The pavement image information of present position simultaneously generates picture；
Image information processing unit, input terminal is electrically connected with the output end of image information collecting unit, to identify figure
The area of pavement marker line and the data information of shape are obtained after the pavement marker line of road surface image information and processing in piece；
Image information detection unit, input terminal is electrically connected with the output end of image information processing unit, to detect road
The defect and breakage of face markings；
Locating information acquisition unit, to obtain the geographical location information of pavement marker line.
The present invention compared to the prior art, using the integrated of detection vehicle and detection device, reduces the peace in detection process
Full hidden danger, also avoid complex road surface is influenced by vehicle and pedestrian, and the accuracy of detection is high, improves operating efficiency and matter
Amount.
Wherein, above-mentioned image information collecting unit includes two high-speed area array cameras, is fixedly installed on detection respectively
The left and right sides of vehicle tailstock lower part；
Above-mentioned locating information acquisition unit includes rotary encoder and GPS receiver, and rotary encoder is set to detection
To record the mileage travelled for detecting vehicle on the wheel of vehicle, GPS receiver is set to the ground on detection vehicle to obtain detection vehicle
Manage location information.
As a preferred option, above-mentioned locating information acquisition unit is connect with the on-vehicle navigation apparatus of detection vehicle, to
It obtains the geographical location information of detection vehicle and marks damaged pavement marker line position on the navigation map of on-vehicle navigation apparatus
To share to road-maintaining truck.
Please supplemental image information process unit composition and between connection relationship.
As a preferred option, above-mentioned be additionally provided with is fixed on the interior image information storage of detection and monitoring unit,
Including information memory card and car-mounted computer, the input terminal and image information detection unit, locating information acquisition of information memory card
The output end of unit is electrically connected, and the output end of information memory card is electrically connected with the input terminal of car-mounted computer, to being detected
Pavement image information, pavement marker line area and shape information, geographical location information and identification region it is whether damaged
Conclusion is stored and is shown.
Based on the above technical solution, following improvement can also be done:
As a preferred option, the present invention also provides a kind of pavement marker line defect detection method, above-mentioned road is applied
Face markings defect detecting device, comprising the following steps:
Step 1: driving detection vehicle drives into road to be detected, and it is true that locating information acquisition unit starts gathering geographic position information
The location information of regular inspection measuring car；
Step 2: in detection garage into the process, using two high-speed area array camera acquisition pavement image information and generating figure
Piece；
Step 3: pictorial information processing unit carries out image procossing according to the picture that two high-speed area array cameras photographed, and will scheme
Pavement marker line in piece identifies, determines the area of identification region and the data information of shape；
Step 4: pictorial information detection unit carries out image procossing according to the pavement marker line identified, detects road marking
Whether will line is defective and damaged.
As a preferred option, above-mentioned further includes step 5: the storage of control image information works with monitoring unit, information
Storage card by pavement marker line area and the data information of shape, geographical location information and identification region whether Po Sun knot
By storage, and will test as the result is shown on car-mounted computer.
As a preferred option, above-mentioned step 4 judges to detect the whether defective and damaged method packet of pavement marker line
Include following steps:
(1) coordinate system is established in the plane of identification region, with zone length direction for the direction x, width direction is the side y
To each point forms a regional space XY on region；
(2) identification region is divided into n sections in zone length direction, that is, direction x, it is identical small forms the n direction x size
Identification region；
(3) to n small identification regions, corresponding the least surrounding boxes are fitted respectively；
(4) it calculates according to the following formula:
Δ i=Ai-ai
Wherein, ΔiIndicate the damaged difference in areas of i-th small identification region, ai indicates the area of each small identification region, Ai
Indicate the area of the corresponding the least surrounding boxes of the 1st small identification region；
(5) it calculates according to the following formula:
Wherein, z indicates total damaged difference in areas of identification region；
(6) a damaged degree limiting value δ is set, if z≤δ, then it is assumed that without breakage；If z > δ, then it is assumed that there is breakage.
It is more acurrate, more effective for the rectangular degree for detecting pavement marker line using above-mentioned preferred embodiment.
As a preferred option, above-mentioned step 4 judges to detect the whether defective and damaged method packet of pavement marker line
Include following steps:
(1) coordinate system is established in the plane of identification region, with zone length direction for the direction x, width direction is the side y
To each point forms a regional space XY on region；
(2) identification region is divided into n sections in zone length direction, that is, direction x, it is identical small forms the n direction x size
Identification region；
(3) area for calculating each small identification region, is denoted asAnd the maximum region of area is found out, it is denoted as
(4) it calculates according to the following formula:
Wherein, α indicates total damaged difference in areas in the direction identification region x；
(5) identification region is divided into m sections in peak width direction, that is, direction y, forms the identical small knowledge of m direction size
Other region；
(6) area for calculating each small identification region, is denoted as Pj；And the maximum region of area is found out, it is denoted as P0；
(7) it calculates according to the following formula:
Wherein, b indicates total damaged difference in areas in the direction identification region y；
(8) it calculates according to the following formula: c=a+b
Wherein, c indicates the comprehensive damaged difference in areas of identification region；
(9) a damaged degree limiting value δ is set, if c≤δ, then it is assumed that without breakage；If c > δ, then it is assumed that there is breakage.
Detailed description of the invention
Fig. 1 is the structural block diagram of one embodiment of the present invention.
Fig. 2 is the structural schematic diagram of the detection vehicle of one embodiment of the present invention.
Fig. 3 is the flow chart of the pavement marker line defect detection method of one embodiment of the present invention.
Fig. 4 is the structural schematic diagram of the pavement marker line defect detection method of one embodiment of the present invention.
Fig. 5 is the flow chart of the pavement marker line defect detection method of another embodiment of the present invention.
Fig. 6 is the structural schematic diagram of the pavement marker line defect detection method of another embodiment of the present invention.
Wherein, 1. detection vehicle, 2. locating information acquisition units, 3. image information collecting units.
Specific embodiment
The preferred embodiment that the invention will now be described in detail with reference to the accompanying drawings.
In order to reach the purpose of the present invention, as shown in Figures 1 to 4, provided in one of embodiment of the invention
A kind of pavement marker line defect detection device, comprising:
Image information collecting unit 3 is fixedly installed on the left and right sides of detection 1 tailstock lower part of vehicle, to obtain detection
The pavement image information of 1 present position of vehicle simultaneously generates picture；
Image information processing unit, input terminal is electrically connected with the output end of image information collecting unit 3, to identify figure
The area of pavement marker line and the data information of shape are obtained after the pavement marker line of road surface image information and processing in piece；
Image information detection unit, input terminal is electrically connected with the output end of described image information process unit, to examine
Survey the defect and breakage of pavement marker line；
Locating information acquisition unit, to obtain the geographical location information of pavement marker line.
Present embodiment compared to the prior art, using the integrated of detection vehicle and detection device, reduces in detection process
Security risk, also avoid complex road surface is influenced by vehicle and pedestrian, and the accuracy of detection is high, improve operating efficiency and
Quality.
Wherein, above-mentioned image information collecting unit includes two high-speed area array cameras, is fixedly installed on detection respectively
The left and right sides of vehicle tailstock lower part；
Above-mentioned locating information acquisition unit includes rotary encoder and GPS receiver, and rotary encoder is set to detection
To record the mileage travelled for detecting vehicle on the wheel of vehicle, GPS receiver is set to the ground on detection vehicle to obtain detection vehicle
Manage location information.
In order to further optimize implementation result of the invention, in another embodiment of the invention, aforementioned interior
On the basis of appearance, above-mentioned locating information acquisition unit is connect with the on-vehicle navigation apparatus of detection vehicle, to obtain detection vehicle
Geographical location information simultaneously marks damaged pavement marker line position on the navigation map of on-vehicle navigation apparatus to share to road
It cares the car.
Please supplemental image information process unit composition and between connection relationship.
As a preferred option, above-mentioned be additionally provided with is fixed on the interior image information storage of detection and monitoring unit,
Including information memory card and car-mounted computer, the output end of the input terminal and locating information acquisition unit of information memory card is electrically connected
It connects, the output end of information memory card is electrically connected with the input terminal of car-mounted computer, to pavement image information detected, road
Data information, geographical location information and the identification region of the areas of face markings and shape whether deposited by Po Sun conclusion
Storage and display.
In order to further optimize implementation result of the invention, in another embodiment of the invention, aforementioned interior
On the basis of appearance, the present embodiment also provides a kind of pavement marker line defect detection method, applies above-mentioned pavement marker line and lacks
Fall into detection device, comprising the following steps:
Step 1: driving detection vehicle drives into road to be detected, and it is true that locating information acquisition unit starts gathering geographic position information
The location information of regular inspection measuring car；
Step 2: in detection garage into the process, using two high-speed area array camera acquisition pavement image information and generating figure
Piece；
Step 3: pictorial information processing unit carries out image procossing according to the picture that two high-speed area array cameras photographed, and will scheme
Pavement marker line in piece identifies, determines the area of identification region and the data information of shape；
Step 4: pictorial information detection unit carries out image procossing according to the pavement marker line identified, detects road marking
Whether will line is defective and damaged.
As a preferred option, above-mentioned further includes step 5: the storage of control image information works with monitoring unit, information
Storage card by pavement marker line area and the data information of shape, geographical location information and identification region whether Po Sun knot
By storage, and will test as the result is shown on car-mounted computer.
As shown in figure 3, in order to further optimize implementation result of the invention, in another embodiment of the invention
In, on the basis of foregoing teachings, above-mentioned step four judges to detect the whether defective and damaged method packet of pavement marker line
Include following steps:
(1) coordinate system is established in the plane of identification region, with zone length direction for the direction x, width direction is the side y
To each point forms a regional space XY on region；
(2) identification region is divided into n (n takes 5) section in zone length direction, that is, direction x, forms 5 direction x size phases
Same small identification region；
(3) to 5 small identification regions, corresponding the least surrounding boxes are fitted respectively；
(4) area for calculating the 1st small identification region, is denoted as a1；Calculate the corresponding minimum envelop of the 1st small identification region
The area of rectangle, is denoted as A1, calculate Δ1 =A1-a1；
The area for calculating the 2nd small identification region, is denoted as a2；Calculate the corresponding minimum envelop square of the 2nd small identification region
The area of shape, is denoted as A2, calculate: Δ2=A2-a2；
The area for calculating the 3rd small identification region, is denoted as a3；Calculate the corresponding minimum envelop square of the 3rd small identification region
The area of shape, is denoted as A3, calculate: Δ3=A3-a3；
The area for calculating the 4th small identification region, is denoted as a4；Calculate the corresponding minimum envelop square of the 4th small identification region
The area of shape, is denoted as A4, calculate: Δ4=A4-a4；
The area for calculating the 5th small identification region, is denoted as a5；Calculate the corresponding minimum envelop square of the 5th small identification region
The area of shape, is denoted as A5, calculate: Δ5=A5-a5；
(5) it calculates according to the following formula:
Wherein, z indicates total damaged difference in areas of identification region；
(6) a damaged degree limiting value δ is set, if z≤δ, then it is assumed that without breakage；If z > δ, then it is assumed that there is breakage.
It is more acurrate, more effective for the rectangular degree for detecting pavement marker line using above-mentioned preferred embodiment.
As shown in figure 4, in order to further optimize implementation result of the invention, in another embodiment of the invention
In, on the basis of foregoing teachings, above-mentioned step four judges to detect the whether defective and damaged method packet of pavement marker line
Include following steps:
(1) coordinate system is established in the plane of identification region, with zone length direction for the direction x, width direction is the side y
To each point forms a regional space XY on region；
(2) identification region is divided into n (n takes 10) section in zone length direction, that is, direction x, forms 10 direction x sizes
Identical small identification region；
(3) area for calculating each small identification region, is denoted asAnd the maximum region of area is found out, it is denoted as
(4) it calculates according to the following formula:
Wherein, α indicates total damaged difference in areas in the direction identification region x；
(5) identification region is divided into m (m takes 20) section in peak width direction, that is, direction y, forms a 20 direction sizes
Identical small identification region；
(6) area for calculating each small identification region, is denoted as Pj；And the maximum region of area is found out, it is denoted as P0；
(7) it calculates according to the following formula:
Wherein, b indicates total damaged difference in areas in the direction identification region y；
(8) it calculates according to the following formula: c=a+b
Wherein, c indicates the comprehensive damaged difference in areas of identification region；
(9) a damaged degree limiting value δ is set, if c≤δ, then it is assumed that without breakage；If c > δ, then it is assumed that there is breakage.
In order to further optimize implementation result of the invention, in another embodiment of the invention, aforementioned interior
On the basis of appearance, in above-mentioned step 3, pictorial information processing unit combination HALCON machine vision software, by the road in image
The region recognition of face markings comes out.
The pavement image Actuallmage obtained for area array cameras is obtained using sobel operator extraction image border
Gradient region image Gradient；And two threshold values are set to determine intensity value ranges, threshold process is carried out to image, is obtained only
There are two the bianry images of gray value, that is, distinguish the biggish region of amplitude, and the pixel for assigning corresponding output image is white
(255), the image-region image Points in setting intensity value ranges is obtained；Then the white pixel Point Coloring that will be extracted,
It is identified with green, thus obtains identification region RegionFillUp.
Steps are as follows for specific algorithm therein:
(1) the pavement image Actuallmage that area array cameras obtains is read, if first pixel in the upper left corner is origin,
To the right it is the positive direction of x-axis, is downwards the positive direction of y-axis.
(2) reduction image domain obtains the Actuallmage image in specified net region StreetGrid, output
For overlay area image Mask.
(3) image border enhancing is handled, and is prepared for subsequent threshold process.
(4) image border for using sobel operator extraction overlay area image Mask, calculates:
With
Obtain gradient:
It wherein, is respectively the template of detection image horizontal edge, vertical edge, F is original image, Gx、GyRespectively pass through
The image of horizontal edge detection, vertical edge detection is crossed, G is the gradient of edge detection.
" sum-abs " filtering type is utilized, gradient region image Gradient is obtained.
(5) threshold process is carried out to gradient region Gradient, is come out Edge extraction by two threshold values.
Two threshold values MinGray, MaxGray are set,
Wherein, (x, y) is the pixel coordinate in processed gradient region Gradient；F (x, y) is processed
The gray value of pixel in gradient region Gradient；Q (x, y) is the pixel in the new region Points obtained after handling
The pixel value of point.Thus the bianry image only there are two gray value is obtained, that is, distinguishes the biggish region of amplitude, and assign correspondence
The pixel for exporting image is white (255), obtains image district of the gray value within the scope of MinGray≤F (x, y)≤MaxGray
Domain Points.
(6) rectangle expansion is carried out centered on the point in the image-region Points detected, obtains expansion area
RegionDilation。
(7) reduction image domain obtains the Actuallmage image in expansion area RegionDilation, output
For white lane line region StripGray.White lane line is extracted from image
(8) threshold process being carried out to white lane line region StripGray, binaryzation finds out the biggish region of amplitude,
Obtain pavement marker line region Strip of the gray value within the scope of 190-225
(9) it fills, the white pixel point in road pavement markings region Strip is coloured with green, obtains lane line
Filling region RegionFillUp, i.e. identification region.
What has been described above is only a preferred embodiment of the present invention, it is noted that for those of ordinary skill in the art
For, without departing from the concept of the premise of the invention, various modifications and improvements can be made, these belong to the present invention
Protection scope.
Claims (2)
1. a kind of pavement marker line defect detection method, which is characterized in that apply pavement marker line defect detection device；The road
Face markings defect detecting device includes:
Image information collecting unit is fixedly installed on the left and right sides of detection vehicle tailstock lower part, to obtain locating for detection vehicle
The pavement image information of position simultaneously generates picture；
Image information processing unit, input terminal is electrically connected with the output end of described image information acquisition unit, to identify figure
The area of pavement marker line and the data information of shape are obtained after the pavement marker line of road surface image information and processing in piece；
Image information detection unit, input terminal is electrically connected with the output end of described image information process unit, to detect road
The defect and breakage of face markings；
Locating information acquisition unit, to obtain the geographical location information of pavement marker line；
It is additionally provided with and is fixed on the interior image information storage of detection and monitoring unit, including information memory card and vehicle computing
The input terminal of machine, the information memory card is electrically connected with the output end of image information detection unit, locating information acquisition unit, institute
The output end for stating information memory card is electrically connected with the input terminal of the car-mounted computer, to believe pavement image detected
Breath, the area of pavement marker line and shape data information, geographical location information and identification region whether Po Sun conclusion into
Row storage and display；
Described image information acquisition unit includes two high-speed area array cameras, is fixedly installed on detection vehicle tailstock lower part respectively
The left and right sides；
The locating information acquisition unit includes rotary encoder and GPS receiver, and the rotary encoder is set to detection vehicle
Wheel on to record the mileage travelled of detection vehicle, the GPS receiver is set on detection vehicle to obtain detection vehicle
Geographical location information；
The locating information acquisition unit is connect with the on-vehicle navigation apparatus of detection vehicle, to obtain the geographical location letter of detection vehicle
It ceases and marks damaged pavement marker line position on the navigation map of on-vehicle navigation apparatus to share to road-maintaining truck；
Described image information process unit includes image recognizer and message handler, the input terminal of described image identifier and institute
State the electrical connection of image information collecting unit output end, the input terminal of the output end of described image identifier and the message handler
Electrical connection, the output end of the message handler are electrically connected with the input terminal of described image information detecting unit；
The following steps are included:
Step 1: driving detection vehicle drives into road to be detected, and locating information acquisition unit starts gathering geographic position information and determines inspection
The location information of measuring car；
Step 2: in detection garage into the process, using two high-speed area array camera acquisition pavement image information and generating picture；
Step 3: pictorial information processing unit carries out image procossing according to the picture that two high-speed area array cameras photographed, will be in picture
Pavement marker line identify, determine the area of identification region and the data information of shape；
Step 4: pictorial information detection unit carries out image procossing according to the pavement marker line identified, detects pavement marker line
It is whether defective and damaged；
The step 4 judge to detect a kind of whether defective and damaged method of pavement marker line the following steps are included:
(1) coordinate system is established in the plane of identification region, with zone length direction for the direction x, width direction is the direction y, area
Each point forms a regional space XY on domain；
(2) identification region is divided into n sections in zone length direction, that is, direction x, forms the identical small identification of the n direction x size
Region；
(3) to the n small identification regions, corresponding the least surrounding boxes are fitted respectively；
(4) it calculates according to the following formula:
Δ i=Ai-ai
Wherein, ΔiIndicate the damaged difference in areas of i-th small identification region, ai indicates that the area of each small identification region, Ai indicate
The area of the corresponding the least surrounding boxes of 1st small identification region；
(5) it calculates according to the following formula:
Wherein, Z indicates total damaged difference in areas of identification region；
(6) a damaged degree limiting value δ is set, if z≤δ, then it is assumed that without breakage；If z > δ, then it is assumed that there is breakage；
Another method can also be used comprising following steps:
(1) coordinate system is established in the plane of identification region, with zone length direction for the direction x, width direction is the direction y, area
Each point forms a regional space XY on domain；
(2) identification region is divided into n sections in zone length direction, that is, direction x, forms the identical small identification of the n direction x size
Region；
(3) area for calculating each small identification region, is denoted as Si；And the maximum region of area is found out, it is denoted as S0；
(4) it calculates according to the following formula:
Wherein, α indicates total damaged difference in areas in the direction identification region x；
(5) identification region is divided into m sections in peak width direction, that is, direction y, forms the identical small identification of m direction size
Region；
(6) area for calculating each small identification region, is denoted as Pj；And the maximum region of area is found out, it is denoted as P0；
(7) it calculates according to the following formula:
Wherein, b indicates total damaged difference in areas in the direction identification region y；
(8) it calculates according to the following formula: c=a+b
Wherein, c indicates the comprehensive damaged difference in areas of identification region；
(9) a damaged degree limiting value δ is set, if c≤δ, then it is assumed that without breakage；If c > δ, then it is assumed that there is breakage.
2. pavement marker line defect detection method according to claim 1, which is characterized in that further include step 5: control figure
As information storage works with monitoring unit, information memory card is by pavement marker line area and the data information of shape, geographical location
Whether damaged conclusion stores for information and identification region, and will test as the result is shown on car-mounted computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610390149.4A CN105891220B (en) | 2016-06-02 | 2016-06-02 | A kind of pavement marker line defect detection device and its detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610390149.4A CN105891220B (en) | 2016-06-02 | 2016-06-02 | A kind of pavement marker line defect detection device and its detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105891220A CN105891220A (en) | 2016-08-24 |
| CN105891220B true CN105891220B (en) | 2019-04-30 |
Family
ID=56710176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610390149.4A Active CN105891220B (en) | 2016-06-02 | 2016-06-02 | A kind of pavement marker line defect detection device and its detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105891220B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108108703A (en) * | 2017-12-27 | 2018-06-01 | 天津英创汇智汽车技术有限公司 | Deceleration strip missing detection method, device and electronic equipment |
| CN108759670B (en) * | 2018-05-31 | 2020-02-04 | 成都唐源电气股份有限公司 | Contact line abrasion dynamic detection device based on non-contact detection technology |
| CN110852453A (en) * | 2018-07-27 | 2020-02-28 | 东旭科技集团有限公司 | Road surface maintenance method and device, street lamp and readable storage medium |
| CN109830000A (en) * | 2019-01-21 | 2019-05-31 | 武汉光庭信息技术股份有限公司 | A kind of SPEED VISION road data acquisition device |
| CN110211112A (en) * | 2019-05-31 | 2019-09-06 | 华中科技大学 | A kind of casting defect inspection method based on filtering selective search |
| CN110887847B (en) * | 2019-11-26 | 2022-04-01 | 重庆工商职业学院 | Road surface detection system |
| CN113780196B (en) * | 2021-09-15 | 2022-05-31 | 江阴市浩华新型复合材料有限公司 | Abnormal data real-time reporting system |
| CN115984806B (en) * | 2023-03-20 | 2023-06-13 | 四川京炜数字科技有限公司 | Dynamic detection system for road marking damage |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2841334B1 (en) * | 2002-06-20 | 2004-12-24 | Renault Sa | METHOD AND DEVICE FOR EVALUATING THE POSITION OF A VEHICLE ON A PATH OF A PAVEMENT |
| CN102592114B (en) * | 2011-12-26 | 2013-07-31 | 河南工业大学 | Method for extracting and recognizing lane line features of complex road conditions |
| CN203551478U (en) * | 2013-10-26 | 2014-04-16 | 西安文理学院 | Automatic detection device for pavement damage |
| CN204882391U (en) * | 2015-08-11 | 2015-12-16 | 江西省公路工程检测中心 | Damaged automatic identification equipment in vehicular road surface based on image processing |
| CN105067633A (en) * | 2015-08-11 | 2015-11-18 | 江西省公路工程检测中心 | Vehicle-mounted type automatic pavement damage recognition device based on image processing and application method |
-
2016
- 2016-06-02 CN CN201610390149.4A patent/CN105891220B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105891220A (en) | 2016-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105891220B (en) | A kind of pavement marker line defect detection device and its detection method | |
| CN106919915B (en) | Map road marking and road quality acquisition device and method based on ADAS system | |
| CN110501018B (en) | Traffic sign information acquisition method for high-precision map production | |
| CN104280036B (en) | A kind of detection of transport information and localization method, device and electronic equipment | |
| CN106778737B (en) | A kind of license plate antidote, device and a kind of video acquisition device | |
| CN108182383B (en) | Vehicle window detection method and device | |
| CN109064495A (en) | A kind of bridge floor vehicle space time information acquisition methods based on Faster R-CNN and video technique | |
| CN109284674A (en) | A kind of method and device of determining lane line | |
| CN107256636A (en) | A kind of traffic flow acquisition methods for merging laser scanning and video technique | |
| CN110008893A (en) | A kind of automobile driving running deviation automatic testing method based on vehicle-mounted imaging sensor | |
| CN105426894B (en) | Railway plug pin image detecting method and device | |
| CN106128115A (en) | Fusion method for detecting road traffic information based on double cameras | |
| CN104050446A (en) | Meter pointer image identification method based on pointer width character | |
| CN109635737A (en) | Automobile navigation localization method is assisted based on pavement marker line visual identity | |
| CN108828608B (en) | Laser radar background data filtering method in vehicle detection method | |
| CN107273802A (en) | A kind of detection method and device of railroad train brake shoe drill ring failure | |
| CN111243003B (en) | Vehicle-mounted binocular camera and method and device for detecting road height limiting rod | |
| JP2008299458A (en) | Vehicle monitoring apparatus and vehicle monitoring method | |
| CN106097332A (en) | A kind of container profile localization method based on Corner Detection | |
| CN108090459A (en) | A kind of road traffic sign detection recognition methods suitable for vehicle-mounted vision system | |
| CN113781537A (en) | Track elastic strip fastener defect identification method and device and computer equipment | |
| JP2019045922A (en) | Deformed spot detection device, deformed spot detection program and deformed spot detection method | |
| CN108009574A (en) | A kind of rail clip detection method | |
| CN107264570A (en) | steel rail light band distribution detecting device and method | |
| CN105303564A (en) | Visual detection method for tower crane load three-dimensional swing angle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |