CN105891220A - Pavement marker line defect detecting device and detecting method thereof - Google Patents
Pavement marker line defect detecting device and detecting method thereof Download PDFInfo
- Publication number
- CN105891220A CN105891220A CN201610390149.4A CN201610390149A CN105891220A CN 105891220 A CN105891220 A CN 105891220A CN 201610390149 A CN201610390149 A CN 201610390149A CN 105891220 A CN105891220 A CN 105891220A
- Authority
- CN
- China
- Prior art keywords
- image information
- pavement marker
- region
- marker line
- detection
- 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
- 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
Abstract
The invention discloses a pavement marker line defect detecting device and a detecting method thereof. The pavement marker line defect detecting device comprises image information collecting units, an image information processing unit, an image information detecting unit and a location information collecting unit, wherein the image information collecting units are fixedly arranged at the left side and the right side of the lower portion of a detecting vehicle tail and used for obtaining pavement image information of the position where the detecting vehicle is located and generating images; the input end of the image information processing unit is electrically connected with the output end of the image information collecting units, and the image information processing unit is used for recognizing and processing pavement marker lines of the pavement image information in the images to obtain area and shape data information of the pavement marker lines; the input end of the image information detecting unit is electrically connected with the output end of the image information processing unit, and the image information detecting unit is used for detecting defect and damage conditions of the pavement marker lines; the location information collecting unit is used for obtaining geographical location information of the pavement marker lines. Compared with the prior art, integration of the detecting vehicle and detection equipment is adopted, potential safety hazards in the detection process are reduced, it is avoided that the complex pavement is affected by vehicles and pedestrians, detection accuracy is high, and operation efficiency and quality are improved.
Description
Technical field
The present invention relates to a kind of pavement marker line defect detection device and detection method thereof.
Background technology
Modern Traffic system is the most flourishing, but due to traffic safety problem, people couple
The demand of road traffic environment is more and more higher.Wherein, pavement marker line is to guide vehicle safety
The pith driven, is directly passed to driver, pedestrian by pattern, symbol, word etc.
Visual information accurately.The most effective pavement marker line can reduce vehicle accident, guarantee
Unimpeded traffic environment;On the other hand pavement marker line is also of road landscape cosmetic treatment
Point.But, after using a period of time, pavement marker line there will be breakage, observability is moved back naturally
The defects such as change, affect its traffic direction-pointing function and road is attractive in appearance, therefore, from road maintenance,
The defect breakage needing road pavement markings carries out periodic detection.
Existing traditional detection method is manual site's visual assessment or hand dipping collection, and it lacks
Point is to waste time and energy, and the accuracy of data is easily by interference from human factor, collection in worksite simultaneously
There is potential safety hazard in operation.
Existing novel detection method is to use Vision Builder for Automated Inspection detection pavement marker line, but this
The means of kind are used for Vehicular navigation system.Its shortcoming is easily by vehicle, pedestrian etc. at complex road surface
Non-detection information is disturbed, and can not be accurately positioned the pavement marker line detected.
Summary of the invention
In order to solve above-mentioned technical problem, the invention provides a kind of pavement marker line defect detection
Device and detection method thereof.
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, including:
Image information collecting unit, its be fixedly installed on detection car tailstock bottom the left and right sides,
In order to obtain the pavement image information of detection car present position and to generate picture;
Image Information Processing unit, its input is electrically connected with the outfan of image information collecting unit
Connect, in order to identify road surface image information in picture pavement marker line and process after obtain road marking
The area of will line and the data message of shape;
Image information detector unit, its input is electrically connected with the outfan of Image Information Processing unit
Connect, in order to detect defect and the breakage of pavement marker line;
Locating information acquisition unit, in order to obtain the geographical location information of pavement marker line.
The present invention is integrated compared to prior art, employing detection car and detection equipment, reduces
Potential safety hazard during detection, it also avoid complex road surface is affected by vehicle and pedestrian, inspection
The accuracy surveyed is high, improves working performance and quality.
Wherein, above-mentioned image information collecting unit includes two high-speed area array cameras, and it is respectively
It is fixedly installed on the left and right sides of detection car tailstock bottom;
Above-mentioned locating information acquisition unit includes rotary encoder and gps receiver, rotates and compiles
Code device is arranged on the wheel of detection car in order to record the distance travelled of detection car, gps receiver
It is arranged on detection car in order to obtain the geographical location information of detection car.
As preferred scheme, above-mentioned locating information acquisition unit and the vehicle mounted guidance detecting car
Device connects, in order to obtain the geographical location information detecting car the navigation at on-vehicle navigation apparatus
The pavement marker line position of breakage is marked to share to road-maintaining truck on map.
Please supplemental image information process unit composition and between annexation.
As preferred scheme, the image information that above-mentioned being additionally provided with is fixed in detection car is deposited
Storage and monitoring means, including information memory card and car-mounted computer, the input of information memory card
With image information collecting unit, Image Information Processing unit, image information detector unit, location
The outfan electrical connection of information acquisition unit, the outfan of information memory card and car-mounted computer
Input electrically connect, in order to the pavement image information detected, the area of pavement marker line and
Shape information, geographical location information and identify the whether damaged conclusion in region carry out storing and
Display.
On the basis of technique scheme, also can do and improve as follows:
As preferred scheme, the present invention also provides for a kind of pavement marker line defect detection method,
Apply above-mentioned pavement marker line defect detection device, comprise the following steps:
Step 1: driving detection car to sail road to be detected into, locating information acquisition unit starts to adopt
Collection geographical location information determines the positional information of detection car;
Step 2: during detection garage enters, use two high-speed area array collected by camera road surfaces
Image information also generates picture;
Step 3: the picture that pictorial information processing unit photographed according to two high-speed area array cameras enters
Row image procossing, identifies the pavement marker line in picture, determines the area identifying region
Data message with shape;
Step 4: pictorial information detector unit carries out image according to the pavement marker line identified
Processing, detection pavement marker line is the most defective and damaged.
As preferred scheme, above-mentioned also includes step 5: control image information storage and prison
Surveying cell operation, information memory card is by pavement marker line area and the data message of shape, geography
Positional information and identify the conclusion storage that region is whether damaged, and testing result is shown
On car-mounted computer.
As preferred scheme, it is the most defective that above-mentioned step 4 judges to detect pavement marker line
Comprise the following steps with damaged method:
(1) in the plane identifying region, set up coordinate system, be x side with zone length direction
To, width is y direction, one regional space XY of each point composition on region;
(2) in i.e. x direction, zone length direction, identification region is divided into n section, forms n
The little identification region that individual x direction is equivalently-sized;
(3) to n little identification region, the least surrounding boxes of correspondence is simulated respectively;
(4) calculate according to below equation:
Δ i=Ai-ai
Wherein, ΔiRepresenting the damaged difference in areas in i-th little identification region, ai represents each little
Identifying the area in region, Ai represents the least surrounding boxes corresponding to the 1st little identification region
Area;
(5) calculate according to below equation:
Wherein, z represents the total damaged difference in areas identifying region;
(6) damaged degree ultimate value δ is set, if z≤δ, then it is assumed that without damaged;If z is > δ,
Then think there is breakage.
Use above-mentioned preferred version, for detecting the rectangular degree of pavement marker line more accurately, more
Effectively.
As preferred scheme, it is the most defective that above-mentioned step 4 judges to detect pavement marker line
Comprise the following steps with damaged method:
(1) in the plane identifying region, set up coordinate system, be x side with zone length direction
To, width is y direction, one regional space XY of each point composition on region;
(2) in i.e. x direction, zone length direction, identification region is divided into n section, forms n
The little identification region that individual x direction is equivalently-sized;
(3) calculate the area in each little identification region, be designated as Si;And find out area maximum
Region, is designated as S0;
(4) calculate according to below equation:
Wherein, α represents the total damaged difference in areas identifying x direction, region;
(5) in i.e. y direction, peak width direction, identification region is divided into m section, forms a m
The little identification region that direction is equivalently-sized;
(6) calculate the area in each little identification region, be designated as Pj;And find out area maximum
Region, is designated as P0;
(7) calculate according to below equation:
Wherein, b represents the total damaged difference in areas identifying y direction, region;
(8) calculate according to below equation: c=a+b
Wherein, c represents the comprehensive damaged difference in areas identifying region;
(9) damaged degree ultimate value δ is set, if c≤δ, then it is assumed that without damaged;If
C > δ, then it is assumed that have breakage.
Accompanying drawing explanation
Fig. 1 is the structured flowchart of one embodiment of the present invention.
Fig. 2 is the structural representation of the detection car of one embodiment of the present invention.
Fig. 3 is the flow process of the pavement marker line defect detection method of one embodiment of the present invention
Figure.
Fig. 4 is that the structure of the pavement marker line defect detection method of one embodiment of the present invention is shown
It is intended to.
Fig. 5 is the flow process of the pavement marker line defect detection method of another embodiment of the present invention
Figure.
Fig. 6 is the structure of the pavement marker line defect detection method of another embodiment of the present invention
Schematic diagram.
Wherein, car, 2. locating information acquisition unit, 3. image information collecting unit are 1. detected.
Detailed description of the invention
Describe the preferred embodiment of the present invention below in conjunction with the accompanying drawings in detail.
In order to reach the purpose of the present invention, as shown in Figures 1 to 4, in wherein the one of the present invention
Plant and embodiment provides a kind of pavement marker line defect detection device, including:
Image information collecting unit 3, it is fixedly installed on the left and right two of detection car 1 tailstock bottom
Side, in order to obtain the pavement image information of detection car 1 present position and to generate picture;
Image Information Processing unit, its input is electric with the outfan of image information collecting unit 3
Connect, in order to identify road surface image information in picture pavement marker line and process after acquisition road surface
The area of markings and the data message of shape;
The outfan of image information detector unit, its input and described Image Information Processing unit
Electrical connection, in order to detect defect and the breakage of pavement marker line;
Locating information acquisition unit, in order to obtain the geographical location information of pavement marker line.
Present embodiment is integrated compared to prior art, employing detection car and detection equipment, fall
Potential safety hazard during low detection, it also avoid complex road surface by vehicle and the shadow of pedestrian
Ringing, the accuracy of detection is high, improves working performance and quality.
Wherein, above-mentioned image information collecting unit includes two high-speed area array cameras, and it is respectively
It is fixedly installed on the left and right sides of detection car tailstock bottom;
Above-mentioned locating information acquisition unit includes rotary encoder and gps receiver, rotates and compiles
Code device is arranged on the wheel of detection car in order to record the distance travelled of detection car, gps receiver
It is arranged on detection car in order to obtain the geographical location information of detection car.
In order to optimize the implementation result of the present invention further, the another kind of embodiment party of the present invention
In formula, on the basis of foregoing teachings, above-mentioned locating information acquisition unit and the car detecting car
Load guider connects, in order to obtain the geographical location information of detection car and at on-vehicle navigation apparatus
Navigation map on mark breakage pavement marker line position to share to road-maintaining truck.
Please supplemental image information process unit composition and between annexation.
As preferred scheme, the image information that above-mentioned being additionally provided with is fixed in detection car is deposited
Storage and monitoring means, including information memory card and car-mounted computer, the input of information memory card
With Image Information Processing unit, image information detector unit, the output of locating information acquisition unit
End electrical connection, the outfan of information memory card electrically connects with the input of car-mounted computer, in order to
To the pavement image information detected, the area of pavement marker line and the data message of shape,
Reason positional information and identify that whether damaged region conclusion store and show.
In order to optimize the implementation result of the present invention further, the another kind of embodiment party of the present invention
In formula, on the basis of foregoing teachings, the present embodiment also provides for a kind of pavement marker line defect inspection
Survey method, applies above-mentioned pavement marker line defect detection device, comprises the following steps:
Step 1: driving detection car to sail road to be detected into, locating information acquisition unit starts to adopt
Collection geographical location information determines the positional information of detection car;
Step 2: during detection garage enters, use two high-speed area array collected by camera road surfaces
Image information also generates picture;
Step 3: the picture that pictorial information processing unit photographed according to two high-speed area array cameras enters
Row image procossing, identifies the pavement marker line in picture, determines the area identifying region
Data message with shape;
Step 4: pictorial information detector unit carries out image according to the pavement marker line identified
Processing, detection pavement marker line is the most defective and damaged.
As preferred scheme, above-mentioned also includes step 5: control image information storage and prison
Surveying cell operation, information memory card is by pavement marker line area and the data message of shape, geography
Positional information and identify the conclusion storage that region is whether damaged, and testing result is shown
On car-mounted computer.
As it is shown on figure 3, for the implementation result optimizing the present invention further, the present invention's
In another embodiment, on the basis of foregoing teachings, above-mentioned step 4 judges detection road
Markings the most defective and damaged method in face comprises the following steps:
(1) in the plane identifying region, set up coordinate system, be x side with zone length direction
To, width is y direction, one regional space XY of each point composition on region;
(2) in i.e. x direction, zone length direction, identification region is divided into n (n takes 5) section,
Form equivalently-sized little identification region, 5 x directions;
(3) to described 5 little identification regions, the least surrounding boxes of correspondence is simulated respectively;
(4) calculate the area in the 1st little identification region, be designated as a1;Calculate the 1st little knowledge
The area of the least surrounding boxes that other region is corresponding, is designated as A1, calculate;Δ1=A1-a1
Calculate the area in the 2nd little identification region, be designated as a2;Calculate the 2nd little identification region
The area of corresponding the least surrounding boxes, is designated as A2, calculate:;Δ2=A2-a2
Calculate the area in the 3rd little identification region, be designated as a3;Calculate the 3rd little identification region
The area of corresponding the least surrounding boxes, is designated as A3, calculate:;Δ3=A3-a3
Calculate the area in the 4th little identification region, be designated as a4;Calculate the 4th little identification region
The area of corresponding the least surrounding boxes, is designated as A4, calculate:;Δ4=A4-a4
Calculate the area in the 5th little identification region, be designated as a5;Calculate the 5th little identification region
The area of corresponding the least surrounding boxes, is designated as A5, calculate:;Δ5=A5-a5
(5) calculate according to below equation:
Wherein, z represents the total damaged difference in areas identifying region;
(6) damaged degree ultimate value δ is set, if z≤δ, then it is assumed that without damaged;If z is > δ,
Then think there is breakage.
Use above-mentioned preferred version, for detecting the rectangular degree of pavement marker line more accurately, more
Effectively.
As shown in Figure 4, in order to optimize the implementation result of the present invention further, the present invention's
In another embodiment, on the basis of foregoing teachings, above-mentioned step 4 judges detection road
Markings the most defective and damaged method in face comprises the following steps:
(1) in the plane identifying region, set up coordinate system, be x side with zone length direction
To, width is y direction, one regional space XY of each point composition on region;
(2) in i.e. x direction, zone length direction, identification region is divided into n (n takes 10) section,
Form equivalently-sized little identification region, 10 x directions;
(3) calculate the area in each little identification region, be designated as Si;And find out area maximum
Region, is designated as S0;
(4) calculate according to below equation:
Wherein, α represents the total damaged difference in areas identifying x direction, region;
(5) in i.e. y direction, peak width direction, identification region is divided into m (m takes 20) section,
Form the little identification region that 20 direction is equivalently-sized;
(6) calculate the area in each little identification region, be designated as Pj;And find out area maximum
Region, is designated as P0;
(7) calculate according to below equation:
Wherein, b represents the total damaged difference in areas identifying y direction, region;
(8) calculate according to below equation: c=a+b
Wherein, c represents the comprehensive damaged difference in areas identifying region;
(9) damaged degree ultimate value δ is set, if c≤δ, then it is assumed that without damaged;If
C > δ, then it is assumed that have breakage.
In order to optimize the implementation result of the present invention further, the another kind of embodiment party of the present invention
In formula, on the basis of foregoing teachings, in above-mentioned step 3, pictorial information processing unit is tied
Close HALCON machine vision software, by the region recognition of the pavement marker line in image out.
The pavement image Actual Image obtained for area array cameras, utilizes sobel operator to carry
Take image border, obtain gradient region image Gradient;And set two threshold values to determine ash
Angle value scope, carries out threshold process to image, obtains the bianry image of only two gray values,
I.e. distinguish the region that amplitude is bigger, and the pixel giving corresponding output image be white (255),
Obtain the image-region image Points set in intensity value ranges;Then the white that will extract
Pixel colours, and identifies by green, is thus identified region RegionFillUp.
Specific algorithm step therein is as follows:
(1) the pavement image Actual Image that reading face array camera obtains, if the of the upper left corner
One pixel is initial point, is to the right the positive direction of x-axis, is downwards the positive direction of y-axis.
(2) reduction image definition territory, in obtaining specifying net region StreetGrid
Actual Image image, is output as overlay area image Mask.
(3) image border enhancement process, prepares for follow-up threshold process.
(4) use the image border of sobel operator extraction overlay area image Mask, calculate:
With
Obtain gradient:
Wherein,It is respectively detection image level edge, hangs down
The template of straight edge, F is original image, Gx、GyIt is respectively through horizontal edge detection, hangs down
The image of straight edge detection, G is the gradient of rim detection.
Utilize " sum-abs " filtering type, obtain gradient region image Gradient.
(5) gradient region Gradient is carried out threshold process, by two threshold values by image
Edge extracting is out.
Set two threshold values MinGray, MaxGray,
Wherein, (x y) is the pixel coordinate in processed gradient region Gradient;
(x, y) for the gray value of the pixel in processed gradient region Gradient for F;Q (x,
Y) for the pixel value of the pixel in new region Points of acquisition after processing.Only thus obtain
There is the bianry image of two gray values, i.e. distinguish the region that amplitude is bigger, and give corresponding defeated
Publish picture picture pixel for white (255), it is thus achieved that gray value is at MinGray≤F (x, y)≤MaxGray model
Enclose interior image-region Points.
(6) rectangle expansion is carried out centered by the point in the image-region Points detected,
Obtain expansion area RegionDilation.
(7) reduction image definition territory, obtains in expansion area RegionDilation
Actual Image image, is output as white lane line region StripGray.I.e. white car
Diatom extracts from image
(8) white lane line region StripGray is carried out threshold process, binaryzation, i.e.
Find out the region that amplitude is bigger, it is thus achieved that gray value pavement marker line in the range of 190-225
Region Strip
(9) filling, the white pixel point green in road pavement markings region Strip is entered
Row coloring, obtains lane line and fills region RegionFillUp, i.e. identify region.
Above-described is only the preferred embodiment of the present invention, it is noted that for this area
Those of ordinary skill for, without departing from the concept of the premise of the invention, it is also possible to do
Going out some deformation and improvement, these broadly fall into protection scope of the present invention.
Claims (10)
1. a pavement marker line defect detection device, it is characterised in that including:
Image information collecting unit, it is fixedly installed on the left and right sides of detection car tailstock bottom, uses
To obtain the pavement image information of detection car present position and to generate picture;
Image Information Processing unit, its input is electric with the outfan of described image information collecting unit
Connect, in order to identify road surface image information in picture pavement marker line and process after acquisition road marking
The area of will line and the data message of shape;
Image information detector unit, its input is electric with the outfan of described Image Information Processing unit
Connect, in order to detect defect and the breakage of pavement marker line;
Locating information acquisition unit, in order to obtain the geographical location information of pavement marker line.
Pavement marker line defect the most according to claim 1 detection device, it is characterised in that
Described image information collecting unit includes two high-speed area array cameras, and it is fixedly installed on detection respectively
The left and right sides of car tailstock bottom.
Pavement marker line defect the most according to claim 1 detection device, it is characterised in that
Described locating information acquisition unit includes rotary encoder and gps receiver, described rotary encoder
Being arranged on the wheel of detection car in order to record the distance travelled of detection car, described gps receiver sets
It is placed on detection car in order to obtain the geographical location information of detection car.
Pavement marker line defect the most according to claim 1 detection device, it is characterised in that
Described locating information acquisition unit is connected, in order to obtain detection car with the on-vehicle navigation apparatus of detection car
Geographical location information and mark on the navigation map of on-vehicle navigation apparatus breakage pavement marker line
Position is to share to road-maintaining truck.
Pavement marker line defect the most according to claim 1 detection device, it is characterised in that
Described Image Information Processing unit includes image recognizer and message handler, described image recognizer
Input electrically connect with described image information collecting unit outfan, described image recognizer defeated
Go out end to electrically connect with the input of described message handler, the outfan of described message handler and institute
State the input electrical connection of image information detector unit.
Pavement marker line defect the most according to claim 1 detection device, it is characterised in that
It is additionally provided with the image information storage and monitoring means being fixed in detection car, including information memory card
And car-mounted computer, the input of described information memory card and described image information collecting unit, figure
As information process unit, image information detector unit, the outfan of locating information acquisition unit are electrically connected
Connecing, the outfan of described information memory card electrically connects with the input of described car-mounted computer, in order to
To the pavement image information detected, the area of pavement marker line and the data message of shape, geography
Positional information and identify that whether damaged region conclusion store and show.
7. a pavement marker line defect detection method, it is characterised in that apply such as claim
The arbitrary described pavement marker line defect detection device of 1-5, comprises the following steps:
Step 1: driving detection car to sail road to be detected into, locating information acquisition unit starts locality
Reason positional information determines the positional information of detection car;
Step 2: during detection garage enters, use two high-speed area array collected by camera pavement images
Information also generates picture;
Step 3: the picture that pictorial information processing unit photographed according to two high-speed area array cameras carries out figure
As processing, the pavement marker line in picture is identified, determine area and the shape identifying region
Data message;
Step 4: pictorial information detector unit is carried out at image according to the pavement marker line identified
Reason, detection pavement marker line is the most defective and damaged.
Pavement marker line defect detection method the most according to claim 7, it is characterised in that
Also include step 5: controlling image information storage and work with monitoring means, information memory card is by road marking
Will line area and the data message of shape, geographical location information and identify that region is the most damaged
Conclusion stores, and testing result is shown on car-mounted computer.
Pavement marker line defect detection method the most according to claim 7, it is characterised in that
Described step 4 judges that the method detecting pavement marker line the most defective and damaged comprises the following steps:
(1) in the plane identifying region, coordinate system is set up, with zone length direction for x direction,
Width is y direction, one regional space XY of each point composition on region;
(2) in i.e. x direction, zone length direction, identification region is divided into n section, forms n x
The little identification region that direction is equivalently-sized;
(3) to described n little identification region, the least surrounding boxes of correspondence is simulated respectively;
(4) calculate according to below equation:
Δ i=Ai-ai
Wherein, ΔiRepresenting the damaged difference in areas in i-th little identification region, ai represents each little identification
The area in region, Ai represents the area of the least surrounding boxes corresponding to the 1st little identification region;
(5) calculate according to below equation:
Wherein, z represents the total damaged difference in areas identifying region;
(6) damaged degree ultimate value δ is set, if z≤δ, then it is assumed that without damaged;If z is > δ,
Then think there is breakage.
Pavement marker line defect detection method the most according to claim 7, it is characterised in that
Described step 4 judges that the method detecting pavement marker line the most defective and damaged comprises the following steps:
(1) in the plane identifying region, coordinate system is set up, with zone length direction for x direction,
Width is y direction, one regional space XY of each point composition on region;
(2) in i.e. x direction, zone length direction, identification region is divided into n section, forms n x
The little identification region that direction is equivalently-sized;
(3) calculate the area in each little identification region, be designated as Si;And find out the region that area is maximum,
It is designated as S0;
(4) calculate according to below equation:
Wherein, α represents the total damaged difference in areas identifying x direction, region;
(5) in i.e. y direction, peak width direction, identification region is divided into m section, forms a m side
To equivalently-sized little identification region;
(6) calculate the area in each little identification region, be designated as Pj;And find out the region that area is maximum,
It is designated as P0;
(7) calculate according to below equation:
Wherein, b represents the total damaged difference in areas identifying y direction, region;
(8) calculate according to below equation: c=a+b
Wherein, c represents the comprehensive damaged difference in areas identifying region;
(9) damaged degree ultimate value δ is set, if c≤δ, then it is assumed that without damaged;If c is >
δ, then it is assumed that have breakage.
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 true CN105891220A (en) | 2016-08-24 |
CN105891220B 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) |
Cited By (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 |
CN108759670A (en) * | 2018-05-31 | 2018-11-06 | 成都唐源电气股份有限公司 | A kind of contact line abrasion device for dynamically detecting based on non-contact detection technology |
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 |
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 |
CN110887847A (en) * | 2019-11-26 | 2020-03-17 | 重庆工商职业学院 | Road surface detection system |
CN113780196A (en) * | 2021-09-15 | 2021-12-10 | 江阴市浩华新型复合材料有限公司 | Abnormal data real-time reporting system |
CN115984806A (en) * | 2023-03-20 | 2023-04-18 | 四川京炜数字科技有限公司 | Road marking damage dynamic detection system |
Citations (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 |
CN102592114A (en) * | 2011-12-26 | 2012-07-18 | 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 |
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 |
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 |
-
2016
- 2016-06-02 CN CN201610390149.4A patent/CN105891220B/en active Active
Patent Citations (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 |
CN102592114A (en) * | 2011-12-26 | 2012-07-18 | 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 |
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 |
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 |
Cited By (10)
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 |
CN108759670A (en) * | 2018-05-31 | 2018-11-06 | 成都唐源电气股份有限公司 | A kind of contact line abrasion device for dynamically detecting 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 |
CN110887847A (en) * | 2019-11-26 | 2020-03-17 | 重庆工商职业学院 | Road surface detection system |
CN110887847B (en) * | 2019-11-26 | 2022-04-01 | 重庆工商职业学院 | Road surface detection system |
CN113780196A (en) * | 2021-09-15 | 2021-12-10 | 江阴市浩华新型复合材料有限公司 | Abnormal data real-time reporting system |
CN115984806A (en) * | 2023-03-20 | 2023-04-18 | 四川京炜数字科技有限公司 | Road marking damage dynamic detection 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 |
Also Published As
Publication number | Publication date |
---|---|
CN105891220B (en) | 2019-04-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105891220A (en) | Pavement marker line defect detecting device and detecting method thereof | |
CN106919915B (en) | Map road marking and road quality acquisition device and method based on ADAS system | |
CN109470254B (en) | Map lane line generation method, device, system and storage medium | |
CN104392212B (en) | The road information detection and front vehicles recognition methods of a kind of view-based access control model | |
US20210342606A1 (en) | Parking Detection Method, System, Processing Device and Storage Medium | |
CN103714343B (en) | Under laser line generator lighting condition, the pavement image of twin-line array collected by camera splices and homogenizing method | |
CN106128115A (en) | A kind of fusion method based on twin camera detection Traffic Information | |
CN103500322A (en) | Automatic lane line identification method based on low-altitude aerial images | |
CN109064495A (en) | A kind of bridge floor vehicle space time information acquisition methods based on Faster R-CNN and video technique | |
CN105260713A (en) | Method and device for detecting lane line | |
CN103778681A (en) | Vehicle-mounted high-speed road inspection system and data acquisition and processing method | |
CN104008377A (en) | Ground traffic sign real-time detection and recognition method based on space-time correlation | |
CN110008893A (en) | A kind of automobile driving running deviation automatic testing method based on vehicle-mounted imaging sensor | |
CN109635737A (en) | Automobile navigation localization method is assisted based on pavement marker line visual identity | |
Lee et al. | Image processing-based pothole detecting system for driving environment | |
CN103440657A (en) | Method for online screening cracks of road | |
CN107796373A (en) | A kind of distance-finding method of the front vehicles monocular vision based on track plane geometry model-driven | |
CN205557277U (en) | Pavement crack disease detection system | |
CN110458050A (en) | Vehicle based on Vehicular video cuts detection method and device | |
CN103164958A (en) | Method and system for vehicle monitoring | |
CN102706883B (en) | System and method for recognizing holes in paved waterproof board of tunnel | |
CN105913034A (en) | Vehicle identification method and apparatus, and vehicle | |
CN105303564A (en) | Tower type crane load stereo pendulum angle vision detection method | |
WO2021193148A1 (en) | Road deterioration diagnostic device, road deterioration diagnostic system, road deterioration diagnostic method, and recording medium | |
CN107121126A (en) | A kind of roadbed settlement monitoring method and system based on image procossing |
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 |