CN104964708B - A kind of road surface pit detection method based on vehicle-mounted binocular vision - Google Patents
A kind of road surface pit detection method based on vehicle-mounted binocular vision Download PDFInfo
- Publication number
- CN104964708B CN104964708B CN201510234379.7A CN201510234379A CN104964708B CN 104964708 B CN104964708 B CN 104964708B CN 201510234379 A CN201510234379 A CN 201510234379A CN 104964708 B CN104964708 B CN 104964708B
- Authority
- CN
- China
- Prior art keywords
- road surface
- surface pit
- vehicle
- pit
- detection method
- 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.)
- Expired - Fee Related
Links
Landscapes
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Navigation (AREA)
- Image Processing (AREA)
Abstract
The present invention is a kind of road surface pit detection method based on vehicle-mounted binocular vision, the detection method takes reasonable threshold value to filter out road surface pit by the vibration sample information of vibrating sensor, the positional information of road surface pit is provided with reference to GPS information, GPS information at that time can be recorded by the artificial external trigger device of button when wheel leaks pressure road surface pit, binocular camera system is sampled and exported to computer to test road surface, after the image for obtaining road surface pit, pretreatment is carried out by image and image processing algorithm obtains the area of road surface pit, depth information.Using technical solution of the present invention, the positioning of road surface pit can not only be completed, and optimizes in terms of algorithm traditional image processing algorithm and can accurately realize road surface pit area, depth calculation function.
Description
Technical field
The present invention relates to field of road detection and image processing field, and in particular to one kind utilizes image based on binocular vision
The position of Processing Algorithm measurement road surface pit, area, the detection method of depth information.
Background technology
In recent years, expanding economy has driven the increase of vehicle fleet size, the abrasion accumulated over a long period with road surface, and pit goes out
It is now inevitable, therefore the importance that is travelled for vehicle of detection of road surface pit is self-evident.Pit detection is pavement quality
Pith in detection, the development of digital image processing techniques, which allows traditional pavement detection to work, becomes more intelligent, more
Plus mechanization.
But road surface pit is a kind of special road surface breakage form, traditional road surface measuring method, such as Bump Integrator,
Laser range finder etc. can only all obtain the curve in road surface vertical section, it is impossible to position the position of road surface pit, can not obtain it empty
Between information.Pavement image processing based on conventional edge detection algorithm can not also obtain similar this irregular closure of road surface pit
The edge in region, the sampling of traditional monocular camera road pavement image, because the limitation that its planar dimensions is two dimension can not yet
Measure the space three-dimensional information of road surface pit.
The content of the invention
The defect of road surface pit spatial information can not be measured in order to solve conventional method, present invention incorporates GPS, binocular phase
The hardware devices such as machine, vibrating sensor, by way of vehicle-mounted, position the position of pit, gather the image of pit, and utilize figure
As algorithm calculates area, the depth information of pit.
To realize above-mentioned technical purpose and the technique effect, the present invention is achieved through the following technical solutions:
A kind of road surface pit detection method based on vehicle-mounted binocular vision, this method based on hardware include main control chip,
The main control chip is connected to binocular camera system, GPS positioning system, vibrating sensor, artificial external trigger device and meter
Calculation machine, it is characterised in that the binocular camera system is installed on road pavement image on vehicle ceiling and is acquired, the GPS determines
Position system is fixed on vehicle ceiling together with binocular camera system, and the vibrating sensor is fixed in meter panel of motor vehicle, institute
State artificial external trigger device to be fixed on copilot panel, the sampled data that the computer is passed back according to main control chip enters walking along the street
Face pit area and the measuring and calculating of road surface pit depth information:
The road surface pit Area computing method comprises the following steps:
Step 1.1)Road surface sampled images are received, while demarcating each pixel occupied area;
Step 1.2)Adaptive median filter noise reduction is used image;
Step 1.3)Using the rapid edge-detection based on Rule of Region-growth;
Step 1.4)Detect whether as closure edge and differentiated, if it is not, it is not road surface pit then to illustrate, record GPS
Information, while jumping to step 1.1), if so, then going to following step 1.5);
Step 1.5)The sum of all pixels in sum of all pixels and border on statistical boundary;
Step 1.6)The area of road surface pit is finally obtained with reference to each pixel occupied area of demarcation;
The road surface pit Determination of The Depth method comprises the following steps:
Step 2.1)Receive road surface sampled images;
Step 2.2)Adaptive median filter noise reduction is used image;
Step 2.3)Using the rapid edge-detection based on Rule of Region-growth;
Step 2.4)Detect whether as closure edge and differentiated, if it is not, it is not road surface pit then to illustrate, gone to following
Step 2.5), if so, then jumping to step 2.6);
Step 2.5)GPS information is recorded, while jumping to step 2.1);
Step 2.6)Obtain the closure edge of binocular image and obtain binocular image in the same time;
Step 2.7)Check whether two images have corresponding image points and differentiated, if it is not, then jumping to step 2.5),
If so, then going to following step 2.8);
Step 2.8)Carry out corresponding image points matching;
Step 2.9)Calculate road surface section;
Step 2.10)The distance between each point in edge is calculated with road surface section respectively;
Step 2.11)Peak value is taken as the depth of road surface pit.
Further, the binocular camera system is arranged on vehicle ceiling with fixed angle.
Further, the vibrating sensor uses three axis accelerometer.
Further, in the step 1.4)With step 2.5)In, when wheel leakage pressure road surface pit by artificial outer tactile
Transmitting apparatus records GPS information at that time.
Further, the artificial external trigger device is button.
The beneficial effects of the invention are as follows:
The present invention can complete the positioning of road surface pit by building for hardware, and traditional image is optimized in terms of algorithm
Processing Algorithm simultaneously can accurately realize road surface pit area, depth calculation function, and these data shortly can be largely
A new detection technique is provided for road quality supervision department, support can be safely provided for guarantee road surface running vehicle in the future again,
With important practical meaning in engineering.
Brief description of the drawings
Fig. 1 is present system structural representation;
Fig. 2 is road surface pit Area computing flow chart;
Fig. 3 is road surface pit Determination of The Depth flow chart;
Fig. 4 is by the different picture point 3 d space coordinate figures that are taken in the embodiment of the present invention.
Embodiment
Below with reference to the accompanying drawings and in conjunction with the embodiments, the present invention is described in detail.
Shown in reference picture 1, a kind of road surface pit detection method based on vehicle-mounted binocular vision, this method based on hardware bag
Include main control chip, the main control chip is connected to binocular camera system, GPS positioning system, vibrating sensor, artificial outer touched
Transmitting apparatus and computer, it is characterised in that the binocular camera system is installed on road pavement image on vehicle ceiling and is acquired,
The GPS positioning system is fixed on vehicle ceiling together with binocular camera system, and the vibrating sensor is fixed on vehicle instrument
In dial plate, the artificial external trigger device is fixed on copilot panel, the sampling that the computer is passed back according to main control chip
Data carry out road surface pit area and the measuring and calculating of road surface pit depth information:
Shown in reference picture 2, the road surface pit Area computing method comprises the following steps:
Step 1.1)Road surface sampled images are received, while demarcating each pixel occupied area;
Step 1.2)Adaptive median filter noise reduction is used image;
Step 1.3)Using the rapid edge-detection based on Rule of Region-growth;
Step 1.4)Detect whether as closure edge and differentiated, if it is not, it is not road surface pit then to illustrate, record GPS
Information, while jumping to step 1.1), if so, then going to following step 1.5);
Step 1.5)The sum of all pixels in sum of all pixels and border on statistical boundary;
Step 1.6)The area of road surface pit is finally obtained with reference to each pixel occupied area of demarcation, is particularly combined
The parameter information of demarcation, according to statistics pit edge pixel coordinate, sum of all pixels in the range of technology pit, and then obtain road surface hole
Groove real area;
Shown in reference picture 3, the road surface pit Determination of The Depth method comprises the following steps:
Step 2.1)Receive road surface sampled images;
Step 2.2)Adaptive median filter noise reduction is used image;
Step 2.3)Using the rapid edge-detection based on Rule of Region-growth;
Step 2.4)Detect whether as closure edge and differentiated, if it is not, it is not road surface pit then to illustrate, gone to following
Step 2.5), if so, then jumping to step 2.6);
Step 2.5)GPS information is recorded, while jumping to step 2.1);
Step 2.6)Obtain the closure edge of binocular image and obtain binocular image in the same time;
Step 2.7)Check whether two images have corresponding image points and differentiated, if it is not, then jumping to step 2.5),
If so, then going to following step 2.8);
Step 2.8)Carry out corresponding image points matching;
Step 2.9)Calculate road surface section;
Step 2.10)The distance between each point in edge is calculated with road surface section respectively;
Step 2.11)Peak value is taken as the depth of road surface pit.
The binocular camera system is arranged on vehicle ceiling with fixed angle.
The vibrating sensor uses three axis accelerometer.
In the step 1.4)With step 2.5)In, remembered when wheel leakage pressure road surface pit by artificial external trigger device
The GPS information of record at that time.
The artificial external trigger device is button.
In the present embodiment, table 1 is represented in process of the test, obtains the area of four road surface pits, moreover, utilizing this hair
Bright method also can be to accurately measuring some object areas in irregular shape:
The pit image area test data of table 1(Square measure:)
In the present embodiment, table 2 is the spatial coordinate value of different picture points:
Table 2 estimates the 3 d space coordinate calculated value of corresponding image points matching based on coefficient correlation maximum performance
For different spatial coordinates, it can be showed in three dimensions.In Fig. 4, the seat in setting such as Fig. 4
Mark system, with reference to Fig. 4 as can be seen that the ordinate of point is larger in the middle part of Fig. 4, this section road surface is relatively low, and the ordinate of surrounding
Numerical value is relatively low, and this section is of a relatively high.
Figure 4, it is seen that the scope of ordinate is 17.122mm-48.772mm.Thus extrapolating needs detection
Road surface pit depth is about 31.65mm.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.
Claims (5)
1. a kind of road surface pit detection method based on vehicle-mounted binocular vision, this method based on hardware include main control chip, institute
State main control chip and be connected to binocular camera system, GPS positioning system, vibrating sensor, artificial external trigger device and calculating
Machine, it is characterised in that the binocular camera system is installed on road pavement image on vehicle ceiling and is acquired, the GPS location
System is fixed on vehicle ceiling together with binocular camera system, and the vibrating sensor is fixed in meter panel of motor vehicle, described
Artificial external trigger device is fixed on copilot panel, and the sampled data that the computer is passed back according to main control chip carries out road surface
Pit area and the measuring and calculating of road surface pit depth information:
The road surface pit Area computing method comprises the following steps:
Step 1.1)Road surface sampled images are received, while demarcating each pixel occupied area;
Step 1.2)Adaptive median filter noise reduction is used image;
Step 1.3)Using the rapid edge-detection based on Rule of Region-growth;
Step 1.4)Detect whether as closure edge and differentiated, if it is not, it is not road surface pit then to illustrate, record GPS information,
Jump to step 1.1 simultaneously), if so, then going to following step 1.5);
Step 1.5)The sum of all pixels in sum of all pixels and border on statistical boundary;
Step 1.6)The area of road surface pit is finally obtained with reference to each pixel occupied area of demarcation;
The road surface pit Determination of The Depth method comprises the following steps:
Step 2.1)Receive road surface sampled images;
Step 2.2)Adaptive median filter noise reduction is used image;
Step 2.3)Using the rapid edge-detection based on Rule of Region-growth;
Step 2.4)Detect whether as closure edge and differentiated, if it is not, it is not road surface pit then to illustrate, go to following step
Rapid 2.5), if so, then jumping to step 2.6);
Step 2.5)GPS information is recorded, while jumping to step 2.1);
Step 2.6)Obtain the closure edge of binocular image and obtain binocular image in the same time;
Step 2.7)Check whether two images have corresponding image points and differentiated, if it is not, then jumping to step 2.5)If,
It is then to go to following step 2.8);
Step 2.8)Carry out corresponding image points matching;
Step 2.9)Calculate road surface section;
Step 2.10)The distance between each point in edge is calculated with road surface section respectively;
Step 2.11)Peak value is taken as the depth of road surface pit.
2. the road surface pit detection method according to claim 1 based on vehicle-mounted binocular vision, it is characterised in that described double
Mesh camera system is arranged on vehicle ceiling with fixed angle.
3. the road surface pit detection method according to claim 1 based on vehicle-mounted binocular vision, it is characterised in that described to shake
Dynamic sensor uses three axis accelerometer.
4. the road surface pit detection method according to claim 1 based on vehicle-mounted binocular vision, it is characterised in that described
Step 1.4)With step 2.5)In, GPS letters at that time are recorded by artificial external trigger device when wheel leaks pressure road surface pit
Breath.
5. the road surface pit detection method according to claim 4 based on vehicle-mounted binocular vision, it is characterised in that the people
Work external trigger device is button.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510234379.7A CN104964708B (en) | 2015-08-03 | 2015-08-03 | A kind of road surface pit detection method based on vehicle-mounted binocular vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510234379.7A CN104964708B (en) | 2015-08-03 | 2015-08-03 | A kind of road surface pit detection method based on vehicle-mounted binocular vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104964708A CN104964708A (en) | 2015-10-07 |
CN104964708B true CN104964708B (en) | 2017-09-19 |
Family
ID=54218756
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510234379.7A Expired - Fee Related CN104964708B (en) | 2015-08-03 | 2015-08-03 | A kind of road surface pit detection method based on vehicle-mounted binocular vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104964708B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105277144A (en) * | 2015-10-16 | 2016-01-27 | 浙江工业大学 | Land area rapid detection method based on binocular vision and detection device thereof |
CN105463973B (en) * | 2015-12-15 | 2017-08-04 | 长安大学 | A kind of intelligent pit repairing car |
CN108360344B (en) * | 2018-02-11 | 2020-12-01 | 云南通衢工程检测有限公司 | Highway technical condition detection system |
CN109919139B (en) * | 2019-04-01 | 2021-02-09 | 杭州晶一智能科技有限公司 | Road surface condition rapid detection method based on binocular stereo vision |
CN110208278A (en) * | 2019-07-09 | 2019-09-06 | 电子科技大学 | The apparent slight crack vision measurement system in road surface |
CN111609892B (en) * | 2020-07-01 | 2021-10-29 | 苏州市东挺河智能科技发展有限公司 | Improved precision evaluation equipment for grooved industrial products |
CN112229362A (en) * | 2020-10-19 | 2021-01-15 | 南京朗禾智能控制研究院有限公司 | Vehicle-mounted device for accurately measuring area in real time |
CN113962301B (en) * | 2021-10-20 | 2022-06-17 | 北京理工大学 | Multi-source input signal fused pavement quality detection method and system |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101907448B (en) * | 2010-07-23 | 2013-07-03 | 华南理工大学 | Depth measurement method based on binocular three-dimensional vision |
CN102061659B (en) * | 2010-10-27 | 2012-07-04 | 毛庆洲 | Urban road pavement routine inspection equipment |
CN202433311U (en) * | 2011-12-08 | 2012-09-12 | 长安大学 | Device for detecting damage of road surface |
JP5776546B2 (en) * | 2011-12-28 | 2015-09-09 | 富士通株式会社 | Road surface inspection program and road surface inspection device |
JP6119097B2 (en) * | 2011-12-28 | 2017-04-26 | 富士通株式会社 | Road surface inspection program and road surface inspection device |
CN102607505B (en) * | 2012-03-23 | 2014-04-16 | 中国科学院深圳先进技术研究院 | Road evenness detection method and road evenness detection system |
CN102706880B (en) * | 2012-06-26 | 2014-04-02 | 哈尔滨工业大学 | Road information extraction device based on two-dimensional image and depth information and road crack information detection method based on same |
CN102829763B (en) * | 2012-07-30 | 2014-12-24 | 中国人民解放军国防科学技术大学 | Pavement image collecting method and system based on monocular vision location |
CN103679127B (en) * | 2012-09-24 | 2017-08-04 | 株式会社理光 | The method and apparatus for detecting the wheeled region of pavement of road |
CN204039886U (en) * | 2014-05-07 | 2014-12-24 | 长安大学 | A kind of pavement damage crack detection system based on multiple stage camera stereoscopic shooting |
CN104005325B (en) * | 2014-06-17 | 2016-01-20 | 武汉武大卓越科技有限责任公司 | Based on pavement crack checkout gear and the method for the degree of depth and gray level image |
CN104361627B (en) * | 2014-11-07 | 2017-11-28 | 武汉科技大学 | Binocular vision bituminous paving Micro texture 3-D view reconstructing method based on SIFT |
-
2015
- 2015-08-03 CN CN201510234379.7A patent/CN104964708B/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
CN104964708A (en) | 2015-10-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104964708B (en) | A kind of road surface pit detection method based on vehicle-mounted binocular vision | |
CN110285793B (en) | Intelligent vehicle track measuring method based on binocular stereo vision system | |
CN110322702B (en) | Intelligent vehicle speed measuring method based on binocular stereo vision system | |
Cortés et al. | ADVIO: An authentic dataset for visual-inertial odometry | |
JP6484228B2 (en) | Visually enhanced navigation | |
CN104704384B (en) | Specifically for the image processing method of the positioning of the view-based access control model of device | |
CN105940429B (en) | For determining the method and system of the estimation of equipment moving | |
US8571354B2 (en) | Method of and arrangement for blurring an image | |
US10424078B2 (en) | Height measuring system and method | |
CN103605978A (en) | Urban illegal building identification system and method based on three-dimensional live-action data | |
CN103530881B (en) | Be applicable to the Outdoor Augmented Reality no marks point Tracing Registration method of mobile terminal | |
CN106978774B (en) | A kind of road surface pit slot automatic testing method | |
CN106375706B (en) | method and device for measuring speed of moving object by using double cameras and mobile terminal | |
CA2684416A1 (en) | Method of and apparatus for producing road information | |
US20160042515A1 (en) | Method and device for camera calibration | |
CN106871906B (en) | Navigation method and device for blind person and terminal equipment | |
CN103292779A (en) | Method for measuring distance and image acquisition equipment | |
US10132635B2 (en) | Method and apparatus for misalignment between device and pedestrian using vision | |
US20210012147A1 (en) | Homography through satellite image matching | |
CN106504227B (en) | Demographic method and its system based on depth image | |
CN112455502B (en) | Train positioning method and device based on laser radar | |
CN104376323B (en) | A kind of method and device for determining target range | |
CN109870126A (en) | A kind of area computation method and a kind of mobile phone for being able to carry out areal calculation | |
CN112422653A (en) | Scene information pushing method, system, storage medium and equipment based on location service | |
CN110345924A (en) | A kind of method and apparatus that distance obtains |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170919 Termination date: 20190803 |