CN106706647A - Road crack size estimation method based on mobile phone photographing - Google Patents

Road crack size estimation method based on mobile phone photographing Download PDF

Info

Publication number
CN106706647A
CN106706647A CN201611230287.2A CN201611230287A CN106706647A CN 106706647 A CN106706647 A CN 106706647A CN 201611230287 A CN201611230287 A CN 201611230287A CN 106706647 A CN106706647 A CN 106706647A
Authority
CN
China
Prior art keywords
crackle
mobile phone
crack
matrix
road
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
Application number
CN201611230287.2A
Other languages
Chinese (zh)
Other versions
CN106706647B (en
Inventor
於志文
孔莹莹
陈荟慧
郭斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Northwestern Polytechnical University
Original Assignee
Northwestern Polytechnical University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Northwestern Polytechnical University filed Critical Northwestern Polytechnical University
Priority to CN201611230287.2A priority Critical patent/CN106706647B/en
Publication of CN106706647A publication Critical patent/CN106706647A/en
Application granted granted Critical
Publication of CN106706647B publication Critical patent/CN106706647B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan 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
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan 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
    • G01N2021/8854Grading and classifying of flaws
    • G01N2021/8874Taking dimensions of defect into account
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan 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
    • G01N2021/8887Scan 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 based on image processing techniques
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10004Still image; Photographic image

Abstract

The invention discloses a road crack size estimation method based on mobile phone photographing. The method is used for solving the technical problem that the existing road crack size estimation method is low in practicability. According to the technical scheme, the method comprises the following steps: photographing road cracks by utilizing a smart phone, and collecting crack photos and mobile phone sensor data during photographing; performing median filter smoothness, sobel operator sharpening and grey processing on the collected crack photos, performing image segmentation by using an OTSU algorithm, segmenting the cracks from a road background, calculating the area of the cracks in the photos, determining the distance from the mobile phone camera to the cracks, and calculating the actual physical size of the cracks. According to the method disclosed by the invention, the cracks do not need to be photographed by a special crack detection vehicle, the actual physical size of the cracks is calculated by utilizing a convex lens imaging principle of the mobile phone camera only, and the practicality is high. Moreover, when the crack width is calculated, the root-mean-square error is 5.2cm, and when the crack length is calculated, the root-mean-square error is 17.1cm.

Description

Road crack size method of estimation based on mobile phone photograph
Technical field
The present invention relates to a kind of road crack size method of estimation, more particularly to a kind of road crackle based on mobile phone photograph Size estimation method.
Background technology
In recent years, traditional municipal services that develop into of smart mobile phone provide new means.In traditional urban road , it is necessary to the equipment of the librarian use specialty of specialty is checked in crack detecting method, substantial amounts of man power and material is so wasted. With the development of smart mobile phone, common citizen can be taken pictures using mobile phone to crackle, but due to mobile phone photograph when Wait, the direction taken pictures and the distance taken pictures all are arbitrary, in the present invention we using mobile phone when taking pictures sensor information, such as Accelerometer, magnetometer, barometer etc., and photo information in itself, estimate road flaw size.
Document " the pavement distress survey technical research Wuhan University of Technologys based on image procossing, 2013 " discloses one kind The method of estimation of road surface crack size.The method fracture first is refined, and obtains the skeleton in crack, and the skeleton to crackle is made Element marking, then the length and width in crack is just can obtain by way of scanning and counting.But because the method is using special Crack detection car crackle is taken pictures, what the distance and angle of camera to crackle were to determine, so the reality of crackle What the proportionate relationship between the size of the picture of physical size and crackle in photo was to determine.
In sum, when judging crack size using mobile phone photograph, because camera is from the angle and distance of crackle It is uncertain, the size of crackle picture can be only obtained by photo.
The content of the invention
In order to overcome the shortcomings of existing road crack size method of estimation poor practicability, the present invention provides a kind of based on mobile phone The road crack size method of estimation taken pictures.The method is taken pictures first with smart mobile phone to road crackle, gathers crackle Photo and mobile phone sensor data when taking pictures.Crackle photo to collecting carries out including median filter smoothness of image, sobel operators Sharpen and gray proces, then carry out image segmentation using OTSU algorithms, crackle is partitioned into from the background of road surface, calculate crackle and exist Area in photo, determines mobile phone camera to the distance of crackle, calculates the actual physical size of crackle.The present invention need not Special crack detection car is taken pictures to crackle, and the reality of crackle is calculated merely with the convex lens imaging principle of mobile phone camera Physical size, practicality is good.
The technical solution adopted for the present invention to solve the technical problems:A kind of road crack size based on mobile phone photograph is estimated Meter method, is characterized in comprising the following steps:
Step one, road crackle is taken pictures using smart mobile phone, collection crackle photo and mobile phone sensing when taking pictures Device data.Mobile phone baroceptor, acceleration transducer and magnetometric sensor are as calculating mobile phone camera with a distance from crackle Data foundation.By all mobile phone sensor data preparations into triple<Crackle photo, sensor name, sensor values>.Its Middle acceleration transducer, the sensor values form of magnetometric sensor are a three-dimensional vectors<X, y, z>, baroceptor is hand The atmospheric pressure value of machine position<baro>.
Step 2, the crackle photo to being collected in step one include median filter smoothness of image, sobel operators sharpen and Gray proces, then carry out image segmentation using OTSU algorithms, and crackle is partitioned into from the background of road surface.Binaryzation square after treatment Battle array is designated as G.
Step 3, mathematical morphology make-before-break treatment is carried out to binaryzation matrix G, the matrix after treatment is designated as M, then Dilation erosion and Refinement operation are carried out to matrix M, crackle skeleton is extracted, the matrix after treatment is designated as N.
Step 4, for pattern cracking, the every a line for the matrix M that scanning step three is obtained, the maximum for finding crackle vertical is sat Punctuate y1With minimum ordinate point y2.Each row of scan matrix M, find the maximum abscissa point x of crackle1With minimum abscissa Point x2.Area s of the pattern cracking in photo is calculated using formula (1):
S=(y1-y2)*(x1-x2) (1)
Split for perpendicular, every a line of scan matrix M calculates the crackle pixel number per a line, is multiplied by each pixel Length, the as crack width of the row.Then the width of the every a line crackle to trying to achieve is averaging and obtains the perpendicular average width for splitting Degree.When seeking the length erected and split, the matrix N that scanning step three is obtained calculates the pixel number of crackle skeleton, is multiplied by each picture The length of element, as erects the length split.Each row of scan matrix M, obtain the crack width of the row, are averaging and obtain transverse fissure Mean breadth.Scan matrix N obtains the length of transverse fissure.
Step 5, camera to three parameters of the distance of crackle is calculated, the vertical range h of mobile phone to ground, mobile phone The left rotation and right rotation angle beta of tilt fore and aft α, mobile phone.Camera is calculated to crackle apart from od by formula (2):
Od=h/ (cos | α | cos | β |) (2)
Mobile phone is calculated to the vertical range h on ground by formula (3), pmIt is the atmospheric pressure value of mobile phone position, by hand The baroceptor of machine is obtained, pgIt is the atmospheric pressure value on ground:
The tilt fore and aft α of mobile phone, left rotation and right rotation angle beta are calculated by acceleration transducer and magnetometric sensor, are passed through Android exploitations API is obtained.
Step 6, size of the crackle in photo is obtained according to step 4, step 5 obtains camera to crackle The focal length of distance and mobile phone, by convex lens formula (4) (5), derives that formula (6) calculates crackle actual physics chi Very little, d is object distance, and i is image distance, and f is focal length, and imagesize is the size of picture, and physicalsize is the actual physics chi of crackle It is very little.
The beneficial effects of the invention are as follows:The method is taken pictures first with smart mobile phone to road crackle, gathers crackle Photo and mobile phone sensor data when taking pictures.Crackle photo to collecting carries out including median filter smoothness of image, sobel operators Sharpen and gray proces, then carry out image segmentation using OTSU algorithms, crackle is partitioned into from the background of road surface, calculate crackle and exist Area in photo, determines mobile phone camera to the distance of crackle, calculates the actual physical size of crackle.The present invention need not Special crack detection car is taken pictures to crackle, and the reality of crackle is calculated merely with the convex lens imaging principle of mobile phone camera Physical size, practicality is good.And when calculating crack width, root-mean-square error is 5.2cm, when counting crack length, Root-mean-square error is 17.1cm.
The present invention is elaborated with reference to the accompanying drawings and detailed description.
Brief description of the drawings
Fig. 1 is the flow chart of road crack size method of estimation of the present invention based on mobile phone photograph.
Specific embodiment
Reference picture 1.Road crack size method of estimation of the present invention based on mobile phone photograph is comprised the following steps that:
Step one, road crackle is taken pictures using smart mobile phone, collection crackle photo and mobile phone when taking pictures are passed Sensor data.The number of baroceptor, acceleration transducer and magnetometric sensor as calculating mobile phone camera with a distance from crackle According to foundation.And further by all data preparations into triple<Crackle photo, sensor name, sensor values>.Wherein plus Velocity sensor, the sensor values form of magnetometric sensor are a three-dimensional vectors<X, y, z>, baroceptor is mobile phone institute In the atmospheric pressure value of position<baro>.
Step 2, the crackle photo to being collected in step one carry out image procossing.Image is carried out to photo first to locate in advance Reason, including the sharpening of median filter smoothness of image, sobel operators, gray proces, then carry out image segmentation, from road using OTSU algorithms Crackle is partitioned into the background of face.Binaryzation matrix after treatment is designated as G.
Step 3, in order to be precisely calculated flaw size in photo, matrix G is carried out at mathematical morphology make-before-break Reason, the matrix after treatment is designated as M, and dilation erosion and Refinement operation are then carried out to matrix M, crackle skeleton is extracted, after treatment Matrix is designated as N.
The size of step 4, calculating crackle in photo.For pattern cracking, the matrix M that scanning step three is obtained Every a line, find the maximum ordinate point y of crackle1With minimum ordinate point y2.Each row of M are scanned, the maximum of crackle is found Abscissa point x1With minimum abscissa point x2.Area s of the pattern cracking in photo is calculated using formula (1):
S=(y1-y2)*(x1-x2) (1)
Split for perpendicular, every a line of scan matrix M calculates the crackle pixel number per a line, is multiplied by each pixel Length, the as crack width of the row.Then the width of the every a line crackle to trying to achieve is averaging and obtains the perpendicular average width for splitting Degree.When seeking the length erected and split, the matrix N that scanning step three is obtained calculates the pixel number of crackle skeleton, is multiplied by each picture The length of element, as erects the length split.Similarly, each row of scan matrix M, obtain the crack width of the row, are averaging and obtain The mean breadth of transverse fissure.Scan matrix N obtains the length of transverse fissure.
Step 5, mobile phone camera are to crackle determination of distance.Calculate camera needs three parameters to the distance of crackle, Mobile phone to the vertical range h on ground, the tilt fore and aft α of mobile phone, mobile phone left rotation and right rotation angle beta.Calculated by formula (2) and imaged Head is to crackle apart from od:
Od=h/ (cos | α | cos | β |) (2)
Mobile phone is calculated to the vertical range h on ground by formula (3), pmIt is the atmospheric pressure value of mobile phone position, by hand The baroceptor of machine can be obtained, pgIt is the atmospheric pressure value on ground:
The tilt fore and aft α of mobile phone, left rotation and right rotation angle beta are calculated by acceleration transducer and magnetometric sensor, are passed through Android exploitations API is obtained.
The calculating of step 6, crackle actual physical size.The principle of taking pictures of mobile phone camera is convex lens imaging principle, step Rapid four have obtained size of the crackle in photo, that is, as size, step 5 obtained camera to crackle away from From, i.e. object distance, the focal length of mobile phone is known, by convex lens formula (4) (5), derives that formula (6) calculates crackle reality Border physical size, d is object distance, and i is image distance, and f is focal length, and imagesize is the size of picture, and physicalsize is the reality of crackle Border physical size.

Claims (1)

1. a kind of road crack size method of estimation based on mobile phone photograph, it is characterised in that comprise the following steps:
Step one, road crackle is taken pictures using smart mobile phone, collection crackle photo and mobile phone sensor number when taking pictures According to;The data of mobile phone baroceptor, acceleration transducer and magnetometric sensor as calculating mobile phone camera with a distance from crackle Foundation;By all mobile phone sensor data preparations into triple<Crackle photo, sensor name, sensor values>;Wherein plus Velocity sensor, the sensor values form of magnetometric sensor are a three-dimensional vectors<X, y, z>, baroceptor is mobile phone institute In the atmospheric pressure value of position<baro>;
Step 2, the crackle photo to being collected in step one carry out including that median filter smoothness of image, sobel operators are sharpened and gray scale Treatment, then carries out image segmentation using OTSU algorithms, and crackle is partitioned into from the background of road surface;Binaryzation matrix note after treatment It is G;
Step 3, mathematical morphology make-before-break treatment is carried out to binaryzation matrix G, the matrix after treatment is designated as M, then to square Battle array M carries out dilation erosion and Refinement operation, extracts crackle skeleton, and the matrix after treatment is designated as N;
Step 4, for pattern cracking, the every a line for the matrix M that scanning step three is obtained finds the maximum ordinate point y of crackle1 With minimum ordinate point y2;Each row of scan matrix M, find the maximum abscissa point x of crackle1With minimum abscissa point x2;Make Area s of the pattern cracking in photo is calculated with formula (1):
S=(y1-y2)*(x1-x2) (1)
Split for perpendicular, every a line of scan matrix M calculates the crackle pixel number per a line, is multiplied by the length of each pixel Degree, the as crack width of the row;Then the width of the every a line crackle to trying to achieve is averaging and obtains the perpendicular mean breadth for splitting;Ask When erecting the length split, the matrix N that scanning step three is obtained calculates the pixel number of crackle skeleton, is multiplied by each pixel Length, as erects the length split;Each row of scan matrix M, obtain the crack width of the row, are averaging and obtain the average of transverse fissure Width;Scan matrix N obtains the length of transverse fissure;
Step 5, calculate camera to three parameters of the distance of crackle, the vertical range h of mobile phone to ground, mobile phone it is front and rear Inclined angle alpha, the left rotation and right rotation angle beta of mobile phone;Camera is calculated to crackle apart from od by formula (2):
Od=h/ (cos | α | cos | β |) (2)
Mobile phone is calculated to the vertical range h on ground by formula (3), pmIt is the atmospheric pressure value of mobile phone position, by the gas of mobile phone Pressure sensor is obtained, pgIt is the atmospheric pressure value on ground:
h = 44300 * &lsqb; 1 - ( p m p g ) 1 5255 &rsqb; - - - ( 3 )
The tilt fore and aft α of mobile phone, left rotation and right rotation angle beta are calculated by acceleration transducer and magnetometric sensor, by android Exploitation API is obtained;
Step 6, size of the crackle in photo is obtained according to step 4, step 5 obtains camera to the distance of crackle And the focal length of mobile phone, by convex lens formula (4) (5), deriving that formula (6) calculates crackle actual physical size, d is Object distance, i is image distance, and f is focal length, and imagesize is the size of picture, and physicalsize is the actual physical size of crackle;
1 d + 1 i = 1 f - - - ( 4 )
p h y s i c a l s i z e i m a g e s i z e = f i - f - - - ( 5 )
p h y s i c a l s i z e = f ( d - f ) f * d - f ( d - f ) * i m a g e s i z e - - - ( 6 ) .
CN201611230287.2A 2016-12-28 2016-12-28 Road crack size estimation method based on mobile phone photograph Active CN106706647B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611230287.2A CN106706647B (en) 2016-12-28 2016-12-28 Road crack size estimation method based on mobile phone photograph

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611230287.2A CN106706647B (en) 2016-12-28 2016-12-28 Road crack size estimation method based on mobile phone photograph

Publications (2)

Publication Number Publication Date
CN106706647A true CN106706647A (en) 2017-05-24
CN106706647B CN106706647B (en) 2019-05-07

Family

ID=58895550

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611230287.2A Active CN106706647B (en) 2016-12-28 2016-12-28 Road crack size estimation method based on mobile phone photograph

Country Status (1)

Country Link
CN (1) CN106706647B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109163698A (en) * 2018-08-06 2019-01-08 百度在线网络技术(北京)有限公司 Building settlement measurement method, device and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100053318A1 (en) * 2008-08-28 2010-03-04 Hironori Sasaki Camera module and method of producing the same
CN104089580A (en) * 2014-06-26 2014-10-08 华南理工大学 Concrete surface crack width measuring instrument and method based on smart phone
US20140330438A1 (en) * 2013-03-27 2014-11-06 Russell Haines Intelligent hvac register
CN104316601A (en) * 2014-10-29 2015-01-28 上海斐讯数据通信技术有限公司 Mobile phone with floor internal defect detection function and working principle of mobile phone
CN204288301U (en) * 2014-12-19 2015-04-22 中国科学院武汉岩土力学研究所 A kind of fracture width change monitoring device
CN105160695A (en) * 2015-06-30 2015-12-16 广东欧珀移动通信有限公司 Picture processing method and mobile terminal

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100053318A1 (en) * 2008-08-28 2010-03-04 Hironori Sasaki Camera module and method of producing the same
US20140330438A1 (en) * 2013-03-27 2014-11-06 Russell Haines Intelligent hvac register
CN104089580A (en) * 2014-06-26 2014-10-08 华南理工大学 Concrete surface crack width measuring instrument and method based on smart phone
CN104316601A (en) * 2014-10-29 2015-01-28 上海斐讯数据通信技术有限公司 Mobile phone with floor internal defect detection function and working principle of mobile phone
CN204288301U (en) * 2014-12-19 2015-04-22 中国科学院武汉岩土力学研究所 A kind of fracture width change monitoring device
CN105160695A (en) * 2015-06-30 2015-12-16 广东欧珀移动通信有限公司 Picture processing method and mobile terminal

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109163698A (en) * 2018-08-06 2019-01-08 百度在线网络技术(北京)有限公司 Building settlement measurement method, device and storage medium

Also Published As

Publication number Publication date
CN106706647B (en) 2019-05-07

Similar Documents

Publication Publication Date Title
Javernick et al. Modeling the topography of shallow braided rivers using Structure-from-Motion photogrammetry
US8571265B2 (en) Measurement apparatus, measurement method, and feature identification apparatus
CN107463918B (en) Lane line extraction method based on fusion of laser point cloud and image data
CN105894502B (en) RGBD image significance detection method based on hypergraph model
US8718328B1 (en) Digital processing method and system for determination of object occlusion in an image sequence
CN104318561B (en) Method for detecting vehicle motion information based on integration of binocular stereoscopic vision and optical flow
CN104700414B (en) A kind of road ahead pedestrian&#39;s fast ranging method based on vehicle-mounted binocular camera
Weinmann et al. Fast and automatic image-based registration of TLS data
CN104330022B (en) Method and system is determined using the volume of structure from motion algorithm
Graham et al. Automated sizing of coarse-grained sediments: image-processing procedures
CN105346706B (en) Flight instruments, flight control system and method
CN104318548B (en) Rapid image registration implementation method based on space sparsity and SIFT feature extraction
Beall et al. 3D reconstruction of underwater structures
Chen et al. Fusion of LIDAR data and optical imagery for building modeling
JPWO2012017650A1 (en) Object detection apparatus, object detection method, and program
CN104574375B (en) Image significance detection method combining color and depth information
CN101923641B (en) Improved human face recognition method
Chen et al. High-accuracy multi-camera reconstruction enhanced by adaptive point cloud correction algorithm
CN104034269B (en) A kind of monocular vision measuring method and device
CN105574488B (en) It is a kind of to be taken photo by plane the pedestrian detection method of infrared image based on low latitude
CN106969706A (en) Workpiece sensing and three-dimension measuring system and detection method based on binocular stereo vision
CN106978774B (en) A kind of road surface pit slot automatic testing method
CN105225482A (en) Based on vehicle detecting system and the method for binocular stereo vision
CN103456038A (en) Method for rebuilding three-dimensional scene of downhole environment
CN104281840B (en) A kind of method and device based on intelligent terminal fixation and recognition building

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant