CN109580137A - A kind of bridge structure displacement influence line measurement method based on computer vision technique - Google Patents

A kind of bridge structure displacement influence line measurement method based on computer vision technique Download PDF

Info

Publication number
CN109580137A
CN109580137A CN201811443250.7A CN201811443250A CN109580137A CN 109580137 A CN109580137 A CN 109580137A CN 201811443250 A CN201811443250 A CN 201811443250A CN 109580137 A CN109580137 A CN 109580137A
Authority
CN
China
Prior art keywords
displacement
video
computer vision
bridge
influence line
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
CN201811443250.7A
Other languages
Chinese (zh)
Other versions
CN109580137B (en
Inventor
徐燕
郑宝锋
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.)
Southeast University
Original Assignee
Southeast 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 Southeast University filed Critical Southeast University
Priority to CN201811443250.7A priority Critical patent/CN109580137B/en
Publication of CN109580137A publication Critical patent/CN109580137A/en
Application granted granted Critical
Publication of CN109580137B publication Critical patent/CN109580137B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M5/00—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings
    • G01M5/0008—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings of bridges
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
    • G01B11/03—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by measuring coordinates of points
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M5/00—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings
    • G01M5/0041—Investigating the elasticity of structures, e.g. deflection of bridges or air-craft wings by determining deflection or stress

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Image Analysis (AREA)

Abstract

The invention belongs to structural health monitoring technology fields, specifically provide a kind of bridge structure displacement influence line measurement method based on computer vision technique, first set up camera in place and acquire video, it is ensured that tested point is respectively positioned within the scope of camera fields of view in structure；It is then based on principle of computer vision, displacement structure time-histories d is extracted from the video of acquisition；The axle distribution of given passing vehicle and axis weight, extract traveling load information A from the video of acquisition；Influence Line of Structural Displacement IL is finally solved according to the relationship of traveling load matrix A and structure measuring point displacement time-histories d；The present invention test outdoors in it is easy to operate, at low cost, do not influence bridge normal operation, the displacement influence line information along span length direction multi-measuring point can be provided simultaneously, be conveniently used for the quantization of construction damage positioning and degree of injury.

Description

A kind of bridge structure displacement influence line measurement method based on computer vision technique
Technical field
The invention belongs to structural health monitoring technology fields, provide a kind of bridge structure based on computer vision technique Displacement influence line measurement method.
Background technique
The displacement influence line of bridge structure corresponding observation point change in displacement song when referring to traveling load by entire span Line can reflect structure information of overall importance.Common application is bridge structural damage identification, using damage front and back displacement influence line and The positioning and degree quantization of structural damage are realized in the variation of its relevant parameter.
Line measurement method is influenced, common are two kinds, pointwise test obtains Bridge Influence Line by way of static test, Quasi-static influence line is obtained by way of demarcating vehicle and at the uniform velocity passing a bridge.Traditional influence line measured test, due to sensor bridge Upper installation and the control of vehicle loading position, often will affect the daily operation of bridge structure, and experimentation cost is high, working efficiency It is low.It is therefore proposed that a kind of economical and practical Bridge Influence Line measurement method, tool have very important significance.
Summary of the invention
To solve the above problems, the invention discloses a kind of bridge structure displacement influence line based on computer vision technique Measurement method, it is easy to operate, at low cost in test outdoors, bridge normal operation is not influenced, can be provided simultaneously along span length direction The displacement influence line information of multi-measuring point, is conveniently used for the quantization of construction damage positioning and degree of injury.
In order to achieve the above objectives, technical scheme is as follows:
A kind of bridge structure displacement influence line measurement method based on computer vision technique, comprising the following steps:
S1: camera is set up in place and acquires video, it is ensured that tested point is respectively positioned within the scope of camera fields of view in structure；
S2: being based on principle of computer vision, and displacement structure time-histories d is extracted from the video of acquisition；
S21: one or more monitoring objective is selected in video initial frame, is located at m in picture plane1；
S22: according to the projection imaging relationship at four or more control point with monitoring objective in the same plane, meter Plane homography H is calculated, wherein α m=HZ, α is the ratio of any scale, and m is that two dimension of the control point in picture plane is sat Mark, Z are the actual physics coordinate at control point；
S23: being based on Lucas-Kanade optical flow algorithm, positions position m of the object in next video framek；It is specific real Existing process is to be based on Shi-Tomasi Corner Detection, identify the key feature points (x, y) in target area；Based on brightness perseverance It is fixed it is assumed that derive that the position of key feature points (x, y) in the next frame is mobile (dx, dy), i.e. solution equationWherein, i indicate the surrounding side key feature points (x, y) row region (such as 3 × 3) the ith pixel point in, Ix、IyAnd ItIndicate gradient of the picture intensity I about picture space and time；Based on random sampling Consistency algorithm, the mobile abnormal key feature points in removal position, obtains average movement of the left point in picture planePosition of the object in the video frame is
S24: the projection imaging relationship α m of object is utilizedk=HZk, obtain the physical coordinates Z of objectk, with initial coordinate Z1Difference be moving displacement d of the target in time step kk；
S3: the axle distribution of given passing vehicle and axis weight extract traveling load information A from the video of acquisition；
S31: the video frame rate FPS of known vehicle body overall length L and acquisition, same observation station on bridge is passed through according to headstock, the tailstock Video frame number Ff、Fr, estimate vehicle pass-through Mean Speed v=LFPS/ (Fr-Ff)；
S32: it is distributed according to speed v and axle, estimates the shift position of each axle at any time, be then aggregated into mobile lotus Matrix A is carried, wherein elements A in matrixkmThe axle load acted on bridge unit m when time step k is indicated, if the unit is at this moment Without imposed load under spacer step, then Akm=0；
S4: according to the relationship of traveling load matrix A and structure measuring point displacement time-histories d, i.e. AIL=d solves structure bit Moving influences line IL.
The beneficial effects of the present invention are:
Compared with prior art, the present invention having the advantage that
1, the testing equipment being related to is simple, at low cost, it is only necessary to which video collector such as camera, mobile phone are equipped with video analysis Computer and the ancillary equipment such as tripod of program；It is easy to operate in test outdoors, without being installed at each measuring point of structure Sensor, on the daily operation of structure without influence；
2, compared with traditional displacement influence line measurement method, camera system proposed by the present invention can extract structure simultaneously The information of displacement and vehicular load position, the stationary problem not being related between sensor；
3, the method can provide the displacement influence line information along span length direction multi-measuring point simultaneously, and it is fixed to be conveniently used for structural damage The quantization of position and degree of injury.
Detailed description of the invention
Fig. 1 is the flow chart of the method for the present invention；
Fig. 2 is the arrangement of the camera system in the case of a single span railway bridge；
Fig. 3 is displacement time-histories of the railway bridge in the case where the train in one or four section compartments is current；
Fig. 4 is displacement influence line of the position at unit load (1N) in railway bridges.
Specific embodiment
Below in conjunction with technical solution, a specific embodiment of the invention is illustrated by the case of a single span railway bridge.
S1: camera is set up in place and acquires video, it is ensured that tested point is respectively positioned within the scope of camera fields of view in structure； The arrangement of camera system is shown in Fig. 2；
S2: being based on principle of computer vision, and displacement structure time-histories d is extracted from the video of acquisition；
S21: the monitoring objective positioned at span centre is selected in video initial frame, is located at m in picture plane1；
S22: according to the projection imaging relationship at four or more control point with monitoring objective in the same plane, meter Calculate plane homography H；
S23: being based on Lucas-Kanade optical flow algorithm, positions position m of the object in next video framek；
S24: the projection imaging relationship α m of object is utilizedk=HZk, obtain the physical coordinates Z of objectk, with initial coordinate Z1Difference be moving displacement d of the target in time step kk；Position is in the case where the train in one or four section compartments is current in bridge span Displacement time-histories is shown in Fig. 3；
S3: the axle distribution of given passing vehicle and axis weight extract traveling load information A from the video of acquisition；
S31: the video frame rate FPS of known vehicle body overall length L and acquisition, same observation station on bridge is passed through according to headstock, the tailstock Video frame number Ff、Fr, the current Mean Speed v=34.0km/h of train is estimated,；
S32: it is distributed according to speed v and axle, estimates the shift position of each axle at any time, be then aggregated into mobile lotus Carry matrix A；
S4: according to the relationship of traveling load matrix A and structure measuring point displacement time-histories d, i.e. AIL=d solves structure bit Moving influences line IL；The displacement influence line of gained span centre position is shown in Fig. 4.

Claims (3)

1. a kind of bridge structure displacement influence line measurement method based on computer vision technique, it is characterised in that: including following Step:
S1: camera is set up in place and acquires video, it is ensured that tested point is respectively positioned within the scope of camera fields of view in structure；
S2: being based on principle of computer vision, and displacement structure time-histories d is extracted from the video of acquisition；
S3: the axle distribution of given passing vehicle and axis weight extract traveling load information A from the video of acquisition；
S4: according to the relationship of traveling load matrix A and structure measuring point displacement time-histories d, i.e. AIL=d solves displacement structure shadow Ring line IL.
2. a kind of bridge structure displacement influence line measurement method based on computer vision technique according to claim 1, It is characterized by: the specific method of step S2 is:
S21: one or more monitoring objective is selected in video initial frame, is located at m in picture plane1；
S22: it according to the projection imaging relationship at four or more control point with monitoring objective in the same plane, calculates Plane homography H, wherein α m=HZ, α are the ratio of any scale, and m is two-dimensional coordinate of the control point in picture plane, Z For the actual physics coordinate at control point；
S23: being based on Lucas-Kanade optical flow algorithm, positions position m of the object in next video framek；Specific implementation process It is to be based on Shi-Tomasi Corner Detection, identify the key feature points (x, y) in target area；Vacation based on brightness constancy It is fixed, derive that the position of key feature points (x, y) in the next frame is mobile (dx, dy), i.e. solution equationWherein, i indicate the surrounding side key feature points (x, y) row region (such as 3 × 3) the ith pixel point in, Ix、IyAnd ItIndicate gradient of the picture intensity I about picture space and time；Based on random sampling Consistency algorithm, the mobile abnormal key feature points in removal position, obtains average movement of the left point in picture planePosition of the object in the video frame is
S24: the projection imaging relationship α m of object is utilizedk=HZk, obtain the physical coordinates Z of objectk, with initial coordinate Z1's Difference is moving displacement d of the target in time step kk。
3. a kind of bridge structure displacement influence line measurement method based on computer vision technique according to claim 1, It is characterized by: the specific method of step S3 is:
S31: the video frame rate FPS of known vehicle body overall length L and acquisition, the video that same observation station on bridge is passed through according to headstock, the tailstock Frame number Ff、Fr, estimate vehicle pass-through Mean Speed v=LFPS/ (Fr-Ff)；
S32: it is distributed according to speed v and axle, estimates the shift position of each axle at any time, be then aggregated into traveling load square Battle array A, wherein elements A in matrixkmThe axle load acted on bridge unit m when time step k is indicated, if the unit is in this time step Lower no imposed load, then Akm=0.
CN201811443250.7A 2018-11-29 2018-11-29 Bridge structure displacement influence line actual measurement method based on computer vision technology Active CN109580137B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811443250.7A CN109580137B (en) 2018-11-29 2018-11-29 Bridge structure displacement influence line actual measurement method based on computer vision technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811443250.7A CN109580137B (en) 2018-11-29 2018-11-29 Bridge structure displacement influence line actual measurement method based on computer vision technology

Publications (2)

Publication Number Publication Date
CN109580137A true CN109580137A (en) 2019-04-05
CN109580137B CN109580137B (en) 2020-08-11

Family

ID=65925345

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811443250.7A Active CN109580137B (en) 2018-11-29 2018-11-29 Bridge structure displacement influence line actual measurement method based on computer vision technology

Country Status (1)

Country Link
CN (1) CN109580137B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112637553A (en) * 2020-11-25 2021-04-09 浙江大学 Bridge structure modal analysis method based on monitoring video
CN112629896A (en) * 2020-09-16 2021-04-09 湘潭大学 Beam structure damage identification method based on horizontal support reaction influence line
CN112710371A (en) * 2020-12-03 2021-04-27 湖南大学 Bridge dynamic weighing method and system based on real-time space position of vehicle
CN114937365A (en) * 2022-06-21 2022-08-23 东南大学 Bridge deck vehicle parameter identification method based on synchronous multi-vision sensor
GB2616322A (en) * 2022-03-03 2023-09-06 Univ Hefei Technology Computer vision-based dynamic bridge shape recognition method
CN118376162A (en) * 2024-06-20 2024-07-23 兰州理工大学 Bridge structure displacement influence line actual measurement method based on computer vision technology

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101297321A (en) * 2005-10-25 2008-10-29 布拉科成像S.P.A.公司 Method of registering images, algorithm for carrying out the method of registering images, a program for registering images using the said algorithm and a method of treating biomedical images to reduc
CN101358897A (en) * 2008-08-08 2009-02-04 重庆交通科研设计院 Influence line wireless remote automatic test equipment for bridge structure
JP5327796B2 (en) * 2009-02-25 2013-10-30 国立大学法人東京工業大学 Vehicle weight measuring system for vehicles passing through bridge, vehicle weight measuring method for vehicles passing through bridge, and computer program
CN104819813A (en) * 2015-04-29 2015-08-05 中南大学 Bridge influence line dynamic test method
CN105865735A (en) * 2016-04-29 2016-08-17 浙江大学 Method for bridge vibration testing and dynamic property recognition based on video monitoring
CN107588915A (en) * 2017-10-18 2018-01-16 厦门大学 A kind of Bridge Influence Line recognition methods and system
CN108491758A (en) * 2018-02-08 2018-09-04 深圳市睿灵创新科技开发有限公司 A kind of track detection method and robot
CN108760200A (en) * 2018-05-18 2018-11-06 苏交科集团股份有限公司 Vehicle it is non-at the uniform velocity by when Bridge Influence Line assay method
CN108844702A (en) * 2018-05-31 2018-11-20 南京东南建筑机电抗震研究院有限公司 The measuring method of Bridge Influence Line when vehicle at the uniform velocity passes through

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101297321A (en) * 2005-10-25 2008-10-29 布拉科成像S.P.A.公司 Method of registering images, algorithm for carrying out the method of registering images, a program for registering images using the said algorithm and a method of treating biomedical images to reduc
CN101358897A (en) * 2008-08-08 2009-02-04 重庆交通科研设计院 Influence line wireless remote automatic test equipment for bridge structure
JP5327796B2 (en) * 2009-02-25 2013-10-30 国立大学法人東京工業大学 Vehicle weight measuring system for vehicles passing through bridge, vehicle weight measuring method for vehicles passing through bridge, and computer program
CN104819813A (en) * 2015-04-29 2015-08-05 中南大学 Bridge influence line dynamic test method
CN105865735A (en) * 2016-04-29 2016-08-17 浙江大学 Method for bridge vibration testing and dynamic property recognition based on video monitoring
CN107588915A (en) * 2017-10-18 2018-01-16 厦门大学 A kind of Bridge Influence Line recognition methods and system
CN108491758A (en) * 2018-02-08 2018-09-04 深圳市睿灵创新科技开发有限公司 A kind of track detection method and robot
CN108760200A (en) * 2018-05-18 2018-11-06 苏交科集团股份有限公司 Vehicle it is non-at the uniform velocity by when Bridge Influence Line assay method
CN108844702A (en) * 2018-05-31 2018-11-20 南京东南建筑机电抗震研究院有限公司 The measuring method of Bridge Influence Line when vehicle at the uniform velocity passes through

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112629896A (en) * 2020-09-16 2021-04-09 湘潭大学 Beam structure damage identification method based on horizontal support reaction influence line
CN112637553A (en) * 2020-11-25 2021-04-09 浙江大学 Bridge structure modal analysis method based on monitoring video
CN112710371A (en) * 2020-12-03 2021-04-27 湖南大学 Bridge dynamic weighing method and system based on real-time space position of vehicle
CN112710371B (en) * 2020-12-03 2021-12-28 湖南大学 Bridge dynamic weighing method and system based on real-time space position of vehicle
GB2616322A (en) * 2022-03-03 2023-09-06 Univ Hefei Technology Computer vision-based dynamic bridge shape recognition method
CN114937365A (en) * 2022-06-21 2022-08-23 东南大学 Bridge deck vehicle parameter identification method based on synchronous multi-vision sensor
CN118376162A (en) * 2024-06-20 2024-07-23 兰州理工大学 Bridge structure displacement influence line actual measurement method based on computer vision technology

Also Published As

Publication number Publication date
CN109580137B (en) 2020-08-11

Similar Documents

Publication Publication Date Title
CN109580137A (en) A kind of bridge structure displacement influence line measurement method based on computer vision technique
Pan et al. Real-time, non-contact and targetless measurement of vertical deflection of bridges using off-axis digital image correlation
CN109584238B (en) Stereoscopic vision-based bow net running state online detection system and method
Han et al. Monitoring tunnel deformations by means of multi-epoch dispersed 3D LiDAR point clouds: An improved approach
McCormick et al. Digital image correlation for structural measurements
CN105067208B (en) A kind of multichannel bridge deflection monitoring method based on CCD
CN109341903B (en) Inhaul cable force measuring method based on edge recognition in computer vision
CN112504414B (en) Vehicle dynamic weighing method and system based on non-contact measurement of dynamic deflection of bridge
CN106049210A (en) Intelligent rail state detection platform
CN109297428A (en) A kind of high-precision deformation based on unmanned plane patrols survey technology method
CN106679567A (en) Contact net and strut geometric parameter detecting measuring system based on binocular stereoscopic vision
CN102175219A (en) High-speed contact network locator gradient detection method and apparatus thereof based on video analysis
CN105157595A (en) Method and device for detecting deformation and defects of existing building
US20220383478A1 (en) Computer vision-based system and method for assessment of load distribution, load rating, and vibration serviceability of structures
CN104973092A (en) Rail roadbed settlement measurement method based on mileage and image measurement
CN108487216A (en) Closed-loop camera series network for monitoring foundation settlement
CN103017672A (en) Non-contact nondestructive testing method for bridge structure
CN109341549A (en) A kind of camera system displacement monitoring improved method based on data fusion
Kromanis et al. Low cost vision-based systems using smartphones for measuring deformation in structures for condition monitoring and asset management
RU2459213C1 (en) Apparatus and method of measuring vertical acceleration of pantograph via image processing
Zhou et al. Vision-based modal parameter identification for bridges using a novel holographic visual sensor
Wang et al. Target-free recognition of cable vibration in complex backgrounds based on computer vision
CN204944448U (en) The pick-up unit of existing building distortion and defect
Ge et al. A Benchmark Data Set for Vision-Based Traffic Load Monitoring in a Cable-Stayed Bridge
CN103983239B (en) Based on the distance-finding method of the wide line in track

Legal Events

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