CN112464788A - Truss arch bridge suspender safety monitoring system and method based on image recognition technology - Google Patents
Truss arch bridge suspender safety monitoring system and method based on image recognition technology Download PDFInfo
- Publication number
- CN112464788A CN112464788A CN202011338182.5A CN202011338182A CN112464788A CN 112464788 A CN112464788 A CN 112464788A CN 202011338182 A CN202011338182 A CN 202011338182A CN 112464788 A CN112464788 A CN 112464788A
- Authority
- CN
- China
- Prior art keywords
- boom
- suspender
- marker
- binocular camera
- arch bridge
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 64
- 238000005516 engineering process Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 33
- 239000003550 marker Substances 0.000 claims abstract description 61
- 238000006073 displacement reaction Methods 0.000 claims abstract description 43
- 238000005259 measurement Methods 0.000 claims abstract description 9
- 230000001133 acceleration Effects 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000009795 derivation Methods 0.000 claims description 11
- 238000009434 installation Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 abstract description 9
- 239000000725 suspension Substances 0.000 description 26
- 238000001514 detection method Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011900 installation process Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M11/00—Testing of optical apparatus; Testing structures by optical methods not otherwise provided for
- G01M11/08—Testing mechanical properties
- G01M11/081—Testing mechanical properties by using a contact-less detection method, i.e. with a camera
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/004—Testing the effects of speed or acceleration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention relates to a method and a system for monitoring the safety of a suspender of a truss arch bridge based on an image recognition technology, wherein the method comprises the following steps: providing a marking piece, and attaching the marking piece to the hanging rod; providing a binocular camera, and shooting a marker on the suspender through the binocular camera to obtain video data; extracting corresponding image data from the video data, and identifying the marker in the image data based on an image identification technology to obtain the horizontal displacement of the marker; obtaining a time course curve of the marker according to the horizontal displacement of the marker and the corresponding time information; calculating the fundamental frequency of the suspender by using the time curve of the marker; and calculating the boom force according to the fundamental frequency. The suspender safety monitoring method can greatly solve the problem of high cost of hardware equipment. In addition, the measurement accuracy of the binocular camera can acquire the micro vibration of the suspender, so that the safety index of the suspender is acquired, and the testing range of the suspender is wide.
Description
Technical Field
The invention relates to the technical field of bridge structure safety, in particular to a truss arch bridge suspender safety monitoring system and method based on an image recognition technology.
Background
The truss arch bridge is particularly favored by design and selection due to reasonable stress and attractive appearance. The main and key stressed member of the truss arch bridge is a boom. The suspension rod has small mass, small damping and large flexibility, so the suspension rod is easy to vibrate under the action of wind, rain and alternating traffic load to cause fatigue effect, and further fatigue fracture is possible. The vibration fatigue of the suspension rod of the arch bridge is a common local damage form of a bridge structure, if the vibration fatigue is not processed in time and developed at will, the steel wire of the suspension rod can be firstly broken, so that the internal force is redistributed, and finally, the extreme condition that the suspension rod is broken successively can be caused, and the consequence is very serious. Therefore, it is important to acquire safety indexes such as stress and vibration of the boom in real time and further quantitatively evaluate the current state of the structure.
At present, aiming at monitoring safety indexes of a suspender, a vibration sensor is mainly arranged on the suspender to obtain vibration amplitude and vibration frequency, and the force of the suspender is solved according to the relation between the frequency and the force of the suspender. Although this monitoring method can produce true and reliable monitoring data, it is limited by limited spatial resolution, usually requires installation of very dense sensor arrays, and requires specialized instrumentation to decode and post-process the signals collected by the sensors. As such, the hardware cost and installation process of the sensors and associated equipment is also quite expensive. And once a large number of sensors are installed and operated, massive monitoring data can be acquired, and the data processing capacity is large.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a truss arch bridge suspender safety monitoring system and method based on an image recognition technology, and solves the problems of high cost and large data processing capacity of the existing sensor detection.
The technical scheme for realizing the purpose is as follows:
the invention provides a truss arch bridge suspender safety monitoring method based on an image recognition technology, which comprises the following steps:
providing a marking piece, and attaching the marking piece to the hanging rod;
providing a binocular camera, and shooting a marker on the suspender through the binocular camera to obtain video data;
extracting corresponding image data from the video data, and identifying the marker in the image data based on an image identification technology to obtain the horizontal displacement of the marker;
obtaining a time course curve of the marker according to the horizontal displacement of the marker and the corresponding time information;
calculating the fundamental frequency of the suspender by using the time curve of the marker; and
the boom force is calculated according to the following formula, the safety monitoring of the boom is realized through the boom force,
T＝4WS2F2/1000
in the above formula, T represents the boom force, W represents the linear density of the boom, S represents the length of the boom, and F represents the fundamental frequency of the boom.
The boom force of the boom is safely monitored by adopting an image recognition technology, hardware equipment of the boom is mainly a binocular camera, the market price is 3 ten thousand yuan, the price of one sensor in the existing sensor detection method is about 2000 yuan, each boom is required to be provided with one sensor, if a demodulator for matching adopts about 10 ten thousand yuan of 16 channels, 10 booms are arranged on an arch bridge, and the hardware cost for detecting by the existing sensor is 12 ten thousand yuan. Therefore, the safety monitoring method for the suspender can greatly solve the problem of high cost of hardware equipment. In addition, the binocular camera can acquire the tiny vibration of the suspension rod with the measurement precision, so that the safety index of the suspension rod is acquired, the test range of the suspension rod is wide, and the existing sensor detection method has the advantages that the vibration acceleration cannot be measured by the sensor due to the fact that the short suspension rod has obvious rigidity effect and small vibration amplitude.
The invention further improves a truss arch bridge suspender safety monitoring method based on an image recognition technology, wherein the step of calculating the fundamental frequency of the suspender by using the time curve of the marker comprises the following steps:
carrying out secondary derivation on the time-course curve to obtain the vibration acceleration of the lifting rod;
and carrying out Fourier transform on the vibration acceleration of the suspender to obtain the fundamental frequency of the suspender.
The truss arch bridge suspender safety monitoring method based on the image recognition technology is further improved in that when the video data of the marker are obtained through the binocular camera, the marker is continuously shot at intervals for a certain time, and therefore the video data are obtained.
The truss arch bridge suspender safety monitoring method based on the image recognition technology is further improved in that the provided marking piece comprises a pair of transverse marking strips and a pair of longitudinal marking strips, and the transverse marking strips and the longitudinal marking strips are connected in a staggered mode to form a groined structure;
and when the time course curve of the marker is obtained, measuring the horizontal displacement and the vertical displacement of the # -shaped structure in the image data, and further combining the time information to obtain the time course curve of the marker.
The truss arch bridge suspender safety monitoring method based on the image recognition technology is further improved in that when a binocular camera is arranged, a corresponding number of suspenders are selected as a measurement group according to the resolution of the binocular camera;
measuring the distance between two adjacent suspenders in a measurement group, and taking the average value of the measured distances as the installation distance;
and arranging the binocular camera on an arch bridge along the center line position of the range of one measuring group, wherein the distance between the binocular camera and the central point of the range of the corresponding measuring group is equal to the installation distance, and shooting the suspenders in the measuring group by using the binocular camera.
The invention also provides a truss arch bridge suspender safety monitoring system based on the image recognition technology, which comprises the following components:
the marking piece is attached to the hanging rod;
the binocular camera is arranged on the arch bridge and corresponds to the marking piece on the suspender, and is used for shooting the marking piece to form video data;
the processing unit is connected with the binocular camera and used for extracting corresponding image data from the video data, identifying the marking piece in the image data based on an image identification technology to obtain the horizontal displacement of the marking piece, further obtaining a time-course curve through the horizontal displacement calculation, obtaining the fundamental frequency of the suspender through the time-course curve calculation, calculating the force of the suspender through a formula, realizing the safety monitoring of the suspender through the force of the suspender,
T＝4WS2F2/1000
in the above formula, T represents the boom force, W represents the linear density of the boom, S represents the length of the boom, and F represents the fundamental frequency of the boom.
The truss arch bridge suspender safety monitoring system based on the image recognition technology is further improved in that the processing unit is used for carrying out secondary derivation on the time-course curve to obtain the vibration acceleration of the suspender and carrying out Fourier transform on the vibration acceleration of the suspender to obtain the fundamental frequency of the suspender.
The truss arch bridge suspender safety monitoring system based on the image recognition technology is further improved in that the binocular camera continuously shoots the marker for a certain time at intervals, so that video data are formed.
The truss arch bridge suspender safety monitoring system based on the image recognition technology is further improved in that the marker comprises a pair of transverse marker strips and a pair of longitudinal marker strips, and the transverse marker strips and the longitudinal marker strips are connected in a staggered mode to form a groined structure;
the processing unit is further used for measuring horizontal displacement and vertical displacement of the # -shaped structure in the image data, and further combining the time information to obtain a time course curve of the marker.
The truss arch bridge suspender safety monitoring system based on the image recognition technology is further improved in that the binocular camera is arranged in front of the plurality of suspenders and is used for shooting the suspenders respectively.
Drawings
Fig. 1 is a flowchart of a truss arch bridge suspender safety monitoring method based on an image recognition technology.
Fig. 2 is a schematic structural diagram of an arch bridge monitored by the truss arch bridge suspender safety monitoring system and method based on the image recognition technology.
Fig. 3 is a schematic structural diagram of a marker in the system and method for monitoring the safety of the boom of the truss arch bridge based on the image recognition technology.
Detailed Description
The invention is further described with reference to the following figures and specific examples.
Referring to fig. 1, the invention provides a truss arch bridge suspender safety monitoring system and method based on an image recognition technology, high-resolution acquisition of spatial information can be realized by acquiring a high-frequency video through a binocular camera and extracting an image for recognition, the spatial information of the whole field of view is encoded in a non-contact manner, and the high cost and the complex installation process of a contact type sensor are avoided. The invention utilizes the image recognition technology to really realize automation and intellectualization of the monitoring process and ensure the stability and accuracy of the result. The following describes a system and a method for monitoring the safety of a boom of a truss arch bridge based on an image recognition technology, with reference to the accompanying drawings.
The invention provides a truss arch bridge suspender safety monitoring system based on an image recognition technology, which is used for monitoring the suspender force of a suspender 11 on an arch bridge 10 as shown in figure 2, and in combination with figure 3, the safety monitoring system comprises a marking part 21, a binocular camera and a processing unit, wherein the marking part 21 is attached to the suspender 11, the binocular camera is arranged on the arch bridge 10 and corresponds to the mark on the suspender 11, and the binocular camera is used for shooting the marking part to form video data; the processing unit is connected with the binocular camera and used for receiving video data formed by shooting of the binocular camera, the processing unit is used for extracting corresponding image data from the video data and identifying a marking piece in the image data based on an image identification technology to obtain horizontal displacement of the marking piece, then a time curve is obtained through horizontal displacement calculation, a fundamental frequency of the suspender is obtained through time curve calculation, therefore, the suspender force is calculated through the following formula, and safety monitoring of the suspender is realized through the suspender force:
T＝4WS2F2/1000
in the above formula, T represents the boom force, W represents the linear density of the boom, S represents the length of the boom, and F represents the fundamental frequency of the boom. Wherein the length of jib is the distance between anchor clamps about the jib, and the accessible is measured and is obtained. The linear density of the suspender is calculated by the length and the density of the suspender.
As shown in fig. 2, a truss is installed on an arch bridge 10, an arch part of the truss is connected with a bridge deck 12 through a suspender 11, a plurality of suspenders 11 are arranged at equal intervals, and the suspenders play a crucial role in the stability of the truss, so that suspender force of the suspenders is an important monitoring index for the structural safety of the arch bridge.
Compared with the traditional means of acquiring the boom force index based on the sensor, the method for monitoring the boom force based on the image recognition technology has the advantages that the image is a dense sensing means which has wider source means, lower acquisition cost and more visual reflected information, and has obvious superiority. In addition, the monitoring system of the invention reduces the dependence on subjective experience and consciousness in manual detection, thereby really realizing automation and intellectualization of the monitoring process and ensuring the stability and accuracy of results. The safety monitoring system can greatly reduce the cost of hardware equipment and simplify hardware installation procedures. In addition, the lengths of the hanging rods are different, the length of the hanging rod arranged at the position with smaller arch degree of the truss is smaller, the self rigidity effect of the short hanging rod is obvious, the vibration amplitude is small, the traditional sensor cannot monitor the vibration acceleration of the hanging rod, and therefore the force of the hanging rod cannot be measured.
In a specific embodiment of the present invention, the processing unit includes a receiving module and an image extraction module, the receiving module is in communication connection with the binocular camera and is configured to receive video data captured by the binocular camera; the image extraction module is connected with the receiving module and is used for carrying out image extraction on the video data and extracting images from the video data according to a 2-frame rate to form image data.
The processing unit further comprises an image recognition module connected with the image extraction module and a calculation module connected with the image recognition module, wherein the image recognition module receives the image data formed by the image extraction module, recognizes each image in the image data according to a time sequence, and recognizes the specific position of the identification piece in the image; the calculation module receives the specific position of the identification piece in each image identified by the image identification module, which is equivalent to obtaining the position change information of the identification piece within a period of time, and the time course curve of the identification piece can be calculated. Preferably, the calculation module calculates the horizontal displacement of the identifier corresponding to each time point according to the actual size of the identifier and the specific position of the identifier, and calculates the time-course curve of the identifier by using the horizontal displacement and the time information.
In an embodiment of the invention, the processing unit is configured to perform a second derivation on the time-course curve to obtain a vibration acceleration of the boom, and further configured to perform a fourier transform on the vibration acceleration of the boom to obtain a fundamental frequency of the boom.
Preferably, the calculation module performs a derivation on the time curve to obtain a speed, which is the speed of the boom, and records and stores the speed of the boom. And the calculation module conducts derivation on the speed of the lifting rod again to obtain the acceleration, namely the vibration acceleration of the lifting rod, and the vibration acceleration of the lifting rod is recorded and stored. The calculation module carries out Fourier transform on the vibration acceleration of the suspension rod to obtain the vibration frequency, namely the fundamental frequency of the vibration of the suspension rod.
In one embodiment of the invention, the binocular camera takes continuous shots of the marker at intervals for a certain length of time to form video data. Preferably, the binocular camera continuously acquires boom vibration video for 1 minute at 60fps every 10 minutes, each boom is monitored for 1 hour, and boom vibration video for 6 minutes is acquired.
In one embodiment of the present invention, as shown in fig. 3, the mark 21 comprises a pair of transverse mark bars 211 and a pair of longitudinal mark bars 212, wherein the transverse mark bars 211 and the longitudinal mark bars 212 are connected in a staggered manner to form a # -shaped structure; the processing unit is also used for measuring the horizontal displacement and the vertical displacement of the # -shaped structure in the image data, and further combining the time information to obtain a time course curve of the marker.
The vertical displacement of the pair of transverse marker strips 211 is the vertical displacement of the suspension rod, and the transverse displacement of the pair of longitudinal marker strips 212 is the horizontal displacement of the suspension rod. The processing unit of the invention considers the horizontal displacement of the suspender and the vertical displacement of the suspender during image recognition, can improve the monitoring precision of the force of the suspender and improve the safety.
Preferably, when measuring the horizontal displacement and the vertical displacement, the corresponding horizontal displacement and the vertical displacement are obtained by measuring the displacement of the pixel points.
Furthermore, a central mark point 213 is arranged at the center of the # -shaped structure, and the # -shaped structure is calibrated by using the central mark point 213. The binocular camera may shoot while aiming at the center mark point 213 when shooting a video. In the image recognition, the center mark point 213 is used for image alignment, and the vertical displacement amount of the pair of horizontal mark bars 211 and the horizontal displacement amount of the pair of vertical mark bars 212 are measured.
In one embodiment of the present invention, the binocular camera is provided in front of the plurality of booms, and photographs each boom individually.
Preferably, as shown in fig. 2, the suspenders 11 are divided into a plurality of groups, and the suspenders are divided according to the arrangement order of the suspenders 11, and each 4 suspenders can be divided into one group. The binocular camera is erected in front of a group of suspenders, and each suspender in the group is shot.
The erection of the binocular camera will be described by taking the boom No. 1 to 4 as an example. And measuring the distance between two adjacent suspenders in the No. 1 to No. 4 suspenders, and averaging all the distances to obtain the average distance. The binocular camera is arranged on the middle line of the No. 1 to No. 4 suspension rods, and the distance between the binocular camera and the middle point of the No. 1 to No. 4 suspension rods is equal to the average distance. The binocular camera may then take video capture of boom nos. 1 to 4, respectively, at that location.
The truss arch bridge suspender safety monitoring system based on the image recognition technology has the beneficial effects that:
the method not only can realize the stable tracking of the time sequence image through the matching of the image characteristics and the random consistency method and ensure that the three-dimensional vibration monitoring precision reaches 0.5mm precision, but also can quickly build a multi-point synchronous observation system through networking use.
The safety monitoring system has the advantages of low equipment cost and convenience in construction. Each suspender of the sensor testing suspender adopting the traditional mode needs a sensor, the price of each sensor is about 2000 yuan, a demodulator needs to be equipped, the price of the 16-channel demodulator is 10 ten thousand, and the purchase, construction, design and installation of the sensor and the demodulation equipment all need certain cost. The main equipment of the invention is a binocular camera, the price is about 3 thousands, and the binocular camera only needs to be shot by electrifying relative to the wiring installation of the sensor, and the mark piece pasted on the suspender can be label paper, so the cost is low, and the pasting is convenient.
The safety monitoring system has a wide test range. The rigidity effect of the short suspension rod on the arch bridge is obvious, the vibration acceleration of the suspension rod cannot be obtained through a sensor, the frame rate of the binocular camera is 60fps, the precision is enough to acquire the micro vibration of the short suspension rod, and the safety indexes of all suspension rods can be obtained.
The safety monitoring system has comprehensive test indexes. The vibration acceleration of the lifting rod is detected by adopting the sensor, so that the vibration speed and the displacement response cannot be obtained through calculation, but the vibration displacement time-course curve of the lifting rod is obtained through image recognition, and the corresponding speed and acceleration can be obtained through derivation.
The safety monitoring system can reduce the influence of external human factors, and the data is safe and reliable. The sensor detection method is short in test time, and can safely and reliably collect and store all test data.
The safety monitoring system is simple to operate. The sensor detection needs filtering, removing and filling due to the problems of data packet loss and the like, and the image acquisition and data analysis of the invention can be automatically realized by adopting a packaged program and has simple operation.
The boom safety index monitoring system based on image recognition is simple in structure, low in use cost, high in precision, wide in test range and strong in popularization. The method has the advantages that the vibration acceleration, the vibration speed and the vibration amplitude of the hanger rod are obtained, the safety of an internal steel wire of the hanger rod is evaluated, an apparent image and a video of the hanger rod can be obtained, and a bridge management department can track the apparent change of the hanger rod and check apparent diseases in time.
The invention also provides a truss arch bridge suspender safety monitoring method based on the image recognition technology, and the safety monitoring method is explained below.
As shown in fig. 1, the method for monitoring the safety of the boom of the truss arch bridge based on the image recognition technology of the invention comprises the following steps:
executing the step S101, providing a marking piece, and attaching the marking piece to the suspender; then, step S102 is executed;
executing step S102, providing a binocular camera, and shooting a mark piece on the suspender through the binocular camera to obtain video data; then, step S103 is executed;
step S103 is executed, corresponding image data is extracted from the video data, and the marker in the image data is identified based on an image identification technology to obtain the horizontal displacement of the marker; then, step S104 is executed;
step S104 is executed, and a time course curve of the marker is obtained according to the horizontal displacement of the marker and the corresponding time information; then, step S105 is executed;
step S105 is executed, and the fundamental frequency of the suspender is calculated by using the time curve of the marker; then, step S106 is executed;
step S106 is executed, the boom force is calculated according to the following formula, the boom safety monitoring is realized through the boom force,
T＝4WS2F2/1000
in the above formula, T represents the boom force, W represents the linear density of the boom, S represents the length of the boom, and F represents the fundamental frequency of the boom.
The suspender safety monitoring method can greatly solve the problem of high cost of hardware equipment. In addition, the binocular camera can acquire the tiny vibration of the suspension rod with the measurement precision, so that the safety index of the suspension rod is acquired, the test range of the suspension rod is wide, and the existing sensor detection method has the advantages that the vibration acceleration cannot be measured by the sensor due to the fact that the short suspension rod has obvious rigidity effect and small vibration amplitude.
In one embodiment of the present invention, the step of calculating the fundamental frequency of the boom using the time curve of the marker comprises:
carrying out secondary derivation on the time-course curve to obtain the vibration acceleration of the lifting rod;
and carrying out Fourier transform on the vibration acceleration of the suspender to obtain the fundamental frequency of the suspender.
Furthermore, the velocity of the suspension rod is obtained by conducting derivation once on the time curve, and the vibration acceleration of the suspension rod is obtained by conducting derivation once again on the velocity of the suspension rod.
In one embodiment of the invention, when the video data of the marker is obtained by the binocular camera, the marker is continuously shot at intervals for a certain time, so that the video data is obtained. Preferably, boom vibration video of 1 minute is continuously acquired at 60fps every 10 minutes using a binocular camera, each boom is monitored for 1 hour each time, and boom vibration video of 6 minutes is acquired.
In one embodiment of the invention, the provided marker comprises a pair of transverse marker strips and a pair of longitudinal marker strips, wherein the transverse marker strips and the longitudinal marker strips are connected in a staggered manner to form a # -shaped structure;
and when the time course curve of the marker is obtained, measuring the horizontal displacement and the vertical displacement of the # -shaped structure in the image data, and further combining the time information to obtain the time course curve of the marker.
In one embodiment of the invention, when the binocular camera is set, a corresponding number of suspenders are selected as a measurement group according to the resolution of the binocular camera;
measuring the distance between two adjacent suspenders in a measurement group, and taking the average value of the measured distances as the installation distance;
and arranging the binocular cameras on the arch bridge along the center line of the range where one measuring group is located, enabling the distance between the binocular cameras and the center point of the range where the corresponding measuring group is located to be equal to the installation distance, and shooting the suspenders in the measuring groups by using the binocular cameras respectively.
While the present invention has been described in detail and with reference to the embodiments thereof as illustrated in the accompanying drawings, it will be apparent to one skilled in the art that various changes and modifications can be made therein. Therefore, certain details of the embodiments are not to be interpreted as limiting, and the scope of the invention is to be determined by the appended claims.
Claims (10)
1. A truss arch bridge suspender safety monitoring method based on an image recognition technology is characterized by comprising the following steps:
providing a marking piece, and attaching the marking piece to the hanging rod;
providing a binocular camera, and shooting a marker on the suspender through the binocular camera to obtain video data;
extracting corresponding image data from the video data, and identifying the marker in the image data based on an image identification technology to obtain the horizontal displacement of the marker;
obtaining a time course curve of the marker according to the horizontal displacement of the marker and the corresponding time information;
calculating the fundamental frequency of the suspender by using the time curve of the marker; and
the boom force is calculated according to the following formula, the safety monitoring of the boom is realized through the boom force,
T＝4WS2F2/1000
in the above formula, T represents the boom force, W represents the linear density of the boom, S represents the length of the boom, and F represents the fundamental frequency of the boom.
2. The method for monitoring the safety of the boom of the truss arch bridge based on the image recognition technology as claimed in claim 1, wherein the step of calculating the fundamental frequency of the boom by using the time curve of the marker comprises:
carrying out secondary derivation on the time-course curve to obtain the vibration acceleration of the lifting rod;
and carrying out Fourier transform on the vibration acceleration of the suspender to obtain the fundamental frequency of the suspender.
3. The truss arch bridge suspender safety monitoring method based on the image recognition technology as claimed in claim 1, wherein when the video data of the marker is obtained through the binocular camera, the marker is continuously shot for a certain time at intervals, so as to obtain the video data.
4. The truss arch bridge suspender safety monitoring method based on the image recognition technology as claimed in claim 1, wherein the provided marking element comprises a pair of transverse marking strips and a pair of longitudinal marking strips, and the pair of transverse marking strips and the pair of longitudinal marking strips are connected in a staggered manner to form a groined structure;
and when the time course curve of the marker is obtained, measuring the horizontal displacement and the vertical displacement of the # -shaped structure in the image data, and further combining the time information to obtain the time course curve of the marker.
5. The method for monitoring the safety of the boom of the truss arch bridge based on the image recognition technology as claimed in claim 1, wherein when a binocular camera is set, a corresponding number of booms are selected as a measurement group according to the resolution of the binocular camera;
measuring the distance between two adjacent suspenders in a measurement group, and taking the average value of the measured distances as the installation distance;
and arranging the binocular camera on an arch bridge along the center line position of the range of one measuring group, wherein the distance between the binocular camera and the central point of the range of the corresponding measuring group is equal to the installation distance, and shooting the suspenders in the measuring group by using the binocular camera.
6. A truss arch bridge suspender safety monitoring system based on image recognition technology is characterized by comprising:
the marking piece is attached to the hanging rod;
the binocular camera is arranged on the arch bridge and corresponds to the marking piece on the suspender, and is used for shooting the marking piece to form video data;
the processing unit is connected with the binocular camera and used for extracting corresponding image data from the video data, identifying the marking piece in the image data based on an image identification technology to obtain the horizontal displacement of the marking piece, further obtaining a time-course curve through the horizontal displacement calculation, obtaining the fundamental frequency of the suspender through the time-course curve calculation, calculating the force of the suspender through a formula, realizing the safety monitoring of the suspender through the force of the suspender,
T＝4WS2F2/1000
in the above formula, T represents the boom force, W represents the linear density of the boom, S represents the length of the boom, and F represents the fundamental frequency of the boom.
7. The image recognition technology-based truss arch bridge boom safety monitoring system of claim 6, wherein the processing unit is configured to perform a second derivation on the time-course curve to obtain a vibration acceleration of the boom, and further configured to perform a fourier transform on the vibration acceleration of the boom to obtain a fundamental frequency of the boom.
8. The truss arch bridge boom safety monitoring system based on image recognition technology of claim 6, wherein the binocular cameras take continuous shots of the markers at intervals for a certain length of time to form video data.
9. The truss arch bridge boom safety monitoring system based on image recognition technology as claimed in claim 6, wherein said marker comprises a pair of transverse marker strips and a pair of longitudinal marker strips, said pair of transverse marker strips and said pair of longitudinal marker strips are connected in a staggered manner to form a groined structure;
the processing unit is further used for measuring horizontal displacement and vertical displacement of the # -shaped structure in the image data, and further combining the time information to obtain a time course curve of the marker.
10. The truss arch bridge boom safety monitoring system based on image recognition technology of claim 6, wherein the binocular camera is arranged in front of the plurality of booms, and is used for shooting each boom respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011338182.5A CN112464788A (en) | 2020-11-25 | 2020-11-25 | Truss arch bridge suspender safety monitoring system and method based on image recognition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011338182.5A CN112464788A (en) | 2020-11-25 | 2020-11-25 | Truss arch bridge suspender safety monitoring system and method based on image recognition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112464788A true CN112464788A (en) | 2021-03-09 |
Family
ID=74798737
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011338182.5A Pending CN112464788A (en) | 2020-11-25 | 2020-11-25 | Truss arch bridge suspender safety monitoring system and method based on image recognition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112464788A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102128694A (en) * | 2010-12-23 | 2011-07-20 | 浙江大学 | Method for testing tension and rigidity of short derrick boom of arch bridge |
| DE102015101634A1 (en) * | 2014-02-05 | 2015-08-06 | Dekra E.V. | Measuring system and method for determining a relative cable force distribution of an elevator |
| CN110553808A (en) * | 2019-08-29 | 2019-12-10 | 山东建筑大学 | Beam bridge overall rigidity evaluation method based on vehicle vibration |
| CN111259770A (en) * | 2020-01-13 | 2020-06-09 | 东南大学 | Rapid cable force testing system and method based on unmanned aerial vehicle platform and deep learning under complex background |
| CN111623942A (en) * | 2020-05-26 | 2020-09-04 | 东南大学 | Displacement measurement method for test structure model of unidirectional vibration table |
-
2020
- 2020-11-25 CN CN202011338182.5A patent/CN112464788A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102128694A (en) * | 2010-12-23 | 2011-07-20 | 浙江大学 | Method for testing tension and rigidity of short derrick boom of arch bridge |
| DE102015101634A1 (en) * | 2014-02-05 | 2015-08-06 | Dekra E.V. | Measuring system and method for determining a relative cable force distribution of an elevator |
| CN110553808A (en) * | 2019-08-29 | 2019-12-10 | 山东建筑大学 | Beam bridge overall rigidity evaluation method based on vehicle vibration |
| CN111259770A (en) * | 2020-01-13 | 2020-06-09 | 东南大学 | Rapid cable force testing system and method based on unmanned aerial vehicle platform and deep learning under complex background |
| CN111623942A (en) * | 2020-05-26 | 2020-09-04 | 东南大学 | Displacement measurement method for test structure model of unidirectional vibration table |
Non-Patent Citations (3)
| Title |
|---|
| 孙冰 等: "动静阻尼影响下锚杆瞬态动力响应的解析解及工作状态预测", 《煤炭学报》, vol. 41, no. 6, pages 1401 - 1405 * |
| 牛明昂 等: "多线程编程下振动物体的双目动态测量实现", 《青海大学学报》, vol. 34, no. 6, pages 51 - 55 * |
| 陈彦 等: "高速公路斜拉桥索力检测数据快速采集与识别方法", 《贵州师范大学学报（自然科学版）》, vol. 31, no. 4, pages 92 - 95 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105652154B (en) | Contact Running State security auditing system | |
| CN110675387B (en) | Method and device for detecting structural defects of transmission line iron tower | |
| CN106840110B (en) | A kind of motion measuring method and device applied to large-scale more Lamb wave wave simulation systems | |
| CN104613891B (en) | A kind of deflection of bridge span detecting system and detection method | |
| JP5861318B2 (en) | Trolley wire data comparison device | |
| WO2021238058A1 (en) | Structural vibration mode testing system and method based on digital image recognition | |
| CN106932084B (en) | Transmission pressure wind-induced vibration mode measurement method based on machine binocular vision system | |
| CN109556521B (en) | Railway steel rail displacement detection method based on unmanned aerial vehicle | |
| CN109839439B (en) | Road and bridge pavement crack detection system and detection method thereof | |
| CN104020430A (en) | Correction method and system for movement artifacts of magnetic resonance imaging | |
| CN109580137A (en) | A kind of bridge structure displacement influence line measurement method based on computer vision technique | |
| CN113192063B (en) | Bridge line-shaped monitoring system and bridge line-shaped monitoring method | |
| CN108760200A (en) | Vehicle it is non-at the uniform velocity by when Bridge Influence Line assay method | |
| CN108520227A (en) | A kind of Bridge Structural Damage localization method of the transfer entropy based on dual sensor information | |
| CN108821117A (en) | A kind of intelligent erection crane | |
| US20220383478A1 (en) | Computer vision-based system and method for assessment of load distribution, load rating, and vibration serviceability of structures | |
| CN102433834B (en) | Bridge safety-appearance sensing monitoring car and safety assessment method utilizing same | |
| CN106121627A (en) | A kind of oil pumper displacement acquisition method based on image recognition | |
| CN112464788A (en) | Truss arch bridge suspender safety monitoring system and method based on image recognition technology | |
| CN110045228A (en) | Device for fault indicator, system and distribution network system | |
| CN103163148A (en) | Method and system for detecting inhaul cable broken wire | |
| CN109522912A (en) | Scanning quality detection method, controller and device | |
| CN106097728A (en) | Vehicle checking method, Apparatus and system | |
| CN207617728U (en) | Track detecting high-accuracy position system | |
| CN111696103B (en) | Constant-load linear mapping method of single-span simple girder bridge under uninterrupted traffic condition |
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 |