CN117190875A - Bridge tower displacement measuring device and method based on computer intelligent vision - Google Patents
Bridge tower displacement measuring device and method based on computer intelligent vision Download PDFInfo
- Publication number
- CN117190875A CN117190875A CN202311156385.6A CN202311156385A CN117190875A CN 117190875 A CN117190875 A CN 117190875A CN 202311156385 A CN202311156385 A CN 202311156385A CN 117190875 A CN117190875 A CN 117190875A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- displacement
- bridge tower
- coordinate system
- 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
- 238000006073 displacement reaction Methods 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 48
- 239000011159 matrix material Substances 0.000 claims abstract description 56
- 238000004364 calculation method Methods 0.000 claims abstract description 41
- 238000012544 monitoring process Methods 0.000 claims abstract description 31
- 238000007781 pre-processing Methods 0.000 claims abstract description 30
- 230000003287 optical effect Effects 0.000 claims abstract description 26
- 238000006243 chemical reaction Methods 0.000 claims abstract description 21
- 238000012937 correction Methods 0.000 claims abstract description 18
- 238000005259 measurement Methods 0.000 claims abstract description 10
- 230000033001 locomotion Effects 0.000 claims description 33
- 238000003384 imaging method Methods 0.000 claims description 17
- 230000009466 transformation Effects 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 10
- 238000013519 translation Methods 0.000 claims description 8
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 229910000831 Steel Inorganic materials 0.000 claims description 3
- 238000003702 image correction Methods 0.000 claims description 3
- 238000007641 inkjet printing Methods 0.000 claims description 3
- 239000003550 marker Substances 0.000 claims description 3
- 239000010959 steel Substances 0.000 claims description 3
- 230000007547 defect Effects 0.000 claims 1
- 230000015654 memory Effects 0.000 description 9
- 239000013598 vector Substances 0.000 description 9
- 238000010276 construction Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 238000013507 mapping Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000000691 measurement method Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 229910000838 Al alloy Inorganic materials 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003064 anti-oxidating effect Effects 0.000 description 1
- 239000002519 antifouling agent Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003707 image sharpening Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000002829 reductive effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a bridge tower displacement measuring device and method based on computer intelligent vision, comprising a camera correction module, an image monitoring module, an image preprocessing module, a feature recognition module, a conversion matrix calculation module, a displacement calculation module and an optical flow method auxiliary module; the camera correction module is connected with the image monitoring module, the image monitoring module is connected with the image preprocessing module, the image preprocessing module is connected with the characteristic recognition module, the characteristic recognition module is connected with the conversion matrix calculation module, the conversion matrix calculation module is connected with the displacement calculation module, and the displacement calculation module is connected with the optical flow method auxiliary module; the problems that the field environment of an actual bridge tower project is very complex, influence factors are numerous, accurate real-time measurement of measuring equipment is difficult to ensure, and an ultra-long-distance accurate monitoring method is required are solved.
Description
Technical Field
The invention relates to the field of bridge tower displacement measurement devices and methods based on computer intelligent vision.
Background
Along with the rapid progress of the economic level in China, the development of information technology is advanced at a high speed, the development of bridges and even the whole building industry is continuously promoted for the technical innovation of meeting the requirement of engineering construction, and the accuracy and the high efficiency of bridge construction are also increasingly important. The bridge tower displacement and the bridge tower rotation in the bridge tower construction process can directly reflect the construction condition of the site and are also important parameters for representing the whole construction condition of the bridge. Thus bridge tower displacement is an important parameter for bridge monitoring.
The existing bridge tower displacement monitoring means are mainly divided into two types, one is a short-distance measurement method based on a displacement meter, a static level gauge and the like; the other is a space measurement method based on Beidou satellites or total stations and the like. However, the first method has a certain influence on the bridge structure and is easy to influence from outside; the second method is easily limited by complicated measurement mode, great influence on measurement accuracy by environment, high cost, no timeliness in monitoring and the like. At present, the binocular camera is also used in the field of image mapping, but the binocular camera has extremely severe parameter control and high equipment cost, and is not suitable for bridge construction site environments. The actual bridge tower project field environment is very complex, the influence factors are numerous, accurate real-time measurement of the measuring equipment is difficult to ensure, and an ultra-long-distance accurate monitoring method is needed.
Disclosure of Invention
The invention aims to solve the problems in the prior art and provides a bridge tower displacement measuring device and method based on computer intelligent vision.
The specific technical scheme is as follows:
the bridge tower displacement measuring device based on the computer intelligent vision is characterized by comprising a camera correction module, an image monitoring module, an image preprocessing module, a feature recognition module, a conversion matrix calculation module, a displacement calculation module and an optical flow method auxiliary module;
the camera correction module is connected with the image monitoring module, the image monitoring module is connected with the image preprocessing module, the image preprocessing module is connected with the feature recognition module, the feature recognition module is connected with the conversion matrix calculation module, the conversion matrix calculation module is connected with the displacement calculation module, and the displacement calculation module is connected with the optical flow method auxiliary module.
Further, the camera correction module is used for correcting distortion caused by lens manufacturing errors and the like; the image monitoring module is used for acquiring target images; the image preprocessing module is used for further processing the acquired image and improving the imaging quality; the characteristic recognition module is used for automatically recognizing characteristic points of the selected checkerboard pattern; the conversion matrix calculation module is used for establishing a two-dimensional coordinate system and a three-dimensional coordinate system according to the known space coordinate information, and calculating a rotation matrix and a translation matrix of the space coordinate system and an imaging plane coordinate system; the displacement calculation module is used for calculating the coordinate transformation quantity of the identified characteristic points to determine the displacement of the bridge tower; the optical flow method auxiliary module is used for calculating continuously-changed target images or ordered videos to obtain movement information of the targets, the movement information is reflected to be actual movement conditions of the bridge tower, and the movement information is compared with the displacement calculation module to assist in correcting results.
On the other hand, the measuring method of the bridge tower displacement based on the computer intelligent vision comprises the following steps:
step S1: correcting the camera to obtain an internal reference matrix and a distortion coefficient;
step S2: acquiring a target image according to the internal reference matrix and the distortion coefficient,
wherein the target image is a checkerboard image;
step S3: preprocessing the target image;
step S4: according to the position information of the characteristic points, a first target coordinate system is established by taking the inner angle points of the target image as reference points, a second camera coordinate system is established by taking the optical center of the camera as an origin, and the conversion relation between the first coordinate system and the second coordinate system is calculated;
step S5: automatically identifying characteristic points of the checkerboard image;
step S6: determining bridge tower displacement according to coordinate transformation quantities of the characteristic point pixels of the acquired checkerboard image in the time domain and the space domain;
step S7: and (5) assisting in monitoring the displacement of the bridge tower according to the result of the optical flow method so as to determine the actual movement condition.
The bridge tower displacement in the step S6 is translational along the x axis, translational along the y axis, translational along the z axis, rotational around the x axis, rotational around the y axis and rotational around the z axis, and the determination of the bridge displacement is specifically to collect the coordinate transformation amount of at least two frames of marker image feature points under a camera coordinate system according to the setting.
Further, the checkerboard image is a black and white checkerboard pattern.
Further, the number of the inner corners of the target image is at least 4.
Further, the selected target image is printed on the PVC plate in a high-precision ink-jet printing mode, and meanwhile, steel plates are additionally arranged on four sides of the PVC plate to be fixed, so that deformation caused by external force is prevented.
Further, the correction in step S1 is specifically to collect 30 image corrections for the markers at the edges of the image.
Further, the image preprocessing in step S3 includes image denoising, image enhancement and super-resolution reconstruction, and obtains a result with higher imaging quality, so as to overcome the device and environmental shortcomings.
The bridge tower displacement measuring device and method based on computer intelligent vision has the following beneficial effects:
1. according to the invention, a target image containing a checkerboard pattern is acquired, camera distortion coefficients and an internal reference matrix are optionally updated, a target coordinate system and a camera coordinate system are established according to known position information, a rotation matrix and a translation matrix are obtained according to a conversion relation between the two coordinate systems, and the acquired image is preprocessed.
2. The invention automatically identifies the characteristic points of the checkerboard, determines the displacement of the bridge tower according to the three-dimensional coordinate transformation quantity of the characteristic points, realizes the real-time measurement of the displacement of the bridge tower, and simultaneously processes continuously-changed target images by an optical flow method to obtain target motion information and assist the measurement of the displacement of the bridge tower.
3. The measuring means is little affected by environment, has a certain weakening effect on noise influence after the random sampling consistency algorithm RanSac is added, and has high measuring precision and strong applicability through the real-time monitoring of the characteristic points of the checkerboard pattern.
Drawings
FIG. 1 is a flow chart of a method for measuring displacement of a pylon based on computer intelligent vision in a first embodiment of the present invention;
FIG. 2 is a schematic diagram of a measuring device for bridge tower displacement based on computer intelligent vision in a first embodiment of the invention;
FIG. 3 is a flowchart of a method for calculating camera distortion parameters based on computer intelligent vision in a second embodiment of the present invention;
FIG. 4 is a diagram of an ideal camera imaging model in accordance with the present invention;
fig. 5 is a schematic diagram of an apparatus according to three embodiments of the present invention.
Detailed Description
The invention is further illustrated below with reference to the figures and examples. It should be noted that the descriptions herein are only for explaining the present invention, and are not limiting of the present invention; it should be further noted that, in order to facilitate understanding of the core part of the present invention, the structure of the present invention is simplified in the drawings, and not the whole content of the present invention is provided.
A bridge tower displacement measuring device based on computer intelligent vision comprises a camera correction module, an image monitoring module, an image preprocessing module, a feature recognition module, a conversion matrix calculation module, a displacement calculation module and an optical flow method auxiliary module;
the camera correction module is connected with the image monitoring module, the image monitoring module is connected with the image preprocessing module, the image preprocessing module is connected with the characteristic recognition module, the characteristic recognition module is connected with the conversion matrix calculation module, the conversion matrix calculation module is connected with the displacement calculation module, and the displacement calculation module is connected with the optical flow method auxiliary module.
The camera correction module is used for correcting distortion caused by lens manufacturing errors and the like; the image monitoring module is used for acquiring target images; the image preprocessing module is used for further processing the acquired image and improving the imaging quality; the characteristic recognition module is used for automatically recognizing characteristic points of the selected checkerboard pattern; the conversion matrix calculation module is used for establishing a two-dimensional coordinate system and a three-dimensional coordinate system according to the known space coordinate information, and calculating a rotation matrix and a translation matrix of the space coordinate system and an imaging plane coordinate system; the displacement calculation module is used for calculating the coordinate transformation quantity of the identified characteristic points to determine the displacement of the bridge tower; the optical flow method auxiliary module is used for calculating continuously-changed target images or ordered videos to obtain movement information of the targets, the movement information is reflected to be actual movement conditions of the bridge tower, and the movement information is compared with the displacement calculation module to assist in correcting results.
A measuring method of bridge tower displacement based on computer intelligent vision comprises the following steps:
step S1: correcting the camera to obtain an internal reference matrix and a distortion coefficient;
step S2: acquiring a target image according to the internal reference matrix and the distortion coefficient,
wherein the target image is a checkerboard image;
step S3: preprocessing the target image;
step S4: according to the position information of the characteristic points, a first target coordinate system is established by taking the inner angle points of the target image as reference points, a second camera coordinate system is established by taking the optical center of the camera as an origin, and the conversion relation between the first coordinate system and the second coordinate system is calculated;
step S5: automatically identifying characteristic points of the checkerboard image;
step S6: determining bridge tower displacement according to coordinate transformation quantities of the characteristic point pixels of the acquired checkerboard image in the time domain and the space domain;
step S7: and (5) assisting in monitoring the displacement of the bridge tower according to the result of the optical flow method so as to determine the actual movement condition.
The displacement of the bridge tower in the step S6 of the embodiment is translational along the x axis, translational along the y axis, translational along the z axis, rotational around the x axis, rotational around the y axis and rotational around the z axis, and the determination of the displacement of the bridge is specifically to collect the coordinate transformation amount of the marker image feature points of at least two frames under the camera coordinate system according to the setting.
The checkerboard image of this embodiment is a black and white checkerboard pattern.
The number of inner corners of the target image in this embodiment is at least 4.
The mode of high accuracy inkjet printing is adopted to the target image of this embodiment to print on the PVC board, installs the steel sheet additional at the four sides of PVC board simultaneously fixedly for prevent to receive external force to influence and produce deformation.
The correction of step S1 of this embodiment is specifically to collect 30 image corrections for markers at the edges of the image.
The image preprocessing in step S3 of this embodiment includes image denoising, image enhancement and super-resolution reconstruction, and obtains a result with higher imaging quality, so as to overcome the device and environmental disadvantages.
The image acquisition and transmission integrated device of the embodiment has the IP grade of more than 67, and is externally provided with an aluminum alloy shell, wherein the surface of the aluminum alloy shell is coated with anti-oxidation, anti-collision and anti-corrosion protective paint.
The target of this embodiment is installed in the flat surface department of bridge tower, and image acquisition device installs in ground fixed point department, is in same one side with the target.
The lens of the present embodiment is an ultra-long shot Jiao Shanmu lens and is adapted to a camera.
The lighting device of the embodiment is a professional photography light filling lamp, can remotely photograph, has modes such as windless silence and the like, and eliminates equipment interference.
The image processing module of the embodiment is a desktop computer, a notebook computer or a cloud server.
The camera of the embodiment contains more than 3.0 USB interfaces or gigE giga or tera-meganet ports and is used for transmitting collected target images to the image processing module.
The power supply module of this embodiment is connected with image acquisition transmission device, shooting device has network power supply integration interface, can carry out continuous charging through transmission interface.
Acquiring 30 calibration images according to a calibration principle, and calculating an internal reference matrix and a distortion coefficient of a camera and a lens;
erecting a shooting device and a target pattern, and collecting target images, wherein the selected target images comprise square checkerboard patterns;
preprocessing the acquired target image, mainly comprising image noise reduction, ranSac algorithm, image enhancement, super-resolution reconstruction and the like, so as to reduce the influence caused by environment and long-distance shooting;
establishing a three-dimensional space coordinate system by using the identified characteristic points of the checkerboard pattern, and establishing a first coordinate system taking a target as a reference;
establishing a two-dimensional plane coordinate system, called a second coordinate system, by taking a camera imaging plane as a reference, and calculating a rotation matrix and a translation matrix converted from the first coordinate system to the second coordinate system;
automatically identifying selected checkerboard pattern feature points;
and determining the bridge tower displacement according to the coordinate transformation quantity of the calculated characteristic points.
Collecting continuously-changing target images or ordered videos; wherein the selected target image comprises a square checkerboard pattern; according to the principle of an optical flow method, converting the motion of a target image in a three-dimensional space into projection on a two-dimensional imaging plane to obtain a two-dimensional vector describing the position change of the target; and obtaining the motion information of the target according to the continuously-changed target images obtained by calculation, wherein the motion information is reflected as the motion condition of the target.
When the implementation is carried out, 30 calibration images are collected according to a calibration principle, and an internal reference matrix and distortion coefficients of a camera and a lens are calculated; erecting a shooting device and a target pattern, and collecting target images, wherein the selected target images comprise square checkerboard patterns;
preprocessing the acquired target image, mainly comprising image noise reduction, ranSac algorithm, image enhancement, super-resolution reconstruction and the like, so as to reduce the influence caused by environment and long-distance shooting;
establishing a three-dimensional space coordinate system by using the identified characteristic points of the checkerboard pattern, and establishing a first coordinate system taking a target as a reference; establishing a two-dimensional plane coordinate system, called a second coordinate system, by taking a camera imaging plane as a reference, and calculating a rotation matrix and a translation matrix converted from the first coordinate system to the second coordinate system; automatically identifying selected checkerboard pattern feature points; and determining the bridge tower displacement according to the coordinate transformation quantity of the calculated characteristic points.
Collecting continuously-changing target images or ordered videos; wherein the selected target image comprises a square checkerboard pattern;
according to the principle of an optical flow method, converting the motion of a target image in a three-dimensional space into projection on a two-dimensional imaging plane to obtain a two-dimensional vector describing the position change of the target; and obtaining the motion information of the target according to the continuously-changed target images obtained by calculation, wherein the motion information is reflected as the motion condition of the target.
In a second aspect, an embodiment of the present invention provides a bridge tower displacement measurement device based on computer intelligent vision, the device including:
the camera correction module is used for updating the internal reference matrix and the distortion coefficient after camera change;
the image acquisition module is used for acquiring target images, wherein the selected target images comprise square checkerboard patterns and transmitting the acquired images to the image preprocessing module;
the image preprocessing module is used for improving the quality of the acquired target image;
the conversion matrix calculation module is used for establishing a two-dimensional coordinate system and a three-dimensional coordinate system according to the known space coordinate information, and calculating a rotation matrix and a translation matrix of the space coordinate system and an imaging plane coordinate system;
the characteristic recognition module is used for automatically recognizing characteristic points of the selected checkerboard pattern;
and the displacement calculation module is used for calculating the coordinate transformation quantity of the identified characteristic points to determine the displacement of the bridge tower.
And the optical flow method auxiliary module is used for calculating continuously-changed target images to obtain the movement information of the targets, and the movement information is reflected to the actual movement condition of the bridge tower.
Example 1
Fig. 2 is a schematic flow chart of a bridge tower displacement measurement method based on computer intelligent vision, which is provided in the embodiment of the present invention, and the embodiment is suitable for the real-time monitoring situation of the bridge tower overall displacement, and the method may be implemented by a bridge tower displacement measurement module in a preprocessing and post-processing manner, and specifically includes the following steps:
step 210, correcting a camera to obtain an internal reference matrix and distortion parameters;
the correction target image is a checkerboard pattern, and a plurality of angles are shot to the checkerboard pattern, so that 30 correction images are corrected in total. When the correction picture is acquired, the automatic focusing function is required to be closed, and manual focusing is adopted.
After the focal length of the camera is changed, the camera needs to be corrected again, and an internal reference matrix and a distortion coefficient are calculated.
Step 220, collecting target images, wherein the selected target images are square checkerboard patterns, and the checkerboard patterns are checkerboard squares drawn on the targets.
The target image selected is a target image of a bridge tower, and can be a checkerboard image shot by a camera shooting device in real time. The camera shoots images into black and white pictures, the black and white pictures reduce data loss when the images are converted into gray scale, the size of transmission space occupied during transmission after image acquisition can be reduced, the transmission speed is increased, and the processing efficiency is improved.
Optionally, the selected checkerboard pattern is generated by adopting a packaging algorithm, and the number of rows and columns and the side length of the unit cell can be set arbitrarily.
Further, the selected checkerboard patterns are black and white, black and white are adopted, the recognition degree is high, the influence of various complex environmental factors is not easy to be caused, the checkerboard targets are ensured to be recognized by algorithms more easily, and for processing images, the smaller the color types are, the better the color types are.
Further, the outer edge of the black frame is provided with a white frame with the width of 10-20cm, so that the black frame is convenient to fix on a ground system, and meanwhile, the arrangement has the advantages that the contrast ratio of the checkerboard pattern can be improved, and the recognition of characteristic points of the checkerboard pattern by an algorithm is quickened.
Step 230, preprocessing the acquired image, wherein the preprocessing comprises image denoising, image enhancement and image sharpening, for the purposes of the present invention, in the long-distance acquisition, the main degradation of the image is noise, so the preprocessing is mainly performed for image denoising.
The image noise points are distributed in an irregular state, but the checkerboard target part can be regarded as Gaussian distribution, and noise reduction treatment in an arithmetic mean mode is adopted.
Further, the probability density function of gaussian noise is:mean value of Gaussian noise isStandard deviation sigma 2 。
Wherein, let Q xy A group of coordinates representing a rectangular sub-window (field) with a size of a.b centered at a pixel point (x, y), and an arithmetic mean filter represented by Q xy In the defined area, the average value of the contaminated image g (x, y) is calculated.
Further, the value of the restored image f (x, y) at the pixel point (x, y) is calculated using Q xy The arithmetic mean calculated for the pixels in the defined field, namely:that is, it can be realized by a spatial filter (kernel) of a.b size, all coefficients of the kernel being 1/ab.
Step 240, automatically identifying the feature points of the selected checkerboard pattern.
The default feature points are all black-white intersection points of the inner ring, and meanwhile, special feature points can be set, and the number of the default feature points can be 3, 4 or more. Specifically, the special feature points include three intersection points that form a triangular plane, and may further include four intersection points that form a square plane.
Optionally, identifying the feature points of the selected checkerboard pattern includes:
determining whether the selected checkerboard pattern is a target checkerboard pattern;
after determining the selected checkerboard pattern as the target checkerboard pattern, the black-and-white intersection points of the inner circles of the selected checkerboard pattern are identified as feature points.
And 250, determining the displacement of the bridge tower according to the coordinate transformation quantity of the selected characteristic points.
Wherein the displacement of the pylon comprises a transverse bridge displacement and a forward bridge displacement, wherein the forward bridge displacement comprises a horizontal displacement and a vertical displacement.
Specifically, the checkerboard displacement can be judged according to the calculation result of the selected characteristic points, namely the bridge tower displacement.
The characteristic points may be all inner ring intersection points or may be special angular points capable of forming planes, initial space positions of the characteristic points are known, coordinates of the current characteristic points under a world coordinate system are determined through a coordinate system conversion relation between an imaging plane and a target space plane after the transmitted real-time image is identified, and displacement of the bridge tower is determined according to the coordinates of the current characteristic points and the variable of the initial position coordinates.
Step 260, the optical flow method assists in monitoring the bridge tower movement condition.
The method comprises the steps of identifying images as continuously-changing checkerboard patterns, calculating the motion information in bridge tower monitoring time as a result, and reflecting the motion information as optical flow motion conditions, so that an observer can observe the motion information directly.
According to the technical scheme, the target patterns containing the checkered patterns are collected, the internal reference matrix and the distortion coefficient of the shooting camera are corrected, black-white intersection points of the checkered patterns are identified, the displacement of the bridge tower is determined according to the coordinate transformation information of the characteristic points, real-time monitoring of the bridge tower displacement is achieved, the continuously-changed bridge tower is calculated in an auxiliary mode through an optical flow method, the result is reflected to be an optical flow movement condition, and accuracy of bridge tower displacement monitoring is guaranteed. Meanwhile, the measuring method is small in influence factors such as environment, high in noise resistance, high in monitoring accuracy and high in applicability, and displacement is monitored through characteristic points of the checkerboard pattern.
Example two
The second embodiment of the present invention provides a flow chart of a measuring method for bridge tower displacement based on computer intelligent vision, as shown in fig. 3, the embodiment is a further description of a camera distortion part in the previous embodiment, including:
step 310, calculating the mapping relation between the pixel coordinate system and the world coordinate system, wherein all coordinate systems include the target (world) coordinate system, the camera coordinate system, the image coordinate system and the pixel coordinate system, and fig. 4 is an ideal camera imaging model.
Coordinate mapping relationship between pixel coordinate system and world coordinate system:
wherein u and v represent coordinates in a pixel coordinate system, s represents a scale factor, and f x 、f y Representing the scale factors of the camera in the u-axis and v-axis, u 0 、v 0 Represents the offset of the optical center and the origin of the camera, gamma represents two coordinate axis deflection parameters caused by manufacturing errors, and r 1 、r 2 Representing a camera extrinsic rotation matrix, t representing a camera extrinsic translation matrix, x w 、y w Representing coordinates in the world coordinate system.
Step 320, obtaining constraint equations of the single image by orthogonal vector properties, wherein for the single image, a homographic mapping can be established between points on the checkerboard plane and pixel points thereof.
The homography matrix is defined as:
further, wherein M 1 As an internal reference matrix, it is easy to see that the homography matrix contains both the camera internal reference matrix and the external reference matrix. Let H= [ H ] 1 h 2 h 3 ]＝sM 1 [r 1 r 2 t]Lambda=1/s
Further, the rotation vectors are mutually orthogonal in construction, and a constraint equation of each image can be obtained according to the property of the orthogonal vectors; wherein the property of the orthogonal matrix comprises that the orthogonal vector dot product is 0, and the orthogonal vectors are equal in length.
Step 330, calculate the camera reference matrix and distortion coefficient for correcting the displacement calculation result.
Further, let the
Further, since B is a symmetric matrix, six-dimensional vectors can be written, and the expression is simplified
Further, the ith column vector defining the homography matrix H is H i ＝[h i1 h i2 h i3 ]Thus, the two constraints can be finally converted into
Further, the camera parameter matrix can be solved, and then the camera internal parameters can be obtained according to the closed solution of the matrix B as follows
Example III
As shown in fig. five, the apparatus according to the embodiment of the present invention includes an image acquisition device 510, a data processor 520, a result output device 530, and a data memory 540. Wherein the number of image acquisition devices 510 is one, the number of data processors 520 is one or more, the number of result output devices 530 is one, and the number of data memories 540 is one or more.
The image acquisition device 510 is used for monitoring and acquiring target images in real time, and transmitting acquired data to the data processor 520 through a data connection line between the acquisition device and the processor, and transmitting results to the result output device and the data memory after the data processor finishes processing. The image acquisition device can be remotely controlled through a computer end to adjust detail parameters.
The data processor 520 is mainly divided into image preprocessing and displacement calculation processing, and the data is transmitted to the data processor by the acquisition device, then the image is preprocessed preferentially, and secondly, the preprocessed image is processed by the displacement calculation part, and the result is transmitted to the result output device 530, and the result output device outputs the result and uploads the data to the management system.
The data memory 540 is mainly divided into an output data memory and a program memory, wherein the program memory mainly stores a main system, so that accidental loss of a program is prevented; the output data memory stores primarily the processing results, records each time data, and therefore includes at least one flash memory element, disk storage element, or other solid state storage element. The cloud storage can be configured under special requirements, and other combinations such as the Internet, the project local area network, the communication network and the like are connected to upload data to the cloud storage, so that the multi-party call is facilitated.
It should be noted that, in the embodiment of the method for measuring bridge tower displacement based on computer intelligent vision, the included modules and flows are only distinguished according to functions, but not limited to the above distinction; in addition, the names of the module units are only for distinguishing each other, and are not used to limit the protection scope of the present invention. The foregoing is merely illustrative of embodiments of the present invention and applicable technical principles, and it will be understood by those skilled in the art that the present invention is not limited to the specific embodiments described herein.
Claims (9)
1. The bridge tower displacement measuring device based on the computer intelligent vision is characterized by comprising a camera correction module, an image monitoring module, an image preprocessing module, a feature recognition module, a conversion matrix calculation module, a displacement calculation module and an optical flow method auxiliary module;
the camera correction module is connected with the image monitoring module, the image monitoring module is connected with the image preprocessing module, the image preprocessing module is connected with the characteristic recognition module, the characteristic recognition module is connected with the conversion matrix calculation module, the conversion matrix calculation module is connected with the displacement calculation module, and the displacement calculation module is connected with the optical flow method auxiliary module.
2. The computer vision based bridge tower displacement measurement device according to claim 1, wherein the camera correction module is used for correcting distortion caused by lens manufacturing errors and the like; the image monitoring module is used for acquiring target images; the image preprocessing module is used for further processing the acquired image and improving the imaging quality; the characteristic recognition module is used for automatically recognizing characteristic points of the selected checkerboard pattern; the conversion matrix calculation module is used for establishing a two-dimensional coordinate system and a three-dimensional coordinate system according to known space coordinate information, and calculating a rotation matrix and a translation matrix of the space coordinate system and an imaging plane coordinate system; the displacement calculation module is used for calculating the coordinate transformation quantity of the identified characteristic points to determine the displacement of the bridge tower; the optical flow method auxiliary module is used for calculating continuously-changed target images or ordered videos to obtain movement information of the targets, the movement information is reflected to be actual movement conditions of the bridge tower, and the movement information is compared with the displacement calculation module to assist in correcting results.
3. The bridge tower displacement measuring method based on computer intelligent vision is characterized by comprising the following steps of:
step S1: correcting the camera to obtain an internal reference matrix and a distortion coefficient;
step S2: acquiring a target image according to the internal reference matrix and the distortion coefficient,
wherein the target image is a checkerboard image;
step S3: preprocessing the target image;
step S4: according to the position information of the characteristic points, a first target coordinate system is established by taking the inner angle points of the target image as reference points, a second camera coordinate system is established by taking the optical center of the camera as an origin, and the conversion relation between the first coordinate system and the second coordinate system is calculated;
step S5: automatically identifying characteristic points of the checkerboard image;
step S6: determining bridge tower displacement according to coordinate transformation quantities of the characteristic point pixels of the acquired checkerboard image in the time domain and the space domain;
step S7: and (5) assisting in monitoring the displacement of the bridge tower according to the result of the optical flow method so as to determine the actual movement condition.
4. The method for measuring displacement of the bridge tower based on computer intelligent vision according to claim 3, wherein the displacement of the bridge tower in the step S6 is translational along an x-axis, translational along a y-axis, translational along a z-axis, rotational about the x-axis, rotational about the y-axis, and rotational about the z-axis, and the determination of the displacement of the bridge is specifically to collect the coordinate transformation amount of the feature points of the marker image under the camera coordinate system of at least two frames according to the setting.
5. A method for measuring bridge tower displacement based on computer intelligence vision as claimed in claim 3, wherein said checkerboard image is a black and white checkerboard pattern.
6. The method for measuring bridge tower displacement based on computer intelligent vision according to claim 3, wherein the number of internal angle points of the target image is at least 4.
7. The method for measuring the displacement of the bridge tower based on the computer intelligent vision according to claim 3, wherein the selected target image is printed on the PVC plate in a high-precision ink-jet printing mode, and meanwhile, steel plates are additionally arranged on four sides of the PVC plate for fixing, so that deformation caused by external force is prevented.
8. A method for measuring bridge tower displacement based on computer-aided vision according to claim 3, wherein the correction of step S1 is specifically to collect 30 image corrections for the markers at the edges of the images.
9. The method for measuring bridge tower displacement based on computer intelligent vision according to claim 3, wherein the image preprocessing in step S3 comprises image denoising, image enhancement and super-resolution reconstruction, and obtains a result with higher imaging quality, so as to overcome the defects in the device and environment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311156385.6A CN117190875A (en) | 2023-09-08 | 2023-09-08 | Bridge tower displacement measuring device and method based on computer intelligent vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311156385.6A CN117190875A (en) | 2023-09-08 | 2023-09-08 | Bridge tower displacement measuring device and method based on computer intelligent vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117190875A true CN117190875A (en) | 2023-12-08 |
Family
ID=88984521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311156385.6A Pending CN117190875A (en) | 2023-09-08 | 2023-09-08 | Bridge tower displacement measuring device and method based on computer intelligent vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117190875A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117490579A (en) * | 2024-01-03 | 2024-02-02 | 苏州大学 | Foundation pit displacement monitoring system based on image vision processing |
| CN117968796A (en) * | 2024-01-30 | 2024-05-03 | 重庆交通大学 | Infrared visual positioning method for concrete pumping liquid level in steel pipe arch bridge pipe |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101865664A (en) * | 2010-05-18 | 2010-10-20 | 武汉大学 | Portable dynamic deflection displacement measuring device and method |
| CN107991665A (en) * | 2017-11-23 | 2018-05-04 | 江苏理工学院 | It is a kind of based on fixed-focus camera to target three-dimensional coordinate method for continuous measuring |
| CN110146030A (en) * | 2019-06-21 | 2019-08-20 | 招商局重庆交通科研设计院有限公司 | Side slope surface DEFORMATION MONITORING SYSTEM and method based on gridiron pattern notation |
| CN115063599A (en) * | 2022-06-16 | 2022-09-16 | 昆明理工大学 | Wavelet optical flow estimation and image-related deformation identification method applied to small and medium reservoir dam monitoring |
| WO2023045147A1 (en) * | 2021-09-24 | 2023-03-30 | 上海闻泰电子科技有限公司 | Method and system for calibrating binocular camera, and electronic device and storage medium |
| CN116678337A (en) * | 2023-06-08 | 2023-09-01 | 交通运输部公路科学研究所 | Image recognition-based bridge girder erection machine girder front and rear pivot point position height difference and girder deformation monitoring and early warning system and method |
| CN116697888A (en) * | 2023-04-28 | 2023-09-05 | 北京天翔睿翼科技有限公司 | Method and system for measuring three-dimensional coordinates and displacement of target point in motion |
-
2023
- 2023-09-08 CN CN202311156385.6A patent/CN117190875A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101865664A (en) * | 2010-05-18 | 2010-10-20 | 武汉大学 | Portable dynamic deflection displacement measuring device and method |
| CN107991665A (en) * | 2017-11-23 | 2018-05-04 | 江苏理工学院 | It is a kind of based on fixed-focus camera to target three-dimensional coordinate method for continuous measuring |
| CN110146030A (en) * | 2019-06-21 | 2019-08-20 | 招商局重庆交通科研设计院有限公司 | Side slope surface DEFORMATION MONITORING SYSTEM and method based on gridiron pattern notation |
| WO2023045147A1 (en) * | 2021-09-24 | 2023-03-30 | 上海闻泰电子科技有限公司 | Method and system for calibrating binocular camera, and electronic device and storage medium |
| CN115063599A (en) * | 2022-06-16 | 2022-09-16 | 昆明理工大学 | Wavelet optical flow estimation and image-related deformation identification method applied to small and medium reservoir dam monitoring |
| CN116697888A (en) * | 2023-04-28 | 2023-09-05 | 北京天翔睿翼科技有限公司 | Method and system for measuring three-dimensional coordinates and displacement of target point in motion |
| CN116678337A (en) * | 2023-06-08 | 2023-09-01 | 交通运输部公路科学研究所 | Image recognition-based bridge girder erection machine girder front and rear pivot point position height difference and girder deformation monitoring and early warning system and method |
Non-Patent Citations (2)
| Title |
|---|
| 安冬等: "水下图像与视觉智能处理技术及应用", 28 February 2022, 中国农业大学出版社, pages: 244 - 247 * |
| 施尚伟等: "桥梁结构试验检测技术", 30 November 2012, 重庆大学出版社, pages: 197 - 198 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117490579A (en) * | 2024-01-03 | 2024-02-02 | 苏州大学 | Foundation pit displacement monitoring system based on image vision processing |
| CN117968796A (en) * | 2024-01-30 | 2024-05-03 | 重庆交通大学 | Infrared visual positioning method for concrete pumping liquid level in steel pipe arch bridge pipe |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109270534B (en) | Intelligent vehicle laser sensor and camera online calibration method | |
| CN117190875A (en) | Bridge tower displacement measuring device and method based on computer intelligent vision | |
| CN112949478B (en) | Target detection method based on tripod head camera | |
| CN111369630A (en) | Method for calibrating multi-line laser radar and camera | |
| CN107492069B (en) | Image fusion method based on multi-lens sensor | |
| CN110246177B (en) | Automatic wave measuring method based on vision | |
| CN109472829B (en) | Object positioning method, device, equipment and storage medium | |
| CN110084785B (en) | Power transmission line vertical arc measuring method and system based on aerial images | |
| CN113793270A (en) | Aerial image geometric correction method based on unmanned aerial vehicle attitude information | |
| CN115187798A (en) | Multi-unmanned aerial vehicle high-precision matching positioning method | |
| CN111220120B (en) | Moving platform binocular ranging self-calibration method and device | |
| CN113205603A (en) | Three-dimensional point cloud splicing reconstruction method based on rotating platform | |
| CN112288848A (en) | Method for calculating engineering quantity through three-dimensional modeling of unmanned aerial vehicle aerial photography | |
| CN113240749B (en) | Remote binocular calibration and ranging method for recovery of unmanned aerial vehicle facing offshore ship platform | |
| CN114283203A (en) | Calibration method and system of multi-camera system | |
| CN115372987A (en) | Lane line extraction method, device, medium and equipment based on laser radar | |
| CN114659523A (en) | Large-range high-precision attitude measurement method and device | |
| CN111260736A (en) | In-orbit real-time calibration method for internal parameters of space camera | |
| CN117252933A (en) | Unmanned aerial vehicle-based camera internal parameter automatic calibration method, system and electronic equipment | |
| CN107423766B (en) | Method for detecting tail end motion pose of series-parallel automobile electrophoretic coating conveying mechanism | |
| CN114693807B (en) | Method and system for reconstructing mapping data of power transmission line image and point cloud | |
| CN110503604A (en) | It is a kind of based on high-precision POS aviation face battle array image just penetrate joining method in real time | |
| WO2023178481A1 (en) | Deformation measurement method and apparatus, electronic device, and storage medium | |
| CN116563370A (en) | Distance measurement method and speed measurement method based on monocular computer vision | |
| CN113405532B (en) | Forward intersection measuring method and system based on structural parameters of vision system |
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 |