CN102645173A - Multi-vision-based bridge three-dimensional deformation monitoring method - Google Patents
Multi-vision-based bridge three-dimensional deformation monitoring method Download PDFInfo
- Publication number
- CN102645173A CN102645173A CN2011100387824A CN201110038782A CN102645173A CN 102645173 A CN102645173 A CN 102645173A CN 2011100387824 A CN2011100387824 A CN 2011100387824A CN 201110038782 A CN201110038782 A CN 201110038782A CN 102645173 A CN102645173 A CN 102645173A
- Authority
- CN
- China
- Prior art keywords
- bridge
- layer
- unique point
- deformation
- point
- 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
Images
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a multi-vision-based bridge three-dimensional deformation monitoring method which comprises the following steps of: (1) obtaining the images of calibration plates and extracting the feature points on the multiple calibration plates by multiple video cameras respectively; (2) establishing a mapping model based on a BP neural network; (3) obtaining each video camera image at the bridge edge feature points; (4) eliminating the error point pairs by use of RANSAC to obtain the correct matching point pairs; (5) extracting the two-dimensional coordinates of each video camera image at the bridge edge feature points, obtaining the three-dimensional world coordinates of the feature points according to the mapping model based on BP neutral network, and drawing a three-dimensional curve of the bridge surface; and (6) extracting the bridge deformation rule according to the bridge curves of the bridge at different moments, and judging the bridge deformation trend. The method provided by the invention can perform non-contact three-dimensional measurement on the bridge deformation, and has the advantages of continuous measurement, instant measurement, synchronous measurement of multiple points, high precision, repeatability, low cost and the like.
Description
Technical field
The invention belongs to the object field of measuring technique, particularly a kind of bridge 3 d deformation monitoring method based on used for multi-vision visual.
Background technology
Along with the fast development of social economy with science and technology, the bridging technology is constantly progressive, and bridge structure is progressively to the development of light and handy, very thin aspect.The load-carrying of bridge meanwhile, stride the footpath and bridge deck width constantly increase, structural shape constantly changes.Traditional deformation monitoring means more and more can not satisfy the deformation monitoring requirement, and this monitors the deformation of bridge with regard to the equipment that presses for more reliable performance.
Present existing bridge deformation monitoring technology can be divided into two big types of contact type measurement and non-contact measurements.Summary is summarized as follows shown in the table 1:
The various measuring techniques of table 1
Conventional Geodetic surveying method is topmost deformation measurement method, is meant and utilizes the space geometry principle, takes measurement of an angle and distance waits the orientation that obtains three-dimensional coordinate through optics or electronic device (transit, total powerstation, spirit-leveling instrument etc.).This method has advantages such as measuring accuracy height, data be reliable; But simultaneously, use Geodetic surveying method also to exist some shortcomings: at first, monitoring velocity is slow, can't accomplish the observation of a plurality of deformation points in the short time; Next receives limitation of field condition, and is narrow and small in some space, can't fulfil assignment under the situation of insufficient light.
The physical sensors method mainly has been meant in observation process widespread use dynamometer, strainometer, accelerometer, displacement meter, weight dynamic measuring instrument, corrosion detector; And sensor such as vibrations, temperature, wind-force, pressure, humidity, rainfall; The advantage of this method is to obtain some the inner information of object of observation and the relative deformation information of high-precision local; And can realize long-continued automatic observation; But this method can only be monitored the local deformation state and the relative deformation situation of bridge, then seems powerless for the globality deformation monitoring of bridge.
A kind of new method that the GPS measuring method was risen over past ten years, its application has brought a deepgoing revolution to measuring technique.The GPS deformation monitoring has many good qualities, and is high such as accuracy of observation, and monitoring is not limited by weather condition, can carry out round-the-clock monitoring, and monitoring, record, calculating are automatically accomplished, and do not need intervisibility between the monitoring point, and reconnaissance does not receive topographic condition restriction etc.Weak point is the observation station limited amount, and all need to lay the measurement cost that receiver causes higher because of each observation station, can't realize indoor or underground work etc.
Measuring method all is the active measuring method, depends on special equipment, and these equipment are relatively more expensive.
Introduce several frequently seen bridge deformation monitoring technology and equipment below:
JZQN-W deflection of bridge span detector adopts traditional contact type measurement; Place it in each check point below of bridge; And with the stent support detector; When bridge force-bearing generation deflection deformation, the displacement transducer on the detector can be sent to the data result of transient measurement controller and store, and after software processes, can show the sound attitude deflection value and the curve of bridge.
Real-time and Dynamic (RTK) technology technology based on GPS is carried out real-time deformation monitoring to bridge.Common RTK deformation monitoring system is made up of base station, monitoring station and communication system etc.; The base station receiver is delivered to the monitoring station with differential correcting information through optical fiber in real time; The monitoring station receiver is except that receiving satellite signal; The differential correcting number of also sending according to base station carries out real time differential, and the three dimensional space coordinate that then difference is obtained is delivered to Surveillance center.
Based on the photoelectric image method is to analyze the miniature deformation of measured target through being fixed on image that the optical target of placing on the measured target is marked on the sensor devices to be become.
In sum, existing deformation measurement technology generally exists following defective: (1) can't accurately be noted the information of subject in moment, obtains the some position relation of moment; (2) precision equipment, expensive, cost is high; (3) most high precision measuring systems are the contact type measurement mode; (4) Training and Learning to operating personnel is difficult.(5) measurement of irregular object seems difficult.
Therefore, need higher and the measuring method that cost is relatively low of a kind of precision of design.
Summary of the invention
The shortcoming that the objective of the invention is to overcome above-mentioned prior art is with not enough, provides a kind of precision higher and the bridge 3 d deformation monitoring method based on used for multi-vision visual that cost is lower.
For reaching above-mentioned purpose, the present invention adopts following technical scheme: a kind of bridge 3 d deformation monitoring method based on used for multi-vision visual comprises the steps:
(1) obtain each camera review of object respectively by a plurality of video cameras, the object each point in each camera review to two-dimensional coordinate should be arranged; Obtain the unique point on several scaling boards;
(2) through pairing each camera review coordinate of each unique point and three-dimensional world coordinate are formed the training of a data sample, set up mapping model based on the BP neural network;
(3) each camera review that obtains according to said step (1), each camera review coordinate of extraction bridge edge feature point;
(4) utilize the RANSAC algorithm that the unique point that extraction obtains is eliminated carrying out mispairing, it is right to obtain correct unique point;
(5) the BP neural network mapping model through said step (2) gained carries out three-dimensional computations to said unique point; Each camera review coordinate of each unique point all is mapped to the three-dimensional world coordinate; And all three-dimensional world coordinate fittings are become three-dimensional world coordinate point set, set up the bridge deformation function;
(6) through asking for the deformation rule that the bridge deformation function obtains bridge.
In the said step (1), the obtaining step of scaling board unique point is following: scaling board is to be made by the chess gridiron pattern, extracts the unique point of tessellated black and white cross-point as scaling board.
In the said step (2), suppose that number of cameras is n, BP neural network mapping model comprises three layers of feedforward network, is respectively input layer, hidden layer and output layer, and said input layer comprises 2n neuron, two coordinate figures of respectively corresponding each unique point image; Said hidden layer comprises 4n neuron; Said output layer comprises three neurons, respectively three coordinate figures of the world coordinates of character pair point; Each neuron of said input layer shines upon one by one with each neuron of hidden layer and is connected, and each neuron of said hidden layer shines upon one by one with each neuron of output layer and is connected.
In the said step (2), set up the BP neural network model and comprise the steps:
(2-1) select training sample, set up training sample set;
(2-2) initialization:, set maximum iteration time, the desired output signal of training to each layer weight vector initialize;
(2-3) import each training sample at random, calculate neuronic input signal of each layer and output signal successively according to the training sample of importing;
(2-4) according to output signal final in the said step (2-3) and desired output signal, error signal judges whether said error signal meets the demands, if satisfy, and execution in step (2-8) then, otherwise, execution in step (2-5);
(2-5) whether judgement iterations next time is greater than maximum iteration time; If greater than; Execution in step (2-8) then; Otherwise; To every layer of neuronic partial gradient of training sample backwards calculation of input, said partial gradient satisfies:
, wherein n is an iterations;
is i layer j the neuronic partial gradient of being asked;
is transfer function;
is i layer j the output after the linear combination of neuronic input signal;
is i-1 layer j neuronic partial gradient; J is the neuron sum of i-1 layer;
is each neuronic weights that is connected of i layer j neuron and i-1 layer;
(2-6) adjust the connection weights of each layer; The adjusted connection weights of each layer satisfy:
;
neuronic connection weights when being the n time iteration of j neuron of i layer wherein;
connection weights when being the n+1 time iteration of j neuron of i layer, n is an iterations; Learning rate when
is the n time adjustment iteration; η is a factor of momentum;
when being this iteration, i layer j neuronic partial gradient;
when being last iteration, i layer j neuronic partial gradient;
(2-7) iterations adds one, gets into next iteration, execution in step (2-3);
(2-8) judge whether to finish all training samples, if, then finish training, obtain exporting the result; Otherwise, execution in step (2-3).
In the said step (2-6), the adjustment of each layer learning rate is satisfied: when the gradient direction of double iteration is identical, learning rate is doubled; When the gradient direction of double iteration is opposite, learning rate is reduced by half.
Said training sample is each camera review coordinate of said step (1) unique point.
The concrete steps of said step (3) are following:
(3-1) through graphical analysis, extract each camera review coordinate of object corresponding bridge edge feature point in the image that said step (1) forms;
(3-2) each unique point at said step (3-1) bridge edge is mated according to radix sorting;
(3-3) bridge edge feature point is trained, each camera review coordinate of the unique point at object bridge edge is mapped to the three-dimensional world coordinate respectively through the BP neural network model of said step (2) gained;
The three-dimensional world coordinate fitting three-dimensional world coordinate point set of each unique point that (3-4) said step (3-3) is calculated is set up the bridge deformation function.
Need eliminate carrying out mispairing the point of coupling after in the said step (4) each unique point being mated according to radix sorting; Utilize the RANSAC method to eliminate the mispairing of coupling centering; In the unique point pairing; The projective rejection of the unique point on model is from the unique point on the plane to an other plane is reacted and is projection matrix H.H is 3 * 3 matrixes that comprise 8 degree of freedom; Its minimum can calculating by 4 pairs of match points in two planes; But 3 points on the same plane are coplane not; The bridge edge feature that extracts is counted and is no less than 3, and the unique point that obtains is carried out just obtaining correct pairing after mispairing is eliminated to utilizing RANSAC.
Said step (6) comprises the steps: to obtain different bridge deformation functions constantly according to (3-4), extracts the deformation rule of bridge, thereby can predict the situation that bridge deforms in difference constantly.
The present invention can obtain the measurement means of a large amount of physical messages of tested bridge and geological information in moment, and is applicable to the bridge that measurement point is numerous, also can under mal-condition, carry out the bridge deformation monitoring.
This method can be used for the different types of rridges deformation monitoring, belongs to Computer Applied Technology, computer vision technique, non-contact measurement field.
Compared with prior art, the present invention has following advantage and beneficial effect:
1, the present invention can obtain the measurement means of a large amount of physical messages of tested bridge and geological information in moment, and is applicable to the bridge target that measurement point is numerous;
2, the present invention is a kind of untouchable measurement means, does not injure measurement target, does not disturb the measured object state of nature; Can be to the bridge under the inclement weather (like typhoon; Volcanic eruption, heavy rain), the bridge that perhaps is difficult for directly measurement (like the hill-side) carries out deformation monitoring;
3, the present invention adopts bridge edge feature point is carried out the particular search method, has advantages such as highly sensitive, that experimental situation adaptability is strong, can prevent the influence of surround lighting effectively;
4, the present invention adopts the training of BP neural network model; Can the image coordinate of two dimension be mapped to the three-dimensional world coordinate; With respect to traditional camera calibration and distortion correction, approach the three-dimensional coordinate function through the BP neural network model, can shield directly finding the solution of calibrating parameters downwards; The direct mapping of two-dimensional coordinate to three-dimensional coordinate upwards is provided; Solved under the not high situation of adverse environment and video camera precision, stably extract minutiae carries out the problem of dimensional visual measurement, and measurement result reaches certain controllable precision requirement;
5, each unique point of the present invention is mated according to radix sorting, and after coupling, carries out mispairing and eliminate, and can effectively simplify BP neural network model training speed, and can guarantee the objective and authenticity of unique point;
6, the present invention is a kind of means that are suitable for dynamic object profile and motion state mensuration;
7, cost of the present invention is low, reconstruct property good, is well positioned to meet the variation of application demand.
Description of drawings
Fig. 1 is the process flow diagram of the inventive method.
Embodiment
Below in conjunction with embodiment and accompanying drawing the present invention is described in further detail, but embodiment of the present invention is not limited thereto.
Embodiment
As shown in Figure 1, this comprises the steps: based on the bridge 3 d deformation monitoring method of used for multi-vision visual
(1) obtained each camera review of object respectively by a plurality of video cameras, the object each point to each camera review coordinate should be arranged, and is two-dimensional coordinate in each camera review; Obtain the unique point on several scaling boards;
(2) through pairing each camera review coordinate of each unique point and three-dimensional world coordinate are formed the training of a data sample, set up mapping model based on the BP neural network;
(3) each camera review that obtains according to said step (1), each camera review coordinate of extraction bridge edge feature point;
(4) utilize the RANSAC algorithm that the unique point that extraction obtains is eliminated carrying out mispairing, it is right to obtain correct unique point;
(5) the BP neural network mapping model through said step (2) gained carries out three-dimensional computations to said unique point; Each camera review coordinate of each unique point all is mapped to the three-dimensional world coordinate; And all three-dimensional world coordinate fittings are become three-dimensional world coordinate point set, set up the bridge deformation function;
(6) through asking for the deformation rule that the bridge deformation function obtains bridge.
In the said step (1), the obtaining step of scaling board unique point is following: scaling board is to be made by the chess gridiron pattern, extracts the unique point of tessellated black and white cross-point as scaling board.
In the said step (2), suppose that number of cameras is n, BP neural network mapping model comprises three layers of feedforward network, is respectively input layer, hidden layer and output layer, and said input layer comprises 2n neuron, two coordinate figures of respectively corresponding each unique point image; Said hidden layer comprises 4n neuron; Said output layer comprises three neurons, respectively three coordinate figures of the world coordinates of character pair point; Each neuron of said input layer shines upon one by one with each neuron of hidden layer and is connected, and each neuron of said hidden layer shines upon one by one with each neuron of output layer and is connected.
In the said step (2), set up the BP neural network model and comprise the steps:
(2-1) select training sample, set up training sample set;
(2-2) initialization:, set maximum iteration time, the desired output signal of training to each layer weight vector initialize;
(2-3) import each training sample at random, calculate neuronic input signal of each layer and output signal successively according to the training sample of importing;
(2-4) according to output signal final in the said step (2-3) and desired output signal, error signal judges whether said error signal meets the demands, if satisfy, and execution in step (2-8) then, otherwise, execution in step (2-5);
(2-5) whether judgement iterations next time is greater than maximum iteration time; If greater than; Execution in step (2-8) then; Otherwise; To every layer of neuronic partial gradient of training sample backwards calculation of input, said partial gradient satisfies:
, wherein n is an iterations;
is i layer j the neuronic partial gradient of being asked;
is transfer function;
is i layer j the output after the linear combination of neuronic input signal;
is i-1 layer j neuronic partial gradient; J is the neuron sum of i-1 layer;
is each neuronic weights that is connected of i layer j neuron and i-1 layer;
(2-6) adjust the connection weights of each layer; The adjusted connection weights of each layer satisfy:
;
neuronic connection weights when being the n time iteration of j neuron of i layer wherein;
connection weights when being the n+1 time iteration of j neuron of i layer, n is an iterations; Learning rate when
is the n time adjustment iteration; η is a factor of momentum;
when being this iteration, i layer j neuronic partial gradient;
when being last iteration, i layer j neuronic partial gradient;
(2-7) iterations adds one, gets into next iteration, execution in step (2-3);
(2-8) judge whether to finish all training samples, if, then finish training, obtain exporting the result; Otherwise, execution in step (2-3).
In the said step (2-6), the adjustment of each layer learning rate is satisfied: when the gradient direction of double iteration is identical, learning rate is doubled; When the gradient direction of double iteration is opposite, learning rate is reduced by half.
Said training sample is each camera review coordinate of said step (1) unique point.
The concrete steps of said step (3) are following:
(3-1) through graphical analysis, extract each camera review coordinate of object corresponding bridge edge feature point in the image that said step (1) forms;
(3-2) each unique point at said step (3-1) bridge edge is mated according to radix sorting;
(3-3) bridge edge feature point is trained, each camera review coordinate of the unique point at object bridge edge is mapped to the three-dimensional world coordinate respectively through the BP neural network model of said step (2) gained;
The three-dimensional world coordinate fitting three-dimensional world coordinate point set of each unique point that (3-4) said step (3-3) is calculated is set up the bridge deformation function.
Need eliminate carrying out mispairing the point of coupling after in the said step (4) each unique point being mated according to radix sorting; Utilize the RANSAC method to eliminate the mispairing of coupling centering; In the unique point pairing; The projective rejection of the unique point on model is from the unique point on the plane to an other plane is reacted and is projection matrix H.H is 3 * 3 matrixes that comprise 8 degree of freedom; Its minimum can calculating by 4 pairs of match points in two planes; But 3 points on the same plane are coplane not; The bridge edge feature that extracts is counted and is no less than 3, and the unique point that obtains is carried out just obtaining correct pairing after mispairing is eliminated to utilizing RANSAC.
Obtain different bridge deformation functions constantly according to (3-4) in the said step (6), extract the deformation rule of bridge, thereby can judge bridge deformation trend.
The present invention can obtain the measurement means of a large amount of physical messages of tested bridge and geological information in moment, and is applicable to the bridge that measurement point is numerous, also can under mal-condition, carry out the bridge deformation monitoring.This method can be used for various large-scale bridge deformation monitorings, belongs to Computer Applied Technology, computer vision technique, non-contact measurement field.
The foregoing description is a preferred implementation of the present invention; But embodiment of the present invention is not restricted to the described embodiments; Other any do not deviate from change, the modification done under spirit of the present invention and the principle, substitutes, combination, simplify; All should be the substitute mode of equivalence, be included within protection scope of the present invention.
Claims (9)
1. the bridge 3 d deformation monitoring method based on used for multi-vision visual is characterized in that, comprises the steps:
(1) obtained the image of scaling board respectively by a plurality of video cameras, the scaling board each point has respective coordinates in each camera review, and is two-dimensional coordinate; Obtain the unique point on several scaling boards;
(2) through pairing each camera review coordinate of each unique point and three-dimensional world coordinate are formed the training of a data sample, set up mapping model based on the BP neural network;
(3) each camera review that obtains according to said step (1), each camera review coordinate of extraction bridge edge feature point;
(4) utilize the RANSAC algorithm that the unique point that extraction obtains is eliminated carrying out mispairing, it is right to obtain correct unique point;
(5) the BP neural network mapping model through said step (2) gained carries out three-dimensional computations to said unique point; Each camera review coordinate of each unique point all is mapped to the three-dimensional world coordinate; And all three-dimensional world coordinate fittings are become three-dimensional world coordinate point set, set up the bridge deformation function;
(6) through difference constantly bridge deformation obtain the deformation rule of bridge.
2. the bridge 3 d deformation monitoring method based on used for multi-vision visual according to claim 1; It is characterized in that; In the said step (1); The obtaining step of scaling board unique point is following: scaling board is to be made by the chess gridiron pattern, extracts the unique point of tessellated black and white cross-point as scaling board.
3. the bridge 3 d deformation monitoring method based on used for multi-vision visual according to claim 1; It is characterized in that, in the said step (2), suppose that number of cameras is n; BP neural network mapping model comprises three layers of feedforward network; Be respectively input layer, hidden layer and output layer, said input layer comprises 2n neuron, two coordinate figures of respectively corresponding each unique point image; Said hidden layer comprises 4n neuron; Said output layer comprises three neurons, respectively three coordinate figures of the world coordinates of character pair point;
Each neuron of said input layer shines upon one by one with each neuron of hidden layer and is connected, and each neuron of said hidden layer shines upon one by one with each neuron of output layer and is connected.
4. the bridge 3 d deformation monitoring method based on used for multi-vision visual according to claim 3 is characterized in that, in the said step (2), sets up BP neural network mapping model and comprises the steps:
(2-1) select training sample, set up training sample set;
(2-2) initialization:, set maximum iteration time, the desired output signal of training to each layer weight vector initialize;
(2-3) import each training sample at random, calculate neuronic input signal of each layer and output signal successively according to the training sample of importing;
(2-4) according to output signal final in the said step (2-3) and desired output signal, error signal judges whether said error signal meets the demands, if satisfy, and execution in step (2-8) then, otherwise, execution in step (2-5);
(2-5) whether judgement iterations next time is greater than maximum iteration time; If greater than; Execution in step (2-8) then; Otherwise; To every layer of neuronic partial gradient of training sample backwards calculation of input, said partial gradient satisfies:
, wherein n is an iterations;
is i layer j the neuronic partial gradient of being asked;
is transfer function;
is i layer j the output after the linear combination of neuronic input signal;
is i-1 layer j neuronic partial gradient; J is the neuron sum of i-1 layer;
is each neuronic weights that is connected of i layer j neuron and i-1 layer;
(2-6) adjust the connection weights of each layer; The adjusted connection weights of each layer satisfy:
;
neuronic connection weights when being the n time iteration of j neuron of i layer wherein;
connection weights when being the n+1 time iteration of j neuron of i layer, n is an iterations; Learning rate when
is the n time adjustment iteration; η is a factor of momentum;
when being this iteration, i layer j neuronic partial gradient;
when being last iteration, i layer j neuronic partial gradient;
(2-7) iterations adds one, gets into next iteration, execution in step (2-3);
(2-8) judge whether to finish all training samples, if, then finish training, obtain exporting the result; Otherwise, execution in step (2-3).
5. the bridge 3 d deformation monitoring method based on used for multi-vision visual according to claim 4 is characterized in that, in the said step (2-6), the adjustment of each layer learning rate is satisfied: when the gradient direction of double iteration is identical, learning rate is doubled; When the gradient direction of double iteration is opposite, learning rate is reduced by half.
6. the bridge 3 d deformation monitoring method based on used for multi-vision visual according to claim 4 is characterized in that, said training sample is each camera review coordinate of said step (1) unique point.
7. the bridge 3 d deformation monitoring method based on used for multi-vision visual according to claim 6; It is characterized in that, need eliminate carrying out mispairing the point of coupling after in the said step (4) each unique point being mated according to radix sorting, utilize the RANSAC method to eliminate the mispairing of coupling centering; In the unique point pairing; The projective rejection of the unique point on model is from the unique point on the plane to an other plane is reacted and is that projection matrix H, H are 3 * 3 matrixes that comprise 8 degree of freedom; Its minimum can calculating by 4 pairs of match points in two planes; But 3 points on the same plane are coplane not, and the bridge edge feature of extraction is counted and is no less than 3, and the unique point that obtains is carried out just obtaining correct pairing after mispairing is eliminated to utilizing RANSAC.
8. the bridge 3 d deformation monitoring method based on used for multi-vision visual according to claim 1 is characterized in that the concrete steps of said step (5) are following:
(3-1) through graphical analysis, extract each camera review coordinate of object corresponding bridge edge feature point in the image that said step (1) forms;
(3-2) each unique point at said step (3-1) bridge edge is mated according to radix sorting;
(3-3) the BP neural network mapping model through said step (2) gained carries out three-dimensional computations to the unique point at bridge edge, and each camera review coordinate of bridge edge feature point is mapped to the three-dimensional world coordinate respectively;
The three-dimensional world coordinate fitting three-dimensional world coordinate point set of each unique point that (3-4) said step (3-3) is calculated is set up the bridge deformation function.
9. the bridge 3 d deformation monitoring method based on used for multi-vision visual according to claim 1 is characterized in that said step (6) comprises the steps:
Obtain different bridge deformation functions constantly according to (3-4), extract the deformation rule of bridge, thereby can judge the deformation tendency of bridge.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011100387824A CN102645173A (en) | 2011-02-16 | 2011-02-16 | Multi-vision-based bridge three-dimensional deformation monitoring method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011100387824A CN102645173A (en) | 2011-02-16 | 2011-02-16 | Multi-vision-based bridge three-dimensional deformation monitoring method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102645173A true CN102645173A (en) | 2012-08-22 |
Family
ID=46658150
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011100387824A Pending CN102645173A (en) | 2011-02-16 | 2011-02-16 | Multi-vision-based bridge three-dimensional deformation monitoring method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102645173A (en) |
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102927917A (en) * | 2012-10-26 | 2013-02-13 | 河北省电力公司电力科学研究院 | Multi-view vision measurement method of iron tower |
CN103292722A (en) * | 2013-06-07 | 2013-09-11 | 温州大学 | Three-dimensional deformation measuring method of non-contact wind power blade whole field |
CN103438823A (en) * | 2012-12-27 | 2013-12-11 | 广州市地下铁道总公司 | Tunnel section outline measuring method and device based on vision measurement |
JP2015036620A (en) * | 2013-08-12 | 2015-02-23 | 復建調査設計株式会社 | Method for measuring altitude of bridge in live load non-loaded state |
CN104482983A (en) * | 2014-12-30 | 2015-04-01 | 中国科学院深圳先进技术研究院 | Method for measuring three-dimensional material pile |
CN105488807A (en) * | 2015-12-25 | 2016-04-13 | 傅之成 | Method for calibrating and rectifying telecentric lens |
CN105930774A (en) * | 2016-04-14 | 2016-09-07 | 中铁大桥勘测设计院集团有限公司 | Automatic bridge bolt come-off identification method based on neural network |
CN106127789A (en) * | 2016-07-04 | 2016-11-16 | 湖南科技大学 | Stereoscopic vision scaling method in conjunction with neutral net Yu virtual target |
CN106643541A (en) * | 2016-12-26 | 2017-05-10 | 深圳高速工程顾问有限公司 | Method and device for management and analysis of real-time monitoring data of bridge |
CN106895792A (en) * | 2017-04-27 | 2017-06-27 | 武汉大学 | Power transmission tower component deformation and Internal Force Monitoring method based on two CCD camera measure system |
CN107063110A (en) * | 2017-04-27 | 2017-08-18 | 武汉大学 | A kind of Transmission Tower-line System panorama multi-angle two CCD camera measure system |
CN107085853A (en) * | 2017-05-04 | 2017-08-22 | 中国矿业大学 | Guide rail single eye stereo vision mining area derrick deformation monitoring method |
CN109186902A (en) * | 2018-09-26 | 2019-01-11 | 中国计量大学 | A kind of bridge structure health detection system of view-based access control model sensing |
CN109269399A (en) * | 2018-10-25 | 2019-01-25 | 清华大学 | A kind of online error parameter identification and self-compensating system and method |
CN109559348A (en) * | 2018-11-30 | 2019-04-02 | 东南大学 | A kind of contactless deformation measurement method of bridge based on tracing characteristic points |
CN109754429A (en) * | 2018-12-14 | 2019-05-14 | 东南大学 | A kind of deflection of bridge structure measurement method based on image |
CN110057515A (en) * | 2019-03-22 | 2019-07-26 | 天津大学 | A kind of Bridge Defect Detecting system and method based on deep learning |
CN110291358A (en) * | 2017-02-20 | 2019-09-27 | 欧姆龙株式会社 | Shape estimation device |
CN110309544A (en) * | 2019-06-04 | 2019-10-08 | 西安工程大学 | A kind of stress point prediction technique of beam large deformation neural network based |
CN110411686A (en) * | 2019-03-13 | 2019-11-05 | 周劲宇 | The quiet dynamic image holography condition health monitoring diagnostic method of bridge and system |
CN110617775A (en) * | 2019-09-26 | 2019-12-27 | 杭州鲁尔物联科技有限公司 | Method, device and system for monitoring bridge deflection based on visual perception |
WO2020133080A1 (en) * | 2018-12-27 | 2020-07-02 | 深圳市优必选科技有限公司 | Object positioning method and apparatus, computer device, and storage medium |
CN112179422A (en) * | 2020-11-27 | 2021-01-05 | 湖南大学 | Method and system for recognizing axle and vehicle speed by using bridge deflection |
CN112833808A (en) * | 2021-01-05 | 2021-05-25 | 厦门银江智慧城市技术股份有限公司 | Equipment deformation detection method and device based on convolutional neural network algorithm |
CN112964193A (en) * | 2021-04-14 | 2021-06-15 | 广州大学 | Novel bridge deformation monitoring method and system |
CN113744352A (en) * | 2021-09-14 | 2021-12-03 | 北京观海科技发展有限责任公司 | Visual space calibration method, device and storage medium |
CN117073565A (en) * | 2023-08-22 | 2023-11-17 | 山东高速济南绕城西线公路有限公司 | Bridge deformation monitoring system and method |
PL442963A1 (en) * | 2022-11-28 | 2024-06-03 | Des Vision Spółka Z Ograniczoną Odpowiedzialnością | Calibration system used in the system for monitoring the displacement of building structures and how it is used |
-
2011
- 2011-02-16 CN CN2011100387824A patent/CN102645173A/en active Pending
Cited By (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102927917A (en) * | 2012-10-26 | 2013-02-13 | 河北省电力公司电力科学研究院 | Multi-view vision measurement method of iron tower |
CN102927917B (en) * | 2012-10-26 | 2016-02-24 | 河北省电力公司电力科学研究院 | Many orders vision measurement method of iron tower |
CN103438823A (en) * | 2012-12-27 | 2013-12-11 | 广州市地下铁道总公司 | Tunnel section outline measuring method and device based on vision measurement |
CN103292722A (en) * | 2013-06-07 | 2013-09-11 | 温州大学 | Three-dimensional deformation measuring method of non-contact wind power blade whole field |
JP2015036620A (en) * | 2013-08-12 | 2015-02-23 | 復建調査設計株式会社 | Method for measuring altitude of bridge in live load non-loaded state |
CN104482983A (en) * | 2014-12-30 | 2015-04-01 | 中国科学院深圳先进技术研究院 | Method for measuring three-dimensional material pile |
CN105488807A (en) * | 2015-12-25 | 2016-04-13 | 傅之成 | Method for calibrating and rectifying telecentric lens |
CN105930774A (en) * | 2016-04-14 | 2016-09-07 | 中铁大桥勘测设计院集团有限公司 | Automatic bridge bolt come-off identification method based on neural network |
CN106127789A (en) * | 2016-07-04 | 2016-11-16 | 湖南科技大学 | Stereoscopic vision scaling method in conjunction with neutral net Yu virtual target |
CN106643541A (en) * | 2016-12-26 | 2017-05-10 | 深圳高速工程顾问有限公司 | Method and device for management and analysis of real-time monitoring data of bridge |
CN106643541B (en) * | 2016-12-26 | 2019-09-06 | 深圳高速工程顾问有限公司 | A kind of method and device of real-time monitoring data of bridge administrative analysis |
CN110291358B (en) * | 2017-02-20 | 2022-04-05 | 欧姆龙株式会社 | Shape estimating device |
US11036965B2 (en) | 2017-02-20 | 2021-06-15 | Omron Corporation | Shape estimating apparatus |
CN110291358A (en) * | 2017-02-20 | 2019-09-27 | 欧姆龙株式会社 | Shape estimation device |
CN106895792A (en) * | 2017-04-27 | 2017-06-27 | 武汉大学 | Power transmission tower component deformation and Internal Force Monitoring method based on two CCD camera measure system |
CN107063110A (en) * | 2017-04-27 | 2017-08-18 | 武汉大学 | A kind of Transmission Tower-line System panorama multi-angle two CCD camera measure system |
CN107085853B (en) * | 2017-05-04 | 2019-08-27 | 中国矿业大学 | Guide rail single eye stereo vision mining area derrick deformation monitoring method |
CN107085853A (en) * | 2017-05-04 | 2017-08-22 | 中国矿业大学 | Guide rail single eye stereo vision mining area derrick deformation monitoring method |
CN109186902A (en) * | 2018-09-26 | 2019-01-11 | 中国计量大学 | A kind of bridge structure health detection system of view-based access control model sensing |
CN109269399A (en) * | 2018-10-25 | 2019-01-25 | 清华大学 | A kind of online error parameter identification and self-compensating system and method |
CN109269399B (en) * | 2018-10-25 | 2020-05-19 | 清华大学 | Online error parameter identification and self-compensation system and method |
CN109559348A (en) * | 2018-11-30 | 2019-04-02 | 东南大学 | A kind of contactless deformation measurement method of bridge based on tracing characteristic points |
CN109559348B (en) * | 2018-11-30 | 2021-09-28 | 东南大学 | Bridge non-contact deformation measurement method based on feature point tracking |
CN109754429A (en) * | 2018-12-14 | 2019-05-14 | 东南大学 | A kind of deflection of bridge structure measurement method based on image |
WO2020133080A1 (en) * | 2018-12-27 | 2020-07-02 | 深圳市优必选科技有限公司 | Object positioning method and apparatus, computer device, and storage medium |
CN110411686B (en) * | 2019-03-13 | 2021-03-23 | 周劲宇 | Bridge static and dynamic image holographic property health monitoring and diagnosis method and system |
CN110411686A (en) * | 2019-03-13 | 2019-11-05 | 周劲宇 | The quiet dynamic image holography condition health monitoring diagnostic method of bridge and system |
CN110057515A (en) * | 2019-03-22 | 2019-07-26 | 天津大学 | A kind of Bridge Defect Detecting system and method based on deep learning |
CN110309544A (en) * | 2019-06-04 | 2019-10-08 | 西安工程大学 | A kind of stress point prediction technique of beam large deformation neural network based |
CN110309544B (en) * | 2019-06-04 | 2023-04-07 | 西安工程大学 | Stress point prediction method for large deformation of beam based on neural network |
CN110617775A (en) * | 2019-09-26 | 2019-12-27 | 杭州鲁尔物联科技有限公司 | Method, device and system for monitoring bridge deflection based on visual perception |
CN112179422A (en) * | 2020-11-27 | 2021-01-05 | 湖南大学 | Method and system for recognizing axle and vehicle speed by using bridge deflection |
CN112833808A (en) * | 2021-01-05 | 2021-05-25 | 厦门银江智慧城市技术股份有限公司 | Equipment deformation detection method and device based on convolutional neural network algorithm |
CN112964193A (en) * | 2021-04-14 | 2021-06-15 | 广州大学 | Novel bridge deformation monitoring method and system |
CN113744352B (en) * | 2021-09-14 | 2022-07-29 | 北京观海科技发展有限责任公司 | Visual space calibration method, device and storage medium |
CN113744352A (en) * | 2021-09-14 | 2021-12-03 | 北京观海科技发展有限责任公司 | Visual space calibration method, device and storage medium |
PL442963A1 (en) * | 2022-11-28 | 2024-06-03 | Des Vision Spółka Z Ograniczoną Odpowiedzialnością | Calibration system used in the system for monitoring the displacement of building structures and how it is used |
CN117073565A (en) * | 2023-08-22 | 2023-11-17 | 山东高速济南绕城西线公路有限公司 | Bridge deformation monitoring system and method |
CN117073565B (en) * | 2023-08-22 | 2024-03-12 | 山东高速济南绕城西线公路有限公司 | Bridge deformation monitoring system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102645173A (en) | Multi-vision-based bridge three-dimensional deformation monitoring method | |
CN101907448B (en) | Depth measurement method based on binocular three-dimensional vision | |
CN109489620B (en) | Monocular vision distance measuring method | |
CN103411553B (en) | The quick calibrating method of multi-linear structured light vision sensors | |
CN109737883A (en) | A kind of three-dimensional deformation dynamic measurement system and measurement method based on image recognition | |
CN105547635B (en) | A kind of contactless structural dynamic response measurement method for wind tunnel test | |
CN102183214B (en) | Light detection method for large-aperture aspherical mirror structure | |
CN110415300B (en) | Three-target-plane-construction-based dynamic displacement measurement method for stereoscopic vision structure | |
CN110068270A (en) | A kind of monocular vision box volume measurement method based on multi-line structured light image recognition | |
CN106657992B (en) | Device and method for adaptively detecting and adjusting double-camera-axis | |
CN102288199B (en) | Ground testing method of star sensor | |
CN103487033B (en) | River surface photographic surveying method based on height-change homography | |
CN103323855A (en) | Method for obtaining accuracy of reference line dynamic measurement system | |
CN105527656B (en) | Tower-type airfield runway Foreign bodies method | |
CN104634248A (en) | Revolving shaft calibration method under binocular vision | |
CN105607760A (en) | Trace restoration method and system based on micro inertial sensor | |
CN102636081A (en) | Transfer alignment method and device based on visual movement modeling | |
CN112683307B (en) | Star sensor star point centroid position precision measurement method | |
CN108398123A (en) | A kind of total powerstation and its scale scaling method | |
CN108088383A (en) | A kind of photogrammetric algorithm applied to hoisting machinery | |
CN108154535B (en) | Camera calibration method based on collimator | |
CN108362205A (en) | Space ranging method based on fringe projection | |
CN115578315A (en) | Bridge strain close-range photogrammetry method based on unmanned aerial vehicle image | |
Meng et al. | Defocused calibration for large field-of-view binocular cameras | |
CN113888641A (en) | Stumpage breast diameter measurement method based on machine vision and deep learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120822 |