CN110146030A - Side slope surface DEFORMATION MONITORING SYSTEM and method based on gridiron pattern notation - Google Patents

Side slope surface DEFORMATION MONITORING SYSTEM and method based on gridiron pattern notation Download PDF

Info

Publication number
CN110146030A
CN110146030A CN201910542738.3A CN201910542738A CN110146030A CN 110146030 A CN110146030 A CN 110146030A CN 201910542738 A CN201910542738 A CN 201910542738A CN 110146030 A CN110146030 A CN 110146030A
Authority
CN
China
Prior art keywords
image
gridiron pattern
side slope
monitoring
depth
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
Application number
CN201910542738.3A
Other languages
Chinese (zh)
Inventor
阎宗岭
张小松
黄河
柴贺军
徐峰
谭玲
李海平
杜孟秦
杨光清
张瑶
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Merchants Chongqing Communications Research and Design Institute Co Ltd
Original Assignee
China Merchants Chongqing Communications Research and Design Institute Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by China Merchants Chongqing Communications Research and Design Institute Co Ltd filed Critical China Merchants Chongqing Communications Research and Design Institute Co Ltd
Priority to CN201910542738.3A priority Critical patent/CN110146030A/en
Publication of CN110146030A publication Critical patent/CN110146030A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
    • G01B11/03—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by measuring coordinates of points
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/16—Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/05—Geographic models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20164—Salient point detection; Corner detection

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Remote Sensing (AREA)
  • Computer Graphics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

A kind of side slope surface DEFORMATION MONITORING SYSTEM based on gridiron pattern notation provided by the invention, including gridiron pattern marker, image capture device and monitoring platform；Gridiron pattern marker is placed in side slope surface as monitoring point；Image capture device is mounted on side slope opposite, for shooting gridiron pattern marker；Monitoring platform includes image processing module and computing module；Image processing module is for carrying out image analysis, including carrying out Corner Detection to gridiron pattern mark object image, angle steel joint image coordinate carries out the three-dimensional reconstruction that Corresponding matching completes side slope surface, the depth image of gridiron pattern marker is obtained, the depth of field distance of gridiron pattern marker and image capture device is calculated；Computing module, with the depth of field distance of the template image of image capture device shooting and monitoring image, calculates shift value of the gridiron pattern marker relative to image capture device, completes the real-time monitoring of side slope surface deformation for calculating.

Description

Side slope surface DEFORMATION MONITORING SYSTEM and method based on gridiron pattern notation
Technical field
The present invention relates to the monitoring technical fields of side slope surface deformation, and in particular to a kind of side based on gridiron pattern notation Slope surface deformation monitors system and method.
Background technique
Currently, the monitoring of side slope surface deformation, general using the embedding sensor in side slope, the displacement of sensor is monitored Situation and then the deformation for calculating side slope surface；Or the space coordinate based on satellite positioning slope monitoring point is used, monitoring Space coordinate changes to calculate the deformation on side slope surface.But above system lay installation it is complex, while implement and Operation expense is higher.
A kind of existing Monitoring of Slope Deformation device and method based on computer vision use gridiron pattern as marker, It is taken pictures by video camera to gridiron pattern marker, the space coordinate of gridiron pattern marker is then restored using image processing techniques, The misalignment of space coordinate is calculated, and then monitors the deformation of side slope.But it is in the prior art when performing image processing, right Straight line intersection extraction algorithm is usually used in the Corner Detection of gridiron pattern marker.This algorithm inclines in gridiron pattern marker When rake angle, when such as more than 30 degree, it may appear that the problem of can not detecting angle point；Meanwhile when camera distortion coefficient is larger When, straight line will bend, and introduce large error, subsequent algorithm calibrates the error can be using a large amount of operation, to figure As the hardware performance requirements of processing equipment can improve, the operational efficiency and monitoring real-time of entire monitoring system also will affect.
Summary of the invention
For the defects in the prior art, the present invention provides a kind of side slope surface deformation monitoring based on gridiron pattern notation System and method, to solve the technical problems existing in the prior art.
A kind of side slope surface DEFORMATION MONITORING SYSTEM based on gridiron pattern notation provided by the invention, including gridiron pattern mark Object, image capture device and monitoring platform；Gridiron pattern marker is placed in side slope surface as monitoring point；Image capture device peace Mounted in side slope opposite, for shooting the template image and monitoring image of gridiron pattern marker, and by the template image and prison of shooting Altimetric image is transmitted to monitoring platform；
Monitoring platform includes image processing module and computing module, at the image of image capture device and the monitoring platform Reason module is connected；Image processing module carries out Corner Detection for carrying out image analysis, including to gridiron pattern mark object image Angle point image coordinate is obtained, angle steel joint image coordinate carries out the three-dimensional reconstruction that Corresponding matching completes side slope surface, obtains gridiron pattern The depth image of marker calculates the depth of field distance of gridiron pattern marker and image capture device；
Computing module is used to calculate separately the template image of image capture device shooting and the depth of field distance of monitoring image, and Whether the depth of field distance of judge templet image and the depth of field distance of monitoring image change, so that it is opposite to calculate gridiron pattern marker In the change in displacement value of image capture device.
Further, image processing module obtains the depth information of each pixel on gridiron pattern marker, with each pixel The arithmetic average of depth information is as depth of field distance.
Further, image processing module carries out edge detection with sobel operator to gridiron pattern marker, writes down edge picture The coordinate of element, carries out Corner Detection with improved SUSAN operator at edge pixel.
Further, SUSAN operator sub-pix Corner Detection Algorithm is improved, further includes being carried out using gray scale square gravity model appoach Sub-pix Corner character.
Further, image capture device carries out Image Acquisition using stereoscopic vision mode side slope surface.
Further, stereoscopic vision mode is binocular vision system.
A kind of monitoring method of the side slope surface DEFORMATION MONITORING SYSTEM based on gridiron pattern notation, which is characterized in that including Following steps:
S1. the side slope surface monitored to needs chooses dangerous point or potential deformation point, places gridiron pattern marker conduct Monitoring point；
S2. on the side slope opposite that needs monitor, the length direction along side slope to be monitored places image capture device；
S3. gridiron pattern marker is shot using image capture device, the gridiron pattern mark object image shot for the first time is as mould Plate image, and the template image of shooting is transferred to the image processing module in monitoring platform；
S4. image processing module carries out side slope three-dimensional reconstruction using the image of gridiron pattern marker；
S5. image capture device timing passes gridiron pattern marker shooting image as monitoring image, and by monitoring image The image processing module being defeated by monitoring platform obtains the depth image of gridiron pattern marker, obtains gridiron pattern marker and figure As the depth of field distance of acquisition equipment；
S6. the computing module of monitoring platform, with image capture device shooting template image and monitoring image the depth of field away from From whether changing, to calculate change in displacement value of the gridiron pattern marker relative to image capture device.
As shown from the above technical solution, beneficial effects of the present invention:
1. being placed in the gridiron pattern marker on side slope surface using image capture device shooting, obtained by the picture taken The depth image of gridiron pattern marker is taken, the depth of field distance of gridiron pattern marker and image capture device is calculated, with Image Acquisition The initial position depth of field distance of equipment shooting is used as reference, and depth of field distance when according to real-time monitoring calculates gridiron pattern marker Relative to the shift value of image capture device, to judge side slope surface deformation.Above-mentioned technical proposal is laid simply, at low cost It is honest and clean, it can be in all dangerous points of side slope or potential deformation point setting observation gridiron pattern marker；Depth of field distance is to pass through figure It is obtained as the depth information of pixel directly converts, the algorithm than calculating theorem in Euclid space geometric distance is simpler.
2. can avoid tradition SUSAN operator by improving SUSAN operator sub-pix Corner Detection Algorithm and obscure angle point and side The problem of edge, effectively detects correct angle point, due to only carrying out Corner Detection, operation speed near gridiron pattern marginal point Degree can greatly improve, and be very suitable to carry out on-line proving to image capture device with gridiron pattern, complete real-time monitoring；It uses Gray scale square gravity model appoach carries out sub-pix Corner character, may be implemented more accurately to demarcate image capture device, improves system Monitoring accuracy.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art Embodiment or attached drawing needed to be used in the description of the prior art are briefly described.In all the appended drawings, similar element Or part is generally identified by similar appended drawing reference.In attached drawing, each element or part might not be drawn according to actual ratio.
Fig. 1 is present invention monitoring system architecture schematic diagram.
Fig. 2 is monitoring method flow chart of the invention.
Appended drawing reference:
The first video camera of 1a-, the second video camera of 1b-, 2- image processing module, 3- computing module, 4- monitoring platform.
Specific embodiment
It is described in detail below in conjunction with embodiment of the attached drawing to technical solution of the present invention.Following embodiment is only used for Clearly illustrate technical solution of the present invention, therefore be only used as example, and cannot be used as a limitation and limit protection model of the invention It encloses.
It should be noted that unless otherwise indicated, technical term or scientific term used in this application should be this hair The ordinary meaning that bright one of ordinary skill in the art are understood.
Embodiment 1
As shown in Figure 1, the present invention provides a kind of side slope surface DEFORMATION MONITORING SYSTEM based on gridiron pattern notation, including chess Disk lattice marker, image capture device and monitoring platform；Gridiron pattern marker is placed in side slope surface as monitoring point；Image is adopted Collection equipment is mounted on side slope opposite, for shooting the template image and monitoring image of gridiron pattern marker, and by the template of shooting Image and monitoring image are transmitted to monitoring platform；
Monitoring platform includes image processing module and computing module, at the image of image capture device and the monitoring platform Reason module is connected；Image processing module carries out Corner Detection for carrying out image analysis, including to gridiron pattern mark object image Angle point image coordinate is obtained, angle steel joint image coordinate carries out the three-dimensional reconstruction that Corresponding matching completes side slope surface, obtains gridiron pattern The depth image of marker calculates the depth of field distance of gridiron pattern marker and image capture device；
Computing module is used to calculate separately the template image of image capture device shooting and the depth of field distance of monitoring image, and Whether the depth of field distance of judge templet image and the depth of field distance of monitoring image change, so that it is opposite to calculate gridiron pattern marker In the change in displacement value of image capture device.
The working principle of following side slope surface deformation monitoring system is described in detail:
To the side slope surface that needs monitor, dangerous point or potential deformation point are chosen, places gridiron pattern scaling board as prison Measuring point.Acrylic plate or glass plate can be used as substrate in gridiron pattern scaling board, has folded up chequered with black and white chess among substrate Disk case marker fixes son, can prevent rainwater or other materials from invading wet and pollution gridiron pattern in this way.Preferably, glass gridiron pattern is demarcated Plate is 100 X of outer dimension, 100 X 5mm, and grid size is 5 X 5mm, and the precision of images is 2 μm.
On the side slope opposite that needs monitor, video camera is placed as Image Acquisition along the length direction of side slope to be monitored and is set It is standby, 2 video cameras are preferably installed and constitute binocular vision system.The placement location of video camera, which is selected in, can make each monitoring point while locate In the coverage of two video cameras, video camera is preferably 8-12 meters apart from side slope.Monitoring platform is placed on any one camera shooting The centre of machine side or two video cameras；Video camera is connected with monitoring platform, and preferably communication carries out image The transmission of file.
The gridiron pattern marker shot using video camera, by the image transmitting of shooting to the image procossing mould in monitoring platform Block.Image processing module carries out side slope three-dimensional reconstruction, the specific steps of three-dimensional reconstruction using the image of gridiron pattern marker are as follows:
1, world coordinate system is transformed by camera according to Zhang Zhengyou gridiron pattern standardization using gridiron pattern mark object image Coordinate system, reconvert are finally transformed into image pixel coordinates system to image physical coordinates system.
2, the internal reference matrix A (dx, dy, r, u, v, f) of video camera is obtained, outer ginseng matrix [R | T].Wherein, in internal reference matrix, Dx and dy is the physical size of a pixel, and f is focal length, and r is the warping factor of image physical coordinates, and u and v are image origin phase For the offset in length and breadth as unit of pixel of optical center imaging point；Outer ginseng matrix is that world coordinate system is transformed into camera coordinates system Rotation R matrix and translation T matrix.
3, image processing module uses improvement SUSAN operator sub-pix Corner Detection to the gridiron pattern marker in image Algorithm carries out Corner Detection, realizes Corner character, converses angle point image coordinate.
4, Corresponding matching is carried out using angle point image coordinate, is converted into the three-dimensional of gridiron pattern marker world coordinate system and sits Mark, realizes the three-dimensional reconstruction of side slope.
Here is the related algorithm of three-dimensional reconstruction:
(a) Zhang Zhengyou gridiron pattern is demarcated
In above-mentioned formula (1):
World coordinate system is the coordinate system of user-defined three-dimensional world, in order to describe position of the object in real world It sets and is introduced into, unit m；
Camera coordinates system is the coordinate system established on camera, is defined to describe object space from the angle of camera, As one ring of centre for linking up world coordinate system and image/pixel coordinate system, unit m.
Image physical coordinates system is to describe projection of the object from camera coordinates system to image coordinate system during imaging Transmission relationship and introduce, the convenient coordinate further obtained under pixel coordinate system, unit m.
Image pixel coordinates system is introduced to describe the coordinate on the digital image of the picture point after image objects, is true Coordinate system where the information just read out of camera, unit are (number of pixels).
By above-mentioned formula algorithm, the image pixel that the world coordinates of gridiron pattern marker and video camera can be shot Coordinate associates, it is known that image pixel coordinates can extrapolate world coordinates.
(b) SUSAN operator sub-pix Corner Detection is improved
For the camera shooting application scenarios used online, if carrying out Corner Detection to entire image using SUSAN operator, Detecting speed can be slow, is not well positioned to meet requirement of the application on site to speed.Since angle point is included in image border In, it is possible to edge detection is carried out to image first with sobel operator, writes down the coordinate of edge pixel, then only to edge The pixel at place carries out SUSAN Corner Detection, can greatly reduce the operand of entire Corner Detection in this way.Here is sobel The algorithmic formula of operator:
In above-mentioned formula (2), GxRepresent the image detected through transverse edge, GyRepresent the image detected through longitudinal edge.
Then Corner Detection, algorithm principle are as follows: for ideal are carried out using improved SUSAN operator at edge pixel Its pixel grey scale of edge do not have centre symmetry, its pixel grey scale of undesirable angle point have certain centre symmetry, And ideal its pixel grey scale of angle point has complete centre symmetry；Its angle point of undesirable angle point is more sharp, central symmetry Property is better.
Algorithmic formula are as follows:
In above-mentioned formula (3), c is pixel coordinate, and I is pixel grey scale, and t is similarity threshold, preferably t=25；Then root The similar area of core value is calculated according to formula (4):
In formula (4), n is core value coordinate；
Initial angle point response is obtained further according to formula (5):
In above-mentioned formula (5), g is geometry threshold value, and g is preferably
Then the half of SUSAN gridiron pattern image pixel is successively searched for, its pixel about core point is found out, according to public affairs Formula (6) finds out the gray scale difference of the two
Δ I=I (x, y)-I (x ', y ') (6)
In above-mentioned formula (6), I (x, y) and I (x ', y ') are about the centrosymmetric grey scale pixel value of core point.
The gray scale symmetry D (x, y) of pixel (x, y) can be obtained in gray scale difference Δ I compared with threshold value d are as follows:
The gray scale symmetry summation of one half-pix of gridiron pattern image-region can be obtained to the gray scale pair of entire chessboard table images Title degree S (x0,y0):
It is based on image grayscale symmetry algorithm in this way, just completes to entire tessellated Corner Detection, obtains each angle point Image coordinate.In above-mentioned formula (8), M indicates whole region, preferably S=12.
(c) angle steel joint image coordinate carries out Corresponding matching
In actual monitoring, a certain gridiron pattern monitoring point of two video cameras in synchronization side slope is shot, should World coordinates of the monitoring point under world coordinate system is (x, y, z)；
In two video cameras, if wherein the corresponding camera coordinates system of the first video camera is O1-x1y1z1, corresponding image seat Mark system is O1-X1Y1, the focal length of the video camera is f1, monitoring point camera coordinates under camera coordinates system are (x1,y1,z1), image Coordinate is (X1,Y1)；
Defining the corresponding camera coordinates system of the second video camera is O2-x2y2z2, corresponding image coordinate system is O2-X2Y2, The focal length of the video camera is f2, monitoring point camera coordinates under camera coordinates system are (x2,y2,z2), image coordinate is (X2,Y2)；
Had according to algorithm:
Camera coordinates system O between two video cameras1-x1y1z1And O2-x2y2z2Between, space conversion matrix M=[R can be passed through | T] it indicates are as follows:
In above-mentioned formula (10),For the spin matrix between two camera coordinates systems,For the translation transformation vector of origin.
So, monitoring point such as a certain for any one spatial point, the point are sat in world coordinate system and two video camera cameras Inhomogeneous coordinate under mark system is x respectivelyw, x1, x2, then have
x1=R1xw+T1, x2=R2xw+T2, (11)
Eliminate xw, can obtainThen the R between two video cameras and T may be expressed as:
It is O for camera coordinates system again according to formula (9) and formula (10)1-x1y1z1In a certain spatial point, two camera shooting The corresponding relationship of point between machine image coordinate system are as follows:
Therefore, monitoring point may be expressed as: in the 3 d space coordinate of world's coordinate-system
In this way, being demarcated according to above-mentioned steps (a) Zhang Zhengyou gridiron pattern standardization to video camera, (b) using improvement SUSAN operator sub-pix Corner Detection Algorithm carries out Corner Detection to gridiron pattern marker, and (c) angle steel joint image coordinate carries out Corresponding matching just completes the three-dimensional reconstruction of side slope.
After the completion of image processing module rebuilds side slope three-dimensional, so that it may according to the threedimensional model on side slope surface and two The inside and outside parameter of video camera, the depth image in Lai Shengcheng slope table face.Depth image is comprising the surface with viewpoint scene object The image of distance dependent information, each pixel value in image be real space of the video camera apart from gridiron pattern marker away from From.
Generate the specific steps of depth image are as follows:
(a) the same gridiron pattern mark object image taken simultaneously using two video cameras, is obtained by Stereo Matching Algorithm Take disparity map
Stereo Matching Algorithm carries out matching cost calculating first, and weighted value is arranged according to the coordinate of pixel in image, Formula (15) can be used the weighted value w (x, y) of pixel (x, y) is arranged:
In above-mentioned formula (15), σxAnd σyFor width parameter, the shooting of two video cameras can be obtained respectively not by calculating With the weighted value w of picture1(x1,y1) and w2(x2,y2)。
Matching cost is calculated by formula (16) again:
In above-mentioned formula (16), function n is for calculating after pixel is converted to bit string data, wherein 1 number.
Then then directly original match cost is handled using Global Algorithm, uses the heat-supplied letter of formula (17) Number, to acquire the minimum value of energy, obtains the parallax value of each pixel.
E (d)=∑p∈RC(p,d)+∑p,q∈RP(p,d) (17)
In above-mentioned formula (17), ∑p∈RC (p, d) indicates the data item of energy function, means that the pixel only considers itself Parallax value tendency, do not consider the influence of other pixels neighborhood Nei, p indicates a pixel in image, R expression parallax value Range, C (p, d) indicate the matching cost when parallax of p point is d；∑p,q∈RP (p, d) indicates the smooth top of energy function, passes through Judge the discontinuity of parallax between adjacent pixel to constrain global energy function, p indicates the parallax of pixel, in d neighborhood region The parallax of pixel, as p=d, P is 0, and as p ≠ d, P is 1.
(b) depth map is calculated using disparity map
In above-mentioned formula (18), Z is the depth value in depth map, and straight line record of the b between two video cameras, f is to take the photograph Internal reference focal length in camera, d are the parallax value in disparity map.
In this way, setting the depth information of gridiron pattern marker as pi(xi,yi), gridiron pattern marker and image can be calculated Acquire the depth of field distance d of equipment:
After side slope surface deforms, for monitoring point gridiron pattern marker, in the Prototype drawing of initial position shooting Picture, and in the monitoring image of real-time monitoring position shooting, the depth of field distance d of this two images changed, by the depth of field away from The real-time monitoring of side slope surface deformation is completed in monitoring from d variation.
Embodiment 2
It advanced optimizes on the basis of embodiment 1, for improving SUSAN operator sub-pix Corner Detection Algorithm, also Including using gray scale square gravity model appoach to carry out sub-pix Corner character.
On the basis of embodiment 1, video camera can be carried out to more accurate calibration, so that image processing process information It is more accurate.Its realization principle are as follows: X-comers image is the symmetrical target of gray scale, and the intensity contrast of image is strong It is strong, it is possible to gray scale square gravity model appoach be taken to carry out sub-pix Corner character.
If the grey scale centre of gravity of angle point is (x0,y0)
In above-mentioned formula (20), W (i, j) is weight, takes W (i, j)=I2(i, j), M are to be calculated using SUSAN after improving The angle point field that son detects.
Embodiment 3
The present invention provides a kind of monitoring method of side slope surface DEFORMATION MONITORING SYSTEM based on gridiron pattern notation, including with Lower step:
S1. the side slope surface monitored to needs chooses dangerous point or potential deformation point, places gridiron pattern marker conduct Monitoring point；
S2. on the side slope opposite that needs monitor, the length direction along side slope to be monitored places image capture device；Preferably 2 video cameras are installed and constitute binocular vision system；
S3. gridiron pattern marker is shot using image capture device, the gridiron pattern mark object image shot for the first time is as mould Plate image, and the template image of shooting is transferred to the image processing module in monitoring platform；Preferably using wireless communication Mode is transmitted；
S4. image processing module carries out side slope three-dimensional reconstruction using the image of gridiron pattern marker, including uses Zhang Zhengyou Gridiron pattern standardization demarcates image capture device, using improvement SUSAN operator sub-pix Corner Detection Algorithm to chessboard Lattice marker carries out Corner Detection, and angle steel joint image coordinate carries out Corresponding matching；
S5. image capture device timing passes gridiron pattern marker shooting image as monitoring image, and by monitoring image The image processing module being defeated by monitoring platform obtains the depth image of gridiron pattern marker, obtains gridiron pattern marker and figure As the depth of field distance of acquisition equipment；
S6. the computing module of monitoring platform, with image capture device shooting template image and monitoring image the depth of field away from From whether changing, to calculate change in displacement value of the gridiron pattern marker relative to image capture device, side slope table is completed The real-time monitoring of face deformation.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution The range of scheme should all cover within the scope of the claims and the description of the invention.

Claims (7)

1. a kind of side slope surface DEFORMATION MONITORING SYSTEM based on gridiron pattern notation, it is characterised in that: including gridiron pattern marker, Image capture device and monitoring platform；The gridiron pattern marker is placed in side slope surface as monitoring point；Described image acquisition Equipment is mounted on side slope opposite, for shooting the template image and monitoring image of gridiron pattern marker, and by the Prototype drawing of shooting Picture and monitoring image are transmitted to monitoring platform；
The monitoring platform includes image processing module and computing module, and described image acquires the figure of equipment and the monitoring platform As processing module is connected；Described image processing module is carried out for carrying out image analysis, including to gridiron pattern mark object image Corner Detection obtains angle point image coordinate, and angle steel joint image coordinate carries out the three-dimensional reconstruction that Corresponding matching completes side slope surface, obtains The depth image of gridiron pattern marker is taken, the depth of field distance of gridiron pattern marker and image capture device is calculated；
The computing module is used to calculate separately the template image of image capture device shooting and the depth of field distance of monitoring image, and Whether the depth of field distance of judge templet image and the depth of field distance of monitoring image change, so that it is opposite to calculate gridiron pattern marker In the change in displacement value of image capture device.
2. a kind of side slope surface DEFORMATION MONITORING SYSTEM based on gridiron pattern notation according to claim 1, feature exist In: described image processing module obtains the depth information of each pixel on gridiron pattern marker, with each pixel depth information Arithmetic average is as depth of field distance.
3. a kind of side slope surface DEFORMATION MONITORING SYSTEM based on gridiron pattern notation according to claim 1, feature exist In, described image processing module carries out edge detection with sobel operator to gridiron pattern marker, the coordinate of edge pixel is write down, Corner Detection is carried out with improved SUSAN operator at edge pixel.
4. a kind of side slope surface DEFORMATION MONITORING SYSTEM based on gridiron pattern notation according to claim 3, feature exist In the improvement SUSAN operator sub-pix Corner Detection Algorithm further includes carrying out sub-pix angle using gray scale square gravity model appoach Point location.
5. a kind of side slope surface DEFORMATION MONITORING SYSTEM based on gridiron pattern notation according to claim 1, feature exist In: described image acquires equipment and carries out Image Acquisition using stereoscopic vision mode side slope surface.
6. a kind of side slope surface DEFORMATION MONITORING SYSTEM based on gridiron pattern notation according to claim 5, feature exist In: the stereoscopic vision mode is binocular vision system.
7. a kind of monitoring side of side slope surface DEFORMATION MONITORING SYSTEM based on gridiron pattern notation according to claim 1 Method, which comprises the following steps:
S1. dangerous point or potential deformation point are chosen in the side slope surface monitored to needs, place gridiron pattern marker as monitoring Point；
S2. on the side slope opposite that needs monitor, the length direction along side slope to be monitored places image capture device；
S3. gridiron pattern marker is shot using image capture device, the gridiron pattern mark object image shot for the first time is as Prototype drawing Picture, and the template image of shooting is transferred to the image processing module in monitoring platform；
S4. image processing module carries out side slope three-dimensional reconstruction using the image of gridiron pattern marker；
S5. image capture device timing is transferred to gridiron pattern marker shooting image as monitoring image, and by monitoring image Image processing module in monitoring platform obtains the depth image of gridiron pattern marker, show that gridiron pattern marker is adopted with image Collect the depth of field distance of equipment；
S6. the computing module of monitoring platform, the depth of field distance with the template image of image capture device shooting and monitoring image are No variation, to calculate change in displacement value of the gridiron pattern marker relative to image capture device.
CN201910542738.3A 2019-06-21 2019-06-21 Side slope surface DEFORMATION MONITORING SYSTEM and method based on gridiron pattern notation Pending CN110146030A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910542738.3A CN110146030A (en) 2019-06-21 2019-06-21 Side slope surface DEFORMATION MONITORING SYSTEM and method based on gridiron pattern notation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910542738.3A CN110146030A (en) 2019-06-21 2019-06-21 Side slope surface DEFORMATION MONITORING SYSTEM and method based on gridiron pattern notation

Publications (1)

Publication Number Publication Date
CN110146030A true CN110146030A (en) 2019-08-20

Family

ID=67596067

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910542738.3A Pending CN110146030A (en) 2019-06-21 2019-06-21 Side slope surface DEFORMATION MONITORING SYSTEM and method based on gridiron pattern notation

Country Status (1)

Country Link
CN (1) CN110146030A (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110515884A (en) * 2019-09-04 2019-11-29 西安工业大学 Construction site reinforcing bar range unit based on image analysis
CN112444209A (en) * 2019-08-27 2021-03-05 保定市天河电子技术有限公司 Steel rail displacement monitoring system and detection method based on machine vision
CN112697050A (en) * 2021-01-13 2021-04-23 南京宥安传感科技有限公司 Night side slope displacement monitoring system based on luminous body
CN113074804A (en) * 2021-04-06 2021-07-06 兰州理工大学 Long-distance all-weather structure vibration monitoring system
CN113324581A (en) * 2021-04-26 2021-08-31 北京中关村智连安全科学研究院有限公司 High-precision non-contact type slope dangerous rock monitoring and early warning method
CN113847905A (en) * 2021-08-19 2021-12-28 深圳特科动力技术有限公司 Three-dimensional binocular recognition slope detection method
CN116734754A (en) * 2023-05-10 2023-09-12 吉林大学 Landslide monitoring system and method
WO2023231098A1 (en) * 2022-05-30 2023-12-07 清华大学 Target tracking method and system, and robot
CN117190875A (en) * 2023-09-08 2023-12-08 重庆交通大学 Bridge tower displacement measuring device and method based on computer intelligent vision

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000228790A (en) * 1999-02-05 2000-08-15 Ntt Hokkaido Mobile Communications Network Inc Remote monitor system and event occurrence position estimate device
CN201627215U (en) * 2010-04-15 2010-11-10 中国科学院武汉岩土力学研究所 Testing device for measuring scoured deformation of side slope
CN102831751A (en) * 2012-09-04 2012-12-19 广东省公路管理局 Road high-dangerous slope monitoring method based on double-camera imaging technology
CN105551048A (en) * 2015-12-21 2016-05-04 华南理工大学 Space surface patch-based three-dimensional corner detection method
CN109579712A (en) * 2018-11-16 2019-04-05 天津大学 Based on the contactless high slope surface displacement monitoring method of unmanned plane and monitoring system

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000228790A (en) * 1999-02-05 2000-08-15 Ntt Hokkaido Mobile Communications Network Inc Remote monitor system and event occurrence position estimate device
CN201627215U (en) * 2010-04-15 2010-11-10 中国科学院武汉岩土力学研究所 Testing device for measuring scoured deformation of side slope
CN102831751A (en) * 2012-09-04 2012-12-19 广东省公路管理局 Road high-dangerous slope monitoring method based on double-camera imaging technology
CN105551048A (en) * 2015-12-21 2016-05-04 华南理工大学 Space surface patch-based three-dimensional corner detection method
CN109579712A (en) * 2018-11-16 2019-04-05 天津大学 Based on the contactless high slope surface displacement monitoring method of unmanned plane and monitoring system

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112444209A (en) * 2019-08-27 2021-03-05 保定市天河电子技术有限公司 Steel rail displacement monitoring system and detection method based on machine vision
CN110515884A (en) * 2019-09-04 2019-11-29 西安工业大学 Construction site reinforcing bar range unit based on image analysis
CN110515884B (en) * 2019-09-04 2023-02-03 西安工业大学 Construction site reinforcing bar range unit based on image analysis
CN112697050A (en) * 2021-01-13 2021-04-23 南京宥安传感科技有限公司 Night side slope displacement monitoring system based on luminous body
CN113074804A (en) * 2021-04-06 2021-07-06 兰州理工大学 Long-distance all-weather structure vibration monitoring system
CN113324581A (en) * 2021-04-26 2021-08-31 北京中关村智连安全科学研究院有限公司 High-precision non-contact type slope dangerous rock monitoring and early warning method
CN113847905A (en) * 2021-08-19 2021-12-28 深圳特科动力技术有限公司 Three-dimensional binocular recognition slope detection method
CN113847905B (en) * 2021-08-19 2024-02-02 深圳特科动力技术有限公司 Three-dimensional binocular recognition slope detection method
WO2023231098A1 (en) * 2022-05-30 2023-12-07 清华大学 Target tracking method and system, and robot
CN116734754A (en) * 2023-05-10 2023-09-12 吉林大学 Landslide monitoring system and method
CN116734754B (en) * 2023-05-10 2024-04-26 吉林大学 Landslide monitoring system and method
CN117190875A (en) * 2023-09-08 2023-12-08 重庆交通大学 Bridge tower displacement measuring device and method based on computer intelligent vision

Similar Documents

Publication Publication Date Title
CN110146030A (en) Side slope surface DEFORMATION MONITORING SYSTEM and method based on gridiron pattern notation
CN106441138B (en) The deformation monitoring method of view-based access control model measurement
CN110285793B (en) Intelligent vehicle track measuring method based on binocular stereo vision system
CN106595528B (en) A kind of micro- binocular stereo vision measurement method of telecentricity based on digital speckle
JP4245963B2 (en) Method and system for calibrating multiple cameras using a calibration object
CN109919911B (en) Mobile three-dimensional reconstruction method based on multi-view photometric stereo
AU2011312140B2 (en) Rapid 3D modeling
CN109544679A (en) The three-dimensional rebuilding method of inner wall of the pipe
CN107886547B (en) Fisheye camera calibration method and system
Zhu et al. Panoramic image stitching for arbitrarily shaped tunnel lining inspection
CN103852060B (en) A kind of based on single visual visible images distance-finding method felt
CN109544628B (en) Accurate reading identification system and method for pointer instrument
KR101759798B1 (en) Method, device and system for generating an indoor two dimensional plan view image
CN113240747B (en) Outdoor structure vibration displacement automatic monitoring method based on computer vision
CN111192235A (en) Image measuring method based on monocular vision model and perspective transformation
CN104318604A (en) 3D image stitching method and apparatus
CN102997891A (en) Device and method for measuring scene depth
CN108362205B (en) Space distance measuring method based on fringe projection
CN106971408A (en) A kind of camera marking method based on space-time conversion thought
CN109325981A (en) Based on the microlens array type optical field camera geometrical parameter calibration method for focusing picture point
CN109341668A (en) Polyphaser measurement method based on refraction projection model and beam ray tracing method
CN109974659A (en) A kind of embedded range-measurement system based on binocular machine vision
CN112348775A (en) Vehicle-mounted all-round-looking-based pavement pool detection system and method
CN109974618A (en) The overall calibration method of multisensor vision measurement system
CN109035343A (en) A kind of floor relative displacement measurement method based on monitoring camera

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20190820