CN117218301B - Elevator traction sheave groove reconstruction method and system based on multi-channel stereoscopic vision - Google Patents
Elevator traction sheave groove reconstruction method and system based on multi-channel stereoscopic vision Download PDFInfo
- Publication number
- CN117218301B CN117218301B CN202311482560.0A CN202311482560A CN117218301B CN 117218301 B CN117218301 B CN 117218301B CN 202311482560 A CN202311482560 A CN 202311482560A CN 117218301 B CN117218301 B CN 117218301B
- Authority
- CN
- China
- Prior art keywords
- traction sheave
- code
- camera
- groove
- traction
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000003384 imaging method Methods 0.000 claims abstract description 43
- 238000001514 detection method Methods 0.000 claims abstract description 30
- 238000005299 abrasion Methods 0.000 claims abstract description 19
- 230000000007 visual effect Effects 0.000 claims abstract description 15
- 238000005259 measurement Methods 0.000 claims abstract description 14
- 238000000691 measurement method Methods 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000013519 translation Methods 0.000 claims description 11
- 238000010586 diagram Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000007547 defect Effects 0.000 abstract description 4
- 239000013598 vector Substances 0.000 description 4
- 239000004033 plastic Substances 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000000465 moulding Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B50/00—Energy efficient technologies in elevators, escalators and moving walkways, e.g. energy saving or recuperation technologies
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a multi-channel stereoscopic vision-based elevator traction sheave groove reconstruction method and system, comprising the following steps: constructing a multi-channel stereoscopic vision camera network, wherein the camera network comprises a first camera and a second camera, the first camera is used for acquiring traction sheave images, and the second camera is used for acquiring images of marking positions of traction sheaves; marking the real-time rotation position of the traction sheave through the encoding strip; three-dimensional information of points on the traction sheave groove is obtained through a visual measurement method, a complete traction sheave groove image is obtained according to the imaging time and the angle relation of the encoding strip, and three-dimensional reconstruction is carried out on the traction sheave groove. The three-dimensional reconstruction of the traction sheave is realized by constructing a multi-camera network and designing a coding mark, so that the accurate measurement of the abrasion loss of the traction sheave is finished, and the accurate and efficient detection of the defect of the traction sheave is realized.
Description
Technical Field
The invention belongs to the technical field of machine vision detection, and relates to a multi-channel stereoscopic vision-based elevator traction sheave groove reconstruction method and system.
Background
The elevator is used as one of indispensable special traffic facilities in high-rise buildings, can effectively improve the flow efficiency of passengers, saves a great deal of time and physical strength, and greatly facilitates the communication of people and the transportation of materials. The traction sheave is an important component of an elevator traction system, and the traction machine provides driving force for the up-and-down movement of an elevator car through friction force between a sheave groove of the traction sheave and a steel wire rope. However, in the long-term running process of the elevator, the traction sheave is easily worn due to the influences of factors such as uneven tension of a steel wire rope, overlarge assembly error and the like, noise and vibration are generated when the elevator runs, accidents such as sliding of the elevator and pier bottom even occur when the elevator is serious, and personal safety of passengers is threatened.
At present, the three-dimensional size detection method of the wheel groove of the elevator traction wheel mainly comprises the following steps: visual method, angle ruler and feeler gauge method, plasticine or plastic glue method, gauge plug type tool measuring method, special depth gauge checking method, acoustic emission judging method, laser displacement non-contact detection method, structured light non-contact detection method, etc. The visual method and the angle square and feeler gauge method are traditional detection methods, and mainly depend on experience, and the plasticine or plastic rubber method is influenced by the molding time and molding state of the plasticine and plastic rubber, so that the problems of low detection precision, low efficiency and the like exist. The plug-gauge tool measurement method and the special depth gauge inspection method are not strong in universality and cannot detect all feature sizes. The acoustic emission judgment method is mainly used for online evaluation and lacks reliability. The laser displacement non-contact detection method and the structured light non-contact detection method have high detection precision, but the fixture is inconvenient to install and has low detection efficiency.
Application number 2021104901488 discloses a machine vision-based elevator traction sheave wear level characterization method and system, wherein a target image to be detected is obtained, and a target rope groove contour image is extracted; fitting the upper boundary and the lower boundary of the target rope groove contour image by adopting a simulated annealing algorithm, searching an optimal threshold value, and fitting the traction sheave groove image boundary; for the unavoidable measurement shielding problem, a traction sheave mathematical model is established, the result is compensated, and the measurement result is ensured to be accurate. The method is obtained through image fitting, and is large in calculated amount and limited in precision.
Disclosure of Invention
The invention aims to provide a multi-channel stereoscopic vision-based elevator traction sheave groove reconstruction method and system, wherein three-dimensional reconstruction of a traction sheave is realized by constructing a multi-camera network and designing coding marks, so that accurate measurement of the abrasion loss of the traction sheave is completed, and accurate and efficient traction sheave defect detection is realized.
The technical solution for realizing the purpose of the invention is as follows:
a multi-channel stereoscopic vision-based elevator traction sheave groove reconstruction method comprises the following steps:
s01: constructing a multi-channel stereoscopic vision camera network, wherein the camera network comprises a first camera and a second camera, the first camera is used for acquiring traction sheave images, and the second camera is used for acquiring images of marking positions of traction sheaves;
s02: marking the real-time rotation position of the traction sheave through the encoding strip;
s03: three-dimensional information of points on the traction sheave groove is obtained through a visual measurement method, a complete traction sheave groove image is obtained according to the imaging time and the angle relation of the encoding strip, and three-dimensional reconstruction is carried out on the traction sheave groove.
In a preferred technical scheme, the step S03 further includes, according to the pixel three-dimensional coordinate data obtained by visual measurement, finally forming a complete traction sheave three-dimensional structure.
In the preferred technical scheme, after the three-dimensional structure of the traction sheave is obtained, generating standard three-dimensional information of the traction sheave according to the structural data of the traction sheave to be detected, and calculating the abrasion loss：
Wherein,、/>coordinate rotation and translation matrices, respectively, +.>For the three-dimensional coordinate data set obtained, +.>Is a measured three-dimensional coordinate data set.
In the preferred technical scheme, the code bar consists of a long straight line and a short straight line which respectively represent binary 0 and 1, and the code direction is from the edge of the traction sheave close to the axis value of the traction sheave, and the code value of one code barThe method comprises the following steps:
wherein,is the position where a symbol is located, +.>Is the number of coded bits.
In a preferred technical solution, the step S02 further includes extracting and decoding the encoding strip, and the method includes:
extracting the code bar by using a straight line detection method according to the profile diagram of the side surface of the traction sheave, and obtaining a point set of the traction sheave code barThe method comprises the following steps:
wherein,coding bit number for coding strip, < >>For the number of code bars +.>For indexing of code bars->Index for symbol in one code strip, < >>、/>Respectively, the horizontal and vertical coordinate sets of the pixels of the code strip,>i.e. < th->The>A set of pixel points of each code element line segment;
length of each symbol line segmentThe calculation was performed using the following formula:
obtaining the corresponding code of each code element according to the length of each bar code element segment;
randomly selecting two code bars to obtain their end point coordinates, respectively setting them as、/>And、/>firstly judging whether two straight lines are collinear or not, if so, discarding one of the two straight lines and then reselecting the two straight lines;
equation combining two straight lines to obtain intersection point of two code bars：
The intersection point of the two straight lines is the center point of the side surface of the traction sheave, and the end point which is closer to the center point is the coding starting point of the current coding table;
and according to the calculation result of the code element length and the coding start point, decoding the code strip is realized.
In a preferred technical solution, the method for obtaining three-dimensional information of the point on the sheave groove of the traction sheave in step S03 includes:
for cameras、/>The binocular stereo vision system is provided with a point on the groove of the traction sheave>The images formed in the two cameras are +.>And->Their pixel coordinates are +.>And->According to the camera imaging principle +.>、/>And (4) point->The following relationship exists:
wherein,、/>camera respectively->、/>Is an internal reference matrix of->、/>Camera respectively->、/>Rotation parameter matrix of>、/>Translation parameter matrix of camera respectively, +.>For->Coordinates in the reference coordinate system, +.>、/>The ratio coefficients of the two-phase camera imaging are obtained by solving:
wherein,，/>respectively is a matrix->、/>Middle->Line->Column element (s)/(S)>，/>Is vector->，/>Middle->An element;
obtaining a pointThe coordinates in the reference coordinate system are:
wherein the intermediate variable。
In a preferred technical solution, the method for three-dimensionally reconstructing the sheave groove of the traction sheave in step S03 includes:
when the traction wheel is imaged, firstly, calculating the included angle between each coding strip and the horizontal direction：
Wherein,for indexing of code bars->、/>、/>And->Two end point coordinates of one code bar are respectively, when a first camera images, a second camera synchronously images the side face of the traction sheave attached with the code bar, and the position of an imaged picture in the integral structure of the traction sheave is determined according to the direction of each code bar;
let the starting time of the image beAt this time, the included angle between the code bar with the code value of 0 and the horizontal direction is recorded>The angle is a reference angle for imaging the traction sheave groove;
imaging each frame of traction sheave grooveThe following structural representation is used:
wherein,coding bar representing a code value of 0 is +.>Angle of moment relative to horizontal, +.>Representation and +.>The imaging distance of the traction sheave groove is the nearest horizontal direction included angle of the coding strip at any time, +.>For indexing of code bars->Is->And (5) dragging pixel data of a region of interest in imaging the wheel groove of the wheel at the moment.
The invention also discloses an elevator traction sheave groove reconstruction system based on multi-channel stereoscopic vision, which comprises the following steps:
the multi-channel stereoscopic vision camera network construction module is used for constructing a multi-channel stereoscopic vision camera network, the camera network comprises a first camera and a second camera, the first camera is used for acquiring traction sheave images, and the second camera is used for acquiring images of marked positions of the traction sheaves;
the encoding strip decoding module marks the real-time rotation position of the traction wheel through the encoding strip;
and the traction wheel groove three-dimensional reconstruction module is used for obtaining three-dimensional information of points on the traction wheel groove through a visual measurement method, obtaining a complete traction wheel groove image according to the imaging moment and the angle relation of the encoding strip, and carrying out three-dimensional reconstruction on the traction wheel groove.
The invention also discloses a multi-channel stereoscopic vision-based elevator traction sheave abrasion loss detection system, which comprises the elevator traction sheave groove reconstruction system and an abrasion loss detection module, wherein the abrasion loss detection module is used for finally forming a complete traction sheave three-dimensional structure according to pixel three-dimensional coordinate data obtained by vision measurement; generating standard traction wheel three-dimensional information according to the structural data of the traction wheel to be tested, and calculating the abrasion loss：
Wherein,、/>coordinate rotation and translation matrices, respectively, +.>For the three-dimensional coordinate data set obtained, +.>Is a measured three-dimensional coordinate data set.
The invention also discloses a computer storage medium, on which a computer program is stored, which when executed realizes the elevator traction sheave groove reconstruction method based on multi-channel stereoscopic vision.
Compared with the prior art, the invention has the remarkable advantages that:
according to the invention, three-dimensional reconstruction of the traction sheave is realized by constructing a multi-camera network and designing the coding mark, so that accurate measurement of the abrasion loss of the traction sheave is completed, and accurate and efficient detection of the traction sheave defect is realized. The accurate three-dimensional measurement and the real-time monitoring of the abrasion loss of the traction sheave of the elevator are realized, so that the abrasion, deformation and the like of the traction sheave are timely found and timely processed, the operation safety and reliability of the elevator can be effectively improved, and the elevator traction sheave has a wide market application prospect.
Drawings
Fig. 1 is a schematic diagram of a traction sheave multi-channel stereoscopic camera network and a coding strip structure;
FIG. 2 is a schematic diagram of a code strip;
FIG. 3 is a schematic diagram of code strip extraction and decoding;
FIG. 4 is a schematic view of the imaged and interested region of the traction sheave after perspective transformation;
FIG. 5 is a schematic diagram of a traction sheave groove imaging process;
fig. 6 is a schematic diagram of traction sheave wear and the difference between the measured and standard coordinates.
Detailed Description
The principle of the invention is as follows: the three-dimensional reconstruction of the traction sheave is realized by constructing a multi-camera network and designing a coding mark, so that the accurate measurement of the abrasion loss of the traction sheave is finished, and the accurate and efficient detection of the defect of the traction sheave is realized.
Example 1:
as shown in fig. 1, the method for reconstructing the wheel groove of the traction sheave of the elevator based on multi-channel stereoscopic vision comprises the following steps:
s01: constructing a multi-channel stereoscopic vision camera network, wherein the camera network comprises a first camera and a second camera, the first camera is used for acquiring an image of the traction sheave, and the second camera is used for acquiring an image of the marking position of the traction sheave;
s02: marking the real-time rotation position of the traction sheave through the encoding strip;
s03: three-dimensional information of points on the traction sheave groove is obtained through a visual measurement method, a complete traction sheave groove image is obtained according to the imaging time and the angle relation of the encoding strip, and three-dimensional reconstruction is carried out on the traction sheave groove.
In a preferred embodiment, step S03 further includes, according to the pixel three-dimensional coordinate data obtained by visual measurement, finally forming a complete traction sheave three-dimensional structure.
In a preferred embodiment, the method further comprises generating standard traction wheel three-dimensional information according to structural data of the traction wheel to be tested, and calculating the abrasion loss：
Wherein,、/>coordinate rotation and translation matrices, respectively, +.>For the three-dimensional coordinate data set obtained, +.>Is a measured three-dimensional coordinate data set.
In a preferred embodiment, the code bar is composed of long and short straight lines, representing binary 0 and 1, respectively, in the coding directionFrom the edge of the traction sheave near the axis of the traction sheave, the code value of a code stripThe method comprises the following steps:
wherein,is the position where a symbol is located, +.>Is the number of coded bits.
In a preferred embodiment, step S02 further includes extracting and decoding the encoded slice, and the method includes:
extracting the code bar by using a straight line detection method according to the profile diagram of the side surface of the traction sheave, and obtaining a point set of the traction sheave code barThe method comprises the following steps:
wherein,coding bit number for coding strip, < >>For the number of code bars +.>For indexing of code bars->Index for symbol in one code strip, < >>、/>Respectively, the horizontal and vertical coordinate sets of the pixels of the code strip,>i.e. < th->The>A set of pixel points of each code element line segment;
length of each symbol line segmentThe calculation was performed using the following formula:
obtaining the corresponding code of each code element according to the length of each bar code element segment;
randomly selecting two code bars to obtain their end point coordinates, respectively setting them as、/>And、/>firstly judging whether two straight lines are collinear or not, if so, discarding one of the two straight lines and then reselecting the two straight lines;
equation combining two straight lines to obtain intersection point of two code bars：
The intersection point of the two straight lines is the center point of the side surface of the traction sheave, and the end point which is closer to the center point is the coding starting point of the current coding table;
and according to the calculation result of the code element length and the coding start point, decoding the code strip is realized.
In a preferred embodiment, the method for obtaining three-dimensional information of the points on the sheave groove of the traction sheave in step S03 includes:
for cameras、/>The binocular stereo vision system is provided with a point on the groove of the traction sheave>The images formed in the two cameras are +.>And->Their pixel coordinates are +.>And->According to the camera imaging principle +.>、/>And (4) point->The following relationship exists:
wherein,、/>camera respectively->、/>Is an internal reference matrix of->、/>Camera respectively->、/>Rotation parameter matrix of>、/>Translation parameter matrix of camera respectively, +.>For->The coordinates in the reference coordinate system are such that,、/>respectively two camera lensAnd solving the proportionality coefficient of the image to obtain:
wherein,，/>respectively is a matrix->、/>Middle->Line->Column element (s)/(S)>，/>Is vector->，/>Middle->An element;
obtaining a pointThe coordinates in the reference coordinate system are:
wherein the intermediate variable。
In a preferred embodiment, the method for three-dimensionally reconstructing the groove of the traction sheave in step S03 includes:
when the traction wheel is imaged, firstly, calculating the included angle between each coding strip and the horizontal direction：
Wherein,for indexing of code bars->、/>、/>And->Two end point coordinates of one code bar are respectively, when a first camera images, a second camera synchronously images the side face of the traction sheave attached with the code bar, and the position of an imaged picture in the integral structure of the traction sheave is determined according to the direction of each code bar;
let the starting time of the image beAt this time, the included angle between the code bar with the code value of 0 and the horizontal direction is recorded>The angle is a reference angle for imaging the traction sheave groove;
imaging each frame of traction sheave grooveThe following structural representation is used:
wherein,coding bar representing a code value of 0 is +.>Angle of moment relative to horizontal, +.>Representation and +.>The imaging distance of the traction sheave groove is the nearest horizontal direction included angle of the coding strip at any time, +.>For indexing of code bars->Is->And (5) dragging pixel data of a region of interest in imaging the wheel groove of the wheel at the moment.
In another embodiment, a computer storage medium has a computer program stored thereon, which when executed implements the above-described multi-channel stereoscopic vision-based elevator traction sheave groove reconstruction method.
In yet another embodiment, an elevator traction sheave reconstruction system based on multi-channel stereoscopic vision, comprising:
the multi-channel stereoscopic vision camera network construction module is used for constructing a multi-channel stereoscopic vision camera network, and the camera network comprises a first camera and a second camera;
the encoding strip decoding module marks the real-time rotation position of the traction wheel through the encoding strip;
and the traction wheel groove three-dimensional reconstruction module is used for obtaining three-dimensional information of points on the traction wheel groove through a visual measurement method, obtaining a complete traction wheel groove image according to the imaging moment and the angle relation of the encoding strip, and carrying out three-dimensional reconstruction on the traction wheel groove.
In still another embodiment, the elevator traction sheave wear detection system based on multi-channel stereoscopic vision comprises the elevator traction sheave groove reconstruction system, and further comprises a wear detection module, wherein the wear detection module is used for finally forming a complete traction sheave three-dimensional structure according to pixel three-dimensional coordinate data obtained through vision measurement; generating standard traction wheel three-dimensional information according to the structural data of the traction wheel to be tested, and calculating the abrasion loss：
Wherein,、/>coordinate rotation and translation matrices, respectively, +.>For the three-dimensional coordinate data set obtained, +.>Is a measured three-dimensional coordinate data set.
Specifically, the following description will be given by taking a preferred embodiment as an example, and the working procedure of the elevator traction sheave wear detection system based on multi-channel stereoscopic vision is as follows:
the method specifically comprises the following steps:
step one: multi-channel stereoscopic vision images the elevator traction sheave.
Step 11: construction of a multichannel stereoscopic camera network.
In order to carry out accurate omnibearing three-dimensional reconstruction on the abrasion loss of the traction sheave, a traction sheave multichannel stereoscopic vision camera network is established, and the network consists of 3 cameras, wherein 2 cameras are symmetrically distributed on two sides of the center line of a wheel track of the traction sheave and are marked as、/>In particular, camera->、/>A binocular stereoscopic vision system can be composed. In addition, 1 machine is positioned at one side of the traction sheave, the optical axis is coincident with the axis of the traction sheave, and is marked as +.>. In the camera network, ++>、/>Imaging and three-dimensional reconstruction of the groove of the traction sheave are responsible for,/->The traction sheave rotation position is determined by imaging the side marks of the traction sheave, and the multi-channel stereoscopic camera network structure of the traction sheave is shown in fig. 1.
The traction sheave is round, no special mark exists on the surface of a sheave groove, and the imaging similarity in a camera is high when the traction sheave with good quality rotates, so that the camera is powered on、/>It is not possible to determine whether the traction sheave is in a state of rotation, rest, rotation angle, etc. by itself only, and thus it is also difficult to construct a complete three-dimensional structure of the traction sheave. Therefore, the invention designs the code bars which are convenient to identify and are used for marking the real-time rotation position of the traction sheave, each code bar consists of a long straight line and a short straight line, which respectively represent binary 0 and 1, and the code direction is from the position close to the axis of the traction sheave to the edge of the traction sheave. At the same time, camera->、/>When imaging the traction sheave, only a certain surface range of the traction sheave can be covered, and the three-dimensional structure of the traction sheave needs to be obtained by a mode of splicing a plurality of images, so that a plurality of encoding bars are needed to determine the relation between the image formed by a camera and the integral structure of the traction sheave, as shown in fig. 2.
Step 12: decoding of the encoded strip.
The coding strip designed by the invention consists of a long straight line and a short straight line, which respectively represent binary 0 and 1, and the coding direction is from the position close to the traction wheel axis value traction wheel edge. Can be set as many codes according to the requirement, and the number of the codes is set asThe code value of one code bar +.>Is calculated as follows:
（1）
wherein the method comprises the steps ofIs where one symbol is located.
To obtain codingStrip, first using cameraImaging the side surface of the traction sheave, and processing the side surface of the traction sheave by methods such as image denoising, binarization, edge detection and the like to obtain a profile diagram of the side surface of the traction sheave. The encoding strip is then extracted from the image using a hough straight line detection method. The principle of the Hough straight line detection method is as follows:
（2）
wherein,for the distance of the origin of coordinates from the straight line, +.>Is the angle between the normal line of the straight line and the abscissa, +.>、/>Respectively the abscissa of a point on a straight line, +.>And->I.e. a parameter of a straight line. A point in the image space corresponds to a straight line in the parameter space, so that the collinear point in the image space and the corresponding straight lines in the parameter space finally meet at a point, and the shop coordinate is +.>. Straight lines in the image can be detected according to this principle. Let the point set of the traction sheave code strip obtained by straight line detection be +>It is expressed as:
（3）
wherein,coding bit number for coding strip, < >>For the number of code bars +.>For indexing of code bars->Index for symbol in one code strip, < >>、/>Respectively, the horizontal and vertical coordinate sets of the pixels of the code strip,>i.e. < th->The>And the pixel points of the code element line segments are assembled on the horizontal and vertical coordinates.
Length of each symbol line segmentThe calculation can be performed using the following formula:
（4）
after the length of each bar code element segment is obtained, the corresponding code of each code element can be determined according to the length of the bar code element segment. Is thatThe code value of each code bar is obtained, and the coding direction is also needed to be judged at the moment. Randomly selecting two code bars to obtain their end point coordinates, respectively setting them as、/>And->、/>. Firstly, judging whether two straight lines are collinear or not, if so, discarding one straight line, and then, reselecting the straight line, wherein the method for judging the collinear uses a vector cross product shown in the formula (5), and the vector cross product is a concept in a three-dimensional space, so that vectors of the two straight lines are expanded to be three-dimensional, and the third bit value is 0. The two lines are illustrated to be collinear when the cross product of the two vectors is equal to 0. However, since there is an error in the actual situation of less than or equal to a very small threshold +.>When two straight lines are illustrated as collinear.
（5）
The intersection point of two encoding bars can be obtained by using the equation of two simultaneous straight linesAs shown in formula (6). The intersection point of the two straight lines is the center point of the side surface of the traction sheave, and the end point which is closer to the center point is the coding start point of the current coding table.
（6）
And according to the calculation result of the code element segment length and the coding starting point, decoding of the code strip can be realized. The code strip extraction and decoding is shown in fig. 3.
Step two: three-dimensional reconstruction of the sheave grooves of the traction sheave.
Step 21: and acquiring three-dimensional information of the point by a visual measurement method.
For cameras、/>The binocular stereo vision system is provided with a point on the groove of the traction sheave>The images formed in the two cameras are +.>And->Their pixel coordinates are +.>And->According to the camera imaging principle +.>、/>And (4) point->The following relationship exists:
（7）
wherein,、/>camera respectively->、/>Is an internal reference matrix of->、/>Camera respectively->、/>Rotation parameter matrix of>、/>Translation parameter matrix of camera respectively, +.>、/>、/>、/>、/>、/>And (5) calibrating by a camera.For->Coordinates in the reference coordinate System +.>，/>、/>The scaling coefficients of the two-phase camera imaging, respectively. Solving the above formula can obtain: /> （8）
Wherein,，/>respectively is a matrix->、/>Middle->Line->Column element (s)/(S)>，/>Is vector->，Middle->The elements. From the above, the point can be found>The coordinates in the reference coordinate system are:
（9）
wherein:
（10）
step 22: imaging the three-dimensional structure of the traction sheave groove.
Due to the perspective transformation of the camera, the imaging of the mutually parallel grooves in the camera is no longer parallel straight lines, but curves with a certain radian, as shown in fig. 4. Therefore, in order to improve the precision and quality of three-dimensional reconstruction, the invention sets a region of interest with a certain size for imaging the traction sheave, wherein the region is rectangular and has a heightEmpirically set to 0.3 times the sheave diameter as shown in fig. 4. The arrangement of the region of interest not only can improve the accuracy of three-dimensional reconstruction, but also greatly reduces the data volume to be processed and improves the reconstruction speed.
When the traction wheel is imaged, firstly, calculating the included angle between each coding strip and the horizontal directionThe calculation method is shown in the formula (11).
（11）
Wherein,、/>、/>and->Two end coordinates of a code bar, respectively, ">Is the index of the code strip. When camera->、/>During imaging, camera->The side surface of the traction sheave attached with the coding bars is imaged synchronously, and the position of an imaged picture in the integral structure of the traction sheave can be determined according to the direction of each coding bar.
Let the starting time of the image beAt this time, the included angle between the code bar with the code value of 0 and the horizontal direction is recorded>This angle is recorded as the reference angle for imaging the sheave grooves of the traction sheave.
Imaging each frame of traction sheave groove in the inventionThe following structural representation is used: />
（12）
Wherein,coding bar representing a code value of 0 is +.>Angle of moment relative to horizontal, +.>Representation and +.>The imaging distance of the traction sheave groove is the nearest horizontal direction included angle of the coding strip at any time, +.>For indexing of code bars->Is->And (5) dragging pixel data of a region of interest in imaging the wheel groove of the wheel at the moment. />For marking the position of a frame of image in the overall construction of the traction sheave,/for the traction sheave>For error determination and fine tuning thereof. The process of imaging the traction sheave groove according to the method is shown in fig. 5, a complete traction sheave groove image can be finally obtained according to the imaging time and the angle relation of the encoding strip, and then a complete traction sheave three-dimensional structure is finally obtained according to pixel three-dimensional coordinate data obtained through visual measurement.
Step three: and detecting the abrasion of the traction sheave of the elevator.
After three-dimensional structural data of the elevator traction sheave are obtained, CAD or other computer aided design software is first used to generate standard three-dimensional information of the traction sheave according to the structural data of the traction sheave to be tested, and the obtained three-dimensional coordinate data set is set asThree-dimensional coordinate data set measured by the present invention +.>. First, the wear amount +.>：
（13）
Wherein the method comprises the steps of、/>For the coordinate rotation and translation matrices, respectively, it acts as +.>Reference coordinate system and->Unifying. />Is a set of differences, when +.>When the sum of the median values is within a certain range, this indicates that the traction sheave is less worn. At the same time, in order to increase the level of monitoring of wear, by calculating +.>According to the magnitude of the differential value in the sequence, the point of greater wear can be located as shown in fig. 6. After the point position with larger abrasion loss is obtained, the point position can be detected in real time in a key way, and potential safety hazards can be found in time.
Table 1 shows the errors of the specification parameters and the standard parameters of the traction sheave portion measured by the present invention, wherein the diameter of the measured traction sheave is 400mm and the pitch of the sheave groove is 16mm. As can be seen from Table 1, the average error of the measured diameter and the wheel groove pitch is smaller than 0.11mm, and the measuring precision is higher.
Table 1 traction sheave three-dimensional reconstruction error table
In addition, 3 mark points are arranged in the traction sheave groove area, imaging is carried out by using the method and three-dimensional reconstruction is carried out, a reference coordinate system is established by taking the center of the traction sheave axle as an origin, the X axis is the central axis of the traction sheave, and the Z axis is a main camera (a slave camera、/>Designated in (a) optical axis, the Y-axis is parallel to the traction sheave side and perpendicular to the Z-axis. The error between the obtained marker point coordinates and the standard coordinates is shown in table 2.
Table 2 error table for three-dimensional reconstruction of marker points
It can be seen that the method of the invention has higher accuracy for three-dimensional reconstruction of spatial points.
The foregoing examples are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the foregoing examples, and any other changes, modifications, substitutions, combinations, and simplifications that do not depart from the spirit and principles of the present invention should be made therein and are intended to be equivalent substitutes within the scope of the present invention.
Claims (9)
1. The elevator traction sheave groove reconstruction method based on multi-channel stereoscopic vision is characterized by comprising the following steps of:
s01: constructing a multi-channel stereoscopic vision camera network, wherein the camera network comprises a first camera and a second camera, the first camera is used for acquiring traction sheave images, and the second camera is used for acquiring images of marking positions of traction sheaves;
s02: marking the real-time rotation position of the traction sheave through the encoding strip; the method for extracting and decoding the encoding strip comprises the following steps:
extracting the code bar by using a straight line detection method according to the profile diagram of the side surface of the traction sheave, and obtaining a point set of the traction sheave code barThe method comprises the following steps:
，
wherein,coding bit number for coding strip, < >>For the number of code bars +.>For indexing of code bars->Index for symbol in one code strip, < >>、/>Respectively, the horizontal and vertical coordinate sets of the pixels of the code strip,>i.e. < th->The>A set of pixel points of each code element line segment;
length of each symbol line segmentThe calculation was performed using the following formula:
，
obtaining the corresponding code of each code element according to the length of each bar code element segment;
randomly selecting two code bars to obtain their end point coordinates, respectively setting them as、/>And->、Firstly judging whether two straight lines are collinear or not, if so, discarding one of the two straight lines and then reselecting the two straight lines;
equation combining two straight lines to obtain intersection point of two code bars：
，
The intersection point of the two straight lines is the center point of the side surface of the traction sheave, and the end point which is closer to the center point is the coding starting point of the current coding table;
according to the calculated result of the code element segment length and the coding starting point, decoding the code strip is realized;
s03: three-dimensional information of points on the traction sheave groove is obtained through a visual measurement method, a complete traction sheave groove image is obtained according to the imaging time and the angle relation of the encoding strip, and three-dimensional reconstruction is carried out on the traction sheave groove.
2. The method for reconstructing the sheave groove of the elevator traction sheave based on multi-channel stereoscopic vision according to claim 1, wherein the step S03 further comprises, according to the pixel three-dimensional coordinate data obtained by visual measurement, finally forming a complete three-dimensional structure of the traction sheave.
3. The method for reconstructing a sheave groove of an elevator traction sheave based on multi-channel stereoscopic vision according to claim 2, further comprising, after obtaining a three-dimensional structure of the traction sheave, generating standard three-dimensional information of the traction sheave according to structural data of the traction sheave to be measured, and calculating an abrasion loss：
，
Wherein,、/>coordinate rotation and translation matrices, respectively, +.>For the three-dimensional coordinate data set obtained, +.>Is a measured three-dimensional coordinate data set.
4. The method for reconstructing a sheave groove of an elevator traction sheave based on multi-channel stereoscopic vision according to claim 1, wherein the code bar is composed of two straight lines of long and short, respectively representing binary 0 and 1, the code direction is from the edge of the traction sheave near the axis value of the traction sheave, the code value of one code barThe method comprises the following steps:
，
wherein,is the position where a symbol is located, +.>Is the number of coded bits.
5. The method for reconstructing the sheave groove of the elevator traction sheave based on multi-channel stereoscopic vision according to claim 1, wherein the method for acquiring three-dimensional information of the point on the sheave groove of the elevator traction sheave in step S03 comprises:
for cameras、/>The binocular stereo vision system is provided with a point on the groove of the traction sheave>The images formed in the two cameras are +.>And->Their pixel coordinates are +.>And->According to the camera imaging principle +.>、/>And (4) point->The following relationship exists:
，
wherein,、/>camera respectively->、/>Is an internal reference matrix of->、/>Camera respectively->、/>Rotation parameter matrix of>、/>Translation parameter matrix of camera respectively, +.>For->Coordinates in the reference coordinate system, +.>、/>The ratio coefficients of the two-phase camera imaging are obtained by solving:
，
wherein,，/>respectively is a matrix->、/>Middle->Line->Column element (s)/(S)>，/>Is vector->，Middle->An element;
obtaining a pointThe coordinates in the reference coordinate system are:
，
wherein the intermediate variable。
6. The method for reconstructing the sheave groove of the elevator traction sheave based on multi-channel stereoscopic vision according to claim 5, wherein the method for reconstructing the sheave groove of the elevator traction sheave in step S03 comprises:
when the traction wheel is imaged, firstly, calculating the included angle between each coding strip and the horizontal direction：
，
Wherein,for indexing of code bars->、/>、/>And->Two end point coordinates of one code bar are respectively, when a first camera images, a second camera synchronously images the side face of the traction sheave attached with the code bar, and the position of an imaged picture in the integral structure of the traction sheave is determined according to the direction of each code bar;
let the starting time of the image beAt this time, the included angle between the code bar with the code value of 0 and the horizontal direction is recorded>The angle is a reference angle for imaging the traction sheave groove;
imaging each frame of traction sheave grooveThe following structural representation is used:
，
wherein,coding bar representing a code value of 0 is +.>Angle of moment relative to horizontal, +.>Representation and +.>The imaging distance of the traction sheave groove is the nearest horizontal direction included angle of the coding strip at any time, +.>For indexing of code bars->Is->And (5) dragging pixel data of a region of interest in imaging the wheel groove of the wheel at the moment.
7. An elevator traction sheave groove rebuilding system based on multi-channel stereoscopic vision, which is characterized by comprising:
the multi-channel stereoscopic vision camera network construction module is used for constructing a multi-channel stereoscopic vision camera network, the camera network comprises a first camera and a second camera, the first camera is used for acquiring traction sheave images, and the second camera is used for acquiring images of marked positions of the traction sheaves;
the encoding strip decoding module marks the real-time rotation position of the traction wheel through the encoding strip; the method for extracting and decoding the encoding strip comprises the following steps:
extracting the code bar by using a straight line detection method according to the profile diagram of the side surface of the traction sheave, and obtaining a point set of the traction sheave code barThe method comprises the following steps:
，
wherein,coding bit number for coding strip, < >>For the number of code bars +.>For indexing of code bars->Index for symbol in one code strip, < >>、/>Respectively, the horizontal and vertical coordinate sets of the pixels of the code strip,>i.e. < th->The>A set of pixel points of each code element line segment;
length of each symbol line segmentThe calculation was performed using the following formula:
，
obtaining the corresponding code of each code element according to the length of each bar code element segment;
randomly selecting two code bars to obtain their end point coordinates, respectively setting them as、/>And->、Firstly judging whether two straight lines are collinear or not, if so, discarding one of the two straight lines and then reselecting the two straight lines;
equation combining two straight lines to obtain intersection point of two code bars：
，
The intersection point of the two straight lines is the center point of the side surface of the traction sheave, and the end point which is closer to the center point is the coding starting point of the current coding table;
according to the calculated result of the code element segment length and the coding starting point, decoding the code strip is realized;
and the traction wheel groove three-dimensional reconstruction module is used for obtaining three-dimensional information of points on the traction wheel groove through a visual measurement method, obtaining a complete traction wheel groove image according to the imaging moment and the angle relation of the encoding strip, and carrying out three-dimensional reconstruction on the traction wheel groove.
8. The elevator traction sheave abrasion loss detection system based on multi-channel stereoscopic vision is characterized by comprising the elevator traction sheave groove reconstruction system according to claim 7, and further comprising a millThe damage detection module is used for finally forming a complete traction wheel three-dimensional structure according to the pixel three-dimensional coordinate data obtained by visual measurement; generating standard traction wheel three-dimensional information according to the structural data of the traction wheel to be tested, and calculating the abrasion loss：
，
Wherein,、/>coordinate rotation and translation matrices, respectively, +.>For the three-dimensional coordinate data set obtained, +.>Is a measured three-dimensional coordinate data set.
9. A computer storage medium having stored thereon a computer program, characterized in that the computer program, when executed, implements the multi-channel stereoscopic vision based elevator traction sheave reconstruction method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311482560.0A CN117218301B (en) | 2023-11-09 | 2023-11-09 | Elevator traction sheave groove reconstruction method and system based on multi-channel stereoscopic vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311482560.0A CN117218301B (en) | 2023-11-09 | 2023-11-09 | Elevator traction sheave groove reconstruction method and system based on multi-channel stereoscopic vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117218301A CN117218301A (en) | 2023-12-12 |
| CN117218301B true CN117218301B (en) | 2024-02-09 |
Family
ID=89049682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311482560.0A Active CN117218301B (en) | 2023-11-09 | 2023-11-09 | Elevator traction sheave groove reconstruction method and system based on multi-channel stereoscopic vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117218301B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112797919A (en) * | 2021-01-29 | 2021-05-14 | 广东省特种设备检测研究院珠海检测院 | Three-dimensional size detection method for elevator traction sheave groove |
| CN112797918A (en) * | 2021-01-29 | 2021-05-14 | 广东省特种设备检测研究院珠海检测院 | Three-dimensional size detection device of elevator driving sheave race |
| CN112819935A (en) * | 2020-11-09 | 2021-05-18 | 南京理工大学 | Method for realizing three-dimensional reconstruction of workpiece based on binocular stereo vision |
| CN113112500A (en) * | 2021-05-06 | 2021-07-13 | 安徽省特种设备检测院 | Machine vision-based elevator traction sheave wear amount characterization method and system |
| CN113720716A (en) * | 2021-09-01 | 2021-11-30 | 桂林电子科技大学 | Quantitative analysis and service life prediction method for wear degree of elevator traction sheave |
| CN115180476A (en) * | 2022-08-24 | 2022-10-14 | 桂林电子科技大学 | Elevator traction sheave race form detection method based on three-dimensional reconstruction |
| CN116958419A (en) * | 2023-07-08 | 2023-10-27 | 复旦大学 | Binocular stereoscopic vision three-dimensional reconstruction system and method based on wavefront coding |
-
2023
- 2023-11-09 CN CN202311482560.0A patent/CN117218301B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819935A (en) * | 2020-11-09 | 2021-05-18 | 南京理工大学 | Method for realizing three-dimensional reconstruction of workpiece based on binocular stereo vision |
| CN112797919A (en) * | 2021-01-29 | 2021-05-14 | 广东省特种设备检测研究院珠海检测院 | Three-dimensional size detection method for elevator traction sheave groove |
| CN112797918A (en) * | 2021-01-29 | 2021-05-14 | 广东省特种设备检测研究院珠海检测院 | Three-dimensional size detection device of elevator driving sheave race |
| CN113112500A (en) * | 2021-05-06 | 2021-07-13 | 安徽省特种设备检测院 | Machine vision-based elevator traction sheave wear amount characterization method and system |
| CN113720716A (en) * | 2021-09-01 | 2021-11-30 | 桂林电子科技大学 | Quantitative analysis and service life prediction method for wear degree of elevator traction sheave |
| CN115180476A (en) * | 2022-08-24 | 2022-10-14 | 桂林电子科技大学 | Elevator traction sheave race form detection method based on three-dimensional reconstruction |
| CN116958419A (en) * | 2023-07-08 | 2023-10-27 | 复旦大学 | Binocular stereoscopic vision three-dimensional reconstruction system and method based on wavefront coding |
Non-Patent Citations (1)
| Title |
|---|
| 基于图像形态学的曳引界面滑移测量方法;赫志亮 等;机械设计与研究(02);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117218301A (en) | 2023-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109949578B (en) | Vehicle line pressing violation automatic auditing method based on deep learning | |
| US10311835B1 (en) | Method for detection and estimation of tire tread wear | |
| US8154594B2 (en) | Mobile peripheral monitor | |
| CN106918299B (en) | A kind of line-structured light machine vision tire wear measurement method | |
| CN112651968B (en) | Wood board deformation and pit detection method based on depth information | |
| CN109341626B (en) | Straightness calculation method, and method for calculating difference between maximum diameter and minimum diameter of cross section | |
| AU2016385541A1 (en) | Object surface deformation feature extraction method based on line scanning three-dimensional point Cloud | |
| CN110942460B (en) | Tire pattern depth measuring method, system and storage medium | |
| JP6450971B2 (en) | Trolley wire wear measuring device and trolley wire wear measuring method | |
| CN102853786A (en) | Apparatus and method for detecting flatness | |
| CN104718562B (en) | Image processing apparatus and image processing method | |
| CN105547166A (en) | 2D laser scanning based rapid detection method for heading window of heading machine | |
| CN111879264A (en) | Flatness measurement and evaluation system based on line structured light | |
| CN115797338B (en) | Panoramic pavement multi-performance index calculation method and system based on binocular vision | |
| CN111307043A (en) | Displacement monitoring system based on structured light | |
| CN111968079B (en) | Three-dimensional pavement crack extraction method based on local extremum of section and segmentation sparsity | |
| CN110793501A (en) | Subway tunnel clearance detection method | |
| CN117218301B (en) | Elevator traction sheave groove reconstruction method and system based on multi-channel stereoscopic vision | |
| CN110490342B (en) | Contact net static geometrical parameter detection method based on Faster R-CNN | |
| CN116128834A (en) | Rail transit platform limit rapid detection method based on three-dimensional laser scanning | |
| JP6929207B2 (en) | Road image processing device, road image processing method, road image processing program, and recording medium | |
| CN116993804B (en) | Stirrup size detection method and system based on LSM algorithm | |
| CN111738907B (en) | Train pantograph detection method based on binocular calibration and image algorithm | |
| CN113658244A (en) | Method for identifying three-dimensional geometric dimension of navigation ship in bridge area | |
| CN104252707A (en) | Object detecting method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |