CN105303564B - Visual detection method for tower crane load three-dimensional swing angle - Google Patents
Visual detection method for tower crane load three-dimensional swing angle Download PDFInfo
- Publication number
- CN105303564B CN105303564B CN201510628739.1A CN201510628739A CN105303564B CN 105303564 B CN105303564 B CN 105303564B CN 201510628739 A CN201510628739 A CN 201510628739A CN 105303564 B CN105303564 B CN 105303564B
- Authority
- CN
- China
- Prior art keywords
- lifting rope
- point
- camera
- cameras
- images
- 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.)
- Expired - Fee Related
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 230000000007 visual effect Effects 0.000 title abstract description 4
- 238000003708 edge detection Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims abstract description 7
- 238000001914 filtration Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 17
- 239000007787 solid Substances 0.000 claims description 14
- 238000003384 imaging method Methods 0.000 claims description 8
- 238000013519 translation Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000007689 inspection Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a visual detection method for a tower crane load three-dimensional swing angle, which comprises the following steps: the method comprises the following steps of calibrating a left camera and a right camera, collecting images, converting the images into gray images, filtering to remove noise, carrying out image binarization, carrying out edge detection, detecting a lifting rope straight line, calculating a plane coordinate point of a white mark point, calculating a three-dimensional coordinate of the white mark point and calculating a three-dimensional swing angle. The visual detection method avoids using expensive sensors such as accelerometers, gyroscopes and the like, has high detection precision and has good application prospect.
Description
Technical field
The present invention relates to a kind of visible detection methods, especially a kind of to be directed to regarding for derrick crane load solid pivot angle
Feel detection method.
Background technology
With the development of productivity, derrick crane in industrial production and civilian is built as a kind of main handling machinery
In building, increasingly important role is played.Derrick crane generally existing load swing problem in operation, can limit load
Derricking speed and rotational speed reduce load precision in place, while also increase the labor intensity of operating personnel, can draw when serious
It plays load to break off relations, causes accident.Therefore it eliminates or control load swing is made to improving derrick crane working efficiency, reducing handling
Industry production hidden danger is of great significance.
At present, the three-dimensional pivot angle of derrick crane load Antisway Control System is detected mainly by accelerometer, gyroscope etc.
Sensor forms sensor assembly to realize that pivot angle detects, and hardware cost is higher and signal processing is complicated.
Invention content
Rely primarily on various kinds of sensors the technical problem to be solved by the present invention is to existing three-dimensional pivot angle detection, it is of high cost and
There are larger errors.
In order to solve the above technical problem, the present invention provides a kind of vision-based detections of derrick crane load solid pivot angle
Method includes the following steps：
Step 1, two cameras of left-right balance installation are demarcated respectively, obtains the opposite geometry between two cameras
Position relationship；
Step 2, Image Acquisition is carried out to the weight that derrick crane carries using calibrated left and right camera；
Step 3, collected two width original color image of left and right is converted into gray level image；
Step 4, two width gray level images of left and right are carried out with Wiener filtering removal noise；
Step 5, inter-class variance is maximized to two width denoising imagery exploitation OTSU global thresholds of left and right and carries out region segmentation, obtained
To two width bianry images of left and right；
Step 6, object edge detection is carried out to two width bianry images of left and right using canny edge detection operators, obtains a left side
Right two breadths edge contour curve images；
Step 7, two breadths edge imagery exploitation Hough transforms of left and right are detected to hang loads in derrick crane image
Straight line lifting rope, and detect using pixel value to be arranged on the white marking point at lifting rope both ends；
Step 8, the white marking of the lifting rope head end point detected is denoted as to the origin coordinates point of image, it is straight to be partitioned into lifting rope
Line region；
Step 9, the ranks coordinate of the white marking point of lifting rope linearity region tail end in the two images of left and right is detected respectively；
Step 10, it is three-dimensional that the white marking of the lifting rope tail end point to be restored is approached using the midpoint of different surface beeline common vertical line
Coordinate, so as to obtain the three-dimensional coordinate of the white marking point of lifting rope tail end to be restored；
Step 11, which is calculated apart from lifting rope head end white according to the three-dimensional coordinate of lifting rope tail end white marking point to be restored
Mark the three-dimensional pivot angle of basic point.
It is demarcated respectively using the inner parameter to two cameras and external parameter, the essence of detection can be effectively improved
Degree establishes accurate calculating basis for three-dimensional coordinate calculating below；Using the white marking point of lifting rope head end, can facilitate from
Lifting rope linearity region is partitioned into image, improves the accuracy of lifting rope identification；Utilize lifting rope linearity region tail in two images
The white marking point at end calculates the three-dimensional coordinate of the white marking point of lifting rope tail end to be restored, so as to further calculate three-dimensional pendulum
The vision-based detection of load solid pivot angle is completed at angle.
As the further limits scheme of the present invention, when being demarcated respectively to two cameras in step 1, specifically include as
Lower step：
Step 1-1, using black and white chess pattern as calibrating template；
Calibrating template is placed in the front of left and right camera by step 1-2, converts plan-position and the rotation angle of calibrating template
Degree, N group picture pieces are acquired with left and right camera simultaneously to the calibrating template of same position；
Step 1-3 chooses same group or so two images, and determines all corresponding black and white grid in each image respectively
The upper left corner, the upper right corner, four boundaries in the lower left corner and the lower right corner characteristic point；
Step 1-4, according to the right angle of characteristic point on the projection imaging plane coordinates (u, v) of character pair point and calibrating template
Coordinate (X, Y) calculates the inner parameter and external parameter of two cameras in left and right respectively.
The calibration of two cameras is the basis of vision-based detection, which is directly related to the essence of entire vision inspection process
Degree, accurately calibration just can ensure that the accuracy of vision-based detection result.
As the further limits scheme of the present invention, calculate in step 1-4 inner parameter, the external parameter of two cameras with
And relative geometry position relationship the specific steps are：
Step 1-44 solves VTThe corresponding feature vector of V minimal eigenvalues is the solution of b, is inverted to b, is utilized
The calculation formula that Choleski decomposes to obtain inner parameter is：
Step 1-45 solves H=[h1 h2 h3]=λ A [r1 r2T], the calculating for obtaining the external parameter R and T of camera is public
Formula is：
Wherein, λ is scale factor, ri(i=1,2,3) represents the i-th column vector of 3 × 3 spin matrix R, i.e. spin matrix R
The i-th row vector be Ri=[ri1 ri2 ri3], the jth column vector of spin matrix R is Rj=[r1j r2j r3j]T, T is 3 × 1
Translation matrix；
The inner parameter and external parameter of two cameras are the bases for calculating the relative geometry position relationship between two cameras
Plinth could carry out vision-based detection after the geometry site for determining two cameras.
As the further limits scheme of the present invention, the three-dimensional coordinate of the white marking point of lifting rope tail end is obtained in step 10
The specific steps are：
Step 10-1 solves the m in following equationsx、my、mz、nx、nyAnd nz,
The beneficial effects of the present invention are：(1) using the inner parameter to two cameras and external parameter respectively into rower
It is fixed, the precision of detection can be effectively improved, accurate calculating basis is established for three-dimensional coordinate calculating below；(2) lifting rope is utilized
The white marking point of head end, can facilitate and lifting rope linearity region is partitioned into from image, improve the accuracy of lifting rope identification；
(3) the white marking point of lifting rope tail end to be restored is calculated using the white marking point of lifting rope linearity region tail end in two images
Three-dimensional coordinate so as to further calculate three-dimensional pivot angle, completes the vision-based detection of load solid pivot angle.
Description of the drawings
Fig. 1 is the visible detection method flow chart of derrick crane load solid pivot angle of the present invention；
Fig. 2 is calibrating template schematic diagram in the visible detection method of derrick crane load solid pivot angle of the present invention；
Fig. 3 is the visible detection method binocular stereo vision detection signal of derrick crane load solid pivot angle of the present invention
Figure；
Fig. 4 illustrates for common vertical line mid-point computation in the visible detection method of derrick crane load solid pivot angle of the present invention
Figure.
Specific embodiment
As shown in Figs 1-4, the visible detection method of a kind of derrick crane load solid pivot angle of the invention, including as follows
Step：
Step 1, two cameras of left-right balance installation are demarcated respectively, obtains the opposite geometry between two cameras
Position relationship, the specific steps are：
Step 1-1, using black and white chess pattern as calibrating template, wherein black and white grid size is 20mm*20mm；
Calibrating template is placed in the front of left and right camera by step 1-2, converts plan-position and the rotation angle of calibrating template
Degree, the calibrating template of same position is acquired N group picture pieces, 20 group picture piece of preferred acquisition of the present invention with left and right camera simultaneously；
Step 1-3 chooses same group or so two images, and determines all corresponding black and white grid in each image respectively
The upper left corner, the upper right corner, four boundaries in the lower left corner and the lower right corner characteristic point；
Step 1-4, according to the right angle of characteristic point on the projection imaging plane coordinates (u, v) of character pair point and calibrating template
Coordinate (X, Y) calculates the inner parameter and external parameter of two cameras in left and right, inner parameter, external parameter and relatively several respectively
What position relationship the specific steps are：
Step 1-44 solves VTThe corresponding feature vector of V minimal eigenvalues is the solution of b, is inverted to b, is utilized
The calculation formula that Choleski decomposes to obtain inner parameter is：
Step 1-45 solves H=[h1 h2 h3]=λ A [r1 r2T], the calculating for obtaining the external parameter R and T of camera is public
Formula is：
Wherein, λ is scale factor, ri(i=1,2,3) represents the i-th column vector of 3 × 3 spin matrix R, i.e. spin matrix R
The i-th row vector be Ri=[ri1 ri2 ri3], the jth column vector of spin matrix R is Rj=[r1j r2j r3j]T, T is 3 × 1
Translation matrix；
Step 2, Image Acquisition is carried out to the weight that derrick crane carries using calibrated left and right camera；
Step 3, collected two width original color image of left and right is converted into gray level image；
Step 4, two width gray level images of left and right are carried out with Wiener filtering removal noise；
Step 5, inter-class variance is maximized to two width denoising imagery exploitation OTSU global thresholds of left and right and carries out region segmentation, obtained
To two width bianry images of left and right；
Step 6, object edge detection is carried out to two width bianry images of left and right using canny edge detection operators, obtains a left side
Right two breadths edge contour curve images；
Step 7, two breadths edge imagery exploitation Hough transforms of left and right are detected to hang loads in derrick crane image
Straight line lifting rope, and detect using pixel value to be arranged on the white marking point at lifting rope both ends；
Step 8, the white marking of the lifting rope head end point detected is denoted as to the origin coordinates point of image, it is straight to be partitioned into lifting rope
Line region；
Step 9, the ranks coordinate of the white marking point of lifting rope linearity region tail end in the two images of left and right is detected respectively；
Step 10, it is three-dimensional that the white marking of the lifting rope tail end point to be restored is approached using the midpoint of different surface beeline common vertical line
Coordinate, so as to obtain the three-dimensional coordinate of the white marking point of lifting rope tail end to be restored, the specific steps are：
Step 10-1 solves the m in following equationsx、my、mz、nx、nyAnd nz,
Step 11, which is calculated apart from lifting rope head end white according to the three-dimensional coordinate of lifting rope tail end white marking point to be restored
Mark the three-dimensional pivot angle of basic point.
It is demarcated respectively using the inner parameter to two cameras and external parameter, the essence of detection can be effectively improved
Degree establishes accurate calculating basis for three-dimensional coordinate calculating below；Using the white marking point of lifting rope head end, can facilitate from
Lifting rope linearity region is partitioned into image, improves the accuracy of lifting rope identification；Utilize lifting rope linearity region tail in two images
The white marking point at end calculates the three-dimensional coordinate of the white marking point of lifting rope tail end to be restored, so as to further calculate three-dimensional pendulum
The vision-based detection of load solid pivot angle is completed at angle；The calibration of two cameras is the basis of vision-based detection, which is directly related to
The precision of entire vision inspection process, accurately calibration just can ensure that the accuracy of vision-based detection result；The inside of two cameras
Parameter and external parameter are the bases for calculating the relative geometry position relationship between two cameras, in the geometry for determining two cameras
Vision-based detection could be carried out after position relationship.
The visible detection method of derrick crane load solid pivot angle that the present invention designs can replace traditional artificial visual
Lengthy and tedious rough detection operation and control process, automatic and accurate detects three-dimensional oscillating model of the lifting rope weight relative to equilbrium position
It encloses, is operated relative to traditional artificial detection, the method that the present invention designs has high degree of automation, accuracy of detection height, speed
Soon, reliability is high, is easily achieved, and the advantages of of low cost, strong applicability.
To sum up, the visible detection method of derrick crane load solid pivot angle designed by establishing and implementing the present invention,
It can realize the detection of non-equilibrium state generated to lifting rope when slinging weight moment or having external interference, provide three-dimensional pendulum
Angle establishes important foundation for subsequent automation anti-swing control, has a vast market application prospect and economic value.
Embodiments of the present invention are explained in detail above in conjunction with attached drawing, but the present invention is not limited to above-mentioned implementations
Mode, within the knowledge of a person skilled in the art, can also be under the premise of present inventive concept not be departed from
It makes a variety of changes.
Claims (1)
1. a kind of visible detection method of derrick crane load solid pivot angle, which is characterized in that include the following steps：
Step 1, two cameras of left-right balance installation are demarcated respectively, obtains the relative geometry position between two cameras
Relationship；
Step 2, Image Acquisition is carried out to the weight that derrick crane carries using calibrated left and right camera；
Step 3, collected two width original color image of left and right is converted into gray level image；
Step 4, two width gray level images of left and right are carried out with Wiener filtering removal noise；
Step 5, inter-class variance is maximized to two width denoising imagery exploitation OTSU global thresholds of left and right and carries out region segmentation, obtain a left side
Right two width bianry images；
Step 6, object edge detection is carried out to two width bianry images of left and right using canny edge detection operators, obtains left and right two
Breadths edge contour curve image；
Step 7, two breadths edge imagery exploitation Hough transforms of left and right are detected to hang in derrick crane image with the straight line of loads
Lifting rope, and detect using pixel value to be arranged on the white marking point at lifting rope both ends；
Step 8, the white marking of the lifting rope head end point detected is denoted as to the origin coordinates point of image, is partitioned into lifting rope linearity sector
Domain；
Step 9, the ranks coordinate of the white marking point of lifting rope linearity region tail end in the two images of left and right is detected respectively；
Step 10, the white marking of the lifting rope tail end point three-dimensional to be restored is approached using the midpoint of different surface beeline common vertical line to sit
Mark, so as to obtain the three-dimensional coordinate of the white marking point of lifting rope tail end to be restored；
Step 11, which is calculated apart from lifting rope head end white marking according to the three-dimensional coordinate of lifting rope tail end white marking point to be restored
The three-dimensional pivot angle of basic point；
Wherein, in step 10 obtain lifting rope tail end white marking point three-dimensional coordinate the specific steps are：
Step 10-1 solves the m in following equationsx、my、mz、nx、nyAnd nz,
Wherein, the lifting rope straight line O of left camera imagingLPLWith the lifting rope straight line O of right camera imagingRPRDirection vector be respectivelyWithLifting rope straight line OLPLThe normal vector of two planes at place isIt hangs
Restrict straight line ORPRThe normal vector of two planes at place is
(uL,vL) and (uR,vR) for the coordinate on left images, m14、m24And m34For calibrating parametersThe corresponding coefficient of matrix；
Step 10-2, calculates the midpoint P' of final common vertical line MN, i.e., the three-dimensional coordinate of the white marking point on lifting rope tail end is：AndWherein (mx,my,mz) and (nx,ny,nz) respectively
Lifting rope straight line O for left camera imagingLPLWith the lifting rope straight line O of right camera imagingRPRCommon vertical line MN vertex M and N point three-dimensional
Coordinate；
When being demarcated respectively to two cameras in step 1, specifically comprise the following steps：
Step 1-1, using black and white chess pattern as calibrating template；
Calibrating template is placed in the front of left and right camera by step 1-2, converts plan-position and the rotation angle of calibrating template,
N group picture pieces are acquired simultaneously to the calibrating template of same position with left and right camera；
Step 1-3 chooses same group or so two images, and determines the upper left of all corresponding black and white grid in each image respectively
Angle, the upper right corner, four boundaries in the lower left corner and the lower right corner characteristic point；
Step 1-4, according to the rectangular co-ordinate of characteristic point on the projection imaging plane coordinates (u, v) of character pair point and calibrating template
(X, Y) calculates the inner parameter and external parameter of two cameras in left and right respectively；
Calculated in step 1-4 the inner parameters of two cameras, external parameter and relative geometry position relationship the specific steps are：
Step 1-41 is solved point by point by least square method
In homography matrix H, the i-th row vector of homography matrix H is hi=[hi1 hi2 hi3], the of homography matrix H
J column vectors are hj=[h1j h2j h3j]T；
Step 1-42, enables symmetrical matrixWherein, A is inner parameter matrix,α、β、u0And v0For the inner parameter of camera, out of plumb of the γ between two axis of camera imaging plane because
The angle of son, i.e. pixel ranks, horizontal direction focal lengths of the α for camera, vertical direction focal lengths of the β for camera, u0And v0For camera
Principal point coordinate, in ideal camera model, (u0,v0) positioned at image center, α=beta, gamma=0 or 90 °；
Step 1-43, then enable vij=[hi1h1j hi1h2j+hi2h1j hi2h2j hi3h1j+hi1h3j hi3h2j+hi2h3j hi3h3j]T, b
=[B11 B12 B22 B13 B23 B33]-T, N width images are acquired, row are write N number ofEquation, i.e. Vb=0
Equation；
Step 1-44 solves VTThe corresponding feature vector of V minimal eigenvalues is the solution of b, inverts to b, is decomposed using Choleski
The calculation formula for obtaining inner parameter is：
Step 1-45 solves H=[h1 h2 h3]=λ A [r1 r2T], the calculation formula for obtaining the external parameter R and T of camera is：
Wherein, λ is scale factor, ri(i=1,2,3) represents the i-th of the i-th column vector, i.e. spin matrix R of 3 × 3 spin matrix R
Row vector is Ri=[ri1 ri2 ri3], the jth column vector of spin matrix R is Rj=[r1j r2j r3j]T, T is 3 × 1 translation square
Battle array；
Step 1-46, further according to formulaThe relative geometry position relationship between two cameras is calculated, wherein, r is
Relative rotation matrices, t be relative translation matrix, R1And R2The spin matrix of two cameras in left and right, T are represented respectively1And T2Respectively
The translation matrix of two cameras in left and right.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510628739.1A CN105303564B (en) | 2015-09-28 | 2015-09-28 | Visual detection method for tower crane load three-dimensional swing angle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510628739.1A CN105303564B (en) | 2015-09-28 | 2015-09-28 | Visual detection method for tower crane load three-dimensional swing angle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105303564A CN105303564A (en) | 2016-02-03 |
| CN105303564B true CN105303564B (en) | 2018-06-26 |
Family
ID=55200786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510628739.1A Expired - Fee Related CN105303564B (en) | 2015-09-28 | 2015-09-28 | Visual detection method for tower crane load three-dimensional swing angle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105303564B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108439221B (en) * | 2018-03-08 | 2019-06-25 | 南开大学 | The overhead crane automatic control system of view-based access control model |
| CN109186549A (en) * | 2018-10-26 | 2019-01-11 | 国网黑龙江省电力有限公司电力科学研究院 | A kind of Iron tower incline angle measurement method of view-based access control model |
| CN111402330B (en) * | 2020-04-03 | 2024-02-27 | 山东省科学院激光研究所 | Laser line key point extraction method based on planar target |
| CN112010187B (en) * | 2020-09-14 | 2022-08-23 | 福建汇川物联网技术科技股份有限公司 | Monitoring method and device based on tower crane |
| CN112125184B (en) * | 2020-09-20 | 2021-08-06 | 中国科学院武汉岩土力学研究所 | Building construction tower crane monitoring and early warning method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0672693A (en) * | 1992-08-26 | 1994-03-15 | Kajima Corp | Deflection detecting method for crane hoisting load |
| WO2010009570A1 (en) * | 2008-07-21 | 2010-01-28 | Yu Qifeng | A hoist-positioning method and intelligent vision hoisting system |
| CN101714252A (en) * | 2009-11-26 | 2010-05-26 | 上海电机学院 | Method for extracting road in SAR image |
| CN102795547B (en) * | 2012-08-31 | 2014-07-16 | 中国人民解放军国防科学技术大学 | Real-time photographic measuring method of position and swing angle of lifting hook of crane |
-
2015
- 2015-09-28 CN CN201510628739.1A patent/CN105303564B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN105303564A (en) | 2016-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105303564B (en) | Visual detection method for tower crane load three-dimensional swing angle | |
| CN112418103B (en) | Bridge crane hoisting safety anti-collision system and method based on dynamic binocular vision | |
| CN106651752B (en) | Three-dimensional point cloud data registration method and splicing method | |
| CN104848851B (en) | Intelligent Mobile Robot and its method based on Fusion composition | |
| CN104915957B (en) | A kind of matching antidote for improving industrial robot 3D vision accuracy of identification | |
| CN103411553B (en) | The quick calibrating method of multi-linear structured light vision sensors | |
| CN105243664B (en) | A kind of wheeled mobile robot fast-moving target tracking method of view-based access control model | |
| CN109472822A (en) | Dimension of object measurement method based on depth image processing | |
| CN106969706A (en) | Workpiece sensing and three-dimension measuring system and detection method based on binocular stereo vision | |
| CN105865329A (en) | Vision-based acquisition system for end surface center coordinates of bundles of round steel and acquisition method thereof | |
| CN106780483B (en) | More continuous casting billet end face visual identifying systems and centre coordinate acquiring method | |
| CN114241298A (en) | Tower crane environment target detection method and system based on laser radar and image fusion | |
| CN108007388A (en) | A kind of turntable angle high precision online measuring method based on machine vision | |
| CN105447853A (en) | Flight device, flight control system and flight control method | |
| CN107067431A (en) | A kind of object volume computational methods based on Kinect | |
| CN106546263A (en) | A kind of laser leveler shoot laser line detecting method based on machine vision | |
| CN106530352B (en) | Intelligent snow grooming machines people positioning system and method | |
| CN108280401A (en) | A kind of pavement detection method, apparatus, cloud server and computer program product | |
| CN107316288B (en) | A kind of boom-type roadheader cutterhead pose vision measuring method | |
| CN116399302A (en) | Method for monitoring dynamic compaction settlement in real time based on binocular vision and neural network model | |
| CN113554667A (en) | Three-dimensional displacement detection method and device based on image recognition | |
| CN115063579A (en) | Train positioning pin looseness detection method based on two-dimensional image and three-dimensional point cloud projection | |
| CN110223332B (en) | Bridge crack calibration method | |
| CN107301371A (en) | A kind of unstructured road detection method and system based on image information fusion | |
| CN117522778A (en) | Hollow brick flaw detection system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220120 Address after: 215159 floor 3, building 2, No. 101, welfare Village, Guangfu Town, Wuzhong District, Suzhou City, Jiangsu Province Patentee after: Suzhou agile Robot Technology Co.,Ltd. Address before: Nanjing City, Jiangsu province 210046 City Xianlin University No. 99 Patentee before: Nanjing Vocational College of Information Technology |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180626 |