CN116894776A - Crimping wire bending degree measuring method and system based on image stitching - Google Patents
Crimping wire bending degree measuring method and system based on image stitching Download PDFInfo
- Publication number
- CN116894776A CN116894776A CN202311160832.5A CN202311160832A CN116894776A CN 116894776 A CN116894776 A CN 116894776A CN 202311160832 A CN202311160832 A CN 202311160832A CN 116894776 A CN116894776 A CN 116894776A
- Authority
- CN
- China
- Prior art keywords
- crimping
- image
- wire
- spliced
- characteristic
- 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.)
- Granted
Links
- 238000002788 crimping Methods 0.000 title claims abstract description 236
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000005452 bending Methods 0.000 title claims abstract description 48
- 238000001914 filtration Methods 0.000 claims abstract description 17
- 238000003708 edge detection Methods 0.000 claims abstract description 16
- 239000004020 conductor Substances 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 22
- 238000005259 measurement Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 19
- 230000009466 transformation Effects 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 241001270131 Agaricus moelleri Species 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000000691 measurement method Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000001000 micrograph Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- 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
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method and a system for measuring bending degree of a crimping wire based on image splicing, wherein the method comprises the steps of extracting characteristic points of two crimping wire images to be spliced, carrying out improved Biref characteristic description on a characteristic point set, carrying out characteristic point rough matching on two characteristic description strings by adopting Hamming distance, carrying out accurate characteristic point matching, carrying out image registration and image splicing on the two crimping wire images to be spliced according to the set of the accurate matching characteristic points, carrying out splicing trace filtering treatment on an initial splicing image by adopting a gray weighted average method, carrying out thresholding treatment on a full-view splicing image of the crimping wire, carrying out edge detection, obtaining a crimping edge fitting equation by carrying out least square fitting on the edge of the crimping wire, determining the maximum radial deformation, and calculating wire crimping bending degree according to the maximum radial deformation and the maximum chord length of the crimping wire, thereby improving the crimping wire bending degree measuring efficiency and accuracy.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a crimping wire bending degree measuring method and system based on image splicing.
Background
The crimping process has wide application in power transmission line construction engineering, and has the main functions as a connecting process: firstly, connecting two sections of wires with the same section; and secondly, connecting the tail ends of the wires with a power transmission tower. The crimping wire pressing connection pipe can be divided into a splicing crimping wire and a wire clamp crimping wire. The connecting crimping lead refers to a lead connected by using a connecting tube, and the two ends of the connecting tube are leads with the same cross section, so that the connecting crimping lead is widely used for long-distance power transportation; the wire clamp crimping wire is a wire connected by using a strain clamp, and two ends of the wire clamp crimping wire are respectively connected with the wire and a power transmission tower and are mainly used for bearing loads such as gravity, tension and the like.
Because of the critical role of crimped wires in power transportation, accurate measurement of their performance parameters is highly necessary. The crimping bending degree is an important parameter for representing the conductivity and the mechanical strength of the crimping wire, and is a conventional measurement item in a crimping wire sampling test and a checking test. The crimp tortuosity is the ratio of the maximum radial deflection of the crimp tube after the pilot wire is crimped to the crimp length.
Currently, the measurement of crimping curvature is mainly performed manually by a worker using a height gauge and a tape measure. Although the method can measure the crimping flexibility, the method has long time consumption, low efficiency and low repeatability of measurement results. With the development of industrial automation, the demand for automatic measurement of crimp bending is becoming stronger. The automatic measurement of crimping curvature mainly adopts an image measurement method, but at present, the image measurement is mainly carried out on crimping curvature of a wire, but because the wire is of various types, the corresponding splicing sleeve and strain clamp are large in size range, the corresponding length range is from 500mm to 1000mm, the working distance needs to be continuously adjusted when an industrial camera is adopted to collect images, a camera platform moving device needs to be increased, the working distance needs to be continuously adjusted, and therefore, the crimping wire curvature measurement efficiency is low, the accuracy is poor, and the difficulty of realizing automatic measurement is increased.
Disclosure of Invention
The invention provides a crimping wire bending measurement method and system based on image stitching, which solve the technical problems that the existing crimping wire bending measurement efficiency is low, the accuracy is poor and the difficulty in realizing automatic measurement is increased.
In view of the above, the first aspect of the present invention provides a method for measuring bending degree of a crimp wire based on image stitching, comprising the steps of:
step one, extracting characteristic points of two crimping conductor images to be spliced to obtain characteristic point sets corresponding to the two crimping conductor images to be spliced respectively;
step two, carrying out improved Biref characteristic description on characteristic point sets respectively corresponding to the two crimping wire images to be spliced to obtain two characteristic description strings;
performing feature point rough matching on the two feature description strings by adopting a Hamming distance to obtain a rough matching feature point pair set, and performing accurate feature point matching on the rough matching feature point pair set based on a two-way matching algorithm to obtain a fine matching feature point pair set;
step four, performing image registration and image stitching on the two crimping wire images to be stitched according to the fine matching characteristic point pair set to obtain an initial stitching image;
step five, performing stitching trace filtering treatment on the initial stitching image by using a gray weighted average method to obtain a full-view stitching image of the crimping lead;
step six, thresholding is carried out on the overall spliced image of the crimping conductor, and then edge detection is carried out, so that the edge of the crimping conductor is obtained;
and step seven, carrying out least square fitting on the edge of the crimping wire to obtain a crimping edge fitting equation, obtaining a first order equation of the chord length of the crimping wire according to the crimping edge fitting equation, calculating the distance from each point of the edge of the crimping wire to the first order equation of the chord length of the crimping wire, determining the maximum radial deformation, and calculating the bending degree of the crimping wire according to the maximum radial deformation and the maximum chord length of the crimping wire.
Optionally, the step one further includes:
and acquiring a first crimping wire image, and then moving a preset distance along the axis direction of the crimping wire, and acquiring a second crimping wire image, wherein the first crimping wire image and the second crimping wire image at least comprise a section of crimping trace.
Optionally, the first step specifically includes:
101. carrying out gray projection on the two crimping wire images to be spliced to obtain two gray projection images;
102. extracting the interested areas in the two gray projection images according to the gray information of the two gray projection images;
103. and respectively extracting characteristic points from the interested areas in the two gray projection images by using a Fast 16-9 corner detection algorithm to obtain characteristic point sets respectively corresponding to the two crimping wire images to be spliced.
Optionally, the second step specifically includes:
201. carrying out convolution processing on the crimping wire images to be spliced by adopting a mean filtering template with the size of 9 multiplied by 9;
202. randomly selecting 128 pairs of pixel points in a 48 multiplied by 48 neighborhood of characteristic points in the crimping wire image to be spliced after convolution processing;
203. comparing the gray scales of each pixel point pair in 128 pairs of pixel points and performing binarization processing to obtain 128-dimensional gray scale characteristic values;
204. convolving the crimping wire images to be spliced by using a vertical Sobel operator to obtain a gradient image;
205. extracting feature points of the gradient image, and carrying out improved Biref feature description on a feature point set of the gradient image to obtain a 128-dimensional gradient feature value;
206. and describing each feature point by using the 128-dimensional gray feature value and the 128-dimensional gradient feature value to obtain a 256-dimensional feature description string.
Optionally, the third step specifically includes:
301. randomly selecting characteristic points in a first crimping wire image to be spliced as reference characteristic points, traversing and selecting the times of different numbers of characteristic description strings between the characteristic points in a second crimping wire image to be spliced and the reference characteristic points at corresponding positions, and determining the Hamming distance;
302. screening out characteristic points in the second crimping wire image to be spliced with the minimum Hamming distance as matching points of the reference characteristic points of the first crimping wire image to be spliced;
303. sequentially traversing other characteristic points in the first crimp wire image to be spliced as reference characteristic points, and repeatedly traversing the times of selecting different numbers of the characteristic description strings between the characteristic points in the second crimp wire image to be spliced and the reference characteristic points at the corresponding positions to determine the Hamming distance until all the characteristic points in the first crimp wire image to be spliced are traversed to obtain a rough matching characteristic point pair set;
304. taking the second crimping wire image to be spliced as a reference, and performing operation according to steps 301-303 to obtain a further rough matching characteristic point pair set;
305. and carrying out intersection processing on the two coarse matching characteristic point pair sets based on a two-way matching algorithm to obtain a coarse matching characteristic point intersection set which is a fine matching characteristic point pair set.
Optionally, the step four specifically includes:
401. determining an image homography transformation matrix according to the fine matching characteristic point pair set;
402. and performing image registration on the two crimping conductor images to be spliced by using the image homography transformation matrix, and splicing the two crimping conductor images to be spliced according to an image registration result to obtain an initial spliced image.
Optionally, the gray weighted average method comprises the following calculation processes:
；
in the method, in the process of the invention,representing overlapping areas of the full view stitched image of the crimped wireEdge gray scale->Representing pixel coordinates +.>Representing a first crimp wire image to be spliced, < >>Representing the edge gray scale of the overlapping area of the first crimp wire image to be spliced +.>Representing a second crimp wire image to be spliced, < >>Representing the edge gray scale of the overlapping area of the second crimp wire image to be spliced +.>And->All represent gray weights, wherein,
；
。
optionally, the sixth step specifically includes:
601. thresholding the overall spliced image of the crimping lead by adopting a minimum error method to obtain a binary image;
602. and carrying out edge detection on the binary image by adopting a Sobel operator to obtain the edge of the crimping lead.
Optionally, the seventh step specifically includes:
701. performing least square fitting on the edge of the crimping wire to obtain a crimping edge fitting equation;
702. the first order equation for obtaining the chord length of the crimping wire according to the crimping edge fitting equation is as follows:
；
wherein L is the chord length, m is the abscissa value of the edge pixel point, and d and k are coefficients;
calculating the distance from each point of the edge of the crimping wire to the first order equation of the chord length of the crimping wire, and determining the maximum radial deformation as follows:
；
wherein n is the ordinate value of the edge pixel point,is the maximum radial deformation;
calculating the bending degree of the wire crimping according to the maximum radial deformation and the maximum chord length of the wire crimping by the following steps:
；
in the method, in the process of the invention,cfor the wire to be crimped in a bending manner,lthe maximum chord is crimped for the wire.
In a second aspect, the present invention further provides a crimping wire bending measurement system based on image stitching, including:
the characteristic extraction module is used for extracting characteristic points of the two crimping conductor images to be spliced to obtain characteristic point sets respectively corresponding to the two crimping conductor images to be spliced;
the characteristic description module is used for carrying out improved Biref characteristic description on the characteristic point sets respectively corresponding to the two crimping wire images to be spliced to obtain two characteristic description strings;
the feature matching module is used for carrying out feature point rough matching on the two feature description strings by adopting the Hamming distance to obtain a rough matching feature point pair set, and carrying out accurate feature point matching on the rough matching feature point pair set based on a two-way matching algorithm to obtain a fine matching feature point pair set;
the image stitching module is used for carrying out image registration on the two crimping wire images to be stitched according to the fine matching characteristic point pair set and carrying out image stitching to obtain an initial stitching image;
the trace filtering module is used for filtering the spliced trace of the initial spliced image by adopting a gray weighted average method to obtain a full-view spliced image of the crimping lead;
the edge detection module is used for carrying out thresholding treatment on the overall spliced image of the crimping wire and then carrying out edge detection to obtain the edge of the crimping wire;
the bending calculation module is used for carrying out least square fitting on the edge of the crimping wire to obtain a crimping edge fitting equation, obtaining a first order equation of the chord length of the crimping wire according to the crimping edge fitting equation, calculating the distance from each point of the edge of the crimping wire to the first order equation of the chord length of the crimping wire, determining the maximum radial deformation, and calculating the bending of the crimping wire according to the maximum radial deformation and the maximum chord length of the crimping wire.
From the above technical scheme, the invention has the following advantages:
according to the invention, feature point extraction is carried out on two crimping wire images to be spliced, improved Biref feature description is carried out on feature point sets corresponding to the two crimping wire images respectively, hamming distance is adopted to carry out feature point rough matching on the two feature description strings, accurate feature point matching is carried out on the rough matching feature point pair set based on a two-way matching algorithm, image registration and image splicing are carried out on the two crimping wire images to be spliced according to the accurate matching feature point pair set, splicing trace filtering processing is carried out on the initial splicing images by adopting a gray weighted average method, a full-view splicing image of the crimping wire is obtained, thresholding processing is carried out on the full-view splicing image of the crimping wire, edge detection is carried out, a crimping edge fitting equation is obtained by carrying out least square fitting on the edge of the crimping wire, a first order equation of the chord length of the crimping wire is obtained according to the crimping edge fitting equation, and the maximum radial deformation is determined, so that wire crimping bending degree measurement efficiency and accuracy are calculated according to the maximum crimping wire bending degree, automatic measurement of crimping wire bending degree can be realized on different sections, and automatic crimping difficulty can be realized, and automatic applicability is reduced, and automatic measurement is realized.
Drawings
Fig. 1 is a flowchart of a method for measuring bending degree of a crimp wire in image stitching according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a first crimped wire image according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a second crimped wire image according to an embodiment of the present invention;
FIG. 4 is a photomicrograph of a full view stitched image of a crimped wire provided by an embodiment of the present invention;
FIG. 5 is a binary diagram of a crimped wire according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a crimping wire bending measurement system for image stitching according to an embodiment of the present invention.
Detailed Description
In order to make the present invention better understood by those skilled in the art, the following description will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
For easy understanding, please refer to fig. 1, the method for measuring bending degree of a crimp wire based on image stitching provided by the invention comprises the following steps:
step one, extracting characteristic points of two crimping conductor images to be spliced to obtain characteristic point sets corresponding to the two crimping conductor images to be spliced respectively.
The crimping wire image to be spliced comprises wire crimping traces.
And secondly, carrying out improved Biref characteristic description on characteristic point sets respectively corresponding to the two crimping wire images to be spliced to obtain two characteristic description strings.
And thirdly, performing characteristic point rough matching on the two characteristic description strings by adopting a Hamming distance to obtain a rough matching characteristic point pair set, and performing accurate characteristic point matching on the rough matching characteristic point pair set based on a two-way matching algorithm to obtain a fine matching characteristic point pair set.
And step four, performing image registration and image stitching on the two crimping wire images to be stitched according to the fine matching characteristic point pair set to obtain an initial stitching image.
And fifthly, performing stitching trace filtering treatment on the initial stitching image by adopting a gray weighted average method to obtain a full-view stitching image of the crimping lead.
And step six, thresholding the overall spliced image of the crimping wire, and then performing edge detection to obtain the edge of the crimping wire.
And step seven, performing least square fitting on the edge of the crimping wire to obtain a crimping edge fitting equation, obtaining a first order equation of the chord length of the crimping wire according to the crimping edge fitting equation, calculating the distance from each point of the edge of the crimping wire to the first order equation of the chord length of the crimping wire, determining the maximum radial deformation, and calculating the bending degree of the crimping wire according to the maximum radial deformation and the maximum chord length of the crimping wire.
It should be noted that, according to the crimp wire bending measurement method based on image stitching provided in this embodiment, feature point extraction is performed on two crimp wire images to be stitched, feature point sets corresponding to the two crimp wire images to be stitched respectively are improved in Biref feature description, feature point rough matching is performed on the two feature description strings by using hamming distances, accurate feature point matching is performed on the rough matching feature point pair set based on a bidirectional matching algorithm, image registration is performed on the two crimp wire images to be stitched according to the fine matching feature point pair set, image stitching is performed on the initial stitching image by using a gray weighted average method, stitching trace filtering is performed on the initial stitching image to obtain a full-view stitching image of the crimp wire, thresholding is performed on the full-view stitching image of the crimp wire, edge detection is performed, a crimp edge fitting equation is obtained by performing least square fitting on the edges of the crimp wire, a first order bending equation of the crimp wire chord length is obtained according to the crimp edge fitting equation, and the maximum radial deformation and wire crimping is calculated according to the maximum chord length, so that crimp wire bending measurement efficiency and accuracy are improved, automatic measurement difficulty can be achieved for different wires, and automatic measurement is achieved.
In one embodiment, the step one further includes, before:
and acquiring a first crimping wire image, and then moving a preset distance along the axis direction of the crimping wire, and acquiring a second crimping wire image, wherein the first crimping wire image and the second crimping wire image at least comprise a section of crimping trace.
Wherein, in one example, the process of continuously acquiring two crimping wire images is: under the condition of fixed working distance, acquiring a first crimping wire image under a proper view field sizeMoving a certain distance along the axis direction of the press-fit wire, and collecting a second press-fit wire image +.>The method comprises the steps of carrying out a first treatment on the surface of the The image acquisition platform is built by using equipment such as a CMOS industrial camera, a strip light source, a linear moving platform, a computer and the like, the working distance of the camera is adjusted, at least one section of crimping trace is contained in a visual field, and a first crimping wire image is acquired>As shown in fig. 2; operating the mobile platform, translating the camera and the light source, and collecting a second crimping wire imageAs shown in fig. 3.
In one embodiment, the first step specifically includes:
101. and carrying out gray projection on the two crimping wire images to be spliced to obtain two gray projection images.
102. And extracting the interested areas in the two gray projection images according to the gray information of the two gray projection images.
Specifically, in the process of extracting the region of interest in the two gray-scale projection images, two abrupt points can be determined according to the gray-scale information of the two gray-scale projection images, and the two abrupt points are respectively two ends of the crimping trace; selecting a mutation point with larger column coordinates as a midpoint of the region of interest for the first crimping wire image, and selecting an image in a left-right 20pixels range as a region of interest ROI of the first crimping wire image; and selecting a sudden change point with smaller column coordinates as a midpoint of the region of interest for the second crimping wire image according to the moving direction of the platform, and taking an image in a left-right 20pixels range as the region of interest of the second crimping wire image.
103. And respectively extracting characteristic points from the interested areas in the two gray projection images by using a Fast 16-9 corner detection algorithm to obtain characteristic point sets respectively corresponding to the two crimping wire images to be spliced.
The corner detection process comprises the following steps: comparing the central pixel point in the gray projection graph with the pixel points on the edge of the neighborhood with the radius of 4, and regarding the central pixel point as a corner point if 9 continuous edge pixel points which are larger or smaller than the central pixel point.
In one embodiment, the second step specifically includes:
201. and carrying out convolution processing on the crimping wire images to be spliced by adopting a mean filtering template with the size of 9 multiplied by 9.
It should be noted that, the convolution processing is performed on the crimp wire images to be spliced by adopting the average filtering template with the size of 9×9, so that the noise interference can be reduced.
202. And randomly selecting 128 pairs of pixel points in the 48 multiplied by 48 neighborhood of the characteristic points in the crimping wire image to be spliced after the convolution processing.
203. And comparing 128 pairs of gray scales of each pixel point pair in the pixel points and performing binarization processing to obtain 128-dimensional gray scale characteristic values.
Wherein, the binarization processing is as follows:
；
in the method, in the process of the invention,、/>the gray value of the pixel point pair is T, which is a binarized gray value, and thus, each feature point can be described by a 128-dimensional gray feature value.
204. And carrying out convolution processing on the crimping wire images to be spliced by using a vertical Sobel operator to obtain a gradient image.
205. Extracting feature points of the gradient image, and carrying out improved Biref feature description on a feature point set of the gradient image to obtain a 128-dimensional gradient feature value.
And performing the same operation on the feature point set of the gradient image according to the steps 201-203 to obtain a 128-dimensional gradient feature value.
206. And describing each feature point by using the 128-dimensional gray feature value and the 128-dimensional gradient feature value to obtain a 256-dimensional feature description string.
In one embodiment, the third step specifically includes:
301. randomly selecting characteristic points in a first crimping wire image to be spliced as reference characteristic points, traversing and selecting the times of different numbers of characteristic description strings between the characteristic points in a second crimping wire image to be spliced and the reference characteristic points at corresponding positions, and determining the Hamming distance;
wherein the Hamming distanceThe calculation process of (1) is as follows:
；
in the method, in the process of the invention,、/>two numbers describing the corresponding positions of the strings.
302. Screening out characteristic points in the second crimping wire image to be spliced with the minimum Hamming distance as matching points of the reference characteristic points of the first crimping wire image to be spliced;
303. sequentially traversing other characteristic points in the first crimp wire image to be spliced as reference characteristic points, and repeatedly traversing the times of selecting different numbers of the characteristic description strings between the characteristic points in the second crimp wire image to be spliced and the reference characteristic points at the corresponding positions to determine the Hamming distance until all the characteristic points in the first crimp wire image to be spliced are traversed to obtain a rough matching characteristic point pair set;
304. taking the second crimping wire image to be spliced as a reference, and performing operation according to steps 301-303 to obtain a further rough matching characteristic point pair set;
305. and carrying out intersection processing on the two coarse matching characteristic point pair sets based on a two-way matching algorithm to obtain a coarse matching characteristic point intersection set which is a fine matching characteristic point pair set.
And after intersection processing is carried out on the two coarse matching characteristic point pair sets, the characteristic point pairs contained in the two coarse matching characteristic point pair sets are obtained and serve as a fine matching characteristic point pair set.
In one embodiment, the fourth step specifically includes:
401. and determining an image homography transformation matrix according to the fine matching characteristic point pair set.
The image homography transformation matrix represents the plane relation (translation and rotation) of the first and second crimping wire images to be spliced, and specifically comprises the following steps:
；
where H is the image homography transformation matrix,、/>、/>、/>which together represent the rotation and the dimensional relationship between the two images, < >>、/>Which together represent the translational relation in column and row direction between two images, +.>、/>The distortion relationship in the column and row directions between the two images is expressed in common. Since the pixel point coordinates of the first and second crimping wire images to be spliced are known, each element in the image homography transformation matrix can be solved in sequence according to the solution of the linear equation.
402. And performing image registration on the two crimping conductor images to be spliced by using the image homography transformation matrix, and splicing the two crimping conductor images to be spliced according to an image registration result to obtain an initial spliced image.
The homography transformation relation corresponding to the characteristic points of the two crimping wire images to be spliced is as follows:
；
in (x) r ,y r ) Pixel point coordinates of the first crimping wire image to be spliced，（x l ,y l ) And the pixel point coordinates of the second crimping wire image to be spliced.
In one embodiment, the gray weighted average method is calculated by:
in the method, in the process of the invention,edge gray scale of overlapping region of full-view spliced image representing crimp wire, < >>Representing pixel coordinates +.>Representing a first crimp wire image to be spliced, < >>Representing the edge gray scale of the overlapping area of the first crimp wire image to be spliced +.>Representing a second crimp wire image to be spliced, < >>Representing the edge gray scale of the overlapping area of the second crimp wire image to be spliced +.>And->All represent gray weights, wherein,
；
。
the gray scale weighted average method is used for easily fusing the gray scales of the edges of the overlapping areas of the full-view spliced images of the crimping wires, so that crimping marks are removed, the full-view spliced images of the crimping wires are obtained, and as shown in fig. 4, fig. 4 illustrates a full-view spliced image micrograph of the crimping wires.
In one embodiment, the sixth step specifically includes:
601. and thresholding the full-view spliced image of the crimping lead by adopting a minimum error method to obtain a binary image.
The thresholding processing is performed on the spliced image by a minimum error method, the minimum error method is realized according to probability distribution density of a background and a target pixel in the image, when the error division probability is minimum, a required optimal threshold value is obtained, and then the binary image of the complete crimping conductor is obtained through area filtering and morphological processing, as shown in fig. 5, the binary image of the crimping conductor is shown in fig. 5.
602. And carrying out edge detection on the binary image by adopting a Sobel operator to obtain the edge of the crimping lead.
And carrying out thinning treatment on the edge of the binary image subjected to edge detection to obtain a single-pixel edge.
In one embodiment, the seventh step specifically includes:
701. and carrying out least square fitting on the edge of the crimping wire to obtain a crimping edge fitting equation.
Wherein, the crimping edge fitting equation isIn the formula, n is the ordinate value of the edge pixel point, m is the abscissa value of the edge pixel point, and a, b and c are coefficients.
702. The first order equation for obtaining the chord length of the crimping wire according to the crimping edge fitting equation is as follows:
；
wherein L is the chord length, m is the abscissa value of the edge pixel point, and d and k are coefficients;
and taking two end points of the crimping edge fitting equation as two points on the maximum chord length, and determining a corresponding first-order chord length equation according to the coordinates of the two points.
703. Calculating the distance from each point at the edge of the crimping wire to the first order equation of the chord length of the crimping wire, and determining the maximum radial deformation as follows:
；
wherein n is the ordinate value of the edge pixel point,is the maximum radial deformation;
704. calculating the bending degree of the wire crimping according to the maximum radial deformation and the maximum chord length of the wire crimping by the following steps:
；
in the method, in the process of the invention,cfor the wire to be crimped in a bending manner,lthe maximum chord is crimped for the wire.
The above is a detailed description of an embodiment of a method for measuring bending of a crimp wire based on image stitching provided by the invention, and the following is a detailed description of an embodiment of a system for measuring bending of a crimp wire based on image stitching provided by the invention.
For easy understanding, please refer to fig. 6, the crimping wire bending measurement system based on image stitching provided by the invention comprises:
the feature extraction module 100 is configured to perform feature point extraction on two crimp wire images to be spliced to obtain feature point sets corresponding to the two crimp wire images to be spliced respectively;
the feature description module 200 is configured to perform improved Biref feature description on feature point sets corresponding to two to-be-spliced crimping wire images respectively, so as to obtain two feature description strings;
the feature matching module 300 is configured to perform feature point rough matching on two feature description strings by using hamming distance to obtain a rough matching feature point pair set, and perform accurate feature point matching on the rough matching feature point pair set based on a two-way matching algorithm to obtain a fine matching feature point pair set;
the image stitching module 400 is configured to perform image registration on two crimp wire images to be stitched according to the fine matching feature point pair set, and perform image stitching to obtain an initial stitched image;
the trace filtering module 500 is configured to perform a trace filtering process on the initial spliced image by using a gray weighted average method, so as to obtain a full-view spliced image of the crimped wire;
the edge detection module 600 is used for thresholding the overall spliced image of the crimping wire, and then carrying out edge detection to obtain the edge of the crimping wire;
the bending calculation module 700 is configured to perform least square fitting on the edge of the crimped wire to obtain a crimp edge fitting equation, obtain a first order equation of the chord length of the crimped wire according to the crimp edge fitting equation, calculate a distance from each point of the edge of the crimped wire to the first order equation of the chord length of the crimped wire, determine a maximum radial deformation, and calculate the bending of the crimped wire according to the maximum radial deformation and the maximum chord length of the crimped wire.
It will be clear to those skilled in the art that, for convenience and brevity of description, reference may be made to the corresponding process in the foregoing method embodiment for the specific working process of the above-described system, which is not described herein again.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. The crimping wire bending measuring method based on image splicing is characterized by comprising the following steps of:
step one, extracting characteristic points of two crimping conductor images to be spliced to obtain characteristic point sets corresponding to the two crimping conductor images to be spliced respectively;
step two, carrying out improved Biref characteristic description on characteristic point sets respectively corresponding to the two crimping wire images to be spliced to obtain two characteristic description strings;
performing feature point rough matching on the two feature description strings by adopting a Hamming distance to obtain a rough matching feature point pair set, and performing accurate feature point matching on the rough matching feature point pair set based on a two-way matching algorithm to obtain a fine matching feature point pair set;
step four, performing image registration and image stitching on the two crimping wire images to be stitched according to the fine matching characteristic point pair set to obtain an initial stitching image;
step five, performing stitching trace filtering treatment on the initial stitching image by using a gray weighted average method to obtain a full-view stitching image of the crimping lead;
step six, thresholding is carried out on the overall spliced image of the crimping conductor, and then edge detection is carried out, so that the edge of the crimping conductor is obtained;
and step seven, carrying out least square fitting on the edge of the crimping wire to obtain a crimping edge fitting equation, obtaining a first order equation of the chord length of the crimping wire according to the crimping edge fitting equation, calculating the distance from each point of the edge of the crimping wire to the first order equation of the chord length of the crimping wire, determining the maximum radial deformation, and calculating the bending degree of the crimping wire according to the maximum radial deformation and the maximum chord length of the crimping wire.
2. The method for measuring bending of a crimped wire based on image stitching according to claim 1, further comprising, before the step one:
and acquiring a first crimping wire image, and then moving a preset distance along the axis direction of the crimping wire, and acquiring a second crimping wire image, wherein the first crimping wire image and the second crimping wire image at least comprise a section of crimping trace.
3. The method for measuring bending of a crimp wire based on image stitching according to claim 1, wherein the step one specifically comprises:
101. carrying out gray projection on the two crimping wire images to be spliced to obtain two gray projection images;
102. extracting the interested areas in the two gray projection images according to the gray information of the two gray projection images;
103. and respectively extracting characteristic points from the interested areas in the two gray projection images by using a Fast 16-9 corner detection algorithm to obtain characteristic point sets respectively corresponding to the two crimping wire images to be spliced.
4. The method for measuring bending of a crimp wire based on image stitching according to claim 3, wherein the second step specifically comprises:
201. carrying out convolution processing on the crimping wire images to be spliced by adopting a mean filtering template with the size of 9 multiplied by 9;
202. randomly selecting 128 pairs of pixel points in a 48 multiplied by 48 neighborhood of characteristic points in the crimping wire image to be spliced after convolution processing;
203. comparing the gray scales of each pixel point pair in 128 pairs of pixel points and performing binarization processing to obtain 128-dimensional gray scale characteristic values;
204. convolving the crimping wire images to be spliced by using a vertical Sobel operator to obtain a gradient image;
205. extracting feature points of the gradient image, and carrying out improved Biref feature description on a feature point set of the gradient image to obtain a 128-dimensional gradient feature value;
206. and describing each feature point by using the 128-dimensional gray feature value and the 128-dimensional gradient feature value to obtain a 256-dimensional feature description string.
5. The method for measuring bending of a crimp wire based on image stitching according to claim 4, wherein the third step specifically comprises:
301. randomly selecting characteristic points in a first crimping wire image to be spliced as reference characteristic points, traversing and selecting the times of different numbers of characteristic description strings between the characteristic points in a second crimping wire image to be spliced and the reference characteristic points at corresponding positions, and determining the Hamming distance;
302. screening out characteristic points in the second crimping wire image to be spliced with the minimum Hamming distance as matching points of the reference characteristic points of the first crimping wire image to be spliced;
303. sequentially traversing other characteristic points in the first crimp wire image to be spliced as reference characteristic points, and repeatedly traversing the times of selecting different numbers of the characteristic description strings between the characteristic points in the second crimp wire image to be spliced and the reference characteristic points at the corresponding positions to determine the Hamming distance until all the characteristic points in the first crimp wire image to be spliced are traversed to obtain a rough matching characteristic point pair set;
304. taking the second crimping wire image to be spliced as a reference, and performing operation according to steps 301-303 to obtain a further rough matching characteristic point pair set;
305. and carrying out intersection processing on the two coarse matching characteristic point pair sets based on a two-way matching algorithm to obtain a coarse matching characteristic point intersection set which is a fine matching characteristic point pair set.
6. The method for measuring bending of a crimp wire based on image stitching according to claim 5, wherein the fourth step specifically comprises:
401. determining an image homography transformation matrix according to the fine matching characteristic point pair set;
402. and performing image registration on the two crimping conductor images to be spliced by using the image homography transformation matrix, and splicing the two crimping conductor images to be spliced according to an image registration result to obtain an initial spliced image.
7. The method for measuring bending degree of a crimp wire based on image splicing according to claim 6, wherein the gray weighted average method comprises the following calculation processes:
；
in the method, in the process of the invention,edge gray scale of overlapping region of full-view spliced image representing crimp wire, < >>Representing pixel coordinates +.>Representing a first crimp wire image to be spliced, < >>Representing the edge gray scale of the overlapping area of the first crimp wire image to be spliced +.>Representing a second crimp wire image to be spliced, < >>Representing the edge gray scale of the overlapping area of the second crimp wire image to be spliced +.>And->All represent gray weights, wherein,
；
。
8. the method for measuring bending of a crimp wire based on image stitching according to claim 7, wherein the sixth step specifically comprises:
601. thresholding the overall spliced image of the crimping lead by adopting a minimum error method to obtain a binary image;
602. and carrying out edge detection on the binary image by adopting a Sobel operator to obtain the edge of the crimping lead.
9. The method for measuring bending of a crimp wire based on image stitching according to claim 7, wherein the seventh step specifically comprises:
701. performing least square fitting on the edge of the crimping wire to obtain a crimping edge fitting equation;
702. the first order equation for obtaining the chord length of the crimping wire according to the crimping edge fitting equation is as follows:
；
wherein L is the chord length, m is the abscissa value of the edge pixel point, and d and k are coefficients;
calculating the distance from each point of the edge of the crimping wire to the first order equation of the chord length of the crimping wire, and determining the maximum radial deformation as follows:
；
wherein n is the ordinate value of the edge pixel point,is the maximum radial deformation;
calculating the bending degree of the wire crimping according to the maximum radial deformation and the maximum chord length of the wire crimping by the following steps:
；
in the method, in the process of the invention,cfor the wire to be crimped in a bending manner,lthe maximum chord is crimped for the wire.
10. Crimping wire crookedness measurement system based on image concatenation, its characterized in that includes:
the characteristic extraction module is used for extracting characteristic points of the two crimping conductor images to be spliced to obtain characteristic point sets respectively corresponding to the two crimping conductor images to be spliced;
the characteristic description module is used for carrying out improved Biref characteristic description on the characteristic point sets respectively corresponding to the two crimping wire images to be spliced to obtain two characteristic description strings;
the feature matching module is used for carrying out feature point rough matching on the two feature description strings by adopting the Hamming distance to obtain a rough matching feature point pair set, and carrying out accurate feature point matching on the rough matching feature point pair set based on a two-way matching algorithm to obtain a fine matching feature point pair set;
the image stitching module is used for carrying out image registration on the two crimping wire images to be stitched according to the fine matching characteristic point pair set and carrying out image stitching to obtain an initial stitching image;
the trace filtering module is used for filtering the spliced trace of the initial spliced image by adopting a gray weighted average method to obtain a full-view spliced image of the crimping lead;
the edge detection module is used for carrying out thresholding treatment on the overall spliced image of the crimping wire and then carrying out edge detection to obtain the edge of the crimping wire;
the bending calculation module is used for carrying out least square fitting on the edge of the crimping wire to obtain a crimping edge fitting equation, obtaining a first order equation of the chord length of the crimping wire according to the crimping edge fitting equation, calculating the distance from each point of the edge of the crimping wire to the first order equation of the chord length of the crimping wire, determining the maximum radial deformation, and calculating the bending of the crimping wire according to the maximum radial deformation and the maximum chord length of the crimping wire.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311160832.5A CN116894776B (en) | 2023-09-11 | 2023-09-11 | Crimping wire bending degree measuring method and system based on image stitching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311160832.5A CN116894776B (en) | 2023-09-11 | 2023-09-11 | Crimping wire bending degree measuring method and system based on image stitching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116894776A true CN116894776A (en) | 2023-10-17 |
| CN116894776B CN116894776B (en) | 2024-01-23 |
Family
ID=88313791
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311160832.5A Active CN116894776B (en) | 2023-09-11 | 2023-09-11 | Crimping wire bending degree measuring method and system based on image stitching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116894776B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117135305A (en) * | 2023-10-27 | 2023-11-28 | 深圳市大而信科技有限公司 | Teleconference implementation method, device and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593832A (en) * | 2013-09-25 | 2014-02-19 | 重庆邮电大学 | Method for image mosaic based on feature detection operator of second order difference of Gaussian |
| CN105205781A (en) * | 2015-08-24 | 2015-12-30 | 电子科技大学 | Power transmission line aerial photographing image splicing method |
| CN106600592A (en) * | 2016-12-14 | 2017-04-26 | 中南大学 | Track long chord measurement method based on the splicing of continuous frame images |
| CN109596075A (en) * | 2019-01-28 | 2019-04-09 | 天津市兆瑞测控技术有限公司 | A kind of straightness or curvature on-line measurement device and method |
| CN114240845A (en) * | 2021-11-23 | 2022-03-25 | 华南理工大学 | Surface roughness measuring method by adopting light cutting method applied to cutting workpiece |
| CN115937116A (en) * | 2022-11-25 | 2023-04-07 | 国网上海市电力公司 | Detection method for strain clamp of power transmission line |
| CN116168037A (en) * | 2023-04-26 | 2023-05-26 | 广东电网有限责任公司江门供电局 | Method and system for calculating bending degree of wire crimping based on image processing |
-
2023
- 2023-09-11 CN CN202311160832.5A patent/CN116894776B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103593832A (en) * | 2013-09-25 | 2014-02-19 | 重庆邮电大学 | Method for image mosaic based on feature detection operator of second order difference of Gaussian |
| CN105205781A (en) * | 2015-08-24 | 2015-12-30 | 电子科技大学 | Power transmission line aerial photographing image splicing method |
| CN106600592A (en) * | 2016-12-14 | 2017-04-26 | 中南大学 | Track long chord measurement method based on the splicing of continuous frame images |
| CN109596075A (en) * | 2019-01-28 | 2019-04-09 | 天津市兆瑞测控技术有限公司 | A kind of straightness or curvature on-line measurement device and method |
| CN114240845A (en) * | 2021-11-23 | 2022-03-25 | 华南理工大学 | Surface roughness measuring method by adopting light cutting method applied to cutting workpiece |
| CN115937116A (en) * | 2022-11-25 | 2023-04-07 | 国网上海市电力公司 | Detection method for strain clamp of power transmission line |
| CN116168037A (en) * | 2023-04-26 | 2023-05-26 | 广东电网有限责任公司江门供电局 | Method and system for calculating bending degree of wire crimping based on image processing |
Non-Patent Citations (2)
| Title |
|---|
| R. C. HARTMANN ET AL.: "Methods for measurement of root canal curvature: a systematic and critical review", 《INTERNATIONAL ENDODONTIC JOURNAL》, pages 1 - 5 * |
| 黄双得 等: "架空输电线路压接管弯曲度测量工具研制及应用", 《电气技术》, vol. 21, no. 12, pages 74 - 77 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117135305A (en) * | 2023-10-27 | 2023-11-28 | 深圳市大而信科技有限公司 | Teleconference implementation method, device and system |
| CN117135305B (en) * | 2023-10-27 | 2024-03-19 | 深圳市大而信科技有限公司 | Teleconference implementation method, device and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116894776B (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116894776B (en) | Crimping wire bending degree measuring method and system based on image stitching | |
| US20160358322A1 (en) | Method and system for data detecting of an instrument | |
| CN109635806B (en) | Ammeter value identification method based on residual error network | |
| CN103134807B (en) | For identifying the system and method for the defect in material | |
| CN116721107B (en) | Intelligent monitoring system for cable production quality | |
| CN111667470B (en) | Industrial pipeline flaw detection inner wall detection method based on digital image | |
| CN103729631A (en) | Vision-based connector surface feature automatically-identifying method | |
| CN114973002A (en) | Improved YOLOv 5-based ear detection method | |
| CN111563896B (en) | Image processing method for detecting abnormality of overhead line system | |
| CN116168037B (en) | Method and system for calculating bending degree of wire crimping based on image processing | |
| CN110260818B (en) | Electronic connector robust detection method based on binocular vision | |
| CN110120013B (en) | Point cloud splicing method and device | |
| CN110634137A (en) | Bridge deformation monitoring method, device and equipment based on visual perception | |
| CN114755243A (en) | FPC connector surface crack detection method based on machine vision | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN116503413A (en) | Filament quality intelligent detection method based on computer vision | |
| CN114926417B (en) | Microscopic imaging detection method and system for weak scratches on surface of high-density flexible FPC | |
| CN116245948A (en) | Monocular vision cooperative target and pose measuring and calculating method | |
| CN111598097A (en) | Instrument position and reading identification method and system based on robot vision | |
| CN113963069A (en) | Method, system, computer and storage medium for measuring distance between jumper and iron tower | |
| CN116091818A (en) | Pointer type instrument reading identification method based on multi-neural network cascading model | |
| CN115641368A (en) | Method for extracting characteristics of defocused checkerboard image for calibration | |
| CN111429411B (en) | X-ray defect image sample generation method for carbon fiber composite core wire | |
| CN109087278B (en) | Condom front and back recognition method based on improved Canny operator | |
| CN109059790B (en) | Spring pitch measurement method based on Fourier transform |
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 |