CN110940372B - Cable arrangement detection system based on machine vision - Google Patents

Cable arrangement detection system based on machine vision Download PDF

Info

Publication number
CN110940372B
CN110940372B CN201911318539.0A CN201911318539A CN110940372B CN 110940372 B CN110940372 B CN 110940372B CN 201911318539 A CN201911318539 A CN 201911318539A CN 110940372 B CN110940372 B CN 110940372B
Authority
CN
China
Prior art keywords
pixel
cable
image
cable reel
value
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201911318539.0A
Other languages
Chinese (zh)
Other versions
CN110940372A (en
Inventor
毛华撑
周妙根
齐红磊
鲁运力
李鹏鹏
周建平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangxi Pacific Cable Group Co ltd
Original Assignee
Jiangxi Pacific Cable Group Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangxi Pacific Cable Group Co ltd filed Critical Jiangxi Pacific Cable Group Co ltd
Priority to CN201911318539.0A priority Critical patent/CN110940372B/en
Publication of CN110940372A publication Critical patent/CN110940372A/en
Application granted granted Critical
Publication of CN110940372B publication Critical patent/CN110940372B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

The utility model provides a cable arrangement detecting system based on machine vision, includes cable drum, image acquisition module, intelligent detection module, winding control module, winding motor and unusual warning module, image acquisition module carries out image acquisition to the cable drum regularly, intelligent detection module is used for handling and the analysis to the cable drum image of gathering, judges whether cable arrangement appears unusually on the cable drum, and the order is unusual when concluding that cable arrangement appears unusually on the cable drum reminds the module to control winding motor stop work through winding control module. The beneficial effects created by the invention are as follows: the invention uses machine vision in a cable arrangement detection system, carries out image acquisition on a cable reel at regular time after the cable reel starts to wind, and judges whether the cable arrangement on the cable reel is normal or not by processing and analyzing the acquired cable image, thereby realizing intelligent detection of the cable arrangement on the cable reel.

Description

Cable arrangement detection system based on machine vision
Technical Field
The invention relates to the field of machine vision, in particular to a cable arrangement detection system based on machine vision.
Background
In the cable production process, due to the characteristics of large production length, heavy unit weight, long transportation distance and the like of the electric wire and cable products, the electric wire and cable are usually packaged in a coiled mode, and the cable coil is widely applied as a wire coil for winding the cable. In the winding process of the cable reel, the problems of uneven winding displacement, rearrangement, missing arrangement and the like easily occur, and if the situation can be found in time, corresponding measures are taken to process, and the quality and the efficiency of cable production can be improved to a great extent.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a cable arrangement detection system based on machine vision.
The purpose of the invention is realized by the following technical scheme:
the utility model provides a cable arrangement detecting system based on machine vision, includes cable drum, image acquisition module, intelligent detection module, winding control module, winding motor and unusual warning module, image acquisition module carries out image acquisition to the cable drum regularly to with the cable drum image transmission who acquires to intelligent detection module, intelligent detection module is used for handling and the analysis the cable drum image that receives, judges whether cable arrangement appears unusually on the cable drum, makes unusual warning module remind when concluding that cable arrangement appears unusually on the cable drum, and controls winding motor stop work through winding control module.
The beneficial effects created by the invention are as follows: the invention uses machine vision in a cable arrangement detection system, carries out image acquisition on a cable reel at regular time after the cable reel starts to wind, and judges whether the cable arrangement on the cable reel is normal or not by processing and analyzing the acquired cable image, thereby realizing intelligent detection of the cable arrangement on the cable reel.
Drawings
The invention is further described with the aid of the accompanying drawings, in which, however, the embodiments do not constitute any limitation to the invention, and for a person skilled in the art, without inventive effort, further drawings may be derived from the following figures.
FIG. 1 is a schematic diagram of the present invention.
Reference numerals:
a cable reel; an image acquisition module; an intelligent detection module; a winding control module; a winding motor; and an abnormity reminding module.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1, the cable arrangement detection system based on machine vision according to this embodiment includes a cable drum, an image acquisition module, an intelligent detection module, a winding control module, a winding motor, and an abnormality reminding module, where the image acquisition module periodically acquires images of the cable drum and transmits the acquired images of the cable drum to the intelligent detection module, and the intelligent detection module is configured to process and analyze the received images of the cable drum, determine whether the arrangement of cables on the cable drum is abnormal, and when it is determined that the arrangement of cables on the cable drum is abnormal, prompt the abnormality reminding module to prompt and control the winding motor to stop working through the winding control module.
Preferably, the image acquisition module acquires images of the cable drum at intervals of T after the cable drum starts to wind.
Preferably, the intelligent detection module includes a database, a target extraction unit and an arrangement detection unit, the database stores cable reel area images corresponding to the cable arrangement at each acquisition time after the cable reel starts to wind, the target extraction unit is used for extracting the cable reel area images in the received cable reel images, and the arrangement detection unit is used for analyzing the extracted cable reel area images and judging whether the cable arrangement on the cable reel is abnormal.
Preferably, the target extracting unit is configured to extract a cable drum area image in the received cable drum image, extract edge pixels of the cable drum area in the cable drum image, and set I (t) to represent a cable drum image acquired after the cable drum starts to wind at time t, where I (I, j) represents a pixel at a coordinate (I, j) in the cable drum image I (t), and l (I, j) represents a pixel at a coordinate (I, j) in the cable drum image I (t)θ(I, j) represents a straight line having a length d around the pixel I (I, j), where θ is a straight line lθ(I, j) and the positive x-axis direction, and the initial value of θ is set to-15 °, defining that b (I, j) represents the edge attribute value of the pixel I (I, j), then b (I, j) is expressed byComprises the following steps:
Figure GDA0002505969240000021
Figure GDA0002505969240000022
Figure GDA0002505969240000023
in the formula, τθ(i, j) is a straight line lθ(I, j), h (I, j) is the gray level of pixel I (I, j), and I (x, y) is the straight line lθPixel at (I, j), h (x, y) is the gray level of pixel I (x, y), M (l)θ(i, j)) is a straight line lθ(i, j) the number of pixels, h (max) and h (min) are the maximum and minimum of the gray-scale value of the pixel in the cable drum image I (t), ηθ(i, j) is a straight line lθ(I, j) and [ omega ] (a, b) in pixels Iθ(a, b) centered
Figure GDA0002505969240000031
Is represented by the local neighborhood of (c, d) in pixels Iθ(c, d) centered
Figure GDA0002505969240000032
Local neighborhood of (I)θ(a, b) and Iθ(c, d) are each a straight line lθ(I, j) end point pixels at both ends, I (m, n) is a pixel in the local neighborhood Ω (a, b), h (m, n) represents a gray value of the pixel I (m, n), w (m, n) is a weight of the pixel I (m, n), and w (m, n) is expressed as:
Figure GDA0002505969240000033
where ρ (a, b) represents the pixel IθStructural coefficients of (a, b), and
Figure GDA0002505969240000034
Figure GDA0002505969240000035
wherein h (a, b +1) represents the gray value of the pixel at the coordinate (a, b +1) in the cable drum image I (t), h (a, b-1) represents the gray value of the pixel at the coordinate (a, b-1) in the cable drum image I (t), hθ(a, b) represents a pixel IθA gray value of (a, b), h (a +1, b) represents a gray value of a pixel at coordinates (a +1, b) in the cable drum image I (t), h (a-1, b) represents a gray value of a pixel at coordinates (a-1, b) in the cable drum image I (t), ρ (m, n) represents a structural coefficient of the pixel I (m, n), and
Figure GDA0002505969240000036
wherein h (m, n +1) represents the gray value of the pixel at the coordinate (m, n +1) in the cable drum image I (t), h (m, n-1) represents the gray value of the pixel at the coordinate (m, n-1) in the cable drum image I (t), h (m +1, n) represents the gray value of the pixel at the coordinate (m +1, n) in the cable drum image I (t), and h (m-1, n) represents the gray value of the pixel at the coordinate (m-1, n) in the cable drum image I (t);
i (m ', n') is the pixel in the local neighborhood Ω (c, d), h (m ', n') represents the gray value of the pixel I (m ', n'), w (m ', n') is the weight of the pixel I (m ', n'), and w (m ', n') is expressed as:
Figure GDA0002505969240000037
where ρ (c, d) represents the pixel IθStructural coefficients of (c, d), and
Figure GDA0002505969240000038
Figure GDA0002505969240000039
wherein h (c, d +1) represents the gray value of the pixel at the coordinate (c, d +1) in the cable reel image I (t), h (c, d-1) represents the gray value of the pixel at the coordinate (c, d-1) in the cable reel image I (t), hθ(c, d) represents a pixel IθThe gray-scale values of (c, d),h (c +1, d) represents the gray value of the pixel at the coordinate (c +1, d) in the cable drum image I (t), h (c-1, d) represents the gray value of the pixel at the coordinate (c-1, d) in the cable drum image I (t), ρ (m ', n') represents the structural coefficient of the pixel I (m ', n'), and
Figure GDA00025059692400000310
Figure GDA0002505969240000041
wherein h (m ', n' +1) represents the gray scale value of the pixel at the coordinate (m ', n' +1) in the cable drum image i (t), h (m ', n' -1) represents the gray scale value of the pixel at the coordinate (m ', n' -1) in the cable drum image i (t), h (m '+ 1, n') represents the gray scale value of the pixel at the coordinate (m '+ 1, n') in the cable drum image i (t), and h (m '-1, n') represents the gray scale value of the pixel at the coordinate (m '-1, n') in the cable drum image i (t);
given the threshold value of edge pixel H (b), when b (i, j) > H (b), the pixel b (i, j) is marked as edge pixel.
The preferred embodiment is used for extracting edge pixels of a cable reel area in a cable reel image, when determining whether a pixel is an edge pixel, by establishing straight lines with different angles and centering on the pixel as a measurement basis, if the pixel is an edge pixel, the pixel inevitably has straight lines with end points at two ends respectively belonging to a background area and a cable reel area, and for the characteristic, an edge attribute value of the pixel is defined, and an edge weight tau is introduced into the edge attribute valueθ(i, j) and edge weighing factor ηθ(i, j), the edge weight τθ(i, j) statistically measuring the degree of the pixel angle straight line reflecting the edge characteristic of the pixel by counting the difference degree of the pixel and the central pixel on the pixel angle straight line, wherein for an edge pixel, the straight lines distributed in the background area and the cable disc area simultaneously in the pixel angle straight line can effectively reflect the edge characteristic of the pixel, so the edge weight tau isθ(i, j) are larger, whereas for non-edge pixels the lines of their angles are all or mostly distributed only in the background area or cable tray area, and for pixels onlyA straight line distributed in the background area or the cable area, the pixel value change of the straight line is smaller, and therefore, the edge weight is smaller, and the edge weight coefficient ηθ(i, j) measuring the edge characteristics of the pixels through the characteristics of the end point pixels at the two ends of the straight line, wherein for one edge pixel, one or more straight lines which are simultaneously distributed in a background area and a cable reel area are inevitably existed, the end point pixels at the two ends of the straight line have larger difference, and the edge measurement coefficient can effectively measure the edge attributes of the pixel through calculating the gray level difference value of the end point pixels at the two ends of the straight line; when the edge measurement coefficient is used for calculating the gray level difference value of the end point pixels at two ends of the straight line, the mean value of the local neighborhoods of the end point pixels at the two ends is used for replacing the gray level value of the end point pixels at the two ends for calculation, so that the influence of noise pollution on the calculation result can be effectively reduced, in the process of calculating by using the pixels in the local neighborhoods of the end point pixels, the pixels in the local neighborhoods of the end point pixels of the straight line of the edge pixels are considered to be possible to simultaneously have the pixels in a background area and the pixels in a cable reel area, aiming at the situation, the preferred embodiment introduces the structural coefficient of the pixels to carry out space limitation on the pixels in the local neighborhoods of the end points, the structural coefficient of the pixels reflects the space structure of the pixels, and can effectively judge whether the pixels and the end point pixels are in the same area by comparing the structural coefficient of the end point pixels, and, therefore, the influence of the participation of the pixels in different structural regions in the operation on the accuracy of the calculation result is avoided, and the accuracy of the edge pixel extraction result is improved.
Preferably, the threshold value h (b) is determined in the following manner:
the arrangement detection unit extracts a cable reel image from a database, artificially marks edge pixels of the cable reel area in the cable reel image, calculates edge attribute values of the marked edge pixels, and sets the minimum value of the edge attribute values of the edge pixels as a threshold value H (b).
The preferred embodiment is used for determining the threshold value h (b) of the edge attribute value of the pixel, the arrangement detection unit extracts a cable reel image from the database, artificially marks the edge pixels in the cable reel image, calculates the edge attribute value of the marked edge pixels, and sets the minimum value of the edge attribute values of the edge pixels as the threshold value h (b), so that the accuracy is high.
Preferably, the cable drum area image in the cable drum image is determined according to the extracted edge pixels, specifically:
and checking the extracted edge pixels, and setting B (t) to represent an edge pixel set of the cable tray area in the extracted cable tray image I (t), wherein I (k, l) is an edge pixel in the edge pixel set B (t), the corresponding reliability of the edge pixel I (k, l) is defined to be D (k, l), and the expression of D (k, l) is as follows:
Figure GDA0002505969240000051
in the formula, Ω (k, l) represents a value centered on the pixel I (k, l)
Figure GDA0002505969240000052
I (x, y) is a pixel in the local neighborhood Ω (k, l), and I (x, y) ≠ I (k, l), b (x, y) represents an edge attribute value of the pixel I (x, y), b (k, l) represents an edge attribute value of the edge pixel I (k, l), α (b (x, y), b (k, l)) is a value-taking function, when b (x, y) < b (k, l), α (b (x, y), b (k, l)) is 1, when b (x, y) ≧ b (k, l), α (b (x, y), b (k, l)) is 0, M (k, l) represents Ω, β (b (x, y), h (b)) represents a value-taking function, when b (x, y) > h, y, h (b) is equal to 0, M (k, l) represents a pixel number (b, h, β (b) (h) (b) in the local neighborhood), wherein (x, y) represents a threshold value (h), (β), (b), (y), (b), (h), (b), (h), (b), (y), (h), (b), (h), (b), (y), (h), (b), (h), (b), (h), (;
when the reliability D (k, l) > 0 of the edge pixel I (k, l), the edge pixel I (k, l) is reserved in the edge pixel set B (t), otherwise, the edge pixel I (k, l) is removed from the edge pixel set B (t), and the rest edge pixels in the edge pixel set B (t) are connected through a curve, wherein the area in the curve is the cable reel area image in the cable reel image.
The preferred embodiment is used for checking the extracted edge pixels and defining the reliability D (k, l) of the edge pixels, wherein the reliability consists of two parts, the first part is used for comparing the edge attribute values of the edge pixels and the pixels in the local neighborhood, the edge attribute value of the edge pixel is higher than that of the common pixel, and when the edge attribute value of the edge pixel is higher than that of most pixels in the local neighborhood, the edge pixel has higher reliability and is the edge pixel; the second part is used for counting the edge pixels in the local neighborhood of the edge pixel, when one pixel is the edge pixel, the edge pixel adjacent to the pixel necessarily exists in the local neighborhood, and through counting other edge pixels in the local neighborhood of the edge pixel, the edge pixels which are separately distributed due to false detection in the edge pixel set B (t) can be effectively removed, and the accuracy of extracting the subsequent cable reel area is improved.
Preferably, the arrangement detecting unit is configured to analyze the extracted cable drum area image, and determine whether the arrangement of the cables on the cable drum is abnormal, and specifically includes:
(1) setting the cable image acquired at the time t as I (t), I1(t) representing the cable reel area image extracted from the cable reel image I (t), and defining the cable area image I1The alignment detection coefficient of (t) was L (I)1(t)), L (I)1(t)) is:
Figure GDA0002505969240000061
in the formula, X and Y respectively represent cable reel area images I1Length and width of (t), h1(I +1, j) represents a cable drum area image I1(t) the gray value of the pixel at coordinate (i +1, j), h1(I-1, j) represents a cable drum area image I1(t) the gray value of the pixel at coordinate (i-1, j), h1(I, j +1) represents a cable drum area image I1(t) the gray value of the pixel at coordinate (i, j +1), h1(I, j-1) image of area of cable drum I1(t) the gray value of the pixel at coordinate (i, j-1), h1(max) represents the cable drum area image I1Maximum value of pixel gray-scale value in (t), h1(min) image of area of cable reel I1(t) the minimum value of the gray value of the pixel;
(2) the arrangement detection unit calls a cable reel area image after the cable reel starts to wind from the database and records the cable reel area image as a reference image I2(t) calculating the reference image I2(t) array detection coefficient L (I)2(t)), the array detection coefficient L (I) obtained by the calculation is calculated2(t)) and cable drum area image I1(t) array detection coefficient L (I)1(t)) are compared when
Figure GDA0002505969240000062
Figure GDA0002505969240000063
When the cable is arranged normally, the arrangement detection unit judges that the cable on the cable drum is arranged normally at the current moment
Figure GDA0002505969240000064
Or
Figure GDA0002505969240000065
And judging that the arrangement of the cables on the cable drum is abnormal at the current moment by the arrangement detection unit.
The preferred embodiment is used for analyzing the extracted cable reel area image, judging whether the cable arrangement on the cable reel is abnormal or not, defining an arrangement detection coefficient, taking the variation degree of row pixels and column pixels in the defined arrangement detection coefficient in the cable reel area image as a detection factor of the cable arrangement on the cable reel according to the characteristic of the cable arrangement on the cable reel, effectively reflecting the characteristic of the cable arrangement on the cable reel, comparing the calculated cable arrangement detection coefficient with the arrangement detection coefficient of the cable reel area image under the condition that the cable arrangement at the same moment is normal, and timely and effectively judging whether the cable arrangement on the cable reel is abnormal or not.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims (3)

1. A cable arrangement detection system based on machine vision is characterized by comprising a cable reel, an image acquisition module, an intelligent detection module, a winding control module, a winding motor and an abnormality reminding module, wherein the image acquisition module acquires images of the cable reel at regular time and transmits the acquired images of the cable reel to the intelligent detection module, the intelligent detection module is used for processing and analyzing the received images of the cable reel, judging whether the arrangement of cables on the cable reel is abnormal or not, reminding the abnormality reminding module when judging that the arrangement of the cables on the cable reel is abnormal, and controlling the winding motor to stop working through the winding control module, the intelligent detection module comprises a database, a target extraction unit and an arrangement detection unit, the database stores the images of the cable reel area corresponding to each acquisition time after the cable reel starts winding under the condition that the arrangement of the cables is normal, the target extraction unit is used for extracting a cable reel area image in the received cable reel image, and specifically comprises:
(1) extracting edge pixels of the cable reel area in the cable reel image, setting I (t) to represent the cable reel image acquired after the cable reel starts to wind at t moment, wherein I (I, j) represents a pixel at a coordinate (I, j) in the cable reel image I (t), and lθ(I, j) represents a straight line having a length d around the pixel I (I, j), where θ is a straight line lθ(I, j) and the positive x-axis direction, and the initial value of θ is set to-15 °, defining that b (I, j) represents the edge attribute value of the pixel I (I, j), the expression of b (I, j) is:
Figure FDA0002505969230000011
Figure FDA0002505969230000012
Figure FDA0002505969230000013
in the formula, τθ(i, j) is a straight line lθ(I, j), h (I, j) is the gray level of pixel I (I, j), and I (x, y) is the straight line lθPixel at (I, j), h (x, y) is the gray level of pixel I (x, y), M (l)θ(i, j)) is a straight line lθ(i, j) the number of pixels, h (max) and h (min) are the maximum and minimum of the gray-scale value of the pixel in the cable drum image I (t), ηθ(i, j) is a straight line lθ(I, j) and [ omega ] (a, b) in pixels Iθ(a, b) centered
Figure FDA0002505969230000014
Is represented by the local neighborhood of (c, d) in pixels Iθ(c, d) centered
Figure FDA0002505969230000015
Local neighborhood of (I)θ(a, b) and Iθ(c, d) are each a straight line lθ(I, j) end point pixels at both ends, I (m, n) is a pixel in the local neighborhood Ω (a, b), h (m, n) represents a gray value of the pixel I (m, n), w (m, n) is a weight of the pixel I (m, n), and w (m, n) is expressed as:
Figure FDA0002505969230000021
where ρ (a, b) represents the pixel IθStructural coefficients of (a, b), and
Figure FDA0002505969230000022
Figure FDA0002505969230000023
wherein h (a, b +1) represents the gray value of the pixel at the coordinate (a, b +1) in the cable drum image I (t), h (a, b-1) represents the gray value of the pixel at the coordinate (a, b-1) in the cable drum image I (t), hθ(a, b) represents a pixel IθA gray value of (a, b), h (a +1, b) represents a gray value of a pixel at coordinates (a +1, b) in the cable drum image I (t), h (a-1, b) represents a gray value of a pixel at coordinates (a-1, b) in the cable drum image I (t), ρ (m, n) represents a structural coefficient of the pixel I (m, n), and
Figure FDA0002505969230000024
wherein h (m, n +1) represents the gray value of the pixel at the coordinate (m, n +1) in the cable drum image I (t), h (m, n-1) represents the gray value of the pixel at the coordinate (m, n-1) in the cable drum image I (t), h (m +1, n) represents the gray value of the pixel at the coordinate (m +1, n) in the cable drum image I (t), and h (m-1, n) represents the gray value of the pixel at the coordinate (m-1, n) in the cable drum image I (t);
i (m ', n') is the pixel in the local neighborhood Ω (c, d), h (m ', n') represents the gray value of the pixel I (m ', n'), w (m ', n') is the weight of the pixel I (m ', n'), and w (m ', n') is expressed as:
Figure FDA0002505969230000025
where ρ (c, d) represents the pixel IθStructural coefficients of (c, d), and
Figure FDA0002505969230000026
Figure FDA0002505969230000027
wherein h (c, d +1) represents the gray value of the pixel at the coordinate (c, d +1) in the cable reel image I (t), h (c, d-1) represents the gray value of the pixel at the coordinate (c, d-1) in the cable reel image I (t), hθ(c, d) represents the gray scale value of the pixel I theta (c, d), and h (c +1, d) represents the gray scale value of the pixel at the coordinate (c +1, d) in the cable drum image I (t)The value h (c-1, d) represents the gray value of the pixel at the coordinate (c-1, d) in the cable drum image I (t), ρ (m ', n') represents the structural coefficient of the pixel I (m ', n'), and
Figure FDA0002505969230000028
Figure FDA0002505969230000029
wherein h (m ', n' +1) represents the gray scale value of the pixel at the coordinate (m ', n' +1) in the cable drum image i (t), h (m ', n' -1) represents the gray scale value of the pixel at the coordinate (m ', n' -1) in the cable drum image i (t), h (m '+ 1, n') represents the gray scale value of the pixel at the coordinate (m '+ 1, n') in the cable drum image i (t), and h (m '-1, n') represents the gray scale value of the pixel at the coordinate (m '-1, n') in the cable drum image i (t);
giving an edge pixel threshold value H (b), and when b (i, j) > H (b), marking the pixel b (i, j) as an edge pixel;
(2) determining a cable reel area image in the cable reel image according to the extracted edge pixels of the cable reel area; the arrangement detection unit is used for analyzing the extracted image of the cable reel area and judging whether the arrangement of the cables on the cable reel is abnormal or not.
2. The system according to claim 1, wherein the cable reel area image in the cable reel image is determined according to the edge pixels of the cable reel area extracted, and specifically comprises:
and checking the extracted edge pixels, and setting B (t) to represent an edge pixel set of the cable tray area in the extracted cable tray image I (t), wherein I (k, l) is an edge pixel in the edge pixel set B (t), the corresponding reliability of the edge pixel I (k, l) is defined to be D (k, l), and the expression of D (k, l) is as follows:
Figure FDA0002505969230000031
in the formula, Ω (k, l) representsCentred on the pixel I (k, l)
Figure FDA0002505969230000032
I (x, y) is a pixel in the local neighborhood Ω (k, l), and I (x, y) ≠ I (k, l), b (x, y) represents an edge attribute value of the pixel I (x, y), b (k, l) represents an edge attribute value of the edge pixel I (k, l), α (b (x, y), b (k, l)) is a value-taking function, when b (x, y) < b (k, l), α (b (x, y), b (k, l)) is 1, when b (x, y) ≧ b (k, l), α (b (x, y), b (k, l)) is 0, M (k, l) represents Ω, β (b (x, y), h (b)) represents a value-taking function, when b (x, y) > h, y, h (b) is equal to 0, M (k, l) represents a pixel number (b, h, β (b) (h) (b) in the local neighborhood), wherein (x, y) represents a threshold value (h), (β), (b), (y), (b), (h), (b), (h), (b), (y), (h), (b), (h), (b), (y), (h), (b), (h), (b), (h), (;
when the reliability D (k, l) > 0 of the edge pixel I (k, l), the edge pixel I (k, l) is reserved in the edge pixel set B (t), otherwise, the edge pixel I (k, l) is removed from the edge pixel set B (t), and the rest edge pixels in the edge pixel set B (t) are connected through a curve, wherein the area in the curve is the cable reel area image in the cable reel image.
3. The system according to claim 2, wherein the arrangement detection unit is configured to analyze the extracted image of the cable drum area to determine whether the arrangement of the cables on the cable drum is abnormal, and specifically includes:
(1) setting the cable image acquired at the time t as I (t), I1(t) representing the cable reel area image extracted from the cable reel image I (t), and defining the cable reel area image I1The alignment detection coefficient of (t) was L (I)1(t)), L (I)1(t)) is:
Figure FDA0002505969230000033
in the formula, X and Y respectively represent cable reel area images I1Length and width of (t), h1(I +1, j) represents a cable drum area image I1(t) the gray value of the pixel at coordinate (i +1, j), h1(I-1, j) represents a cable drum area image I1(t) the gray value of the pixel at coordinate (i-1, j), h1(I, j +1) represents a cable drum area image I1(t) the gray value of the pixel at coordinate (i, j +1), h1(I, j-1) image of area of cable drum I1(t) the gray value of the pixel at coordinate (i, j-1), h1(max) represents the cable drum area image I1Maximum value of pixel gray-scale value in (t), h1(min) image of area of cable reel I1(t) the minimum value of the gray value of the pixel;
(2) the arrangement detection unit calls a cable reel area image after the cable reel starts to wind from the database and records the cable reel area image as a reference image I2(t) calculating the reference image I2(t) array detection coefficient L (I)2(t)), the array detection coefficient L (I) obtained by the calculation is calculated2(t)) and cable drum area image I1(t) array detection coefficient L (I)1(t)) are compared when
Figure FDA0002505969230000041
Figure FDA0002505969230000042
When the cable is arranged normally, the arrangement detection unit judges that the cable on the cable drum is arranged normally at the current moment
Figure FDA0002505969230000043
Or
Figure FDA0002505969230000044
And judging that the arrangement of the cables on the cable drum is abnormal at the current moment by the arrangement detection unit.
CN201911318539.0A 2019-12-19 2019-12-19 Cable arrangement detection system based on machine vision Active CN110940372B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911318539.0A CN110940372B (en) 2019-12-19 2019-12-19 Cable arrangement detection system based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911318539.0A CN110940372B (en) 2019-12-19 2019-12-19 Cable arrangement detection system based on machine vision

Publications (2)

Publication Number Publication Date
CN110940372A CN110940372A (en) 2020-03-31
CN110940372B true CN110940372B (en) 2020-07-21

Family

ID=69912116

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911318539.0A Active CN110940372B (en) 2019-12-19 2019-12-19 Cable arrangement detection system based on machine vision

Country Status (1)

Country Link
CN (1) CN110940372B (en)

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3997128A (en) * 1974-12-18 1976-12-14 The Furukawa Electric Co., Ltd. Wire take up apparatus
JPS56164688A (en) * 1980-05-23 1981-12-17 Hitachi Ltd Remote visual device
GB2273278A (en) * 1992-12-09 1994-06-15 Deutsche Tiefbohr Ag Controlling a cable hoist
CN102032875A (en) * 2009-09-28 2011-04-27 王吉林 Image-processing-based cable sheath thickness measuring method
CN103839247A (en) * 2012-11-20 2014-06-04 富士通株式会社 Edge pixel determination method, edge pixel determination apparatus, and image processing device
CN104535356A (en) * 2015-01-19 2015-04-22 中南大学 Method and system for monitoring rope arrangement faults of drum steel wire rope on basis of machine vision
CN105718842A (en) * 2014-12-02 2016-06-29 中国科学院沈阳自动化研究所 Machine vision-based detection method for transmission line strand breakage fault
CN106629234A (en) * 2016-10-12 2017-05-10 哈尔滨理工大学 Vision-based automatic winding scheme
CN207730842U (en) * 2017-12-20 2018-08-14 武汉国电武仪电气股份有限公司 A kind of cable line sequence detection device
CN208013105U (en) * 2018-03-20 2018-10-26 天津凯西固德技术发展有限公司 Finished cable outward appearance check out test set
CN108921132A (en) * 2018-07-27 2018-11-30 广东电网有限责任公司 Unmanned aerial vehicle onboard cable detection system
CN109179064A (en) * 2018-07-27 2019-01-11 南京理工大学 Cable arrangements detection system and method on a kind of cable reel
CN109409272A (en) * 2018-10-17 2019-03-01 北京空间技术研制试验中心 Cable Acceptance Test System and method based on machine vision

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6247664B1 (en) * 1999-06-25 2001-06-19 Siecor Operations, Llc Reel monitor devices and methods of using the same

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3997128A (en) * 1974-12-18 1976-12-14 The Furukawa Electric Co., Ltd. Wire take up apparatus
JPS56164688A (en) * 1980-05-23 1981-12-17 Hitachi Ltd Remote visual device
GB2273278A (en) * 1992-12-09 1994-06-15 Deutsche Tiefbohr Ag Controlling a cable hoist
CN102032875A (en) * 2009-09-28 2011-04-27 王吉林 Image-processing-based cable sheath thickness measuring method
CN103839247A (en) * 2012-11-20 2014-06-04 富士通株式会社 Edge pixel determination method, edge pixel determination apparatus, and image processing device
CN105718842A (en) * 2014-12-02 2016-06-29 中国科学院沈阳自动化研究所 Machine vision-based detection method for transmission line strand breakage fault
CN104535356A (en) * 2015-01-19 2015-04-22 中南大学 Method and system for monitoring rope arrangement faults of drum steel wire rope on basis of machine vision
CN106629234A (en) * 2016-10-12 2017-05-10 哈尔滨理工大学 Vision-based automatic winding scheme
CN207730842U (en) * 2017-12-20 2018-08-14 武汉国电武仪电气股份有限公司 A kind of cable line sequence detection device
CN208013105U (en) * 2018-03-20 2018-10-26 天津凯西固德技术发展有限公司 Finished cable outward appearance check out test set
CN108921132A (en) * 2018-07-27 2018-11-30 广东电网有限责任公司 Unmanned aerial vehicle onboard cable detection system
CN109179064A (en) * 2018-07-27 2019-01-11 南京理工大学 Cable arrangements detection system and method on a kind of cable reel
CN109409272A (en) * 2018-10-17 2019-03-01 北京空间技术研制试验中心 Cable Acceptance Test System and method based on machine vision

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于机器视觉的电缆方位检测系统;曹东晨等;《东华大学学报（自然科学版）》;20190228;第45卷(第1期);第75-81页 *

Also Published As

Publication number Publication date
CN110940372A (en) 2020-03-31

Similar Documents

Publication Publication Date Title
US8254723B2 (en) System and method for extracting boundary elements of an object
CN103759758B (en) A kind of method for detecting position of the automobile meter pointer based on mechanical angle and scale identification
CN109813722B (en) Contact net dropper defect detection method
CN106709905B (en) Vibration damper fault online detection and identification method based on binocular vision image
CN110390306A (en) Detection method, vehicle and the computer readable storage medium of right angle parking stall
CN110706210B (en) Deep learning-based rebar counting method and device
CN110766095A (en) Defect detection method based on image gray level features
CN114255405A (en) Hidden danger target identification method and device
CN114459372A (en) Online intelligent early warning method for deformation and damage of steel frame steel column
CN116342598B (en) Steel strand quality detection method based on machine vision
CN112907027A (en) Intelligent logistics full-period tracking management method based on big data analysis and cloud computing and cloud management platform
CN115171361B (en) Dangerous behavior intelligent detection and early warning method based on computer vision
CN110940372B (en) Cable arrangement detection system based on machine vision
CN115761509A (en) Multi-point track form and position disease measurement method based on image recognition
CN116338392A (en) Method, device and equipment for identifying lightning discharge defects of glass insulator
CN116721096B (en) New energy harness quality online detection method based on artificial intelligence
CN115600747B (en) Tunnel state monitoring and management method and system based on Internet of things
CN111932061A (en) Highway technical condition evaluation method and device
CN111695735A (en) Railway bow net real-time early warning method, system and device based on flow calculation
CN116645446A (en) Road and bridge safety detection system and detection method
CN114111576B (en) Aircraft skin gap surface difference detection method
CN112858725B (en) Vehicle speed consistency detection method, terminal equipment and storage medium
CN112734753A (en) Assembly type bridge deck safety real-time monitoring method based on cloud computing and image analysis and monitoring management cloud platform
CN103018327A (en) Ultrasonic flaw detection brazed rate measuring method of rectifier of aero-engine
CN111775760A (en) Intelligent management system for solar charging piles

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
CB03 Change of inventor or designer information
CB03 Change of inventor or designer information

Inventor after: Mao Huacheng

Inventor after: Zhou Miaogen

Inventor after: Qi Honglei

Inventor after: Lu Yunli

Inventor after: Li Pengpeng

Inventor after: Zhou Jianhua

Inventor before: Mao Huacheng

Inventor before: Zhou Miaogen

Inventor before: Qi Honglei

Inventor before: Lu Yunli

Inventor before: Li Pengpeng

Inventor before: Zhou Jianping