CN115147416A - Rope disorder detection method and device for rope rewinder and computer equipment - Google Patents
Rope disorder detection method and device for rope rewinder and computer equipment Download PDFInfo
- Publication number
- CN115147416A CN115147416A CN202211068137.1A CN202211068137A CN115147416A CN 115147416 A CN115147416 A CN 115147416A CN 202211068137 A CN202211068137 A CN 202211068137A CN 115147416 A CN115147416 A CN 115147416A
- Authority
- CN
- China
- Prior art keywords
- rope
- pixel points
- edge
- gray
- disorder
- 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
Images
Classifications
-
- 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
- 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
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device for detecting rope disorder of a rope rewinder and computer equipment, and belongs to the technical field of image processing; the method comprises the following steps: acquiring a gray scale image of a steel wire rope winding area; acquiring the gray gradient value and the gray gradient direction of each pixel point; obtaining a linear edge binary image; calculating to obtain a rope disorder coefficient according to the gray values of all pixel points projected towards the winding direction of the steel wire rope in the linear edge binary image and the angle of each edge line; and judging the rope disorder condition on the rope rewinder according to the rope disorder coefficient. The invention adopts a camera to collect the depression angle image of the rope rewinding machine and segment the winding part; analyzing a rope disorder coefficient of the image by using an improved LSD straight line detection method; and judging the rope disorder condition of the rope rewinder according to the obtained rope disorder coefficient of the rope rewinder.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a rope disorder detection method and device for a rope rewinder and computer equipment.
Background
Steel wire ropes play an important role in many industrial operations, so the quality and reliability of steel wire ropes are always concerned, but the steel wire ropes often have premature failure phenomena such as abrasion, deformation and structural damage in the operation, and disorder ropes are one of the main reasons for premature failure of the steel wire ropes.
At present, when detecting whether a rope disorder phenomenon exists on a steel wire rope on a rope rewinding machine, when a line detection algorithm (LSD) is adopted to perform line detection, as the LSD line detection is a local algorithm, usually a line is extracted by combining information of image gradient and direction, a line support area is firstly generated, gradient values, namely gradient directions, of each pixel point are calculated, a gradient field is generated, and then pixels with the same gradient are connected into the line support area by manually setting a threshold value. And then selecting the minimum bounding rectangle of each straight line support area, wherein the main axis of the rectangle represents the main axis direction of the support area, and the rectangle covers the whole area, so that the minimum bounding rectangle represents the straight line information. In the traditional LSD algorithm, although the calculation amount is much smaller than that of Hough line detection, the algorithm has the defect that when two lines are intersected, the algorithm cannot well process the intersection, the detected line is likely to be split into a plurality of line segments due to intersection and the like, and the accuracy of wire rope disorder detection is reduced.
Disclosure of Invention
The invention provides a method, a device and computer equipment for detecting rope disorder of a rope rewinding machine, wherein the method adopts a camera to acquire a depression image of the rope rewinding machine and divides a winding part of the rope rewinding machine; analyzing a rope disorder coefficient of the image by using an improved LSD straight line detection method; and judging the rope disorder condition of the rope rewinder according to the obtained rope disorder coefficient of the rope rewinder.
The embodiment of the application provides a rope disorder detection method for a rope rewinder, which comprises the following steps:
acquiring a gray scale image of a steel wire rope winding area;
acquiring the gray gradient value and the gray gradient direction of each pixel point according to the gray value of each pixel point in the gray map and the gray value of the neighborhood pixel point;
dividing all pixel points into edge pixel points and smooth pixel points according to the gray gradient value of each pixel point;
obtaining the similarity of two edge pixel points according to the gray gradient value and the gray gradient direction of one edge pixel point and a neighborhood edge pixel point and the Euclidean distance between the two pixel points, and clustering all the edge pixel points according to the similarity of any two edge pixel points; sequentially dividing all edge pixel points into different categories;
thinning edge pixel points in each category and combining the gray gradient direction of the edge pixel points to obtain edge straight lines, sequentially obtaining a plurality of edge straight lines, and performing semantic segmentation on pixel points and all smooth pixel points on each edge straight line in a gray-scale image to obtain a straight line edge binary image;
calculating to obtain a rope disorder coefficient according to the gray values of all pixel points projected towards the winding direction of the steel wire rope in the linear edge binary image and the angle of each edge line;
and judging the rope disorder condition on the rope rewinder according to the rope disorder coefficient.
In an embodiment, the dividing of all the pixels into edge pixels and smooth pixels according to the gray scale gradient value of each pixel is to arrange all the pixels from large to small according to the number of levels of the gray scale gradient value, and divide all the pixels into two types, namely edge pixels and smooth pixels, by obtaining two adjacent numbers of levels with the largest difference.
In an embodiment, the two adjacent levels are the maximum gray scale gradient value of the smooth pixel point and the minimum gray scale gradient value of the edge pixel point respectively, an average value of the maximum gray scale gradient value of the smooth pixel point and the minimum gray scale gradient value of the edge pixel point is calculated according to the maximum gray scale gradient value of the smooth pixel point and the minimum gray scale gradient value of the edge pixel point, and all the pixel points are divided into the edge pixel point and the smooth pixel point by taking the average value as a boundary.
In an embodiment, in the process of clustering all edge pixels according to the similarity of any two edge pixels, when the similarity of two edge pixels is smaller than a preset threshold, the two edge pixels are similar pixels, the similar edge pixels are classified into one category, and all the edge pixels are sequentially classified into different categories.
In an embodiment, the similarity calculation formula of the two edge pixels is as follows:
in the formula (I), the compound is shown in the specification,
and
expressing the gray gradient values of any two edge pixel points in the image;
In an embodiment, the dividing of all edge pixel points into multiple categories sequentially removes the category with the number of edge pixel points less than 20.
In an embodiment, the gray value obtaining method of the projection of all pixel points in the linear edge binary image towards the winding direction of the steel wire rope is as follows: projecting the gray values of all pixel points in a row according to columns, and adding the gray values of each column of pixel points in the linear edge binary image to be used as the gray value of the projection of the column of pixel points; the angle of each straight line is an included angle between each straight line and the axial direction of the rope rewinding machine.
In one embodiment, the rope tangling coefficient is calculated as follows:
in the formula (I), the compound is shown in the specification,
the rope disorder coefficient of the rope rewinder is represented;
representing a total of k gray values less than
The number of pixel points;
the number of pixel points representing that the gray value after projection is not 0;
representing the gray value corresponding to the projected pixel point; e represents the number of edge lines;
representing the angle of each edge line;
the number of lines representing the pixel points in the binary image,
and (5) expressing the column number of the pixel points in the binary image.
In addition, in order to achieve the above object, the present invention further provides a rope disorder detecting device for a rope rewinding machine, comprising:
the image acquisition module is used for acquiring a gray scale image of a steel wire rope winding area;
the pixel point dividing module is used for acquiring the gray gradient value and the gray gradient direction of each pixel point according to the gray value of each pixel point in the gray map of the winding area of the steel wire rope and the gray value of the adjacent pixel point; dividing all pixel points into edge pixel points and smooth pixel points according to the gray gradient value of each pixel point;
the binary image acquisition module is used for clustering all edge pixel points according to the gray gradient values and the gray gradient directions of the edge pixel points and the Euclidean distance between any two edge pixel points, and dividing all the edge pixel points into different categories; thinning edge pixel points in each category and combining the gray gradient direction of the edge pixel points to obtain edge straight lines, sequentially obtaining a plurality of edge straight lines, and performing semantic segmentation on pixel points and all smooth pixel points on each edge straight line in a gray-scale image to obtain a straight line edge binary image;
the rope disorder coefficient calculation module is used for calculating a rope disorder coefficient according to the gray values of all pixel points in the linear edge binary image projected towards the winding direction of the steel wire rope and the angle of each edge line;
and the rope disorder judging module is used for judging the rope disorder condition on the rope rewinder according to the obtained rope disorder coefficient.
Further, to achieve the above object, the present invention also provides a computer apparatus comprising:
the rope-tangling detection method comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the computer program realizes the steps of the rope-tangling detection method when being executed by the processor.
The invention has the beneficial effects that:
the invention provides a rope disorder detection method and device for a rope rewinder and computer equipment, wherein a camera is adopted to collect a depression image of the rope rewinder and divide a winding part of the rope rewinder; analyzing a rope disorder coefficient of the image by using an improved LSD straight line detection method; and judging the rope disorder condition of the rope rewinder according to the obtained rope disorder coefficient of the rope rewinder.
The invention uses the rope disorder coefficient to express the rope disorder condition of the rope rewinder, the larger the coefficient is, the larger the rope disorder condition is, when
In time, the service life and the efficiency of the equipment are not influenced too much even if the rope is disordered by the rope rewinding machine;
in time, the rope-rewinding machine is considered to have serious rope disorder, and the service life and the efficiency of the machine are greatly influenced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic flow chart showing the general steps of a rope disorder detection method of a rope rewinder according to an embodiment of the present invention;
fig. 2 is a control schematic block diagram of a rope disorder detection device of the rope rewinding machine.
Fig. 3 is a schematic structural diagram of a hardware operating environment according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention adopts a camera to collect the depression angle image of the rope rewinding machine and segment the winding part; analyzing a rope disorder coefficient of the image by using an improved LSD straight line detection method; and judging the rope disorder condition of the rope rewinder according to the obtained rope disorder coefficient of the rope rewinder.
Referring to fig. 1, in an embodiment of the present application, a rope disorder detection method of a rope rewinding machine includes the following steps:
s1, acquiring a gray scale image of a steel wire rope winding area; firstly, acquiring an image of a steel wire rope on a rope rewinding machine, and acquiring a gray-scale image of a steel wire rope winding area after gray-scale processing of the image;
in this embodiment, a top-down view camera is used to capture an image of the winding state of the steel wire rope of the rope rewinder, the image is first converted into a gray image, the captured image is processed by semantic segmentation, and the wound part of the steel wire rope in the rewinder is segmented and processed. After the image is collected and grayed by the rope rewinding machine, the image is semantically segmented into an image only comprising a rope winding area.
The semantic segmentation network specifically comprises the following steps: 1) The network input is a gray image of a rope-rewinding machine depression image collected at a fixed distance; 2) In semantic segmentation, marking the pixel point of a rope winding area as 1, marking the pixel point of a background as 0, and separating the two areas; 3) The loss function used by semantic segmentation is a cross entropy loss function; for the divided image, the image size is set to be n × m.
S2, acquiring a gray gradient value and a gray gradient direction value of each pixel point according to the gray value of each pixel point in the gray map of the steel wire rope winding area and the gray values of the neighborhood pixel points;
the gray-scale image which is semantically segmented is scaled, so that the sawtooth effect of the image is avoided, and the detection precision is reduced. Then, the gradient value of each pixel and the gradient direction thereof are calculated, and the calculation formula is as follows:
in the formula (I), the compound is shown in the specification,
expressing the gray gradient value of the pixel point in the horizontal direction;
Then, the whole image is subjected to the calculation to obtain the gray gradient value of each pixel point
And gray scale gradient direction
For the image, the more the edge part is, the more the gray value changes violently, the more the smooth part is, the more the gray value changes slowly, so after the gray gradient value and the gray gradient direction value of each pixel point are obtained, the straight line edge can be determined according to the similarity between the pixel points by using the two values. Wherein the gray gradient valueThe larger the gradient direction is, the more the pixel point is at the edge position, and the gradient direction can judge whether the edge is a straight line or not.
S3, dividing all the pixel points into edge pixel points and smooth pixel points according to the gray gradient value of each pixel point;
specifically, all the pixel points are arranged from large to small according to the number of levels of the gray gradient values, and all the pixel points are divided into two types, namely edge pixel points and smooth pixel points by obtaining two adjacent levels with the largest difference value. The two adjacent levels are respectively the maximum gray scale gradient value of the smooth pixel point and the minimum gray scale gradient value of the edge pixel point, the average value of the two adjacent levels is calculated according to the maximum gray scale gradient value of the smooth pixel point and the minimum gray scale gradient value of the edge pixel point, and all the pixel points are divided into the edge pixel points and the smooth pixel points by taking the average value as a boundary.
S4, obtaining the similarity of two edge pixel points according to the gray gradient value and the gray gradient direction of one edge pixel point and a neighborhood edge pixel point and the Euclidean distance between the two pixel points, clustering all the edge pixel points according to the similarity of any two edge pixel points, and dividing all the edge pixel points into different categories;
in this embodiment, when the similarity between two edge pixels is smaller than the preset threshold, the two edge pixels are similar pixels, the similar edge pixels are classified into one category, and all the edge pixels are sequentially classified into different categories.
Specifically, the gray gradient information and the gray direction information of each edge pixel point and the position information of the gray direction information are obtained, the similarity between the pixel points is constructed through the three information, and the similar edge pixel points are divided into a cluster.
The similarity calculation formula is as follows:
in the formula (I), the compound is shown in the specification,
and
representing the gray gradient values of any two edge pixels in the image,
and
the gray gradient directions of the two edge pixels are represented,
the Euclidean distance between two edge pixels represents the position information of the two edge pixels;
it indicates the degree of similarity of the two,
the smaller the size, the higher the similarity. When in use
If the preset threshold value is less than 3, the pixel points are considered to be similar, and the pixel points are classified into a cluster. The preset threshold value of 3 is obtained from manual experience.
Therefore, the edge pixel point with the maximum gray gradient is selected in sequence, the similarity between the edge pixel point and surrounding points is calculated by taking the edge pixel point as a basic point, if the similar edge pixel points exist in a circle around the edge pixel point, the similar edge pixel points are continuously searched until all the edge pixel points are traversed, and at the moment, all the edge pixel points are classified according to the position, the gradient and the direction.
And sequentially dividing all edge pixel points into different categories, removing the undersized categories according to the sizes after classification, and removing the categories with the number of the edge pixel points less than 20 from a plurality of divided categories to reduce the noise influence.
S5, thinning edge pixel points in each category and combining the gray gradient direction of the edge pixel points to obtain edge straight lines, sequentially obtaining a plurality of edge straight lines, and performing semantic segmentation on pixel points and all smooth pixel points on each edge straight line in a gray-scale image to obtain a straight line edge binary image;
in this embodiment, the LSD algorithm is improved based on the LSD algorithm, a straight line is determined by using a clustering idea, and since the gradient direction of each edge pixel is known, the direction of the edge pixel of each cluster can be obtained according to the known gradient direction in each cluster. And thinning the pixel points in each category, and combining the directions of the straight lines to obtain an edge straight line during thinning. The thinning is to thin the pixels on the edge straight line, for example, thinning the pixel strip with the length of 50 and the width of 5 into a straight line with the length of 50 and the width of 1;
and then segmenting the grey-scale image of the steel wire rope winding area, marking thinned pixel points in each edge straight line as 1, and marking the rest smooth pixel points as 0, so as to obtain the straight line edge binary image of all the steel wire ropes, wherein the grey value of the pixel points at the straight line edge is 1, and the grey value of the pixel points at the rest part is 0.
S6, calculating to obtain a rope disorder coefficient according to the gray values of all pixel points projected towards the winding direction of the steel wire rope in the linear edge binary image and the angle of each edge line; the gray value obtaining method for projection of all pixel points in the linear edge binary image towards the winding direction of the steel wire rope comprises the following steps: and projecting the gray values of all the pixel points in a row according to columns, and adding the gray values of each column of pixel points in the linear edge binary image to be used as the gray value of the projection of the column of pixel points. The angle of each edge straight line is the included angle between each edge straight line and the axial direction of the rope rewinding machine.
All the edge straight lines of the steel wire ropes are obtained through the operation, all the steel wire ropes are closely arranged in the rope rewinding machine without the disorder ropes, and the edge lines of all the steel wire ropes are approximately parallel; in the rope rewinder with rope disorder, the obtained edge straight lines may intersect with each other.
In the embodiment, the rope disorder coefficient of the image is judged by combining the gray values of all pixel points projected towards the winding direction of the steel wire rope and the angle of each edge straight line; it should be noted that, the obtained linear edge binary image;
on one hand, firstly, a binary image is projected, gray values of all pixel points are projected in a row towards the winding direction of a steel wire rope, namely gray values of pixel points in each row in the image are accumulated, so that one row is changed into one pixel point, the value of the pixel point is the sum of gray values of the pixel points in the corresponding row, the binary image at the edge of a straight line has n pixel points in total, namely the maximum gray value of the pixel point in the row is n when any row of pixel points is projected to one row; secondly, the application considers that if the gray value of the projected pixel point is less than the gray value of the projected pixel point
The messy rope phenomenon exists when the number of the columns corresponding to the pixel points is considered, and meanwhile, the more the pixel points exist, the larger the corresponding gray value of the pixel points is, and the more serious the messy rope phenomenon is. In the analysis process, the edge straight lines in the binary image are arranged in the longitudinal direction, and each column represents one edge straight line.
On the other hand, the angle of each edge straight line is calculated through the obtained straight lines by taking the numerical direction as a reference, all the edge straight lines are close to 90 degrees for the rope rewinding machine without rope disorder, and in the application, the smaller the angle is, the larger the rope disorder degree is. Wherein, the angle of each edge straight line is the included angle between each edge straight line and the axial direction of the rope rewinding machine.
Obtaining a rope disorder coefficient calculation formula through the two aspects as follows:
in the formula (I), the compound is shown in the specification,
representing a total of k gray values less than
The number of pixel points;
the number of pixel points representing that the gray value after projection is not 0;
representing the gray value corresponding to the projected pixel point; e represents the number of edge lines;
representing the angle of each edge line;
the number of lines representing the pixel points in the binary image,
and expressing the column number of the pixel points in the binary image.
At this moment, a linear edge image is obtained through an LSD linear detection and clustering algorithm, and a rope disorder coefficient is obtained through a linear edge binary image.
And S7, judging the rope disorder condition on the rope rewinder according to the rope disorder coefficient.
The rope disorder can cause different problems, the rope disorder condition of the rope rewinder is expressed by a rope disorder coefficient in the application, the larger the coefficient is, the larger the rope disorder condition is, and when the coefficient is larger, the rope disorder condition is
The application considers the rope rewinding machineThe service life and the efficiency of the equipment are not influenced too much even if the rope disorder exists;
in time, this application just thinks that this rope rewinder has serious indiscriminate rope condition, the life and the efficiency of influence machine that can be great.
At this moment, the rope disorder condition of the machine is obtained by judging the rope disorder coefficient.
Referring to fig. 2, in an embodiment of the present application, the present application further provides a rope disorder detection device for a rope rewinding machine, including:
the image acquisition module is used for acquiring a gray scale image of a steel wire rope winding area;
the pixel point dividing module is used for acquiring the gray gradient value and the gray gradient direction of each pixel point according to the gray value of each pixel point in the gray map of the winding area of the steel wire rope and the gray value of the adjacent pixel point; dividing all pixel points into edge pixel points and smooth pixel points according to the gray gradient value of each pixel point;
the binary image acquisition module is used for clustering all edge pixel points according to the gray gradient values and the gray gradient directions of the edge pixel points and the Euclidean distance between any two edge pixel points, and dividing all the edge pixel points into different categories; thinning edge pixel points in each category and combining the gray gradient direction of the edge pixel points to obtain edge straight lines, sequentially obtaining a plurality of edge straight lines, and performing semantic segmentation on pixel points and all smooth pixel points on each edge straight line in a gray-scale image to obtain a straight line edge binary image;
the rope disorder coefficient calculation module is used for calculating a rope disorder coefficient according to the gray values of all pixel points in the linear edge binary image projected towards the winding direction of the steel wire rope and the angle of each edge line;
and the rope disorder judging module is used for judging the rope disorder condition on the rope rewinder through the obtained rope disorder coefficient.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a hardware operating environment according to an embodiment of the present invention.
It should be noted that fig. 3 is a schematic structural diagram of a hardware operating environment of the computer device.
Referring to fig. 3, the computer apparatus may include: a processor 101, e.g., a CPU, a memory 105, a user interface 103, a network interface 104, a communication bus 102; wherein the communication bus 102 is used for enabling connection communication between these components. The user interface 103 may comprise a display screen, an input unit such as a keyboard, and the optional user interface 103 may also comprise a standard wired interface, a wireless interface. The network interface 104 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 105 may be a high-speed RAM memory or a non-volatile memory (e.g., a disk memory). The memory 105 may alternatively be a storage device separate from the processor 101 described above.
Those skilled in the art will appreciate that the computer device configuration illustrated in FIG. 3 is not intended to be limiting of computer devices and may include more or fewer components than those illustrated, or some components may be combined, or a different arrangement of components.
Referring to fig. 3, the memory 105, which is a storage medium, may include therein an operating system, a network communication module, a user interface module, and a computer program. Among other things, an operating system is a program that manages and controls the hardware and software resources of a computer device, the operation of a computer program, and other software or programs.
In the computer device shown in fig. 3, the user interface 103 is mainly used for connecting a terminal and performing data communication with the terminal; the network interface 104 is mainly used for a background server and performs data communication with the background server; the processor 101 may be used to invoke computer programs stored in the memory 105.
In this embodiment, the computer device includes: a memory 105, a processor 101, and a computer program stored on the memory 105 and executable on the processor, wherein:
when the processor 101 calls the computer program stored in the memory 105, the following operations are performed:
acquiring a gray scale image of a steel wire rope winding area;
acquiring a gray gradient value and a gray gradient direction of each pixel point according to the gray value of each pixel point in the gray map and the gray value of the neighborhood pixel point;
dividing all pixel points into edge pixel points and smooth pixel points according to the gray gradient value of each pixel point;
clustering all edge pixel points according to the gray gradient value and the gray gradient direction of the edge pixel points and the Euclidean distance between any two edge pixel points, and dividing all the edge pixel points into different categories;
thinning edge pixel points in each category and combining the gray gradient direction of the edge pixel points to obtain edge straight lines, sequentially obtaining a plurality of edge straight lines, and performing semantic segmentation on pixel points and all smooth pixel points on each edge straight line in a gray-scale image to obtain a straight line edge binary image;
calculating to obtain a rope disorder coefficient according to the gray values of all pixel points projected towards the winding direction of the steel wire rope in the linear edge binary image and the angle of each edge line;
and judging the rope disorder condition on the rope rewinder according to the rope disorder coefficient.
When the processor 101 calls the calculation mechanism program stored in the memory 105, the following operations are also performed:
all the pixel points are arranged from large to small according to the level number of the gray scale gradient value, and all the pixel points are divided into edge pixel points and smooth pixel points by obtaining two adjacent level numbers with the maximum difference value.
When the processor 101 invokes the computer mechanism program stored in the memory 105, it further performs the following operations:
the two adjacent levels are respectively the maximum gray scale gradient value of the smooth pixel point and the minimum gray scale gradient value of the edge pixel point, the average value of the two adjacent levels is calculated according to the maximum gray scale gradient value of the smooth pixel point and the minimum gray scale gradient value of the edge pixel point, and all the pixel points are divided into the edge pixel point and the smooth pixel point by taking the average value as a boundary.
When the processor 101 calls the calculation mechanism program stored in the memory 105, the following operations are also performed:
and obtaining the similarity of two edge pixel points according to the gray gradient value and the gray gradient direction of one edge pixel point and the adjacent edge pixel point and the Euclidean distance between the two pixel points, and clustering all the edge pixel points according to the similarity of any two edge pixel points.
When the processor 101 calls the calculation mechanism program stored in the memory 105, the following operations are also performed:
when the similarity of the two edge pixel points is smaller than a preset threshold value, the two edge pixel points are similar pixel points, the similar edge pixel points are classified into one category, and all the edge pixel points are sequentially classified into different categories.
When the processor 101 calls the calculation mechanism program stored in the memory 105, the following operations are also performed:
removing the category with the number of edge pixels less than 20
When the processor 101 calls the calculation mechanism program stored in the memory 105, the following operations are also performed:
the gray value obtaining method of all pixel points in the linear edge binary image projected towards the winding direction of the steel wire rope comprises the following steps: and projecting the gray values of all the pixel points in a row according to columns, and adding the gray values of each column of pixel points in the linear edge binary image to be used as the gray value of the projection of the column of pixel points.
When the processor 101 calls the calculation mechanism program stored in the memory 105, the following operations are also performed:
the angle of each straight line is the included angle between each straight line and the axial direction of the rope rewinding machine.
In summary, the invention provides a rope disorder detection method, a rope disorder detection device and computer equipment for a rope rewinder, wherein a camera is adopted to acquire a depression angle image of the rope rewinder and divide a winding part of the rope rewinder; analyzing a rope disorder coefficient of the image by using an improved LSD straight line detection method; and judging the rope disorder condition of the rope rewinder according to the obtained rope disorder coefficient of the rope rewinder.
The invention uses the rope disorder coefficient to express the rope disorder condition of the rope rewinder, the larger the coefficient is, the larger the rope disorder condition is, when
In time, the service life and the efficiency of the equipment are not influenced too much even if the rope is disordered by the rope rewinding machine;
in the process, the rope-reversing machine has serious rope disorder condition, and the service life and the efficiency of the machine can be greatly influenced.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A rope disorder detection method of a rope rewinder is characterized by comprising the following steps:
acquiring a gray scale image of a steel wire rope winding area;
acquiring a gray gradient value and a gray gradient direction of each pixel point according to the gray value of each pixel point in the gray map and the gray value of the neighborhood pixel point;
dividing all pixel points into edge pixel points and smooth pixel points according to the gray gradient value of each pixel point;
obtaining the similarity of two edge pixel points according to the gray gradient value and the gray gradient direction of one edge pixel point and a neighborhood edge pixel point and the Euclidean distance between the two pixel points, and clustering all the edge pixel points according to the similarity of any two edge pixel points; sequentially dividing all edge pixel points into different categories;
thinning edge pixel points in each category and combining the gray gradient direction of the edge pixel points to obtain edge straight lines, sequentially obtaining a plurality of edge straight lines, and performing semantic segmentation on pixel points and all smooth pixel points on each edge straight line in a gray-scale image to obtain a straight line edge binary image;
calculating to obtain a rope disorder coefficient according to the gray value of projection of all pixel points in the linear edge binary image towards the winding direction of the steel wire rope and the angle of each edge line;
and judging the rope disorder condition on the rope rewinder according to the rope disorder coefficient.
2. The rope disorder detection method of the rope winding machine according to claim 1, wherein the step of dividing all the pixel points into edge pixel points and smooth pixel points according to the gray scale gradient value of each pixel point is that all the pixel points are arranged from large to small according to the number of the gray scale gradient values, and all the pixel points are divided into two types, namely edge pixel points and smooth pixel points by obtaining two adjacent numbers of the difference values.
3. The method for detecting the rope disorder of the rope winding machine according to claim 2, wherein the two adjacent levels are the maximum gray gradient value of the smooth pixel and the minimum gray gradient value of the edge pixel, respectively, the average value of the two adjacent levels is calculated according to the maximum gray gradient value of the smooth pixel and the minimum gray gradient value of the edge pixel, and all the pixels are divided into the edge pixel and the smooth pixel by taking the average value as a boundary.
4. The method for detecting the rope disorder of the rope winding machine according to claim 1, wherein in the process of clustering all edge pixels according to the similarity of any two edge pixels, when the similarity of the two edge pixels is smaller than a preset threshold, the two edge pixels are similar pixels, the similar edge pixels are classified into one category, and all the edge pixels are sequentially classified into different categories.
5. The rope disorder detection method of the rope winding machine according to claim 1, wherein the similarity calculation formula of the two edge pixel points is as follows:
in the formula (I), the compound is shown in the specification,
and
expressing the gray gradient values of any two edge pixel points in the image;
6. The rope disorder detection method of the rope rewinder according to claim 1, wherein all the edge pixel points are sequentially classified into a plurality of categories, and the categories with the number of the edge pixel points less than 20 are removed.
7. The rope disorder detection method of the rope rewinder as claimed in claim 1, wherein the gray value obtaining method of the projection of all pixel points in the linear edge binary image towards the winding direction of the steel wire rope is as follows: projecting the gray values of all pixel points in a row according to columns, and adding the gray values of each column of pixel points in the linear edge binary image to be used as the gray value of the projection of the column of pixel points; the angle of each straight line is the included angle between each straight line and the axial direction of the rope rewinding machine.
8. The rope disorder detection method of the rope rewinder as claimed in claim 7, wherein the rope disorder coefficient calculation formula is as follows:
in the formula (I), the compound is shown in the specification,
the rope disorder coefficient of the rope rewinder is represented;
representing a total of k gray values less than
The number of pixel points;
the number of pixel points representing that the gray value after projection is not 0;
representing the corresponding gray value of the projected pixel point; e represents the number of edge lines;
representing the angle of each edge line;
the number of lines representing the pixel points in the binary image,
and expressing the column number of the pixel points in the binary image.
9. The utility model provides a rope-tangling detection device of rope-rewinding machine which characterized in that includes:
the image acquisition module is used for acquiring a gray scale image of a steel wire rope winding area;
the pixel point division module is used for acquiring the gray gradient value and the gray gradient direction of each pixel point according to the gray value of each pixel point in the gray map of the steel wire rope winding area and the gray value of the neighborhood pixel point; dividing all pixel points into edge pixel points and smooth pixel points according to the gray gradient value of each pixel point;
the binary image acquisition module is used for clustering all edge pixel points according to the gray gradient values and the gray gradient directions of the edge pixel points and the Euclidean distance between any two edge pixel points, and dividing all the edge pixel points into different categories; thinning edge pixel points in each category and combining the gray gradient direction of the edge pixel points to obtain edge straight lines, sequentially obtaining a plurality of edge straight lines, and performing semantic segmentation on pixel points and all smooth pixel points on each edge straight line in a gray-scale image to obtain a straight line edge binary image;
the rope disorder coefficient calculation module is used for calculating a rope disorder coefficient according to the gray value of projection of all pixel points in the linear edge binary image towards the winding direction of the steel wire rope and the angle of each edge straight line;
and the rope disorder judging module is used for judging the rope disorder condition on the rope rewinder through the obtained rope disorder coefficient.
10. A computer device, comprising:
memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the roundabout detection method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211068137.1A CN115147416B (en) | 2022-09-02 | 2022-09-02 | Rope disorder detection method and device for rope rewinder and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211068137.1A CN115147416B (en) | 2022-09-02 | 2022-09-02 | Rope disorder detection method and device for rope rewinder and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115147416A true CN115147416A (en) | 2022-10-04 |
| CN115147416B CN115147416B (en) | 2022-11-15 |
Family
ID=83415165
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211068137.1A Active CN115147416B (en) | 2022-09-02 | 2022-09-02 | Rope disorder detection method and device for rope rewinder and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115147416B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115496751B (en) * | 2022-11-16 | 2023-03-24 | 威海捷诺曼自动化股份有限公司 | Winding detection method of fiber winding machine |
| CN117400066A (en) * | 2023-12-15 | 2024-01-16 | 西安航飞精密工具有限公司 | Numerical control machine tool wear identification method and system |
| CN117495722A (en) * | 2023-12-25 | 2024-02-02 | 青岛天仁微纳科技有限责任公司 | Image processing method for nanoimprint lithography |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815831A (en) * | 2016-12-21 | 2017-06-09 | 深圳增强现实技术有限公司 | The detection method and device of a kind of steel rope abrasion |
| CN107403443A (en) * | 2017-07-28 | 2017-11-28 | 中南大学 | A kind of more rope multi-lay windings row's rope form state online test method and device based on machine vision |
| CN108682017A (en) * | 2018-04-11 | 2018-10-19 | 浙江工业大学 | Super-pixel method for detecting image edge based on Node2Vec algorithms |
| US20190228517A1 (en) * | 2018-05-29 | 2019-07-25 | University Of Electronic Science And Technology Of China | Method for separating out a defect image from a thermogram sequence based on feature extraction and multi-objective optimization |
| CN111784681A (en) * | 2020-07-08 | 2020-10-16 | 长沙克莱自动化设备有限公司 | Steel wire rope disorder detection method and device, computer equipment and storage medium |
| WO2021133801A1 (en) * | 2019-12-23 | 2021-07-01 | Boon Logic Inc. | Product inspection system and method |
| CN114235825A (en) * | 2022-02-24 | 2022-03-25 | 武汉祥文钢材制品有限公司 | Steel wire rope quality detection method based on computer vision |
| CN114723701A (en) * | 2022-03-31 | 2022-07-08 | 南通博莹机械铸造有限公司 | Gear defect detection method and system based on computer vision |
-
2022
- 2022-09-02 CN CN202211068137.1A patent/CN115147416B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106815831A (en) * | 2016-12-21 | 2017-06-09 | 深圳增强现实技术有限公司 | The detection method and device of a kind of steel rope abrasion |
| CN107403443A (en) * | 2017-07-28 | 2017-11-28 | 中南大学 | A kind of more rope multi-lay windings row's rope form state online test method and device based on machine vision |
| CN108682017A (en) * | 2018-04-11 | 2018-10-19 | 浙江工业大学 | Super-pixel method for detecting image edge based on Node2Vec algorithms |
| US20190228517A1 (en) * | 2018-05-29 | 2019-07-25 | University Of Electronic Science And Technology Of China | Method for separating out a defect image from a thermogram sequence based on feature extraction and multi-objective optimization |
| WO2021133801A1 (en) * | 2019-12-23 | 2021-07-01 | Boon Logic Inc. | Product inspection system and method |
| CN111784681A (en) * | 2020-07-08 | 2020-10-16 | 长沙克莱自动化设备有限公司 | Steel wire rope disorder detection method and device, computer equipment and storage medium |
| CN114235825A (en) * | 2022-02-24 | 2022-03-25 | 武汉祥文钢材制品有限公司 | Steel wire rope quality detection method based on computer vision |
| CN114723701A (en) * | 2022-03-31 | 2022-07-08 | 南通博莹机械铸造有限公司 | Gear defect detection method and system based on computer vision |
Non-Patent Citations (2)
| Title |
|---|
| RONGHUA SHANG 等: "A Fast Algorithm for SAR Image Segmentation Based on Key Pixels", 《IEEE》 * |
| 仵坤 等: "一种基于卷筒外轮廓特征的提升机排绳自稳定监测方法", 《振动与冲击》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115496751B (en) * | 2022-11-16 | 2023-03-24 | 威海捷诺曼自动化股份有限公司 | Winding detection method of fiber winding machine |
| CN117400066A (en) * | 2023-12-15 | 2024-01-16 | 西安航飞精密工具有限公司 | Numerical control machine tool wear identification method and system |
| CN117400066B (en) * | 2023-12-15 | 2024-03-08 | 西安航飞精密工具有限公司 | Numerical control machine tool wear identification method and system |
| CN117495722A (en) * | 2023-12-25 | 2024-02-02 | 青岛天仁微纳科技有限责任公司 | Image processing method for nanoimprint lithography |
| CN117495722B (en) * | 2023-12-25 | 2024-03-29 | 青岛天仁微纳科技有限责任公司 | Image processing method for nanoimprint lithography |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115147416B (en) | 2022-11-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115147416B (en) | Rope disorder detection method and device for rope rewinder and computer equipment | |
| CN110008809B (en) | Method and device for acquiring form data and server | |
| WO2018103608A1 (en) | Text detection method, device and storage medium | |
| CN110942074B (en) | Character segmentation recognition method and device, electronic equipment and storage medium | |
| CN110032998B (en) | Method, system, device and storage medium for detecting characters of natural scene picture | |
| CN107977639B (en) | Face definition judgment method | |
| CN111488791A (en) | On-device classification of fingertip movement patterns as gestures in real time | |
| CN109446061B (en) | Page detection method, computer readable storage medium and terminal device | |
| CN111784681A (en) | Steel wire rope disorder detection method and device, computer equipment and storage medium | |
| CN110599453A (en) | Panel defect detection method and device based on image fusion and equipment terminal | |
| CN111182367A (en) | Video generation method and device and computer system | |
| CN113610831B (en) | Wood defect detection method based on computer image technology and transfer learning | |
| CN116485779B (en) | Adaptive wafer defect detection method and device, electronic equipment and storage medium | |
| CN111597845A (en) | Two-dimensional code detection method, device and equipment and readable storage medium | |
| CN111612787B (en) | Concrete crack high-resolution image lossless semantic segmentation method and device and storage medium | |
| CN113610854B (en) | Cable defect detection method, terminal device and computer storage medium | |
| CN113486881B (en) | Text recognition method, device, equipment and medium | |
| CN115690037A (en) | Method, device and system for detecting yarn broken ends of ring spinning frame and storage medium | |
| CN114005019B (en) | Method for identifying flip image and related equipment thereof | |
| CN114022865A (en) | Image processing method, apparatus, device and medium based on lane line recognition model | |
| CN112183554B (en) | Automatic road boundary contour extraction method | |
| JP5027201B2 (en) | Telop character area detection method, telop character area detection device, and telop character area detection program | |
| CN112949584A (en) | Image screening method and device, electronic equipment and storage medium | |
| CN111444834B (en) | Image text line detection method, device, equipment and storage medium | |
| CN110348353B (en) | Image processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A method, device, and computer equipment for detecting rope disorder in a rope rewinding machine Effective date of registration: 20230321 Granted publication date: 20221115 Pledgee: Bank of China Limited Sishui sub branch Pledgor: SHANDONG DASHAN STAINLESS STEEL PRODUCTS Co.,Ltd. Registration number: Y2023980035351 |