CN117585399B - Coal mine conveyor belt tearing detection method based on image processing - Google Patents
Coal mine conveyor belt tearing detection method based on image processing Download PDFInfo
- Publication number
- CN117585399B CN117585399B CN202410076891.2A CN202410076891A CN117585399B CN 117585399 B CN117585399 B CN 117585399B CN 202410076891 A CN202410076891 A CN 202410076891A CN 117585399 B CN117585399 B CN 117585399B
- Authority
- CN
- China
- Prior art keywords
- frequency
- straight line
- line segment
- point
- standard
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000003245 coal Substances 0.000 title claims abstract description 29
- 238000001514 detection method Methods 0.000 title claims abstract description 16
- 230000002159 abnormal effect Effects 0.000 claims abstract description 39
- 230000005856 abnormality Effects 0.000 claims description 70
- 238000000034 method Methods 0.000 claims description 32
- 230000008859 change Effects 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 12
- 238000005286 illumination Methods 0.000 abstract description 9
- 238000001228 spectrum Methods 0.000 description 10
- 238000009826 distribution Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 4
- 238000010606 normalization Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000004931 aggregating effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003818 cinder Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000001125 extrusion Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G43/00—Control devices, e.g. for safety, warning or fault-correcting
- B65G43/02—Control devices, e.g. for safety, warning or fault-correcting detecting dangerous physical condition of load carriers, e.g. for interrupting the drive in the event of overheating
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G15/00—Conveyors having endless load-conveying surfaces, i.e. belts and like continuous members, to which tractive effort is transmitted by means other than endless driving elements of similar configuration
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
- B65G2203/02—Control or detection
- B65G2203/0266—Control or detection relating to the load carrier(s)
- B65G2203/0275—Damage on the load carrier
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G2203/00—Indexing code relating to control or detection of the articles or the load carriers during conveying
- B65G2203/04—Detection means
- B65G2203/041—Camera
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to the technical field of image data processing, in particular to a coal mine conveyor belt tearing detection method based on image processing, which comprises the following steps: determining the abnormal degree of the frequency points according to the difference between the distance from the frequency point on the reference straight line segment to the center point of the spectrogram in the spectrogram of the surface image of the conveyor belt and the frequency value and the corresponding fitting curve value, determining the standard window according to the abnormal degree of all the frequency points in the sliding window corresponding to the frequency point on the main body reference straight line segment, determining the center point of the crack frequency, taking the center point as a circle, determining the radius of the crack according to the number and the abnormal degree of the frequency points in the circle, obtaining the boundary point of the crack, determining the optimal enhancement threshold according to the slope and the abnormal degree of all the frequency points on the standard straight line segment and the distance from the boundary point of the crack, further obtaining the surface image of the conveyor belt after enhancement, and accurately detecting the crack region. According to the invention, the influence of uneven illumination is reduced by self-adapting the optimal enhancement threshold value, and the crack region is accurately obtained.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to a coal mine conveyor belt tearing detection method based on image processing.
Background
The belt conveyor has the advantages of large conveying capacity, high conveying efficiency, convenient loading and unloading and continuous operation, and is widely applied to industrial production. The coal mine conveyor belt is used as a traction and transportation tool in the working process, and is often in a severe production environment, and the conveyor belt is aged, hard objects are extruded, the conveyor belt is excessively loaded and the like to cause the faults of tearing, deviation, surface damage and the like of the conveyor belt, and the conveyor belt is broken when serious, so that production accidents and production stoppage are caused. Therefore, the defect detection of the coal mine conveyor belt is particularly important in the production process, but the acquired conveyor belt image often has the phenomenon of uneven illumination due to the severe coal mine operation environment, so that the defect detection accuracy is affected.
Homomorphic filtering can enhance and correct the illumination non-uniform image, so that details in the image are more clearly visible. It converts the original image into an enhanced frequency domain representation by operating on the logarithm of the image in the frequency domain, and performs the filtering operation in the frequency domain followed by an inverse transformation to obtain the enhanced image. Proper selection of the appropriate enhancement threshold in the algorithm may preserve the required detail in the image and reduce unnecessary noise or artifacts.
The existing problems are as follows: the coal mine operation environment is complex and changeable, the collected images of different conveyor belts are affected to different degrees by uneven illumination, and the effects of different degrees such as global brightness or darkness, local highlighting or shadow and the like can occur. Different conveyor belt images require different enhancement thresholds, while too high an enhancement threshold may introduce excessive enhancement and artifacts, and too low an enhancement threshold may not effectively enhance the required image details.
Disclosure of Invention
The invention provides a coal mine conveyor belt tearing detection method based on image processing, which aims to solve the existing problems.
The coal mine conveyor belt tearing detection method based on image processing adopts the following technical scheme:
an embodiment of the invention provides a coal mine conveyor belt tearing detection method based on image processing, which comprises the following steps:
acquiring an image of the lower side of a coal mine conveyor belt by using an industrial camera to obtain a surface image of the conveyor belt; converting the surface image of the conveyor belt into a spectrogram by using a two-dimensional discrete Fourier transform method;
acquiring a reference straight line segment on a reference transverse line in the spectrogram, and determining the degree of abnormality of the frequency point on the reference straight line segment according to the Euclidean distance from the frequency point on the reference straight line segment to the center point of the spectrogram and the difference between the frequency value of the frequency point on the reference straight line segment and the corresponding fitting curve value;
acquiring a main body reference straight line segment in a spectrogram, and determining a standard window according to the degree of abnormality of frequency points on all reference straight line segments in a sliding window corresponding to the frequency points on the main body reference straight line segment; determining a crack frequency center point according to the abnormality degree and the frequency value of the frequency points on all the reference straight line segments in the standard window;
taking the center point of the crack frequency as a round point to form a circle, and determining the radius of the crack according to the number and the degree of abnormality of the frequency points on all the reference straight line segments in the circle;
acquiring a standard straight line segment, and determining the slopes of all frequency points on the standard straight line segment according to the frequency value difference of adjacent frequency points on the standard straight line segment; the intersection point of a circle with the center point of the fracture frequency as a round point and the radius as the fracture radius and a standard straight line segment is marked as a fracture boundary point; determining an optimal enhancement threshold according to the slopes and the degree of abnormality of all frequency points on the standard straight line segment and the Euclidean distance from the standard straight line segment to the crack boundary point;
determining a low-pass filter according to the optimal enhancement threshold; filtering the spectrogram by using a low-pass filter to obtain an enhanced spectrogram; performing inverse Fourier transform on the enhanced spectrogram to obtain an enhanced surface image of the conveyor belt; and obtaining a crack area according to the enhanced surface image of the conveyor belt.
Further, the step of obtaining a reference straight line segment on a reference horizontal line in the spectrogram, and determining the degree of abnormality of the frequency point on the reference straight line segment according to the difference between the Euclidean distance from the frequency point on the reference straight line segment to the center point of the spectrogram and the frequency value of the frequency point on the reference straight line segment and the corresponding fitting curve value, wherein the specific steps include:
taking a transverse line of a center point of the frequency spectrogram in the frequency spectrogram and a plurality of adjacent transverse lines above and below the transverse line of the center point of the frequency spectrogram, and marking the transverse lines as reference transverse lines to obtain a reference transverse lines; wherein a is the number of preset transverse lines;
dividing a reference transverse line into two straight line segments by using a central point of the reference transverse line, and marking the reference transverse line as a reference straight line segment;
performing curve fitting on the frequency values of all the frequency points on the reference straight line segment by using a least square method to obtain a fitted curve value corresponding to the frequency value of each frequency point on the reference straight line segment;
and (3) recording the product of the normalized value of the Euclidean distance from the frequency point on the reference straight line segment to the center point of the spectrogram and the absolute value of the difference value between the frequency value of the frequency point on the reference straight line segment and the corresponding fitting curve value as the degree of abnormality of the frequency point on the reference straight line segment.
Further, the main body reference straight line segment in the obtained spectrogram, and determining a standard window according to the degree of abnormality of the frequency points on all the reference straight line segments in the sliding window corresponding to the frequency points on the main body reference straight line segment, wherein the specific steps include:
a reference straight line segment corresponding to a reference transverse line passing through a spectrogram center point in the spectrogram is recorded as a main body reference straight line segment;
traversing frequency points on the main body reference straight line segment by using a preset sliding window to obtain a sliding window corresponding to each frequency point on the main body reference straight line segment;
the sum of abnormal ranges of the frequency points on all the reference straight line segments in the sliding window corresponding to each frequency point on the main body reference straight line segment is recorded as the integral abnormal degree of each frequency point on the main body reference straight line segment;
and (3) marking the sliding window corresponding to the frequency point corresponding to the maximum value in the overall abnormality degree of all the frequency points on the main body reference straight line segment as a standard window.
Further, the step of determining the crack frequency center point according to the abnormality degree and the frequency value of the frequency points on all the reference straight line segments in the standard window comprises the following specific steps:
determining the probability that the frequency point on each reference straight line segment in the standard window is a crack frequency center point according to the abnormality degree of the frequency points on all the reference straight line segments in the standard window and the frequency value of the frequency point on each reference straight line segment in the standard window;
and (3) marking the frequency points on the reference straight line segments corresponding to the maximum value in the probability that the frequency points on all the reference straight line segments in the standard window are the crack frequency center points as the crack frequency center points.
Further, according to the degree of abnormality of the frequency points on all the reference straight line segments in the standard window and the frequency value of the frequency point on each reference straight line segment in the standard window, the specific calculation formula corresponding to the probability that the frequency point on each reference straight line segment in the standard window is the crack frequency center point is determined as follows:
wherein the method comprises the steps ofIs the probability that the frequency point on the y-th reference straight line segment in the standard window is the center point of the crack frequency, < ->For the frequency value of the frequency point on the y-th reference straight line segment in the standard window, +.>For the degree of abnormality of the frequency point on the y-th reference straight line segment within the standard window, +.>Is the mean value of the degree of abnormality of the frequency points on all the non-y-th reference straight line segments in the standard window.
Further, the circle is made by taking the center point of the crack frequency as a round point, and the crack radius is determined according to the number and the degree of abnormality of the frequency points on all the reference straight line segments in the circle, comprising the following specific steps:
obtaining a preset radius value range according to the Euclidean distance from the crack frequency center point to the spectrogram center point;
taking the central point of the crack frequency as a round point, and obtaining the variation rate of the abnormal degree corresponding to each radius in the preset radius value range by taking the difference between the number and the abnormal degree of each radius in the preset radius value range and the frequency points on all the reference straight line segments in the corresponding circle after subtracting one from each radius;
and (3) marking the radius corresponding to the maximum value in the abnormal degree change rate corresponding to all the radii in the preset radius value range as the fracture radius.
Further, the specific calculation formula corresponding to the abnormal degree change rate corresponding to each radius in the preset radius value range is obtained by taking the central point of the crack frequency as a round point and subtracting the number and the abnormal degree of the frequency points on all the reference straight line segments in the corresponding circle from each radius in the preset radius value range from each radius:
wherein the method comprises the steps ofIs the corresponding abnormal degree change rate when the radius is r,>in order to determine the degree of abnormality of the frequency point on the ith reference straight line segment in a circle with the center point of the crack frequency as the circle point and the radius r, +.>For the number of frequency points on all reference straight line segments within a circle with the center point of the crack frequency as the circle point and the radius r, +.>To break atThe mark frequency center point is the degree of abnormality of the frequency point on the jth reference straight line segment in the circle with the radius of r-1, and +.>Is the number of frequency points on all reference straight line segments within a circle with the center point of the fracture frequency as a dot and the radius r-1.
Further, the step of obtaining the standard straight line segment, and determining the slopes of all the frequency points on the standard straight line segment according to the frequency value difference of the adjacent frequency points on the standard straight line segment comprises the following specific steps:
marking a straight line segment from the center point of the spectrogram to the center point of the crack frequency as a standard straight line segment;
and (3) subtracting the frequency value of the previous frequency point from the frequency value of the next frequency point on the standard straight line segment, and recording the difference as the slope of the previous frequency point on the standard straight line segment to obtain the slopes of all the frequency points on the standard straight line segment.
Further, the determining the optimal enhancement threshold according to the slope and the degree of abnormality of all the frequency points on the standard straight line segment and the Euclidean distance from the crack boundary point comprises the following specific steps:
if the slope of the frequency point on the standard straight line segment is smaller than or equal to a preset slope threshold value, setting the slope characteristic value of the frequency point on the standard straight line segment as a preset slope characteristic value;
if the slope of the frequency point on the standard straight line segment is larger than a preset slope threshold value, adding one to the normalized value of the slope of the frequency point on the standard straight line segment, and marking the normalized value as a slope characteristic value of the frequency point on the standard straight line segment;
recording one half of the absolute value of the difference between the abnormal degrees of two adjacent frequency points of the frequency points on the standard straight line segment as the abnormal degree change rate of the frequency points on the standard straight line segment;
determining the optimal enhancement threshold probability corresponding to the frequency point on the standard straight line segment according to the slope characteristic value of the frequency point on the standard straight line segment, the abnormal degree change rate of the frequency point on the standard straight line segment and the Euclidean distance from the frequency point on the standard straight line segment to the crack boundary point;
and marking the Euclidean distance from the frequency point corresponding to the maximum value in the optimal enhancement threshold probabilities corresponding to all the frequency points on the standard straight line segment to the center point of the spectrogram as the optimal enhancement threshold.
Further, according to the slope characteristic value of the frequency point on the standard straight line segment, the abnormal degree change rate of the frequency point on the standard straight line segment and the euclidean distance from the frequency point on the standard straight line segment to the crack boundary point, the specific calculation formula corresponding to the optimal enhancement threshold probability corresponding to the frequency point on the standard straight line segment is determined as follows:
wherein the method comprises the steps ofIs the optimal enhancement threshold probability corresponding to the xth frequency point on the standard straight line segment, +.>Slope characteristic value of the xth frequency point on standard straight line segment, < ->Is the Euclidean distance from the xth frequency point to the crack boundary point on the standard straight line segment,and->The degree of abnormality of the x+1 th and x-1 st frequency points on the standard straight line segment respectively.
The technical scheme of the invention has the beneficial effects that:
in the embodiment of the invention, the abnormal degree of the frequency point on the reference straight line segment is determined according to the difference between the Euclidean distance from the frequency point on the reference straight line segment to the center point of the spectrogram in the spectrogram of the surface image of the conveyor belt and the frequency value of the frequency point on the reference straight line segment and the fitting curve value corresponding to the Euclidean distance, the standard window is determined according to the abnormal degree of the frequency point on all the reference straight line segments in the sliding window corresponding to the frequency point on the main body reference straight line segment, the crack frequency center point is determined according to the abnormal degree and the frequency value of the frequency point on all the reference straight line segments in the standard window, and the crack frequency center point is used as a round point, according to the number and the degree of abnormality of frequency points on all reference straight line segments in a circle, determining a crack radius, obtaining a crack boundary point, determining an optimal enhancement threshold according to the slope and the degree of abnormality of all frequency points on a standard straight line segment and the Euclidean distance to the crack boundary point, determining a low-pass filter according to the optimal enhancement threshold, performing filtering treatment on a spectrogram by using the low-pass filter to obtain an enhanced spectrogram, performing inverse Fourier transformation on the enhanced spectrogram to obtain an enhanced conveyor belt surface image, and obtaining a precise crack region according to the enhanced conveyor belt surface image. According to the size of a high-frequency range caused by cracks in a spectrogram, the optimal enhancement threshold is searched, the influence of uneven illumination is reduced in an image, the contrast between the cracks and a normal area of a belt is enhanced, and the existence of the cracks and the position information of the cracks are accurately judged.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the steps of the method for detecting the tearing of the coal mine conveyor belt based on image processing.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of the specific implementation, structure, characteristics and effects of the coal mine conveyor belt tearing detection method based on image processing according to the invention with reference to the attached drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The specific scheme of the coal mine conveyor belt tearing detection method based on image processing provided by the invention is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of the steps of a method for detecting tearing of a coal mine conveyor belt based on image processing according to an embodiment of the present invention is shown, the method includes the following steps:
step S001: acquiring an image of the lower side of a coal mine conveyor belt by using an industrial camera to obtain a surface image of the conveyor belt; the belt surface image is converted into a spectrogram using a two-dimensional discrete fourier transform method.
Coal mine conveyor belt tears are generally classified into two major categories, transverse tears, which are typically caused by conveyor belt self-quality problems, and longitudinal tears, which occur rarely. Longitudinal tearing is generally caused by extrusion and overload penetration during production operation, and can better reflect problems during production operation. The present embodiment is therefore directed mainly to the analytical detection of longitudinal tears.
The upper part of the coal mine conveyor belt is provided with interference factors such as coal mine, cinder and the like, and when the conveyor belt is provided with cracks, the lower part of the conveyor belt is also provided with defects, so that the lower part of the conveyor belt is selected for image acquisition, and defect detection is carried out according to the images. And arranging a fixed industrial camera right below the conveyor belt, and shooting images on the lower side of the conveyor belt to obtain the surface image of the conveyor belt.
And carrying out graying treatment on the surface image of the conveyor belt, carrying out two-dimensional discrete Fourier transform to obtain a magnitude spectrum, and then adjusting four quadrants to obtain a centralized magnitude spectrum, namely a spectrogram. The basic information and illumination influence in the frequency spectrum image belong to low-frequency components, the cracks belong to detail texture information and are represented as high-frequency information in the frequency spectrum, so that the enhancement of the surface image of the conveyor belt can be realized by filtering the frequency spectrum image. The conversion of gray scale images into spectrograms is a well-known technique, and the specific method is not described here.
The cracks on the coal conveyor belt appear darker than the normal area of the conveyor belt, and the edges of the cracks belong to high-frequency information in the frequency domain. And the non-uniform illumination affecting detection in the space domain is represented as low frequency information in the frequency domain. Homomorphic filtering processing is carried out on the spectrogram, low-frequency information such as illumination is restrained, and high-frequency information of cracks is enhanced. The homomorphic filtering algorithm in this embodiment uses a gaussian function as a low pass filter for adjusting the frequency range of the image. Judging the position of a longitudinal crack frequency center point according to the distribution of the frequency points in the spectrogram, determining the frequency range of the crack according to the relation of the frequency points near the center point, combining the enhancement requirement after determining the frequency range of the crack, obtaining the standard deviation of the self-adaptive Gaussian kernel as an enhancement threshold, and enhancing the image.
Step S002: and acquiring a reference straight line segment on a reference transverse line in the spectrogram, and determining the degree of abnormality of the frequency point on the reference straight line segment according to the Euclidean distance from the frequency point on the reference straight line segment to the center point of the spectrogram and the difference between the frequency value of the frequency point on the reference straight line segment and the corresponding fitting curve value.
In the airspace, the longitudinal crack mainly runs along the longitudinal direction of the conveyor belt and is converted into the frequency domain, and due to the characteristic of the frequency domain, high-frequency points of the longitudinal crack in the spectrogram are mainly concentrated on a transverse straight line passing through the center point of the frequency spectrum, and because the longitudinal crack is not completely running along the longitudinal direction of the conveyor belt, offset possibly exists, and therefore the high-frequency points of the region near the transverse straight line passing through the center point of the frequency spectrum need to be considered.
The present embodiment is described by taking the set number of transverse lines a=5 as an example, and other values may be set in other embodiments, and the present embodiment is not limited thereto. And (3) taking a transverse line of a center point of the spectrogram in the spectrogram and two adjacent transverse lines above and below the transverse line of the center point of the spectrogram as reference transverse lines, thereby obtaining a reference transverse lines.
And analyzing the frequency point distribution on each reference transverse line by taking each reference transverse line as a unit. Because the spectrum image is symmetrical along the center point, one side is taken for analysis, each reference transverse line is divided into two straight line segments by the center point in the spectrum chart, the two straight line segments are marked as reference straight line segments, and one reference straight line segment is taken as an example.
In the spectrogram, the farther from the center point, the higher the frequency of the frequency point, and the crack belongs to the high-frequency pixel point in the spectrogram, so the farther from the center point of the spectrum, the higher the probability that the frequency point is the crack frequency point.
In the spectrogram, frequency points near a center point are low frequency, the basic information in the corresponding spatial domain image is described, frequency points far away from the center point are high frequency, and the texture details in the corresponding spatial domain image are described. In the spatial domain image of the conveyor belt, most of the spatial domain image is texture and edge pixel points and is in low frequency. The crack belongs to detail information and is at high frequency.
And performing curve fitting on the frequency values of all the frequency points on the reference straight line segment in the spectrogram by using a least square method, wherein the fitted curve takes Euclidean distance from all the frequency points on the reference straight line segment to the center point of the spectrogram as a horizontal axis and takes the frequency value as a vertical axis. And obtaining a fitting curve value corresponding to the frequency value of each frequency point on the reference straight line segment. When the horizontal axis value on the fitting curve is smaller, the gray level change of the airspace image is slow, the number of low-frequency points is more, and the frequency value is larger. According to the fitting curve of the frequency values of all the frequency points on the reference straight line segment, the frequency point distribution at the fracture is concentrated, and the absolute value of the difference value between the frequency value and the corresponding fitting curve value is larger as the transverse axis value on the fitting curve is closer to the fracture center frequency point position.
Taking the z-th frequency point on the reference straight line segment as an example, the degree of abnormality of the z-th frequency point on the reference straight line segmentThe calculation formula of (2) is as follows:
wherein the method comprises the steps ofFor the degree of abnormality of the z-th frequency point on the reference straight line segment,/and->The larger the probability of belonging to the fracture frequency is. />For the absolute value of the difference between the frequency value of the z-th frequency point on the reference straight line segment and the corresponding fitting curve value,/of>The larger the frequency point is, the higher the anomaly probability is. />The normalization method is that the normalization value of the Euclidean distance from the z-th frequency point to the center point of the spectrogram on the reference straight line segment is as follows: use->A linear normalization function to normalize the data values to [0,1 ]]In the interval, the frequency point corresponding to the crack belongs to the high frequency point, and +.>As->The product of the two is the degree of abnormality of the z-th frequency point on the reference straight line segment.
What needs to be described is: the greater the absolute value of the difference between the frequency value and the corresponding fitting curve value, the greater the distance between the frequency point and the center point of the spectrogram, and the greater the degree of abnormality.
According to the mode, the abnormal degrees of all frequency points on all reference straight line segments in the spectrogram are obtained.
Step S003: acquiring a main body reference straight line segment in a spectrogram, and determining a standard window according to the degree of abnormality of frequency points on all reference straight line segments in a sliding window corresponding to the frequency points on the main body reference straight line segment; and determining a crack frequency center point according to the abnormality degree and the frequency value of the frequency points on all the reference straight line segments in the standard window.
Since the crack appears as a continuous high-frequency point on the spectrogram, the overall degree of abnormality in the local area needs to be calculated. The present embodiment is described by taking a square sliding window of b×b as an example, where b=5, and other values may be set in other embodiments, and the present embodiment is not limited thereto.
And marking a reference straight line segment corresponding to a reference transverse line passing through a spectrogram center point in the spectrogram as a main body reference straight line segment, taking one main body reference straight line segment as an example, traversing the main body reference straight line segment by frequency points by using a set sliding window to obtain a sliding window corresponding to each frequency point on the main body reference straight line segment, and marking the sum of abnormal processes of the frequency points on all the reference straight line segments in each sliding window as the integral abnormal degree of each frequency point on the main body reference straight line segment.
Because the frequency of the longitudinal crack in the frequency domain has the characteristic of continuous regionality, a sliding window corresponding to a frequency point corresponding to the maximum value in the overall abnormal degree of all frequency points on the main body reference straight line segment is recorded as a standard window, and a crack frequency center point exists in the standard window. If there are a plurality of maximum values in the overall anomaly degree of all the frequency points on the main body reference straight line segment, the sliding window corresponding to the frequency point with the largest Euclidean distance with the center point of the spectrogram in the frequency points corresponding to the maximum values is taken as the standard window.
The fracture frequency points are concentrated in the spectrogram, and the probability that the frequency point with the larger frequency value is the fracture frequency center point is higher.
And calculating the probability that each frequency point in the standard window is a crack frequency center point according to the abnormality degree and the frequency value of the frequency point. Taking the frequency point on the y-th reference straight line segment in the standard window as an example, the frequency point on the y-th reference straight line segment in the standard windowProbability of being a crack frequency center pointThe calculation formula of (2) is as follows:
wherein the method comprises the steps ofIs the probability that the frequency point on the y-th reference straight line segment in the standard window is the center point of the crack frequency, < ->For the frequency value of the frequency point on the y-th reference straight line segment in the standard window, +.>For the degree of abnormality of the frequency point on the y-th reference straight line segment within the standard window, +.>Is the mean value of the degree of abnormality of the frequency points on all the non-y-th reference straight line segments in the standard window.
What needs to be described is: the higher the degree of abnormality of the frequency point, the larger the frequency value, and the greater the probability that the frequency point is the crack frequency center point.
According to the mode, the probability that the frequency points on all the reference straight line segments in the standard window are the crack frequency center points is obtained, and the frequency points on the reference straight line segments corresponding to the maximum value in the probability that the frequency points on all the reference straight line segments in the standard window are the crack frequency center points are recorded as the crack frequency center points. If a plurality of maximum values exist in the probability that the frequency points on all the reference straight line segments in the standard window are the crack frequency center points, the frequency points corresponding to the maximum values in the Euclidean distance from the frequency points corresponding to the maximum values to the spectrogram center points are taken as the crack frequency center points.
Step S004: and taking the center point of the crack frequency as a round point to form a circle, and determining the crack radius according to the number and the degree of abnormality of the frequency points on all the reference straight line segments in the circle.
Since the crack frequency points are distributed around the crack frequency center point, the crack frequency point distribution is concentrated, and the crack frequency range is determined according to the position of the crack frequency center point and the abnormal degree of the frequency points nearby the crack frequency center point.
The embodiment uses the value range of the set radius r asFor example, describe, wherein->For rounding down, L is the euclidean distance from the center point of the fracture frequency to the center point of the spectrogram, and the radius r is an integer, and other values may be set in other embodiments, which are not limited in this embodiment. And taking the central point of the crack frequency as a round point, acquiring the average change characteristics of the abnormal degrees of the frequency points on all the reference straight line sections in the circle when the radius r is gradually amplified, wherein the crack frequency points are concentrated in distribution, when the average change of the abnormal degrees of the frequency points is maximum, the distinction between the crack frequency points and the normal area frequency points is most obvious, and taking the radius r corresponding to the maximum average change of the abnormal degrees of the frequency points as the critical value of the crack frequency points and the normal area frequency points.
From this, it can be seen that the degree of abnormality change rate at radius rThe calculation formula of (2) is as follows:
wherein the method comprises the steps ofIs the degree of abnormality change rate when the radius is r, < >>For the frequency on the ith reference straight line segment in a circle with the center point of the crack frequency as a round point and the radius rDegree of abnormality of the rate point->For the number of frequency points on all reference straight line segments within a circle with the center point of the crack frequency as the circle point and the radius r, +.>For the degree of abnormality of the frequency point on the jth reference straight line segment in a circle with the center point of the crack frequency as a circle point and the radius r-1, +.>For the number of frequency points on all reference straight line segments within a circle with the center point of the crack frequency as a circle point and the radius r-1, < >>To get round downwards, add>Is the Euclidean distance from the center point of the fracture frequency to the center point of the spectrogram. Thereby obtaining the abnormality degree change rate set->Wherein->Is of radius ofThe degree of abnormality change rate at that time.
What needs to be described is: when the average value of the degree of abnormality of the frequency points in the circle having the radius r with the center point of the crack frequency as a circle point is larger than the difference value of the average value of the degree of abnormality of the frequency points in the circle having the radius r-1, the degree of abnormality change rate is larger.
Aggregating degree of abnormality rate of changeThe radius r corresponding to the maximum value of the number is denoted as a fracture radius J, and thus a fracture frequency point distribution range is obtained. It should be noted that if there is abnormalityDegree change Rate set->If there are a plurality of maximum values, the largest radius r among the radii r corresponding to the maximum values is denoted as a fracture radius J.
Step S005: acquiring a standard straight line segment, and determining the slopes of all frequency points on the standard straight line segment according to the frequency value difference of adjacent frequency points on the standard straight line segment; the intersection point of a circle with the center point of the fracture frequency as a round point and the radius as the fracture radius and a standard straight line segment is marked as a fracture boundary point; and determining the optimal enhancement threshold according to the slopes and the degree of abnormality of all frequency points on the standard straight line segment and the Euclidean distance from the boundary point of the crack.
The homomorphic filtering algorithm in this embodiment uses a gaussian function as a low pass filter for adjusting the frequency range of the image. The enhancement of the image needs to be performed according to the frequency threshold of enhancement and compression, in combination with the standard deviation of the gaussian kernel. The standard deviation of the Gaussian kernel is used as an enhancement threshold, and the frequency is displayed as the distance from the center point of the frequency domain in the frequency domain, so that the characteristics of the frequency points on the straight line segment from the center point of the spectrogram to the center point of the crack frequency are calculated, and the optimal enhancement threshold is judged.
And (3) marking a straight line segment from the center point of the spectrogram to the center point of the crack frequency as a standard straight line segment. And (3) subtracting the frequency value of the previous frequency point from the frequency value of the next frequency point on the standard straight line segment to obtain a difference value, and recording the difference value as the slope of the previous frequency point on the standard straight line segment to obtain the slopes of all the frequency points on the standard straight line segment. It should be noted that the slope of the last frequency point on the standard straight line segment is the slope of the penultimate frequency point on the standard straight line segment.
The slope of each frequency point on the standard straight line segment should be positive, and the probability of being the optimal enhancement threshold is greater when the slope is maximum, i.e. the frequency value changes the most. And calculating the degree of abnormality of each frequency point on the standard straight line segment, wherein the probability of the maximum enhancement threshold value is the greater at the position with the maximum difference of the degree of abnormality of adjacent frequency points.
The intersection of a circle with the center point of the fracture frequency as a dot and the radius of the circle as the fracture radius J and a standard straight line segment is denoted as a fracture boundary point Q.
Taking the x-th frequency point on the standard straight line segment as an example, the optimal enhancement threshold probability corresponding to the x-th frequency point on the standard straight line segmentThe calculation formula of (2) is as follows:
when (when)When (I)>The acquisition mode of (a) is as follows:
when (when)When (I)>The acquisition mode of (a) is as follows:
wherein the method comprises the steps ofIs the optimal enhancement threshold probability corresponding to the xth frequency point on the standard straight line segment, +.>Slope characteristic value of the xth frequency point on standard straight line segment, < ->Is the x-th frequency on the standard straight line segmentSlope of point +.>For the set slope threshold value, K is the set slope characteristic value, ++>Is the Euclidean distance from the xth frequency point to the crack boundary point Q on the standard straight line segment,/>And->Degree of abnormality of the (x+1) th and (x-1) th frequency points on the standard straight line segment, respectively, +.>Normalizing the data values to [0,1 ] as a linear normalization function]Within the interval, the present embodiment is with +.>，/>For the sake of example, other values may be set in other embodiments, and the present example is not limited thereto.
What needs to be described is: slope at a frequency pointLess than or equal to the set slope threshold +.>Let the slope characteristic value of the frequency point +.>Equal to the set slope characteristic value K, when the slope of the frequency point +.>Greater than a set slope threshold +.>Let the slope characteristic value of the frequency point +.>Slope of frequency point normalized for one>. Wherein the slope of the frequency bin ∈ ->The larger the enhancement is, the stronger the enhancement necessity is. />The Euclidean distance from the corresponding frequency point to the center point of the spectrogram at maximum is the optimal enhancement threshold value, +.>The smaller the value of (2), the more complete the fracture is enhanced, < >>The degree of abnormality change rate at the x-th frequency point on the standard straight line segment is represented, and when the standard straight line segment is at both end points, the degree of abnormality change rate at the end points is represented by using the absolute value of the difference between the degree of abnormality of the end point and the unique frequency point adjacent thereto.
According to the mode, the optimal enhancement threshold probability corresponding to all the frequency points on the standard straight line segment is obtained, and the Euclidean distance from the frequency point corresponding to the maximum value in the optimal enhancement threshold probability corresponding to all the frequency points on the standard straight line segment to the center point of the spectrogram is taken as the optimal enhancement threshold. What needs to be described is. If a plurality of maximum values exist in the optimal enhancement threshold probabilities corresponding to all the frequency points on the standard straight line segment, taking the Euclidean distance from the frequency point corresponding to the maximum value to the center point of the spectrogram as the optimal enhancement threshold.
Step S006: determining a low-pass filter according to the optimal enhancement threshold; filtering the spectrogram by using a low-pass filter to obtain an enhanced spectrogram; performing inverse Fourier transform on the enhanced spectrogram to obtain an enhanced surface image of the conveyor belt; and obtaining a crack area according to the enhanced surface image of the conveyor belt.
The optimal enhancement threshold is taken as three times standard deviation of Gaussian kernelWherein->Is the standard deviation of the gaussian kernel. And taking the Gaussian function as a low-pass filter in a homomorphic filtering algorithm, and thus filtering the spectrogram to obtain an enhanced spectrogram.
And (3) performing inverse Fourier transform on the enhanced spectrogram to obtain an enhanced belt surface image, wherein belt cracks are displayed as black in the image, and other normal areas are displayed as gray and have similar gray values. And obtaining a segmentation threshold value in the reinforced conveyor belt surface image by using an Ojin method, wherein pixels with gray values smaller than the segmentation threshold value in the reinforced conveyor belt surface image are taken as crack areas, and pixels with gray values larger than or equal to the segmentation threshold value are taken as normal areas. Thereby completing the detection of the tearing of the coal mine conveyor belt.
The present invention has been completed.
In summary, in the embodiment of the present invention, according to the difference between the euclidean distance from the frequency point on the reference straight line segment to the center point of the spectrogram in the spectrogram of the surface image of the conveyor belt and the frequency value of the frequency point on the reference straight line segment and the fitting curve value corresponding to the frequency point, the anomaly degree of the frequency point on the reference straight line segment is determined, then the anomaly degree of the frequency points on all the reference straight line segments in the sliding window corresponding to the frequency point on the main body reference straight line segment is determined, the standard window is determined, the center point of the fracture frequency is used as a circle, the radius of the fracture is determined according to the number and anomaly degree of the frequency points on all the reference straight line segments in the circle, the boundary point of the fracture is obtained, and the optimal enhancement threshold is determined according to the slope and anomaly degree of all the frequency points on the standard straight line segment and the euclidean distance to the boundary point of the fracture, and the surface image of the conveyor belt is further obtained, and the accurate fracture region is finally obtained. According to the size of a high-frequency range caused by cracks in a spectrogram, the optimal enhancement threshold is searched, the influence of uneven illumination is reduced in an image, the contrast between the cracks and a normal area of a belt is enhanced, and the existence of the cracks and the position information of the cracks are accurately judged.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (6)
1. The coal mine conveyor belt tearing detection method based on image processing is characterized by comprising the following steps of:
acquiring an image of the lower side of a coal mine conveyor belt by using an industrial camera to obtain a surface image of the conveyor belt; converting the surface image of the conveyor belt into a spectrogram by using a two-dimensional discrete Fourier transform method;
acquiring a reference straight line segment on a reference transverse line in the spectrogram, and determining the degree of abnormality of the frequency point on the reference straight line segment according to the Euclidean distance from the frequency point on the reference straight line segment to the center point of the spectrogram and the difference between the frequency value of the frequency point on the reference straight line segment and the corresponding fitting curve value;
acquiring a main body reference straight line segment in a spectrogram, and determining a standard window according to the degree of abnormality of frequency points on all reference straight line segments in a sliding window corresponding to the frequency points on the main body reference straight line segment; determining a crack frequency center point according to the abnormality degree and the frequency value of the frequency points on all the reference straight line segments in the standard window;
taking the center point of the crack frequency as a round point to form a circle, and determining the radius of the crack according to the number and the degree of abnormality of the frequency points on all the reference straight line segments in the circle;
acquiring a standard straight line segment, and determining the slopes of all frequency points on the standard straight line segment according to the frequency value difference of adjacent frequency points on the standard straight line segment; the intersection point of a circle with the center point of the fracture frequency as a round point and the radius as the fracture radius and a standard straight line segment is marked as a fracture boundary point; determining an optimal enhancement threshold according to the slopes and the degree of abnormality of all frequency points on the standard straight line segment and the Euclidean distance from the standard straight line segment to the crack boundary point;
determining a low-pass filter according to the optimal enhancement threshold; filtering the spectrogram by using a low-pass filter to obtain an enhanced spectrogram; performing inverse Fourier transform on the enhanced spectrogram to obtain an enhanced surface image of the conveyor belt; obtaining a crack area according to the enhanced surface image of the conveyor belt;
the method for determining the fracture radius by using the center point of the fracture frequency as a round point to make a circle and determining the fracture radius according to the number and the degree of abnormality of the frequency points on all the reference straight line segments in the circle comprises the following specific steps:
obtaining a preset radius value range according to the Euclidean distance from the crack frequency center point to the spectrogram center point;
taking the central point of the crack frequency as a round point, and obtaining the variation rate of the abnormal degree corresponding to each radius in the preset radius value range by taking the difference between the number and the abnormal degree of each radius in the preset radius value range and the frequency points on all the reference straight line segments in the corresponding circle after subtracting one from each radius;
the radius corresponding to the maximum value in the abnormal degree change rate corresponding to all the radii in the preset radius value range is recorded as the fracture radius;
the specific calculation formula corresponding to the abnormal degree change rate corresponding to each radius in the preset radius value range is obtained by taking the central point of the crack frequency as a round point and subtracting the difference between the number and the abnormal degree of each radius in the preset radius value range and the frequency points on all the reference straight line segments in the corresponding circle after subtracting one from each radius, wherein the specific calculation formula is as follows:
wherein the method comprises the steps ofIs the corresponding abnormal degree change rate when the radius is r,>in order to determine the degree of abnormality of the frequency point on the ith reference straight line segment in a circle with the center point of the crack frequency as the circle point and the radius r, +.>For the number of frequency points on all reference straight line segments within a circle with the center point of the crack frequency as the circle point and the radius r, +.>For the degree of abnormality of the frequency point on the jth reference straight line segment in a circle with the center point of the crack frequency as a circle point and the radius r-1, +.>The number of frequency points on all reference straight line segments in a circle with the center point of the crack frequency as a round point and the radius r-1;
the method for determining the optimal enhancement threshold according to the slopes and the degree of abnormality of all frequency points on the standard straight line segment and the Euclidean distance from the frequency points to the crack boundary point comprises the following specific steps:
if the slope of the frequency point on the standard straight line segment is smaller than or equal to a preset slope threshold value, setting the slope characteristic value of the frequency point on the standard straight line segment as a preset slope characteristic value;
if the slope of the frequency point on the standard straight line segment is larger than a preset slope threshold value, adding one to the normalized value of the slope of the frequency point on the standard straight line segment, and marking the normalized value as a slope characteristic value of the frequency point on the standard straight line segment;
recording one half of the absolute value of the difference between the abnormal degrees of two adjacent frequency points of the frequency points on the standard straight line segment as the abnormal degree change rate of the frequency points on the standard straight line segment;
determining the optimal enhancement threshold probability corresponding to the frequency point on the standard straight line segment according to the slope characteristic value of the frequency point on the standard straight line segment, the abnormal degree change rate of the frequency point on the standard straight line segment and the Euclidean distance from the frequency point on the standard straight line segment to the crack boundary point;
the Euclidean distance from the frequency point corresponding to the maximum value in the optimal enhancement threshold probability corresponding to all the frequency points on the standard straight line segment to the center point of the spectrogram is recorded as an optimal enhancement threshold;
the specific calculation formula corresponding to the optimal enhancement threshold probability corresponding to the frequency point on the standard straight line segment is determined according to the slope characteristic value of the frequency point on the standard straight line segment, the abnormal degree change rate of the frequency point on the standard straight line segment and the Euclidean distance from the frequency point on the standard straight line segment to the crack boundary point, wherein the specific calculation formula is as follows:
wherein the method comprises the steps ofIs the optimal enhancement threshold probability corresponding to the xth frequency point on the standard straight line segment, +.>Slope characteristic value of the xth frequency point on standard straight line segment, < ->Is the Euclidean distance from the xth frequency point to the crack boundary point on the standard straight line segment, +.>Andthe degree of abnormality of the x+1 th and x-1 st frequency points on the standard straight line segment respectively.
2. The method for detecting the tearing of the coal mine conveyor belt based on the image processing according to claim 1, wherein the step of obtaining the reference straight line segment on the reference transverse line in the spectrogram and determining the degree of abnormality of the frequency point on the reference straight line segment according to the difference between the euclidean distance from the frequency point on the reference straight line segment to the center point of the spectrogram and the frequency value of the frequency point on the reference straight line segment and the fitting curve value corresponding to the frequency point on the reference straight line segment comprises the following specific steps:
taking a transverse line of a center point of the frequency spectrogram in the frequency spectrogram and a plurality of adjacent transverse lines above and below the transverse line of the center point of the frequency spectrogram, and marking the transverse lines as reference transverse lines to obtain a reference transverse lines; wherein a is the number of preset transverse lines;
dividing a reference transverse line into two straight line segments by using a central point of the reference transverse line, and marking the reference transverse line as a reference straight line segment;
performing curve fitting on the frequency values of all the frequency points on the reference straight line segment by using a least square method to obtain a fitted curve value corresponding to the frequency value of each frequency point on the reference straight line segment;
and (3) recording the product of the normalized value of the Euclidean distance from the frequency point on the reference straight line segment to the center point of the spectrogram and the absolute value of the difference value between the frequency value of the frequency point on the reference straight line segment and the corresponding fitting curve value as the degree of abnormality of the frequency point on the reference straight line segment.
3. The method for detecting the tearing of the coal mine conveyor belt based on the image processing according to claim 1, wherein the main body reference straight line segment in the acquired spectrogram is used for determining a standard window according to the degree of abnormality of the frequency points on all the reference straight line segments in the sliding window corresponding to the frequency points on the main body reference straight line segment, and the method comprises the following specific steps:
a reference straight line segment corresponding to a reference transverse line passing through a spectrogram center point in the spectrogram is recorded as a main body reference straight line segment;
traversing frequency points on the main body reference straight line segment by using a preset sliding window to obtain a sliding window corresponding to each frequency point on the main body reference straight line segment;
the sum of abnormal ranges of the frequency points on all the reference straight line segments in the sliding window corresponding to each frequency point on the main body reference straight line segment is recorded as the integral abnormal degree of each frequency point on the main body reference straight line segment;
and (3) marking the sliding window corresponding to the frequency point corresponding to the maximum value in the overall abnormality degree of all the frequency points on the main body reference straight line segment as a standard window.
4. The method for detecting the tearing of the coal mine conveyor belt based on the image processing according to claim 1, wherein the step of determining the center point of the frequency of the fracture according to the degree of abnormality and the frequency value of the frequency point on all the reference straight line segments in the standard window comprises the following specific steps:
determining the probability that the frequency point on each reference straight line segment in the standard window is a crack frequency center point according to the abnormality degree of the frequency points on all the reference straight line segments in the standard window and the frequency value of the frequency point on each reference straight line segment in the standard window;
and (3) marking the frequency points on the reference straight line segments corresponding to the maximum value in the probability that the frequency points on all the reference straight line segments in the standard window are the crack frequency center points as the crack frequency center points.
5. The method for detecting the tearing of the coal mine conveyor belt based on the image processing according to claim 4, wherein the specific calculation formula corresponding to the probability that the frequency point on each reference straight line segment in the standard window is the center point of the fracture frequency is determined according to the degree of abnormality of the frequency points on all the reference straight line segments in the standard window and the frequency value of the frequency point on each reference straight line segment in the standard window, and is as follows:
wherein the method comprises the steps ofIs the probability that the frequency point on the y-th reference straight line segment in the standard window is the center point of the crack frequency, < ->For the frequency value of the frequency point on the y-th reference straight line segment in the standard window, +.>Is a standard windowDegree of abnormality of frequency point on the y-th reference straight line segment in mouth, +.>Is the mean value of the degree of abnormality of the frequency points on all the non-y-th reference straight line segments in the standard window.
6. The method for detecting the tearing of the coal mine conveyor belt based on the image processing according to claim 1, wherein the step of obtaining the standard straight line segment and determining the slopes of all the frequency points on the standard straight line segment according to the frequency value difference of the adjacent frequency points on the standard straight line segment comprises the following specific steps:
marking a straight line segment from the center point of the spectrogram to the center point of the crack frequency as a standard straight line segment;
and (3) subtracting the frequency value of the previous frequency point from the frequency value of the next frequency point on the standard straight line segment, and recording the difference as the slope of the previous frequency point on the standard straight line segment to obtain the slopes of all the frequency points on the standard straight line segment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410076891.2A CN117585399B (en) | 2024-01-19 | 2024-01-19 | Coal mine conveyor belt tearing detection method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410076891.2A CN117585399B (en) | 2024-01-19 | 2024-01-19 | Coal mine conveyor belt tearing detection method based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117585399A CN117585399A (en) | 2024-02-23 |
| CN117585399B true CN117585399B (en) | 2024-04-09 |
Family
ID=89922375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410076891.2A Active CN117585399B (en) | 2024-01-19 | 2024-01-19 | Coal mine conveyor belt tearing detection method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117585399B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117979508B (en) * | 2024-03-05 | 2024-07-12 | 六班电气有限公司 | Intelligent lamplight regulation and control method based on underground environment sensing |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003059789A2 (en) * | 2002-01-14 | 2003-07-24 | Carnegie Mellon University | Conveyor belt inspection system and method |
| CN110980192A (en) * | 2019-12-10 | 2020-04-10 | 安徽银河物联通信技术有限公司 | Belt tearing detection method |
| CN114187237A (en) * | 2021-11-12 | 2022-03-15 | 广东能源集团科学技术研究院有限公司 | Method, device and equipment for detecting tearing and deviation of conveyer belt and storage medium |
| CN114419048A (en) * | 2022-03-31 | 2022-04-29 | 启东亦大通自动化设备有限公司 | Conveyor online detection method and system based on image processing |
| CN115535525A (en) * | 2022-09-08 | 2022-12-30 | 潍坊大友电子科技有限公司 | Conveyor belt longitudinal tearing detection system and method based on image matching |
| CN115954291A (en) * | 2023-03-04 | 2023-04-11 | 天合光能(宿迁)光电有限公司 | Crack monitoring system of TOPCon structure photovoltaic cell panel |
| CN117237359A (en) * | 2023-11-15 | 2023-12-15 | 天津市恒一机电科技有限公司 | Conveyor belt tearing detection method and device, storage medium and electronic equipment |
-
2024
- 2024-01-19 CN CN202410076891.2A patent/CN117585399B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2003059789A2 (en) * | 2002-01-14 | 2003-07-24 | Carnegie Mellon University | Conveyor belt inspection system and method |
| CN110980192A (en) * | 2019-12-10 | 2020-04-10 | 安徽银河物联通信技术有限公司 | Belt tearing detection method |
| CN114187237A (en) * | 2021-11-12 | 2022-03-15 | 广东能源集团科学技术研究院有限公司 | Method, device and equipment for detecting tearing and deviation of conveyer belt and storage medium |
| CN114419048A (en) * | 2022-03-31 | 2022-04-29 | 启东亦大通自动化设备有限公司 | Conveyor online detection method and system based on image processing |
| CN115535525A (en) * | 2022-09-08 | 2022-12-30 | 潍坊大友电子科技有限公司 | Conveyor belt longitudinal tearing detection system and method based on image matching |
| CN115954291A (en) * | 2023-03-04 | 2023-04-11 | 天合光能(宿迁)光电有限公司 | Crack monitoring system of TOPCon structure photovoltaic cell panel |
| CN117237359A (en) * | 2023-11-15 | 2023-12-15 | 天津市恒一机电科技有限公司 | Conveyor belt tearing detection method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117585399A (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115239704B (en) | Accurate detection and repair method for wood surface defects | |
| CN116721106B (en) | Profile flaw visual detection method based on image processing | |
| CN115311270B (en) | Plastic product surface defect detection method | |
| CN114842017A (en) | HDMI cable surface quality detection method and system | |
| CN108389216B (en) | Local self-adaptive threshold segmentation method for online ferrographic image abrasive particle identification | |
| CN117585399B (en) | Coal mine conveyor belt tearing detection method based on image processing | |
| CN110706210B (en) | Deep learning-based rebar counting method and device | |
| CN117853493B (en) | Wallboard production quality detection method based on image processing | |
| CN116805317B (en) | Rotary furnace inner wall defect detection method based on artificial intelligence | |
| CN115115612A (en) | Surface defect detection method and system for mechanical parts | |
| CN116188468B (en) | HDMI cable transmission letter sorting intelligent control system | |
| CN112085651B (en) | Automatic shock wave detection and tracking algorithm based on image self-adaptive threshold and feature extraction | |
| CN117689655B (en) | Metal button surface defect detection method based on computer vision | |
| CN117291919B (en) | Visual detection method for lubricating grease on surface of steel rail bolt | |
| CN117541582A (en) | IGBT insulation quality detection method for high-frequency converter | |
| CN116229438A (en) | Spinning quality visual identification system | |
| CN118014994B (en) | Rice hull degradable meal box crack detection method | |
| CN117314940B (en) | Laser cutting part contour rapid segmentation method based on artificial intelligence | |
| CN117808796B (en) | Gear surface damage detection method based on computer vision | |
| CN117388263B (en) | Hardware terminal quality detection method for charging gun | |
| CN117237350B (en) | Real-time detection method for quality of steel castings | |
| CN117542488B (en) | Intelligent processing method for brain tumor CT data | |
| CN111723808B (en) | Infrared weak target extraction method based on maximum value background prediction | |
| CN117274203B (en) | Visual detection method for surface quality of environment-friendly plastic product | |
| CN117474897B (en) | Visual detection method for surface defects of charger |
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 |