CN114972349A - Carrier roller running state detection method and system based on image processing - Google Patents
Carrier roller running state detection method and system based on image processing Download PDFInfo
- Publication number
- CN114972349A CN114972349A CN202210913082.3A CN202210913082A CN114972349A CN 114972349 A CN114972349 A CN 114972349A CN 202210913082 A CN202210913082 A CN 202210913082A CN 114972349 A CN114972349 A CN 114972349A
- Authority
- CN
- China
- Prior art keywords
- image
- moment
- carrier roller
- gray
- roller
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 34
- 238000001514 detection method Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 67
- 230000008569 process Effects 0.000 claims abstract description 24
- 230000002159 abnormal effect Effects 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims description 17
- 230000008901 benefit Effects 0.000 claims description 16
- 230000033001 locomotion Effects 0.000 claims description 16
- 238000003709 image segmentation Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000008859 change Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 150000001875 compounds Chemical class 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a system for detecting the running state of a carrier roller based on image processing, and relates to the field of artificial intelligence. The method mainly comprises the following steps: acquiring a multi-frame gray image of the carrier roller to be detected at each moment in the running process of the conveyor belt; overlapping edge vibration areas in adjacent multi-frame gray scale images at each moment to obtain an edge vibration image corresponding to each moment; carrying out non-blind deconvolution on the edge vibration image at each moment to obtain a clear vibration image at each moment; and respectively obtaining the similarity between the edge vibration image and the clear vibration image corresponding to each moment so as to determine whether the carrier roller to be tested is an abnormal carrier roller. According to the embodiment of the invention, the front images of the carrier rollers are processed, so that the state detection result of each carrier roller can be respectively obtained in the operation process of the conveying device provided with the carrier rollers, and the state detection precision of the carrier rollers is improved.
Description
Technical Field
The application relates to the field of artificial intelligence, in particular to a method and a system for detecting running states of carrier rollers based on image processing.
Background
The belt conveyor is large-scale transportation coal mine equipment and has the advantages of simple structure, large transportation amount, low manufacturing cost, low maintenance cost and the like. However, the mine working environment is relatively complex, a plurality of safety accidents are caused by the running state of the belt conveyor, wherein the carrier roller is one of the most important parts in the belt conveyor, the carrier roller is mainly used for supporting the conveying belt and the conveyed materials, and in the running process of the belt conveyor, the carrier roller can not be in close contact with the conveying belt due to the fact that the carrier roller cannot be installed in place or the surface of the carrier roller has defects and the like, so that the carrier roller vibrates up and down, the service life of a bearing in the carrier roller is further shortened, and the service life of the conveying belt is damaged.
In the prior art, whether the carrier roller is abnormal or not is mainly determined by analyzing the audio frequency at the carrier roller, however, the carrier roller has interference of various sounds such as the sound in the material conveying process and the sound of parts except the carrier roller on a belt conveyor in the operation process, so that the audio frequency of the single carrier roller in the operation process is difficult to acquire, and the accurate state detection result of the carrier roller is difficult to acquire.
Disclosure of Invention
In view of the above technical problems, the present invention provides a method and a system for detecting an operation state of a carrier roller based on image processing, which can respectively obtain a state detection result for each carrier roller during the operation of a conveyor equipped with the carrier roller by processing a front image of the carrier roller, and can improve the state detection accuracy for the carrier roller compared with the state detection for the carrier roller by audio frequency in the prior art.
In a first aspect, an embodiment of the present invention provides a method for detecting a running state of a carrier roller based on image processing, including:
and acquiring a multi-frame front image of the carrier roller to be detected at each moment in the running process of the conveyor belt, and performing graying to obtain a multi-frame gray image corresponding to each moment.
And overlapping edge vibration areas in the adjacent multi-frame gray scale images at each moment to obtain an edge vibration image corresponding to each moment, wherein the edge vibration areas are areas with preset heights at the upper and lower boundaries of the gray scale images.
And obtaining a convolution kernel corresponding to the edge vibration image at each moment by utilizing variational Bayes, and performing a non-blind deconvolution deblurring method on the edge vibration image at each moment according to the convolution kernel to obtain a clear vibration image at each moment after deblurring.
Respectively obtaining the similarity between the edge vibration image and the clear vibration image corresponding to each moment, obtaining the proportion of the similarity smaller than or equal to the similarity threshold in all the similarities corresponding to all the moments in a preset time period, and determining the carrier roller to be detected as an abnormal carrier roller under the condition that the proportion is larger than the proportion threshold.
Further, in the method for detecting the running state of the idler roller based on image processing, the method further includes updating the similarity corresponding to each time, including:
the method comprises the steps of obtaining the long-run low-gray-level advantage of a gray run matrix of any frame of gray images at each moment in the moving direction, and taking the long-run low-gray-level advantage as a first characteristic value at each moment, wherein the moving direction is the corresponding direction of the moving direction of a carrier roller to be tested in the gray images;
acquiring the long-run low-gray-level advantage of the gray-level run matrix of any frame of gray-level image in each direction except the motion direction at each moment, and taking the average value of the long-run low-gray-level advantages of the gray-level run matrix in each direction except the motion direction as a second characteristic value at each moment; the directions other than the moving direction are directions other than the direction corresponding to the moving direction among 0 degree, 45 degrees, 90 degrees and 135 degrees;
taking the division operation result of the second characteristic value and the first characteristic value at each moment as a third characteristic value at each moment;
and taking the product result of the similarity corresponding to each moment and the third characteristic value corresponding to each moment as the updated similarity corresponding to each moment.
Further, in the method for detecting the running state of the carrier roller based on image processing, the method further includes obtaining the moving direction of the carrier roller to be detected according to the gray level image, and obtaining the moving direction of the carrier roller to be detected according to the gray level image includes:
respectively taking the direction with the minimum gray value difference between each pixel point in the gray image and the pixel points in the eight neighborhoods thereof as the characteristic direction of each pixel point in the gray image;
and taking the characteristic direction with the included angle of 180 degrees as the same characteristic direction, and taking the characteristic direction with the largest frequency number in all the characteristic directions of all pixel points in the gray level image as the motion direction of the carrier roller to be detected.
Further, in the method for detecting the running state of the carrier roller based on image processing, before graying the front image of the carrier roller to be detected to obtain a grayscale image, the method further comprises:
the method comprises the steps of collecting an image of the front side of a carrier roller to be detected, carrying out image segmentation to obtain a front side image of the carrier roller to be detected, wherein the pixel value of a pixel point in the front side image, except the carrier roller to be detected, is 0.
Further, in the idler running state detection method based on image processing, image segmentation is performed on the image containing the front surface of the idler to be detected to obtain the front surface image of the idler to be detected, and the DNN is used for realizing the image segmentation.
Further, in the method for detecting the running state of the carrier roller based on image processing, before acquiring the multi-frame front image of the carrier roller to be detected at each moment, the method further comprises the step of determining the carrier roller to be detected, wherein the step of determining the carrier roller to be detected comprises the following steps:
and respectively acquiring the audio frequency of each carrier roller in the running process of the conveyor belt, and determining the carrier roller with the difference degree between the audio frequency of the carrier roller and the standard carrier roller being greater than the difference degree threshold value as the carrier roller to be detected.
Further, in the method for detecting the running state of the carrier roller based on image processing, the similarity between the edge vibration image and the clear vibration image corresponding to each moment is structural similarity SSIM.
In a second aspect, an embodiment of the present invention provides an idler running state detection system based on image processing, including: the device comprises a memory and a processor, wherein the processor executes a computer program stored in the memory to realize the idler running state detection method based on image processing in the embodiment of the invention.
The invention provides a method and a system for detecting the running state of a carrier roller based on image processing, compared with the prior art, the embodiment of the invention has the beneficial effects that: through processing the positive image of bearing roller, can be equipped with the running process of conveyer of bearing roller, obtain the state testing result to each bearing roller respectively, compare and carry out the state detection of bearing roller through the audio frequency among the prior art, can improve the state detection precision to the bearing roller.
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 of a method for detecting an operation state of a carrier roller based on image processing according to an embodiment of the present invention;
fig. 2 is a schematic diagram of the relative positions of the front face of the idler and the direction of belt travel provided by an embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating updating of the similarity corresponding to each time according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention. 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.
In the following description, for purposes of explanation and not limitation, specific details are set forth such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature; in the description of the present embodiment, "a plurality" means two or more unless otherwise specified.
The embodiment of the invention provides a method for detecting the running state of a carrier roller based on image processing, which comprises the following steps of:
and S100, acquiring multi-frame front images of the carrier roller to be detected at each moment in the running process of the conveyor belt, and performing graying to obtain multi-frame gray images corresponding to each moment.
In the conveyer belt operation in-process, need pass through the material of bearing roller support conveyer belt and conveyer belt top, however, when the bearing roller because the defect such as pit that the surface exists, can make bearing roller and conveyer belt can't fully contact to cause the bearing roller to vibrate in upper and lower direction, and further shorten the life of bearing in the bearing roller, consequently, the unusual vibration condition that appears in the needs in time discovery bearing roller.
Fig. 2 is a schematic diagram of relative positions of the front surface of the idler and the moving direction of the conveyor belt in the embodiment of the invention, multiple frames of front surface images of the idler to be measured in the operation process of the conveyor belt can be collected from the front surface of the idler, the collected multiple frames of front surface images are RGB images, RGB is a color standard, and various colors are obtained by changing and mutually overlapping three color channels of red (R), green (G) and blue (B), wherein RGB is a color representing the three channels of red, green and blue.
And graying the collected multi-frame front images at each moment respectively to obtain multi-frame gray images corresponding to each moment, wherein the graying process can adopt maximum graying or average graying.
Optionally, before graying the front image of the to-be-detected carrier roller to obtain a grayscale image, acquiring an image of the front surface of the to-be-detected carrier roller, and performing image segmentation on the image of the front surface of the to-be-detected carrier roller to obtain the front image of the to-be-detected carrier roller, wherein the pixel values of pixel points other than the to-be-detected carrier roller in the front image obtained after segmentation are 0, so that adverse effects of the pixel points other than the carrier roller on the detection result can be removed.
The image segmentation process for the front surface including the carrier roller to be measured can be implemented by a Deep Neural Network (DNN), and the DNN training process may include the following steps: the method comprises the steps of carrying out manual marking on pixel points in an image of the front face including a carrier roller, dividing the pixel points into carrier roller types and background types except the carrier roller, marking the pixel of the background type as 0, training DNN by using the image after marking is finished, and meanwhile, supervising the training process by adopting a cross entropy loss function in the training process.
Optionally, before obtaining the multi-frame front image of the to-be-measured carrier roller at each moment, the to-be-measured carrier roller can be determined from all carrier rollers, and the method specifically includes: the method comprises the steps of collecting audio frequencies of carrier rollers in the running process of a conveyor belt respectively, determining the carrier rollers with the difference degrees of the audio frequencies of the carrier rollers and standard carrier rollers larger than a difference threshold value as carrier rollers to be tested, wherein it needs to be explained that the carrier rollers under different load conditions and motion speeds of different cargos can present different states of the corresponding audio frequencies, and when the difference degrees of the audio frequencies of the carrier rollers and the corresponding standard audio frequencies under the current state of the carrier rollers are larger than the difference threshold value, the carrier rollers are more likely to be carrier rollers with faults and can be determined as the carrier rollers to be tested, so that preliminary screening of the carrier rollers can be realized.
Wherein, for the difference degree between the audios, the absolute value of the difference value of the amplitudes between different audios can be used as the difference degree between different audios by determining the amplitude of the audio, which is the difference value between the maximum value and the minimum value of the audio.
And S200, overlapping edge vibration areas in the adjacent multi-frame gray scale images at each moment to obtain an edge vibration image corresponding to each moment, wherein the edge vibration areas are areas with preset heights at the upper and lower boundaries of the gray scale images.
The reason why the edge vibration regions in the adjacent multi-frame gray scale images at each moment are superposed in the embodiment of the invention is that the vertical vibration condition of the edge vibration regions in a single frame at the same moment cannot be effectively reflected through the edge vibration regions in the single frame, and meanwhile, the vertical vibration condition of the upper and lower boundary parts of the gray scale image on the front surface of the carrier roller can be effectively reflected through the upper and lower boundary parts of the gray scale image, so the edge vibration regions in the embodiment of the invention are regions with preset heights positioned at the upper and lower boundaries of the gray scale image.
And step S300, obtaining a convolution kernel corresponding to the edge vibration image at each moment by using variational Bayes, and performing a non-blind deconvolution deblurring method on the edge vibration image at each moment according to the convolution kernel to obtain a clear vibration image at each moment after deblurring.
In the embodiment of the invention, a clear vibration image corresponding to the edge vibration image is obtained by using a motion deblurring algorithm, and the larger the vibration amplitude is, the deeper the blurring degree of the image is, so that the similarity before and after motion deblurring is smaller, therefore, in the subsequent steps, the embodiment of the invention reflects the vibration intensity of the carrier roller to be tested by comparing the similarity between the images before and after the motion deblurring of the edge vibration image.
And S400, respectively obtaining the similarity between the edge vibration image and the clear vibration image corresponding to each moment, obtaining the proportion of the similarity which is less than or equal to a similarity threshold value in all the similarities corresponding to all the moments in a preset time length, and determining the carrier roller to be detected as an abnormal carrier roller under the condition that the proportion is greater than the proportion threshold value.
Because the larger the vibration amplitude of the carrier roller is, the larger the blurring degree caused to the edge vibration region is, the smaller the similarity between the deblurred sharp vibration image and the edge vibration image is, in the embodiment of the invention, the vibration amplitude of the carrier roller at the edge can be reflected by determining the similarity between the edge vibration image and the corresponding sharp vibration image.
As a possible implementation manner, the obtaining process of the similarity between the edge vibration image and the sharp vibration image in the embodiment of the present invention includes:
in the formula (I), the compound is shown in the specification,
is the gray level average of the pixel points in the edge vibration image,
is the average value of the gray levels of the pixel points in the sharp vibration image,
is the variance of the gray values of the pixel points in the edge vibration image,
is the variance of the gray values of the pixels in the sharp vibration image,
is the covariance of the gray values of the pixels in the edge vibration image and the sharp vibration image,
，
wherein, in the step (A),
in order to preset the first value of the first value,
to preset the second value, as an example, the embodiment of the present invention
，
。
As another possible implementation manner, in the embodiment of the present invention, the similarity between the edge vibration image and the sharp vibration image is calculated by using a structural similarity SSIM, it should be noted that the structural similarity SSIM (structural similarity index) is an index for measuring the similarity between two images, and from the perspective of image composition, the structural information is defined as being independent of brightness and contrast, and reflects the attribute of an object structure in a scene, and distortion is modeled as a combination of three different factors, namely brightness, contrast and structure, where a mean value is used as an estimate of brightness, a standard deviation is used as an estimate of contrast, and a covariance is used as a measure of structural similarity.
As another possible implementation manner, in the embodiment of the present invention, the similarity between the edge vibration image and the sharp vibration image is calculated by using a Pearson correlation coefficient, and it should be noted that, in statistics, the Pearson correlation coefficient, which is also called Pearson product-moment correlation coefficient (PPMCC or PCCs), may be applied to calculate the similarity between the two images.
Under the condition that the proportion of the similarity smaller than or equal to the similarity threshold value in all the similarities corresponding to all the moments in the preset time length is larger than the proportion threshold value, the carrier roller to be tested can be determined as an abnormal carrier roller; as an example, in the embodiment of the present invention, the similarity threshold is 0.7, and an implementer may determine a value of the similarity threshold according to an actual requirement.
It should be noted that when the ratio of the similarity smaller than or equal to the similarity threshold in all the similarities in the preset time period is greater than the proportional threshold, it indicates that the vibration of the idler exceeds the allowable range, and the idler to be tested may be determined as the idler with the abnormality.
Optionally, can change unusual bearing roller after determining to have unusual bearing roller, simultaneously, to the change process of unusual bearing roller, can utilize the bearing roller to change the device, temporarily replace the unusual bearing roller of waiting to change and accomplish the work that supports the conveyer belt, wait to accomplish the change back to the bearing roller, lift off bearing roller and change the device, utilize the bearing roller after changing to continue to support the conveyer belt.
Optionally, in the embodiment of the present invention, the similarity corresponding to each time may also be updated, as shown in fig. 3, which specifically includes the following steps:
and S110, acquiring the advantage of the long-run low gray level of the gray level run matrix of any frame of gray level image at each moment in the moving direction, and taking the advantage as a first characteristic value at each moment, wherein the moving direction is the corresponding direction of the moving direction of the carrier roller to be detected in the gray level image.
Because the moving speed of the carrier roller can also influence the vibration condition of the carrier roller in the running process of the conveyor belt, meanwhile, the carrier roller with the same texture has different textures in the front image under different moving speeds, which is mainly shown in that more strip-shaped connected domains in the moving direction can exist in the front image of the carrier roller with the faster moving speed.
Meanwhile, the characteristic can be well reflected by utilizing the long-run first gray level of the gray run matrix, so that the advantage of the long-run low gray level of the gray run matrix in the motion direction of any frame gray level image at each moment is obtained and taken as the first characteristic value at each moment.
It should be noted that the gray level run matrix of the image reflects the comprehensive information of the gray level of the image about the direction, adjacent interval, and variation range, which is one of the bases of the local pattern of the analyzed image and the arrangement rule thereof. The gray level run-length matrix can realize the statistics of the number of continuous occurrence of the same gray level value in the same direction in an image, continuous pixel points in a certain direction on the image have the same gray level value, and the gray level run-length matrix is obtained by counting the distribution of the pixel points to obtain texture characteristics.
Specifically, the process for obtaining the long-run-length gray-level-first advantage of the gray-level co-occurrence matrix of the gray-level image includes:
in the formula (I), the compound is shown in the specification,
as a gray scale image
The long run-length gray-level dominance of the directional gray-level co-occurrence matrix,
is the first in a gray scale image
Pixel point edge of gray level
Run of direction of
The frequency of (a) to (b) is,
for the maximum run in the gray level run matrix,
run length, which is the number of gray levels in a gray image, refers to the number of consecutive occurrences, and, at the same time,
at any one of 0 degrees, 45 degrees, 90 degrees and 135 degrees.
Optionally, the movement direction of the roller to be measured can be obtained according to the grayscale image, and the method specifically includes: respectively taking the direction with the minimum gray value difference between each pixel point in the gray image and the pixel points in the eight neighborhoods thereof as the characteristic direction of each pixel point in the gray image; and taking the characteristic direction with the included angle of 180 degrees as the same characteristic direction, and taking the characteristic direction with the largest frequency number in all the characteristic directions of all pixel points in the gray level image as the motion direction of the carrier roller to be detected.
Step S120, obtaining the long-run low-gray-level advantage of the gray-level run matrix of any frame of gray-level image in each direction except the motion direction at each moment, and taking the average value of the long-run low-gray-level advantages of the gray-level run matrix in each direction except the motion direction as a second characteristic value at each moment; the directions other than the moving direction are directions other than the direction corresponding to the moving direction among 0 degrees, 45 degrees, 90 degrees, and 135 degrees.
Step S130, taking a division operation result of the second characteristic value and the first characteristic value at each moment as a third characteristic value at each moment; and taking the product result of the similarity corresponding to each moment and the third characteristic value corresponding to each moment as the updated similarity corresponding to each moment.
Therefore, the obtained updated similarity includes the influence on vibration caused by the movement speed, so that a more accurate roller state detection result is obtained.
Based on the same inventive concept as the method, the embodiment also provides an image processing-based idler running state detection system, and the image processing-based idler running state detection system in the embodiment comprises a memory and a processor, wherein the processor executes a computer program stored in the memory to realize the detection of the idler running state as described in the image processing-based idler running state detection method embodiment.
Since the method for detecting the state of the idler in the idler running state detection method based on image processing has been described in the embodiment, details are not described here.
In summary, the present invention provides a method and a system for detecting an operation status of a idler based on image processing, which can obtain status detection results for each idler respectively during operation of a conveyor equipped with idlers by processing front images of idlers, and can improve accuracy of detecting the status of the idler compared with the prior art in which status detection of the idler is performed by audio.
The use of words such as "including," "comprising," "having," and the like in this disclosure is an open-ended term that means "including, but not limited to," and is used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
It should also be noted that the various components or steps may be broken down and/or re-combined in the methods and systems of the present invention. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.
The above-mentioned embodiments are merely examples for clearly illustrating the present invention and do not limit the scope of the present invention. It will be apparent to those skilled in the art that other variations and modifications may be made in the foregoing description, and it is not necessary or necessary to exhaustively enumerate all embodiments herein. All designs identical or similar to the present invention are within the scope of the present invention.
Claims (8)
1. An idler running state detection method based on image processing is characterized by comprising the following steps:
acquiring a multi-frame front image of the carrier roller to be detected at each moment in the operation process of the conveyor belt, and performing graying to obtain a multi-frame gray image corresponding to each moment;
overlapping edge vibration areas in adjacent multi-frame gray scale images at each moment to obtain edge vibration images corresponding to each moment, wherein the edge vibration areas are areas with preset heights at the upper and lower boundaries of the gray scale images;
obtaining a convolution kernel corresponding to the edge vibration image at each moment by using variational Bayes, and performing a non-blind deconvolution deblurring method on the edge vibration image at each moment according to the convolution kernel to obtain a clear vibration image at each moment after deblurring;
respectively obtaining the similarity between the edge vibration image and the clear vibration image corresponding to each moment, obtaining the proportion of the similarity smaller than or equal to the similarity threshold value in all the similarities corresponding to all the moments in a preset time period, and determining the carrier roller to be detected as an abnormal carrier roller under the condition that the proportion is larger than the proportion threshold value.
2. A method for detecting a roller operating condition based on image processing as claimed in claim 1, wherein the method further includes updating the corresponding similarity at each time, including:
the method comprises the steps of obtaining the advantage of long-run low gray level of a gray run matrix of any frame of gray image in the moving direction at each moment, and taking the advantage as a first characteristic value at each moment, wherein the moving direction is the corresponding direction of the moving direction of a carrier roller to be tested in the gray image;
obtaining the long-run low-gray level advantage of the gray run matrix of any frame of gray image in each direction except the motion direction at each moment, and taking the average value of the long-run low-gray level advantages of the gray run matrix in each direction except the motion direction as a second characteristic value at each moment; the directions other than the moving direction are directions other than the direction corresponding to the moving direction among 0 degree, 45 degrees, 90 degrees and 135 degrees;
taking the division operation result of the second characteristic value and the first characteristic value at each moment as a third characteristic value at each moment;
and taking the product result of the similarity corresponding to each moment and the third characteristic value corresponding to each moment as the updated similarity corresponding to each moment.
3. The image processing-based idler running state detecting method according to claim 2, wherein the method further comprises obtaining a moving direction of the idler to be tested according to a gray image, and the obtaining of the moving direction of the idler to be tested according to the gray image comprises:
respectively taking the direction with the minimum gray value difference between each pixel point in the gray image and the pixel points in the eight neighborhoods thereof as the characteristic direction of each pixel point in the gray image;
and taking the characteristic direction with the included angle of 180 degrees as the same characteristic direction, and taking the characteristic direction with the largest frequency number in all the characteristic directions of all pixel points in the gray level image as the motion direction of the carrier roller to be detected.
4. A roller operating condition detecting method based on image processing according to claim 1, wherein before graying the front image of the roller to be tested to obtain a grayscale image, the method further comprises:
the method comprises the steps of collecting an image of the front side of a carrier roller to be detected, carrying out image segmentation to obtain a front side image of the carrier roller to be detected, wherein the pixel value of a pixel point in the front side image, except the carrier roller to be detected, is 0.
5. A idler running state detection method based on image processing according to claim 4 wherein image segmentation of the image containing the front face of the idler under test to obtain the front face image of the idler under test is achieved by DNN.
6. A roller operating state detecting method based on image processing according to claim 1, wherein before acquiring the multi-frame front images of the roller to be tested at each moment, the method further comprises determining the roller to be tested, wherein the process of determining the roller to be tested comprises:
and respectively acquiring the audio frequency of each carrier roller in the running process of the conveyor belt, and determining the carrier roller with the difference degree between the audio frequency of the carrier roller and the standard carrier roller being greater than the difference degree threshold value as the carrier roller to be detected.
7. The image processing-based idler roller operating state detection method according to claim 1, wherein the similarity between the edge vibration image and the sharp vibration image corresponding to each moment is structural similarity SSIM.
8. An image processing-based idler run status detection system comprising: a memory and a processor, wherein the processor executes a computer program stored in the memory to implement the image processing-based idler run state detection method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210913082.3A CN114972349B (en) | 2022-08-01 | 2022-08-01 | Carrier roller running state detection method and system based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210913082.3A CN114972349B (en) | 2022-08-01 | 2022-08-01 | Carrier roller running state detection method and system based on image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114972349A true CN114972349A (en) | 2022-08-30 |
| CN114972349B CN114972349B (en) | 2022-10-25 |
Family
ID=82969569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210913082.3A Active CN114972349B (en) | 2022-08-01 | 2022-08-01 | Carrier roller running state detection method and system based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114972349B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117876363A (en) * | 2024-03-11 | 2024-04-12 | 宝鸡杭叉工程机械有限责任公司 | On-line detection method and system for carrier roller running state of belt conveyor |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070258707A1 (en) * | 2006-05-08 | 2007-11-08 | Ramesh Raskar | Method and apparatus for deblurring images |
| US20080025627A1 (en) * | 2006-07-28 | 2008-01-31 | Massachusetts Institute Of Technology | Removing camera shake from a single photograph |
| KR20100034500A (en) * | 2008-09-24 | 2010-04-01 | 한양대학교 산학협력단 | Structure inspection system using image deblurring technique and method of thereof |
| CN101996406A (en) * | 2010-11-03 | 2011-03-30 | 中国科学院光电技术研究所 | No-reference structure definition image quality evaluation method |
| US20130163882A1 (en) * | 2011-12-23 | 2013-06-27 | Leslie N. Smith | Method of estimating blur kernel from edge profiles in a blurry image |
| CN109124782A (en) * | 2018-08-29 | 2019-01-04 | 合肥工业大学 | Intelligent integral cavity mirror system |
| CN208407807U (en) * | 2018-04-18 | 2019-01-22 | 山东华力机电有限公司 | A kind of brush roll arrangement of mobile cleanser |
| CN109821596A (en) * | 2019-02-25 | 2019-05-31 | 吉林省三稻梁农业科技有限公司 | A kind of novel rice Rice processing system and control method |
| US20190324432A1 (en) * | 2017-08-02 | 2019-10-24 | Strong Force Iot Portfolio 2016, Llc | Data monitoring systems and methods to update input channel routing in response to an alarm state |
| CN111754498A (en) * | 2020-06-29 | 2020-10-09 | 河南科技大学 | Conveyor belt carrier roller detection method based on YOLOv3 |
| CN111951338A (en) * | 2019-05-17 | 2020-11-17 | 通用电气公司 | System and method for improved component inspection |
| CN112465776A (en) * | 2020-11-26 | 2021-03-09 | 常州信息职业技术学院 | Intelligent crack detection method based on fuzzy image on surface of wind turbine |
| WO2021052025A1 (en) * | 2019-04-26 | 2021-03-25 | 深圳市豪视智能科技有限公司 | Electric fan vibration fault detecting method and apparatus |
| CN113012064A (en) * | 2021-03-10 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Image processing method, device, equipment and storage medium |
| US20210201068A1 (en) * | 2019-12-30 | 2021-07-01 | Sensetime International Pte. Ltd. | Image processing method and apparatus, and electronic device |
| CN113213101A (en) * | 2021-05-06 | 2021-08-06 | 华润电力技术研究院有限公司 | Method and system for detecting abnormity of carrier roller |
| CN113405825A (en) * | 2021-06-11 | 2021-09-17 | 曲阜师范大学 | Belt conveyor fault diagnosis method based on sound signals |
| CN113753525A (en) * | 2021-10-19 | 2021-12-07 | 精基科技有限公司 | Fault protection system and fault elimination method of belt conveyor |
| CN113850808A (en) * | 2021-12-01 | 2021-12-28 | 武汉泰盛包装材料有限公司 | Multilayer corrugated paper arrangement defect detection method and device based on image processing |
| CN114418877A (en) * | 2022-01-12 | 2022-04-29 | 新乡学院 | Image non-blind deblurring method and system based on gradient amplitude similarity |
| CN114820607A (en) * | 2022-06-28 | 2022-07-29 | 南通佰瑞利电动工具有限公司 | Automatic control method, device and system for concrete vibrator |
-
2022
- 2022-08-01 CN CN202210913082.3A patent/CN114972349B/en active Active
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070258707A1 (en) * | 2006-05-08 | 2007-11-08 | Ramesh Raskar | Method and apparatus for deblurring images |
| US20080025627A1 (en) * | 2006-07-28 | 2008-01-31 | Massachusetts Institute Of Technology | Removing camera shake from a single photograph |
| KR20100034500A (en) * | 2008-09-24 | 2010-04-01 | 한양대학교 산학협력단 | Structure inspection system using image deblurring technique and method of thereof |
| CN101996406A (en) * | 2010-11-03 | 2011-03-30 | 中国科学院光电技术研究所 | No-reference structure definition image quality evaluation method |
| US20130163882A1 (en) * | 2011-12-23 | 2013-06-27 | Leslie N. Smith | Method of estimating blur kernel from edge profiles in a blurry image |
| US20190324432A1 (en) * | 2017-08-02 | 2019-10-24 | Strong Force Iot Portfolio 2016, Llc | Data monitoring systems and methods to update input channel routing in response to an alarm state |
| CN208407807U (en) * | 2018-04-18 | 2019-01-22 | 山东华力机电有限公司 | A kind of brush roll arrangement of mobile cleanser |
| CN109124782A (en) * | 2018-08-29 | 2019-01-04 | 合肥工业大学 | Intelligent integral cavity mirror system |
| CN109821596A (en) * | 2019-02-25 | 2019-05-31 | 吉林省三稻梁农业科技有限公司 | A kind of novel rice Rice processing system and control method |
| WO2021052025A1 (en) * | 2019-04-26 | 2021-03-25 | 深圳市豪视智能科技有限公司 | Electric fan vibration fault detecting method and apparatus |
| CN111951338A (en) * | 2019-05-17 | 2020-11-17 | 通用电气公司 | System and method for improved component inspection |
| US20210201068A1 (en) * | 2019-12-30 | 2021-07-01 | Sensetime International Pte. Ltd. | Image processing method and apparatus, and electronic device |
| CN111754498A (en) * | 2020-06-29 | 2020-10-09 | 河南科技大学 | Conveyor belt carrier roller detection method based on YOLOv3 |
| CN112465776A (en) * | 2020-11-26 | 2021-03-09 | 常州信息职业技术学院 | Intelligent crack detection method based on fuzzy image on surface of wind turbine |
| CN113012064A (en) * | 2021-03-10 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Image processing method, device, equipment and storage medium |
| CN113213101A (en) * | 2021-05-06 | 2021-08-06 | 华润电力技术研究院有限公司 | Method and system for detecting abnormity of carrier roller |
| CN113405825A (en) * | 2021-06-11 | 2021-09-17 | 曲阜师范大学 | Belt conveyor fault diagnosis method based on sound signals |
| CN113753525A (en) * | 2021-10-19 | 2021-12-07 | 精基科技有限公司 | Fault protection system and fault elimination method of belt conveyor |
| CN113850808A (en) * | 2021-12-01 | 2021-12-28 | 武汉泰盛包装材料有限公司 | Multilayer corrugated paper arrangement defect detection method and device based on image processing |
| CN114418877A (en) * | 2022-01-12 | 2022-04-29 | 新乡学院 | Image non-blind deblurring method and system based on gradient amplitude similarity |
| CN114820607A (en) * | 2022-06-28 | 2022-07-29 | 南通佰瑞利电动工具有限公司 | Automatic control method, device and system for concrete vibrator |
Non-Patent Citations (5)
| Title |
|---|
| DDS0003MDN: "数据相似度与异常检测", 《DOC88.COM/P-5843118333109.HTML》 * |
| M. M. MARU 等: "Influence of oil contamination on vibration and wear in ball and roller bearings", 《INDUSTRIAL LUBRICATION AND TRIBOLOGY》 * |
| 刘金根: "基于影像组学的脑部胶质瘤高低级别分类模型研究与实现", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
| 白亮 等: "基于时间序列相似度挖掘的水电机组振动故障诊断研究", 《水力发电学报》 * |
| 齐秀飞 等: "一种强迫激励下的弦线模型振动分析与求解", 《辽宁工程技术大学学报（自然科学版）》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117876363A (en) * | 2024-03-11 | 2024-04-12 | 宝鸡杭叉工程机械有限责任公司 | On-line detection method and system for carrier roller running state of belt conveyor |
| CN117876363B (en) * | 2024-03-11 | 2024-06-07 | 宝鸡杭叉工程机械有限责任公司 | On-line detection method and system for carrier roller running state of belt conveyor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114972349B (en) | 2022-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114529549B (en) | Cloth defect labeling method and system based on machine vision | |
| WO2021168733A1 (en) | Defect detection method and apparatus for defect image, and computer-readable storage medium | |
| CN115249246B (en) | Optical glass surface defect detection method | |
| CN114842027A (en) | Fabric defect segmentation method and system based on gray level co-occurrence matrix | |
| WO2022082904A1 (en) | Lens smudge detection method, apparatus and device | |
| CN115953398B (en) | Defect identification method for strip steel surface | |
| CN114972349B (en) | Carrier roller running state detection method and system based on image processing | |
| CN114187289B (en) | Plastic product shrinkage pit detection method and system based on computer vision | |
| CN115018765A (en) | Powder metallurgy part finished product detection method based on gray level gradient co-occurrence matrix | |
| CN114782329A (en) | Bearing defect damage degree evaluation method and system based on image processing | |
| CN115861310B (en) | Method for detecting textile defects on surface of bed sheet | |
| CN115100191A (en) | Metal casting defect identification method based on industrial detection | |
| CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| CN115619708A (en) | Method for judging fault based on image recognition of oil quality change of main shaft bearing lubricating oil | |
| CN115345821A (en) | Steel coil binding belt loosening abnormity detection and quantification method based on active visual imaging | |
| CN113469293B (en) | Panel array short circuit detection method and device, electronic equipment and storage medium | |
| CN113192061A (en) | LED package appearance detection image extraction method and device, electronic equipment and storage medium | |
| JP4346379B2 (en) | Defect inspection method | |
| CN114881952A (en) | Casting defect area detection and edge accurate segmentation method | |
| CN115861259A (en) | Lead frame surface defect detection method and device based on template matching | |
| CN114998354A (en) | Steel belt roll mark detection method based on graph filtering | |
| CN114882009A (en) | Fatigue crack tip automatic detection method and system capable of adapting to various surface states | |
| JPH08145907A (en) | Inspection equipment of defect | |
| JP4247993B2 (en) | Image inspection apparatus, image inspection method, control program, and readable storage medium | |
| JP4491922B2 (en) | Surface defect inspection method |
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 |