CN113066076A - Rubber tube leakage detection method, device, equipment and storage medium - Google Patents

Rubber tube leakage detection method, device, equipment and storage medium Download PDF

Info

Publication number
CN113066076A
CN113066076A CN202110391866.XA CN202110391866A CN113066076A CN 113066076 A CN113066076 A CN 113066076A CN 202110391866 A CN202110391866 A CN 202110391866A CN 113066076 A CN113066076 A CN 113066076A
Authority
CN
China
Prior art keywords
bubble
preset
calculating
image
rubber tube
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
Application number
CN202110391866.XA
Other languages
Chinese (zh)
Other versions
CN113066076B (en
Inventor
孟凡武
吴长烁
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Institute of Technology BIT
Original Assignee
Beijing Institute of Technology BIT
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Institute of Technology BIT filed Critical Beijing Institute of Technology BIT
Priority to CN202110391866.XA priority Critical patent/CN113066076B/en
Publication of CN113066076A publication Critical patent/CN113066076A/en
Application granted granted Critical
Publication of CN113066076B publication Critical patent/CN113066076B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M3/00—Investigating fluid-tightness of structures
    • G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
    • G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
    • G01M3/06—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point by observing bubbles in a liquid pool
    • G01M3/08—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point by observing bubbles in a liquid pool for pipes, cables or tubes; for pipe joints or seals; for valves; for welds
    • G01M3/083—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point by observing bubbles in a liquid pool for pipes, cables or tubes; for pipe joints or seals; for valves; for welds for tubes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Geometry (AREA)
  • Quality & Reliability (AREA)
  • Examining Or Testing Airtightness (AREA)

Abstract

The application provides a rubber tube leakage detection method, a rubber tube leakage detection device, rubber tube leakage detection equipment and a storage medium, and relates to the technical field of airtightness detection. The rubber tube leakage detection method comprises the following steps: acquiring a bubble image of the rubber tube to be detected; selecting an area with a preset size containing a leakage port from the bubble image according to the position of the leakage port on the rubber tube to be detected; according to the region of interest, calculating the contour size of a target connected domain which meets the preset roundness value condition in the bubble image, and calculating the volume of a single bubble; extracting bubble outlines of continuous multi-frame bubble images in preset unit time to obtain bubble generation amount in the preset unit time; the leak rate was calculated from the individual bubble volume and the amount of bubble generation. This application accessible adopts machine vision principle, handles the bubble image and obtains single bubble volume and predetermine the bubble production of unit time, then calculates and obtains revealing the rate, has solved present rubber tube and has revealed that the detection can't obtain revealing the particular case, and the objectivity is not strong, problem that efficiency is not high.

Description

Rubber tube leakage detection method, device, equipment and storage medium
Technical Field
The invention relates to the technical field of airtightness detection, in particular to a rubber tube leakage detection method, a rubber tube leakage detection device, rubber tube leakage detection equipment and a storage medium.
Background
The rubber tube is widely applied to the fields of automobiles, energy sources, fire fighting and the like, and as one of important modes for conveying, the rubber tube is widely applied to various scenes for conveying liquid gas, and the air tightness of the rubber tube is very important for the conveying efficiency of the rubber tube and is a very key ring in the whole conveying process.
In the detection of the air tightness of the rubber hose, the leakage condition of the rubber hose needs to be determined. The traditional container tightness detection methods include an ultrasonic detection method and an automatic water pressure external detection method, which have limitations and cannot obtain the specific leakage condition of the rubber tube. The immersion bubble detection method is an ideal choice, and the traditional immersion bubble detection method is carried out manually, so that the efficiency is not high, the objectivity is not high, and the error is large.
Therefore, the existing rubber tube leakage detection method has the problems that the specific leakage condition of the rubber tube cannot be obtained, and the efficiency, the objectivity and the error range cannot meet the requirements.
Disclosure of Invention
The present invention aims to provide a method, an apparatus, a device and a storage medium for detecting a rubber tube, so as to solve the problem of unsatisfactory rubber tube leakage detection effect.
In order to achieve the above purpose, the embodiment of the present invention adopts the following technical solutions:
in a first aspect, an embodiment of the present invention provides a method for detecting rubber tube leakage, including:
acquiring a bubble image of the rubber tube to be detected, wherein the bubble image is an image of the rubber tube to be detected placed in a transparent water tank and bubbles generated when the air pressure of gas injected into the rubber tube to be detected is preset;
according to the position of the leakage port on the rubber tube to be detected, selecting an interested area from the bubble image, wherein the interested area is as follows: a region of a predetermined size containing a leak;
according to the region of interest, calculating the outline size of a target connected domain which meets the preset roundness value condition in the bubble image, and calculating the volume of a single bubble according to the outline size of the target connected domain;
carrying out bubble outline extraction on continuous multiple frames of bubble images in preset unit time to obtain the bubble generation amount in the preset unit time;
and calculating the leakage rate of the preset unit time according to the volume of the single bubble and the generation amount of the bubble.
In one implementation, selecting a region of interest from the bubble image according to the position of the leakage opening on the rubber tube to be detected includes:
and according to the position of the leakage port, selecting the leakage port from the bubble image to be positioned at the lower edge of the region, wherein the region with the size of a preset size is the region of interest, and the lower edge of the region is the edge departing from the rising direction of the bubble.
In another implementation manner, calculating the contour size of a target connected domain satisfying a preset roundness value condition in the bubble image according to the region of interest includes:
carrying out edge detection on the region of interest to obtain an edge image in the region of interest;
calculating the outline size of each connected region in the region of interest according to the edge image of the region of interest;
calculating the circularity value of each connected domain according to the contour size of each connected domain;
and determining a target connected domain meeting the preset circularity value condition from the bubble image according to the circularity value of each connected domain in the region of interest, and calculating the outline size of the target connected domain.
In yet another implementation, the dimensions of each connected domain include: the perimeter and area of each connected domain; calculating the roundness value of each connected domain according to the contour size of each connected domain, wherein the roundness value comprises the following steps:
and calculating the circularity value of each connected domain according to the perimeter and the area of each connected domain.
In yet another implementation, calculating a contour dimension of a target connected component includes:
calculating the outline centroid of the target connected domain;
calculating the distance from a plurality of points on the contour of the target connected domain to the centroid of the contour;
correspondingly, calculating the volume of a single bubble according to the contour size of the target connected domain comprises the following steps:
calculating the radius of the bubble according to the average distance from the points to the centroid of the contour;
and calculating the volume of a single bubble according to the radius of the bubble and a preset scale factor, wherein the scale factor is the ratio of the size of the object in the image obtained by calibration in advance to the size of the actual object.
In another implementation manner, performing bubble contour extraction on consecutive multi-frame bubble images in a preset unit time to obtain a bubble generation amount in the preset unit time includes:
extracting bubble outlines of continuous multi-frame bubble images by adopting a preset frame difference method to obtain a plurality of frame difference images;
filling pixel values of all connected domains in the frame difference image into preset pixel values;
traversing pixel values of preset position points in the plurality of frame difference images according to a time sequence;
determining the number of bubbles in a preset unit time according to the number of jumping times of the pixel values at the preset positions in the traversed multiple frame difference images;
the bubble generation amount is calculated based on the number of bubbles and a preset unit time.
In yet another implementation, the method for detecting a rubber tube leakage further includes:
calculating expressions of the gas pressure and the leakage rate according to the leakage rate of the preset unit time under the first preset gas pressure and the leakage rate of the preset unit time under the second preset gas pressure, wherein the expressions are used for calculating the leakage rate under any gas pressure, and the first preset gas pressure and the second preset gas pressure are different gas pressures within a preset gas pressure range.
In a second aspect, an embodiment of the present application further provides a rubber tube leakage detection device, including:
the device comprises an acquisition module, a detection module and a control module, wherein the acquisition module is used for acquiring a bubble image of the rubber tube to be detected, the bubble image is an image of the rubber tube to be detected placed in a transparent water tank, and bubbles are generated when the air pressure of gas injected into the rubber tube to be detected is preset;
the selecting module is used for selecting an interested area from the bubble image according to the position of the leakage port on the rubber tube to be detected, wherein the interested area is as follows: a region of a predetermined size containing a leak;
the first calculation module is used for calculating the outline size of a target connected domain which meets the preset roundness value condition in the bubble image according to the region of interest and calculating the volume of a single bubble according to the outline size of the target connected domain;
the contour extraction module is used for carrying out bubble contour extraction on continuous multi-frame bubble images in preset unit time to obtain the bubble generation amount in the preset unit time;
and the second calculation module is used for calculating the leakage rate of the preset unit time according to the single bubble volume and the bubble generation amount.
In a third aspect, an embodiment of the present application further provides a computer device, including: the device comprises a memory and a processor, wherein the memory stores a computer program executable by the processor, and the processor implements any one of the rubber tube leakage detection methods provided by the first aspect when executing the computer program.
In a fourth aspect, an embodiment of the present application further provides a storage medium, where a computer program is stored on the storage medium, and when the computer program is read and executed, the method for detecting leakage of a rubber tube provided in the first aspect is implemented.
The beneficial effect of this application is:
according to the rubber tube leakage detection method, device, equipment and storage medium, the bubble image of the rubber tube to be detected can be obtained, wherein the bubble image is an image that the rubber tube to be detected is placed in a transparent water tank and bubbles are generated by injecting preset air pressure into the rubber tube to be detected; selecting an area with a preset size containing a leakage port from the bubble image according to the position of the leakage port on the rubber tube to be detected; according to the region of interest, calculating the contour size of a target connected domain which meets the preset roundness value condition in the bubble image, and calculating the volume of a single bubble; extracting bubble outlines of continuous multi-frame bubble images in preset unit time to obtain bubble generation amount in the preset unit time; the leak rate was calculated from the individual bubble volume and the amount of bubble generation. According to the method, the bubble image of the rubber tube to be detected is processed by adopting a machine vision principle to obtain the volume of a single bubble and the bubble generation amount in a preset unit time, and then the leakage rate is calculated, so that the detailed leakage condition of the rubber tube is obtained by automatically calculating the leakage rate based on the bubble image, manual detection is not needed, the detection efficiency of the leakage rate is improved, the leakage rate is calculated by the way of calculating the bubble image, the influence of artificial subjective factors is reduced as much as possible, the objectivity is higher, and the detection result is more accurate.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic structural diagram of an air tightness detecting device according to the present invention;
fig. 2 is a schematic flow chart of a rubber tube leakage detection method according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of another method for detecting a leak in a hose according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of another method for detecting a leakage of a hose according to an embodiment of the present disclosure;
fig. 5 is a schematic diagram of another rubber tube leakage detection method provided in the embodiment of the present application;
fig. 6 is a schematic view of a rubber tube leakage detection apparatus according to an embodiment of the present disclosure;
fig. 7 is a schematic diagram of a computer device provided in an embodiment of the present application.
Reference numerals:
11-a transparent water tank; 12-rubber tube; 13-a camera; 14-a light source; 15-visor.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention.
The embodiments of the present application relate to a gas tightness detection device, and for ease of understanding, the gas tightness detection device will be described first.
Fig. 1 is a schematic structural diagram of a rubber tube leakage detection device provided in an embodiment of the present application, and as shown in fig. 1, the air tightness detection device includes a transparent water tank 11, a rubber tube 12, a camera 13, a light source 14, and a light shielding plate 15. The rubber tube 12 is arranged in a transparent water tank 11 containing water, the camera 13 and the light source 14 are located on the same side face of the transparent water tank 11, the shading plate 15 is located on the other side face of the transparent water tank 11 opposite to the camera 13, the optical axis of the camera 13 is perpendicular to the direction of the rubber tube 12 to be tested, and the light source 14 can be arranged at the top of the camera 13 so as to polish a shooting area when the rubber tube 12 is shot by the camera 13 and ensure the definition of an image of the rubber tube 12 obtained through shooting.
The transparent water tank is made of transparent hard materials, can be made of glass materials and plastic materials, and is internally provided with a water body for displaying bubbles leaked by the rubber tube. The side of transparent basin is the planishing face for the water can not refract the reflection light in the transparent basin, avoids influencing the camera and gets for instance.
The rubber tube to be detected can be a rubber tube, and in actual production, the number of leakage openings of the rubber tube is small, so that a plurality of leakage openings can not exist on a small distance of the rubber tube, and the condition that the leakage rate cannot be detected due to too many leakage openings does not exist.
It should be noted that, in the transparent water tank 11, a preset calibration object is arranged at a position having the same distance as the distance between the rubber tube 12 and the camera 13, and the size of the preset calibration object in the image and the preset size of the preset calibration object, that is, the actual size of the preset calibration object, are obtained by calculating the image of the preset calibration object obtained by shooting by the camera 13, so as to obtain the ratio of the size of the object in the image to the size of the actual object. The preset calibration object may be, for example: a solid circle of known radius.
The method for detecting the leakage of the rubber hose provided by the present application is illustrated by the following examples.
Fig. 2 is a schematic flow chart of a method for detecting leakage of a rubber hose according to an embodiment of the present invention, and as shown in fig. 2, the method may include:
s201, acquiring a bubble image of the rubber tube to be detected, wherein the bubble image is an image of the rubber tube to be detected placed in a transparent water tank, and bubbles are generated when the air pressure of gas injected into the rubber tube to be detected is preset.
Optionally, before acquiring the bubble image, the angle of the camera is adjusted to make the optical axis of the camera perpendicular to the light shielding plate, and the bubble should record a video with a certain duration in the center of the field of view of the camera, and the video frame rate may be above 125fps to ensure that the bubble can be clearly imaged.
The rubber tube to be detected can be horizontally and transversely or vertically placed in the middle or the middle lower part of the transparent water tank, and the rubber tube to be detected is placed in the middle of the transparent water tank in the shooting direction of the camera, so that the camera can obtain a complete image.
In a possible implementation manner, after the rubber tube is placed in the clear water tank as shown in fig. 1, a gas with a preset air pressure can be input into the rubber tube through one end of the rubber tube, so that bubbles are generated at a leakage port of the rubber tube placed in the clear water tank. The air with preset air pressure can be generated by an air pump or other equipment with air delivery function, one end of the rubber tube is closed, and the other end of the rubber tube is connected with air delivery equipment such as an air pump. The air pressure of the gas output to the rubber tube is adjusted, so that bubbles generated by the rubber tube meet a preset bubble condition, if the bubbles meeting the preset condition can be single-cycle bubbles, the single-cycle bubbles can be a group of bubbles with the same size, and the leakage interval time of any two adjacent bubbles is the same. For example, a gas pressure meter may be provided on the gas delivery device, and the gas pressure meter may indicate the gas pressure output by the gas delivery device, i.e., the gas pressure of the gas in the hose.
Optionally, the preset air pressure may be any air pressure value in a preset air pressure set, and different air pressure values in the preset air pressure set are all air pressure values capable of enabling the rubber tube to generate a preset bubble condition. The different air pressure values in the preset air pressure set can be air pressure values which can enable the rubber tube to generate air pressure values meeting preset air bubble conditions under different air bubble leakage conditions. The different bubble leakage conditions may include, for example, the depth of the transparent water tank where the rubber tube is located, the material of the rubber tube, the structure of the rubber tube leakage port, the ambient temperature, and the gas movement state, which is not limited herein.
In a specific implementation process, a preset air pressure value can be set first, and the air pressure value is slowly adjusted, so that the adjusted air pressure value is one air pressure value in a preset air pressure set, and the rubber tube can generate bubbles meeting preset bubble conditions.
Under the condition that the bubbles generated by the rubber tube meet the preset bubble conditions, the bubble images can be acquired through the camera. In this case, the sizes of the bubbles in the acquired bubble images are similar, the leakage time interval of every two adjacent bubbles is the same, and the distances between every two corresponding adjacent bubbles are the same.
S202, selecting an interested area from the bubble image according to the position of a leakage port on the rubber tube to be detected, wherein the interested area is as follows: a region of a predetermined size containing a leak;
optionally, the region of interest selected from the bubble image may be a region including the leakage port manually selected, or may be a region including the leakage port automatically selected by locating the position of the leakage port.
In a possible implementation manner, after the position of the region of interest is manually selected, the preset size of the region of interest is manually set. The leakage area matched with the size of the leakage port can be calculated and selected based on the size of the leakage port detected by the bubble image after the position of the leakage port is positioned.
Alternatively, the region of interest may be rectangular, circular or other shape that includes a leak port, which may be located below or in the middle of the region of interest, as long as the leak port can be included and a complete bubble image can be obtained.
S203, calculating the outline size of a target connected domain meeting the preset roundness value condition in the bubble image according to the region of interest, and calculating the volume of a single bubble according to the outline size of the target connected domain;
optionally, the preset circularity value condition may be a circularity value range, and may be an upper limit value or a lower limit value. The target connected domain may be one connected domain or may be a plurality of connected domains.
In one implementation, the preset roundness value condition is that within a roundness value range, for example, the roundness value range is 0.8-1.2, and one or more target connected domains within the roundness value range are available, so that the contour sizes of the target connected domains with roundness values within the range are used as data bases for calculating the volume of a single bubble. Optionally, if there are a plurality of target connected domains within the roundness value range, the multiple profile sizes corresponding to the multiple target connected domains may be averaged to obtain an average profile size, so as to obtain a single bubble volume, or single bubble volumes corresponding to the multiple profile sizes may be respectively obtained, and the average value of the multiple bubble volumes is obtained as the single bubble volume.
In another implementation, the preset circularity value condition may be a circularity value sorting condition, an optimal circularity value is set as a sorting criterion, and one target connected domain or a plurality of target connected domains with circularity values closest to the optimal circularity value are selected. If a plurality of target connected domains are selected, a plurality of profile sizes corresponding to the plurality of target connected domains can be averaged to obtain an average profile size so as to obtain a single bubble volume, or single bubble volumes corresponding to the plurality of profile sizes can be respectively obtained, and the average value of the plurality of bubble volumes is obtained as the single bubble volume.
And calculating the volume of a single bubble according to the outline size of the target connected domain, wherein the outline size of the target connected domain in the bubble image needs to be calculated by combining with a scale factor to obtain the target outline size, the target outline size is the actual outline size of the bubble, and the volume of the single bubble is calculated according to the target outline size.
Optionally, the method for obtaining the scale factor may be that after the rubber tube leakage detection device is installed, the position of the camera is fixed, and in the transparent water tank, a preset calibration object with a known size is set at a position with the same distance as the distance between the rubber tube and the camera, and the preset calibration object may be, for example: the method comprises the steps of acquiring an image of a preset calibration object by shooting an entity circle with a known radius, finding an entity circle edge in the image through an edge detection algorithm, such as a canny operator, and performing circle fitting by using a least square method, wherein the specific fitting method comprises the following steps:
let the expression of the circle in the image be: (x-a)2+(x-b)2＝r2R is the radius of the circle in the image, let:
Figure BDA0003015716370000101
Figure BDA0003015716370000102
Figure BDA0003015716370000103
Figure BDA0003015716370000104
Figure BDA0003015716370000105
calculating to obtain:
Figure BDA0003015716370000111
in the formula, N is the total number of boundary points participating in fitting; i ranges from [0, N ], and X and Y are the abscissa and ordinate of each boundary point, respectively.
This yields the scaling factor α R/R, where R is the radius of the solid circle and R is the radius of the circle in the image.
And S204, extracting the bubble outline of the continuous multi-frame bubble image in the preset unit time to obtain the bubble generation amount in the preset unit time.
Optionally, the method for detecting the moving object in the video may be used to extract the bubble outline of the continuous multiple frames of bubble images in the preset unit time frame by frame, so as to obtain dynamic change information of the bubbles in the preset unit time, thereby obtaining the bubble generation amount in the preset unit time, and being used to mark the bubble generation rate in the preset unit time.
And S205, calculating the leakage rate of the preset unit time according to the volume of the single bubble and the generation amount of the bubble.
For example, the leak rate per unit time is calculated using equation (1) based on the volume of a single bubble and the amount of bubble generation.
V ═ V × s formula (1)
Where V is the leak rate, V is the volume of a single bubble, and s is the bubble generation amount.
In the method for detecting leakage of the rubber tube, the bubble image under the preset air pressure is obtained, the region of interest including the leakage port is selected from the image, the target connected region which accords with the circularity value is selected from the region of interest, the outline size of the target connected region is calculated to obtain the volume of a single bubble, the bubble outline is extracted from the multi-frame image in the preset unit time to obtain the amount of the bubble generated in the preset unit time, the leakage rate in the preset unit time is calculated according to the volume and the generation amount of the single bubble, and the problems that the specific leakage condition cannot be obtained in the current rubber tube leakage detection, the objectivity is low, and the efficiency is low are solved.
The selection of the region of interest is important to whether a clear and complete bubble image can be obtained, and on the basis that the region of interest includes a leak, a positional relationship between the region of interest and the leak still needs to be further set, so in some embodiments of the present application, the specific implementation of step S202 may further include:
and selecting an area with the leakage at the lower edge of the area and the size of the area as a preset size from the bubble image as an interested area according to the position of the leakage, wherein the lower edge of the area is an edge departing from the rising direction of the bubble.
Optionally, the leakage opening is located regional lower limb department, can hug closely the lower limb, can be apart from the lower limb 1 centimetre department, also can be other suitable distances of adjusting according to actual conditions, so set up and avoid the bubble rising speed too fast, lead to the bubble too short and make the camera can't get for the picture to the bubble clearly in the dwell time of the region of interest, can guarantee to obtain clear complete bubble image.
On the basis of the rubber tube leakage detection method in any one of the embodiments, the embodiment of the application further provides an implementation manner for calculating the contour dimension in the rubber tube leakage detection method. Fig. 3 is a schematic flow chart illustrating a process of calculating a contour dimension of a connected domain in a method for detecting a rubber tube leakage according to another embodiment of the present disclosure, as shown in fig. 3, in some embodiments of the present disclosure, step S203 may include:
s301, carrying out edge detection on the region of interest to obtain an edge image in the region of interest.
Before edge detection, gray level processing is carried out, and then binarization processing is carried out on the image after gray level processing.
Optionally, before the edge detection, the image is subjected to gray processing to make the edge detection result clear, and in actual operation, if the image quality is poor, the image quality can be processed before the gray processing to make the gray image obtained after the gray processing clear. The specific gray scale processing method may be to frame the captured video, set R, G, B three components of each pixel in each frame image to be the same, and convert the image into a gray scale image. Further, the gray level image is subjected to binarization processing, and the gray level image is converted into a binarization image with only two pixel values of 0 and 255.
For example, the following formula (2) can be used to perform binarization processing on a grayscale image:
Figure BDA0003015716370000131
t is a preset pixel threshold value, val is a pixel value, the size of the preset pixel threshold value T needs to be adjusted according to the condition of an image obtained by shooting under specific light due to the intensity of a light source and other factors influencing the image capturing brightness of the camera, a plurality of binary images with different image display effects can be obtained in the process of adjusting the preset pixel threshold value T, and therefore the threshold value corresponding to the binary image with the clearest effect can be directly selected.
Optionally, the edge detection may use a Canny edge detection algorithm, a first-order edge detection operator, or a Sobel edge detection operator to obtain a bubble edge image of the region of interest in the preprocessed image, where a pixel value of an object edge in the edge image is 255, and a pixel value of a non-edge region is 0, that is, a black-and-white image, and if two pixel points with pixel values of 255 in the edge image are adjacent, the two pixel points form a connected domain, and a set of the connected domains may form the edge image.
S302, calculating the outline size of each connected domain in the region of interest according to the edge image of the region of interest.
The size of the outline of each connected domain may characterize the size of one bubble in the bubble image.
And S303, calculating the circularity value of each connected domain according to the contour size of each connected domain.
Optionally, the outline dimension of the connected component includes parameters describing the size and shape of the connected component, which may be diameter, radius, area, and the circularity value is calculated by the parameters.
S304, according to the circularity values of all connected domains in the region of interest, determining a target connected domain meeting the preset circularity value condition from the bubble image, and calculating the outline size of the target connected domain.
In this instance, the preset roundness value condition is satisfied, and for example, a roundness value in which a deviation of the roundness value from 1 is within a preset range, for example, 0.8 or 0.9 may be satisfied. In the case where the target connected component is determined, the contour size of the target connected component may be taken as the contour size for calculating the volume of a single bubble. The target connected domain meeting the preset roundness value condition is actually a connected domain corresponding to the approximately spherical bubble in the image.
The method comprises the steps of obtaining an edge image through edge detection, calculating the outline size of a connected domain in the edge image, judging the roundness value of each connected domain according to the outline size, selecting the outline size meeting the roundness value condition, selecting the connected domain meeting the roundness value condition, obtaining a representative target connected domain, and screening bubbles close to a sphere.
In some embodiments of the present application, the specific implementation of step S303 may further include: the contour dimension of each connected domain comprises the perimeter and the area of each connected domain; and (4) calculating the circularity value of each connected domain according to the perimeter and the area of each connected domain by adopting the following formula (3).
Figure BDA0003015716370000141
Wherein L is the perimeter of each connected domain, S is the area of each connected domain, and p is the circularity value of each connected domain.
The circumference and the area of each connected domain are adopted, the roundness value of each connected domain is calculated more accurately, the target connected domain obtained by screening based on the roundness value condition is more reliable, and the reliability and the accuracy of rubber tube leakage detection are effectively guaranteed.
Fig. 4 is a schematic flow chart of a method for detecting a rubber tube leakage according to another embodiment of the present application, as shown in fig. 4, in some embodiments of the present application, the step S304 may further include:
s401, calculating the outline centroid of the target connected domain.
In a possible implementation, the contour centroid of the target connected domain may be calculated, for example, using equation (4):
Figure BDA0003015716370000151
wherein the content of the first and second substances,
Figure BDA0003015716370000152
is the abscissa of the centroid of the profile,
Figure BDA0003015716370000153
and X and Y are respectively the abscissa and the ordinate of a point on the contour of the target connected domain, and Q is the area of the region surrounded by the contour.
S402, calculating the distance from a plurality of points on the contour of the target connected domain to the centroid of the contour.
Optionally, distances from all points on the contour to the contour centroid may be calculated, or distances from a plurality of points to the contour centroid may be selected, and a more selected point may obtain a more accurate calculation result. The selected points are uniformly dispersed on the outline, so that the selected points are prevented from being too flat.
Optionally, the same number of points are selected in multiple opposite directions of the contour for calculation, and an included angle between two adjacent directions may be 90 degrees, that is, four-direction points are selected, and may be 60 degrees, that is, 6-direction points are selected. For example, the distance from a plurality of points on the contour of the target connected component to the centroid of the contour can be calculated using the following formula (5).
Figure BDA0003015716370000154
Wherein d isijDistance of a point on the contour to the centroid of the contour, pijIs a point on the contour, x is pijOn the abscissa, y is pijThe ordinate of (c).
And S403, calculating the radius of the bubble according to the average distance from the points to the centroid of the contour.
And (4) calculating the average distance from the distances from the points to the centroid of the contour, wherein the average distance is the radius of the bubble, and calculating the radius of the bubble by adopting a formula (6).
Figure BDA0003015716370000161
Figure BDA0003015716370000162
K is the number of points on the contour of the target connected component, which is the bubble radius.
S404, calculating the volume of a single bubble according to the radius of the bubble and a preset scale factor, wherein the scale factor is the ratio of the size of an object in the image obtained by calibration in advance to the size of an actual object.
And (3) calculating the volume of a single bubble by adopting the following formula (7) according to the radius of the bubble and a preset scale factor.
Figure BDA0003015716370000163
Where v is the individual bubble volume and α is a preset scaling factor.
The method comprises the steps of calculating the outline centroid of a representative target connected domain, obtaining the average distance from a plurality of points on the outline to the centroid, obtaining the target connected domain which meets the roundness value condition, calculating the radius of the bubbles based on the outline size of the target connected domain, and obtaining the volume of a single bubble by combining with a preset scale factor, so that the volume of the single bubble obtained by calculation is closer to the real size of the bubble.
After the bubble image is obtained, whether the extracted bubble outline is clear or not determines whether more accurate data can be obtained or not for calculation, and if the obtained bubble outline is fuzzy, accurate counting of bubbles is not facilitated. Fig. 5 is a schematic flow chart of a method for detecting a rubber tube leakage according to another embodiment of the present application, and as shown in fig. 5, in some embodiments of the present application, the step S104 may further include: S501-S505.
S501, extracting bubble outlines of continuous multi-frame bubble images by adopting a preset frame difference method to obtain a plurality of frame difference images;
optionally, a frame difference method is used to extract the bubble profile in the rise, and a three-frame difference method, an adjacent frame difference method or other algorithms can be used. For example, a three-frame difference method is used to extract the motion bubble contour of the original image sequence, the previous two frames of images are subjected to gray level difference, and the current frame of image and the previous frame of image are subjected to gray level difference, and the specific formula (8) is as follows:
Figure BDA0003015716370000171
DiffImg1 is gray scale difference result 1, DiffImg2 is gray scale difference result 2, DiffImg1 and DiffImg2 are and-operated to obtain final frame difference image DiffImg, and if n images are obtained within a preset unit time, n-2 frame difference images can be finally obtained. Where curr denotes a bubble image of the current frame, prev1 denotes a bubble image of the previous frame before the current frame, and prev2 denotes a bubble image of the previous two frames before the current frame. T 'is a suitable threshold, and needs to be valued and adjusted for specific frame difference effects, and the difference in specific frame difference effects causes corresponding change in T'.
And S502, filling the pixel values of all connected domains in the frame difference image into preset pixel values.
For convenience of counting, different pixel values of each connected component are set to be uniform pixel values, in this embodiment, the pixel value in the connected component is set to be 255, that is, white, in this embodiment, the preset pixel value may also be other pixel values, and is not limited herein.
S503, traversing the pixel values of the preset position points in the frame difference images according to the time sequence;
optionally, the preset position points can be set at will in the image, and according to the time sequence, the set of the preset position points in the plurality of frame difference images is a transverse line along the time sequence, so that each bubble can pass through the transverse line in the ascending process, the omission of the calculated bubbles is avoided, and the accuracy of the number of the calculated bubbles in the preset unit time is ensured.
S504, determining the number of bubbles in a preset unit time according to the jumping times of the pixel values at the preset positions in the traversed frame difference images.
In the image obtained by the frame difference method, only the moving object can be captured to the contour, the captured contour pixel value is 255, and the pixel value of each connected domain is filled to the preset pixel value of 255, so that only the pixel value of each bubble in the processed image is 255, and since the preset position does not have the moving object, the pixel value of the preset position is always 0 when the bubble does not pass through, and in the process that the bubble passes through the preset position, the pixel value of the preset position can be from 0 to 255 to 0, so that the pixel value of the preset position is considered to have finished one jump, and the bubble number is added by 1. Therefore, the number of bubbles can be obtained by calculating the jumping times of the preset position pixel value, all the n-2 images are traversed to obtain the counter value count, and S505, the bubble generation amount in unit time is calculated according to the number of bubbles and the preset unit time.
The amount of bubble generation per unit time was calculated using the following formula (9):
s is the count/t equation (9)
Wherein s is the amount of generated bubbles, count is the number of bubbles, and t is the preset unit time.
The frame difference method can accurately capture the outline of the bubbles in motion, the three-frame difference method can better detect the target with higher motion speed, the obtained object edge is more accurate, more targets exist in a bonding cavity, the pixel value of each target connected domain in the obtained frame difference image is filled to 255, the motion of the bubbles is represented through jumping by setting a preset position, the number of the bubbles can be accurately counted in the rising process of the bubbles only by observing the jumping of the pixel value of the preset position, the counting of the bubbles is convenient, and the accuracy is ensured.
In some embodiments of the present application, the method of detecting hose leakage may further comprise:
calculating an expression of the gas pressure and the leakage rate according to the leakage rate of the preset unit time under the first preset gas pressure and the leakage rate of the preset unit time under the second preset gas pressure, wherein the expression is used for calculating the leakage rate under any gas pressure, and the first preset gas pressure and the second preset gas pressure are different gas pressures within a preset gas pressure range.
Optionally, first atmospheric pressure of predetermineeing and the atmospheric pressure is all in certain atmospheric pressure scope is predetermine to the second, if the atmospheric pressure in the rubber tube is too big, then just can only produce not of uniform size, reveals the chaotic bubble of time confusion, then can't accurately obtain in the certain time, the gas leakage volume under certain atmospheric pressure. The first preset air pressure is the air pressure for measuring the leakage rate of the bubbles under a certain specific air pressure for the first time, and the second preset air pressure is the air pressure for measuring the leakage rate of the bubbles under another specific air pressure for the second time.
Leakage rate V at first predetermined air pressure1The bubble generation amount s in unit time is multiplied by the bubble volume v under the first preset air pressure, and the specific formula (10) is as follows:
V1v s formula (10)
A general expression of the leak rate V and the gas pressure P, and a specific formula (11) is:
V＝CPnformula (11)
Where C and n are unknown parameters related to leak diameter, water pressure, ambient temperature, and gas motion status.
And changing the gas pressure to a second preset gas pressure to ensure that the bubble leakage state is still in single-cycle leakage, and recording the pressure at the moment. Repeating the steps S201-S205 to obtain the leakage rate V2. Simultaneous:
Figure BDA0003015716370000191
obtaining:
Figure BDA0003015716370000201
Figure BDA0003015716370000202
thus, an expression of the leak rate V with respect to the gas pressure P is obtained. Therefore, the leakage rate under any pressure in a certain pressure range can be obtained.
By calculating the leakage rate under two different preset pressures, a general expression of the leakage rate V and the gas pressure P can be obtained, and the accurate corresponding relation between the leakage rate V and the gas pressure P is obtained, so that under the condition that parameters of the expression are known, a specific test step can be omitted, and the values of other gas pressures P are input into the expression, so that the corresponding leakage rate under other gas pressures can be obtained.
The following describes a device, equipment, and a storage medium for executing the method for detecting rubber tube leakage provided by the present application, and specific implementation processes and technical effects thereof are referred to above, and will not be described again below.
Fig. 6 is a schematic diagram of a rubber tube leakage detecting device according to an embodiment of the present application, and as shown in fig. 6, the rubber tube leakage detecting device 6 may include:
the acquiring module 601 is configured to acquire a bubble image of the rubber tube to be detected, where the bubble image is an image of a rubber tube to be detected placed in a transparent water tank and bubbles are generated when the air pressure of gas injected into the rubber tube to be detected is preset;
a selecting module 602, configured to select an interested region from the bubble image according to the position of the leak on the rubber tube to be detected, where the interested region is: a region of a predetermined size containing a leak;
a first calculating module 603, configured to calculate, according to the region of interest, a contour size of a target connected domain that meets a preset circularity value condition in the bubble image, and calculate a volume of a single bubble according to the contour size of the target connected domain;
the contour extraction module 604 is configured to perform bubble contour extraction on consecutive multiple frames of bubble images within a preset unit time to obtain a bubble generation amount of the preset unit time;
a second calculating module 605, configured to calculate the leak rate of the preset unit time according to the volume of the single bubble and the bubble generation amount.
Optionally, the selecting module 602 is specifically configured to: and selecting the lower edge of the area of the leakage from the bubble image according to the position of the leakage, wherein the area with the size of the preset size is the region of interest, and the lower edge of the area is the edge deviating from the rising direction of the bubble.
Optionally, the first calculating module 603 is specifically configured to: performing edge detection on the region of interest to obtain an edge image in the region of interest; calculating the outline size of each connected region in the region of interest according to the edge image of the region of interest; calculating the circularity value of each connected domain according to the contour size of each connected domain; and determining a target connected domain meeting the preset roundness value condition from the bubble image according to the roundness value of each connected domain in the region of interest, and calculating the contour size of the target connected domain.
Optionally, the contour dimension of each connected domain includes: the perimeter and area of each connected domain; the first calculating module 603 is specifically configured to: and calculating the circularity value of each connected domain according to the perimeter and the area of each connected domain.
Optionally, the first calculating module 603 is specifically configured to: calculating the outline centroid of the target connected domain; calculating the distance from a plurality of points on the contour of the target connected domain to the centroid of the contour; calculating the radius of the bubble according to the average distance from the plurality of points to the centroid of the contour; and calculating the volume of the single bubble according to the radius of the bubble and a preset scale factor, wherein the scale factor is the ratio of the size of an object in the image obtained by calibration in advance to the size of an actual object.
Optionally, the second calculating module 605 is specifically configured to perform bubble contour extraction on the continuous multiple frames of bubble images by using a preset frame difference method to obtain multiple frame difference images; filling the pixel values of all connected domains in the frame difference image into preset pixel values; traversing pixel values of preset position points in the plurality of frame difference images according to a time sequence; determining the number of bubbles in the preset unit time according to the number of jumping times of the pixel values of the preset positions in the traversed frame difference images; and calculating the bubble generation amount according to the number of the bubbles and the preset unit time.
Optionally, the rubber tube leakage detection device 6 further includes:
a third calculating module 606, configured to calculate an expression of the gas pressure and the leakage rate according to the leakage rate of the preset unit time under the first preset gas pressure and the leakage rate of the preset unit time under the second preset gas pressure, where the expression is used to calculate the leakage rate under any gas pressure, and the first preset gas pressure and the second preset gas pressure are different gas pressures within a preset gas pressure range.
The above-mentioned apparatus is used for executing the method provided by the foregoing embodiment, and the implementation principle and technical effect are similar, which are not described herein again.
These above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when one of the above modules is implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, the modules may be integrated together and implemented in the form of a System-on-a-chip (SOC).
Fig. 7 is a schematic diagram of a computer device provided in an embodiment of the present application. The computer device 7 includes: memory 701, processor 702. The memory 701 and the processor 702 are connected by a bus 703.
The memory 701 is used for storing programs, and the processor 702 calls the programs stored in the memory 701 to execute the above method embodiments. The specific implementation and technical effects are similar, and are not described herein again.
Optionally, the invention also provides a program product, for example a computer-readable storage medium, comprising a program which, when being executed by a processor, is adapted to carry out the above-mentioned method embodiments.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (10)

1. A rubber tube leakage detection method is characterized by comprising the following steps:
acquiring a bubble image of the rubber tube to be detected, wherein the bubble image is an image of the rubber tube to be detected placed in a transparent water tank and bubbles generated when the air pressure of gas injected into the rubber tube to be detected is preset;
according to the position of the leakage port on the rubber tube to be detected, selecting an interested area from the bubble image, wherein the interested area is as follows: a region of a predetermined size containing a leak;
according to the region of interest, calculating the outline size of a target connected domain which meets the preset roundness value condition in the bubble image, and calculating the volume of a single bubble according to the outline size of the target connected domain;
carrying out bubble outline extraction on continuous multiple frames of bubble images in preset unit time to obtain the bubble generation amount in the preset unit time;
and calculating the leakage rate of the preset unit time according to the volume of the single bubble and the generation amount of the bubble.
2. The method according to claim 1, wherein the selecting a region of interest from the bubble image according to the position of the leakage opening on the rubber hose to be detected comprises:
and selecting the lower edge of the area of the leakage from the bubble image according to the position of the leakage, wherein the area with the size of the preset size is the region of interest, and the lower edge of the area is the edge deviating from the rising direction of the bubble.
3. The method according to claim 1, wherein the calculating, according to the region of interest, the contour size of the target connected component in the bubble image that meets the preset roundness value condition includes:
performing edge detection on the region of interest to obtain an edge image in the region of interest;
calculating the outline size of each connected region in the region of interest according to the edge image of the region of interest;
calculating the circularity value of each connected domain according to the contour size of each connected domain;
and determining a target connected domain meeting the preset roundness value condition from the bubble image according to the roundness value of each connected domain in the region of interest, and calculating the contour size of the target connected domain.
4. The method of claim 3, wherein the outline dimensions of each connected domain comprise: the perimeter and area of each connected domain; the calculating the roundness value of each connected domain according to the contour size of each connected domain comprises:
and calculating the circularity value of each connected domain according to the perimeter and the area of each connected domain.
5. The method of claim 3, wherein the calculating the contour dimension of the target connected component comprises:
calculating the outline centroid of the target connected domain;
calculating the distance from a plurality of points on the contour of the target connected domain to the centroid of the contour;
correspondingly, the calculating the volume of the single bubble according to the contour size of the target connected domain comprises:
calculating the radius of the bubble according to the average distance from the plurality of points to the centroid of the contour;
and calculating the volume of the single bubble according to the radius of the bubble and a preset scale factor, wherein the scale factor is the ratio of the size of an object in the image obtained by calibration in advance to the size of an actual object.
6. The method according to claim 1, wherein the performing bubble contour extraction on consecutive frames of the bubble image in a preset unit time to obtain the bubble generation amount in the preset unit time comprises:
extracting bubble outlines of continuous multiple frames of bubble images by adopting a preset frame difference method to obtain multiple frame difference images;
filling the pixel values of all connected domains in the frame difference image into preset pixel values;
traversing pixel values of preset position points in the plurality of frame difference images according to a time sequence;
determining the number of bubbles in the preset unit time according to the number of jumping times of the pixel values of the preset positions in the traversed frame difference images;
and calculating the bubble generation amount according to the number of the bubbles and the preset unit time.
7. The method according to any one of claims 1-6, further comprising:
calculating expressions of gas pressure and leakage rate according to the leakage rate of the preset unit time under the first preset gas pressure and the leakage rate of the preset unit time under the second preset gas pressure, wherein the expressions are used for calculating the leakage rate under any gas pressure, and the first preset gas pressure and the second preset gas pressure are different gas pressures within a preset gas pressure range.
8. The utility model provides a detection device is revealed to rubber tube which characterized in that includes:
the device comprises an acquisition module, a detection module and a control module, wherein the acquisition module is used for acquiring a bubble image of the rubber tube to be detected, the bubble image is an image of the rubber tube to be detected placed in a transparent water tank, and bubbles are generated when the air pressure of gas injected into the rubber tube to be detected is preset;
the selecting module is used for selecting an interested area from the bubble image according to the position of the leakage port on the rubber tube to be detected, wherein the interested area is as follows: a region of a predetermined size containing a leak;
the first calculation module is used for calculating the outline size of a target connected domain which meets the preset roundness value condition in the bubble image according to the region of interest and calculating the volume of a single bubble according to the outline size of the target connected domain;
the contour extraction module is used for carrying out bubble contour extraction on continuous multi-frame bubble images in preset unit time to obtain the bubble generation amount in the preset unit time;
and the second calculation module is used for calculating the leakage rate of the preset unit time according to the single bubble volume and the bubble generation amount.
9. A computer device, comprising: a memory storing a computer program executable by the processor, and a processor implementing the method of any one of claims 1 to 7 when the computer program is executed by the processor.
10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when being read and executed, the computer program implements the method for detecting hose leakage according to any one of claims 1 to 7.
CN202110391866.XA 2021-04-12 2021-04-12 Rubber tube leakage detection method, device, equipment and storage medium Active CN113066076B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110391866.XA CN113066076B (en) 2021-04-12 2021-04-12 Rubber tube leakage detection method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110391866.XA CN113066076B (en) 2021-04-12 2021-04-12 Rubber tube leakage detection method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN113066076A true CN113066076A (en) 2021-07-02
CN113066076B CN113066076B (en) 2022-08-26

Family

ID=76566486

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110391866.XA Active CN113066076B (en) 2021-04-12 2021-04-12 Rubber tube leakage detection method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113066076B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113628213A (en) * 2021-10-12 2021-11-09 深圳市帝迈生物技术有限公司 Sample analyzer, method for detecting liquid path thereof, and computer-readable storage medium
CN113947109A (en) * 2021-10-15 2022-01-18 大连海事大学 Vision-based ship system equipment leakage state monitoring method and system and storage medium
CN114992813A (en) * 2022-06-17 2022-09-02 珠海格力电器股份有限公司 Method and device for detecting substance leakage, air conditioning equipment and storage medium
CN115009579A (en) * 2022-05-25 2022-09-06 东莞市华美食品有限公司 Food safety intelligent detection system

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012136209A1 (en) * 2011-04-07 2012-10-11 Dantaet A/S A method and means for detecting leakages in pipe installations
CN104535275A (en) * 2014-12-11 2015-04-22 天津大学 Underwater gas leakage amount detection method and device based on bubble acoustics
CN105389814A (en) * 2015-11-03 2016-03-09 浙江工业大学 Air bubble detection method for air tightness test
JP2019174455A (en) * 2018-03-27 2019-10-10 株式会社コムウェーブ Automatic leaked air bubble detection system and automatic leaked air bubble detection method
CN110487493A (en) * 2019-08-27 2019-11-22 浙江工业大学 A kind of multizone leakage detection method for pressure vessel air tightness test
CN111060257A (en) * 2019-12-26 2020-04-24 中国能源建设集团华东电力试验研究院有限公司 Air tightness experiment testing device and testing method thereof
CN111680459A (en) * 2020-06-11 2020-09-18 中国石化销售股份有限公司华南分公司 Pipeline leakage analysis method and device and computer readable storage medium
CN112308828A (en) * 2020-10-26 2021-02-02 王坚 Artificial intelligence detection method and detection system for air tightness of sealing equipment
CN112414623A (en) * 2020-11-04 2021-02-26 周婷婷 Method and system for detecting part air tightness leakage defect based on artificial intelligence
CN112465895A (en) * 2020-11-27 2021-03-09 河南耀蓝智能科技有限公司 Bubble volume calculation method in air tightness detection based on computer vision

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012136209A1 (en) * 2011-04-07 2012-10-11 Dantaet A/S A method and means for detecting leakages in pipe installations
CN104535275A (en) * 2014-12-11 2015-04-22 天津大学 Underwater gas leakage amount detection method and device based on bubble acoustics
CN105389814A (en) * 2015-11-03 2016-03-09 浙江工业大学 Air bubble detection method for air tightness test
JP2019174455A (en) * 2018-03-27 2019-10-10 株式会社コムウェーブ Automatic leaked air bubble detection system and automatic leaked air bubble detection method
CN110487493A (en) * 2019-08-27 2019-11-22 浙江工业大学 A kind of multizone leakage detection method for pressure vessel air tightness test
CN111060257A (en) * 2019-12-26 2020-04-24 中国能源建设集团华东电力试验研究院有限公司 Air tightness experiment testing device and testing method thereof
CN111680459A (en) * 2020-06-11 2020-09-18 中国石化销售股份有限公司华南分公司 Pipeline leakage analysis method and device and computer readable storage medium
CN112308828A (en) * 2020-10-26 2021-02-02 王坚 Artificial intelligence detection method and detection system for air tightness of sealing equipment
CN112414623A (en) * 2020-11-04 2021-02-26 周婷婷 Method and system for detecting part air tightness leakage defect based on artificial intelligence
CN112465895A (en) * 2020-11-27 2021-03-09 河南耀蓝智能科技有限公司 Bubble volume calculation method in air tightness detection based on computer vision

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
A.O.MAKSIMOV等: "Sounds of marine seeps：A study of bubble activity near a rigid boundary", 《THE JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA》 *
FANWU MENG等: "Design of a Fast Measuring System for the Section Size of Automobile Rubber Hose Withhold Parts", 《IOP CONFERENCE SERIES: MATERIALS SCIENCE AND ENGINEERING》 *
FANWU MENG等: "Rubber hose surface defect detection system based on machine vision", 《IOP CONFERENCE SERIES: EARTH AND ENVIRONMENTAL SCIENCE》 *
张志刚等: "利用多波束水体成像数据进行管道气体泄漏检测", 《应用科技》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113628213A (en) * 2021-10-12 2021-11-09 深圳市帝迈生物技术有限公司 Sample analyzer, method for detecting liquid path thereof, and computer-readable storage medium
CN113947109A (en) * 2021-10-15 2022-01-18 大连海事大学 Vision-based ship system equipment leakage state monitoring method and system and storage medium
CN113947109B (en) * 2021-10-15 2024-05-07 大连海事大学 Ship system equipment leakage state monitoring method, system and storage medium based on vision
CN115009579A (en) * 2022-05-25 2022-09-06 东莞市华美食品有限公司 Food safety intelligent detection system
CN114992813A (en) * 2022-06-17 2022-09-02 珠海格力电器股份有限公司 Method and device for detecting substance leakage, air conditioning equipment and storage medium

Also Published As

Publication number Publication date
CN113066076B (en) 2022-08-26

Similar Documents

Publication Publication Date Title
CN113066076B (en) Rubber tube leakage detection method, device, equipment and storage medium
CN104173054B (en) Measuring method and measuring device for height of human body based on binocular vision technique
EP3446065A1 (en) Flight parameter measuring apparatus and flight parameter measuring method
CN101806700B (en) Method and system for measuring soil infiltration capability
Watamura et al. LCD-projector-based 3D color PTV
CN113256611B (en) RGB-D registration precision testing method and device
CN108592948A (en) A kind of pipe bubble offset method for automatic measurement
US20170048518A1 (en) Method and apparatus for adjusting installation flatness of lens in real time
CN116721391A (en) Method for detecting separation effect of raw oil based on computer vision
CN110260945B (en) Total reflection type gas-liquid interface flow display method and gas-liquid interface position identification method
Samann Real-time liquid level and color detection system using image processing
CN108844959B (en) Method for measuring and correcting gas-liquid two-phase annular flow section phase content in circular tube
CN113749646A (en) Monocular vision-based human body height measuring method and device and electronic equipment
CN106056612A (en) Blood layered identification method
CN112184710A (en) Line scanning laser bubble detection method and system based on visual perception
Utomo et al. Early warning flood detector adopting camera by Sobel Canny edge detection algorithm method
CN111445510A (en) Method for detecting straight line in image
CN114193647B (en) Rubber plasticator control method and device based on image processing
CN114093018B (en) Vision screening equipment and system based on pupil positioning
CN113723380B (en) Face recognition method, device, equipment and storage medium based on radar technology
CN113554688B (en) O-shaped sealing ring size measurement method based on monocular vision
CN111368596A (en) Face recognition backlight compensation method and device, readable storage medium and equipment
Prasser et al. Probabilistic visual recognition of artificial landmarks for simultaneous localization and mapping
CN114663681A (en) Method for reading pointer type meter and related product
CN112911164A (en) Exposure time adjusting method and system for camera for air tightness test

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