CN113203359A - Fog column automatic check out system based on machine vision - Google Patents
Fog column automatic check out system based on machine vision Download PDFInfo
- Publication number
- CN113203359A CN113203359A CN202110308263.9A CN202110308263A CN113203359A CN 113203359 A CN113203359 A CN 113203359A CN 202110308263 A CN202110308263 A CN 202110308263A CN 113203359 A CN113203359 A CN 113203359A
- Authority
- CN
- China
- Prior art keywords
- fog column
- fog
- image
- column
- module
- 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
- 238000001514 detection method Methods 0.000 claims abstract description 78
- 238000012545 processing Methods 0.000 claims abstract description 53
- 238000007405 data analysis Methods 0.000 claims abstract description 18
- 238000000034 method Methods 0.000 claims description 26
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 21
- 238000003708 edge detection Methods 0.000 claims description 12
- 239000004744 fabric Substances 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 10
- 239000013589 supplement Substances 0.000 claims description 9
- 239000007921 spray Substances 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 4
- 229910000838 Al alloy Inorganic materials 0.000 claims description 3
- 238000000889 atomisation Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 15
- 238000005507 spraying Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 239000003595 mist Substances 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004040 coloring Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/028—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by measuring lateral position of a boundary of the object
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/28—Measuring arrangements characterised by the use of optical techniques for measuring areas
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G06T5/70—
-
- G06T5/80—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- 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
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention discloses a fog column automatic detection system based on machine vision, which comprises a camera calibration module for calibrating each image acquisition device in a fog column image acquisition module, a fog column image acquisition module for acquiring an image of a fog column sprayed by a nozzle, a fog column image processing module for carrying out image processing on the fog column image acquired by the fog column image acquisition module, a detection data analysis module for acquiring the coverage area and the maximum width of the fog column according to the information acquired by the fog column image processing module, and a detection result display module for displaying the relevant result acquired by the detection data analysis module, wherein the detection data analysis module specifically acquires the boundary line of the outer contour of the fog column through a polynomial fitting algorithm and then acquires the coverage area and the maximum width of the fog column. The system of the invention can complete automatic measurement of the fog column, solves the problem of high randomness of manual measurement, and has the advantages of high detection precision, good objectivity, high efficiency, simple operation and wide application prospect.
Description
Technical Field
The invention belongs to the technical field of fog column image processing, relates to an automatic fog column detection system based on machine vision, and particularly relates to an automatic fog column detection system capable of automatically acquiring the coverage area and the maximum width of a spray nozzle for spraying a fog column.
Background
In actual production, there are many processes that require high-pressure spraying to spray mist on the surface of a workpiece, such as spraying and coloring of a vehicle body panel, cleaning of the surface of the workpiece, cooling of a steel mill, and the like, wherein the geometrical shape of the mist has a crucial influence on the performance of the workpiece. However, on an automatic assembly line, the fog column cannot be measured and detected manually. Take the spraying of automobile body panel to color as the example, if use the manual work, then need a large amount of time to go the inspection, cost a large amount of manpower and materials to the testing result has the randomness height, characteristics that the reliability is low. In addition, after the fog column is sprayed by the high-pressure spray head, the fog column is semitransparent by visual observation, so that the visual manual detection is difficult even if auxiliary tools such as a black curtain are added, the detection difficulty is increased, and the occasion of detecting the fog column is sometimes accompanied by severe conditions such as high temperature and high pressure, and the like, such as a steel plant. The fog column can be automatically detected and fed back under the severe environment under the non-contact condition, which is very necessary.
Machine vision is widely applied to industries with increasing intelligence, such as industrial manufacturing, artificial intelligence and the like as a convenient, quick and stable detection mode in recent years. The machine vision is used as a monitoring and detecting system, so that the labor is greatly reduced, the cost is saved, and meanwhile, the machine vision has high accuracy and stability, so that the machine vision is more and more distant in the aspects of manufacturing, application and the like. Machine vision becomes a fundamental stone for manufacturing automation and intellectualization.
Therefore, based on the inconvenience of the manual measurement and the unstable measurement result, the development of the automatic fog column coverage area and maximum width detection system based on the machine vision is very significant.
Disclosure of Invention
The invention aims to overcome the defects that the operation of manually measuring a fog column is inconvenient and the measurement result is unstable at present, and provides an automatic fog column coverage area and maximum width detection system based on machine vision. According to the invention, a visual hardware platform is built, clear nozzle fog column images are acquired, then the coverage area and the maximum width of a fog column are calculated through image processing, the obtained detection result is displayed on an original image, the overall output of the fog column images and the measurement and output of the area width of the fog column at a specific distance are realized, and the system can also complete the analysis of the influence of air pressure, water pressure and gravity parameters on the fog column outline.
In order to achieve the purpose, the invention provides the following technical scheme:
a fog column automatic detection system based on machine vision comprises a camera calibration module, a fog column image acquisition module, a fog column image processing module, a detection data analysis module and a detection result display module;
the camera calibration module is used for calibrating each image acquisition device in the fog column image acquisition module to correct image distortion, facilitate subsequent image processing and analyze the internal relation between cameras by utilizing a calibration result;
the fog column image acquisition module is used for acquiring fog column images sprayed by the nozzle, and comprises a plurality of image acquisition devices and background cloth arranged below the nozzle, wherein the background cloth is used for covering sundries to protrude the fog column sprayed by the nozzle so as to facilitate subsequent image processing;
the fog column image processing module is used for carrying out image processing on the fog column image acquired by the fog column image acquisition module;
the detection data analysis module is used for acquiring the coverage area and the maximum width of the fog column according to the information acquired by the fog column image processing module, and particularly acquiring the boundary line of the outer contour of the fog column through a polynomial fitting algorithm and then acquiring the coverage area and the maximum width of the fog column (compared with the existing methods such as edge detection and the like, the method for acquiring the outer contour of the fog column through the polynomial fitting algorithm has stronger generalization capability and more objective and representative results), and a statistical pixel method is adopted for calculating the width of the fog column so as to improve the detection precision; in addition, the module can also be provided with software to complete the analysis of the influence of the analysis air pressure, water pressure and gravity parameters on the spraying profile;
and the detection result display module is used for displaying the related result obtained by the detection data analysis module. The detection result display module can also display the obtained detection result on the original image, so that the overall output of the fog column image and the measurement and output of the area width of the fog column at a specific distance are realized.
The automatic fog column detection system based on machine vision has high degree of automation, can finish automatic measurement of fog columns, solves the problem of high randomness of manual measurement, has high detection precision, good objective consistency and high working efficiency, is simple and convenient to operate (parameters are configured in an interactive interface, so that the parameters can be conveniently controlled and the process can be conveniently operated in various requirements) and has wide application prospect.
As a preferred technical scheme:
the fog column image acquisition module comprises a platform, a fixing part, a nozzle, a water pump, an air pump, a barometer, a light supplementing lamp, fog column image acquisition equipment, background cloth and a processing terminal;
the platform is built by aluminum alloy and is used for fixing various test devices;
the fixing piece is fixed in front of the platform and used for fixing the nozzle;
the water pump is used for providing a water source for the spray of the nozzle;
the air pump is used for realizing nozzle atomization;
the fog column image acquisition equipment is fixed at the top of the platform and used for shooting fog columns sprayed by the nozzles;
the barometer is fixed in front of the platform and used for displaying the current air pressure;
the light supplement lamp is fixed below the fog column image acquisition equipment and used for providing a supplement light source for the fog column image acquisition equipment;
the background cloth (black cloth) is positioned in front of and below the nozzle so as to prevent the collected fog column image from entering other components by mistake and reduce the pressure of subsequent image processing;
the air pump, the water pump and the fog column image acquisition equipment are respectively connected with the processing terminal through cables, the processing terminal controls the trigger signals to realize control over the water pump, the air pump and the fog column image acquisition equipment, and the fog column image acquisition equipment receives the trigger signals and sends shot fog column images to the processing terminal for subsequent processing. The fog column image acquisition module has reasonable structural design, reasonable control logic and wide application prospect. The nozzle has good replacement convenience, can meet different industrial measurement requirements, and has great application prospect.
According to the fog column automatic detection system based on machine vision, the camera calibration module is used for calibrating the image acquisition equipment by adopting a Zhangnyou chessboard calibration method.
The fog column image processing module comprises an image preprocessing unit, a fog column image splicing unit, an edge detection unit and a contour analysis unit;
data acquired by the fog column image acquisition module are processed by the image preprocessing unit, the fog column image splicing unit, the edge detection unit and the contour analysis unit in sequence.
The automatic fog column detection system based on the machine vision comprises an image preprocessing unit and an image processing unit, wherein the image preprocessing unit comprises the following operation processes:
firstly, distortion correction is carried out on a shot fog column image by utilizing a camera calibration module calibration result, then noise filtering processing is carried out on the image through a median filtering algorithm, then an edge is cut to obtain a target image, and a binary image is obtained through binarization operation.
The fog column automatic detection system based on the machine vision comprises the following operation processes of:
and splicing the fog column images through a SURF/SIFT algorithm to obtain a complete fog column image for subsequent processing.
The automatic fog column detection system based on the machine vision comprises the following operation processes of:
and carrying out edge detection on the binary image by a Canny algorithm.
The automatic fog column detection system based on the machine vision comprises the following operation processes of:
and calculating the area occupied by each water drop contour by setting a threshold value, and filling the contour smaller than the set threshold value into a background color, so as to screen out the outer contour of the spray.
The automatic fog column detection system based on the machine vision comprises the following processing procedures of the detection data analysis module:
(1) respectively counting the number of 255 pixel values in the left and right half images by taking the height of the fog image as an index through a Counter function in Python;
(2) obtaining the coefficient value of the fitting function through a polyfit function;
(3) generating a fitting function generated by the left and right half images through a poly1d function, and integrating the two fitting functions to obtain a boundary line of the outer contour of the fog column;
(4) calculating the coverage area of the fog column by utilizing a trapz function in Numpy based on the integral idea of the binarized image, wherein the maximum width of the fog column is the maximum value of the difference between the upper value and the lower value of the outer contour of the fog column;
(5) and (4) completing proportion conversion according to the relation between the pixels of the fog column image and the actual distance, and converting the calculated value in the step (4) into an actual value.
The fog column automatic detection system based on the machine vision comprises the following processing procedures of a detection result display module:
after a fitting function generated by the left and right half images obtained by the detection data analysis module is obtained, the outer contour of the fog column can be obtained by taking the middle scale of the image as an X axis and the fitting value as a Y value through a matplotlib function (the difference between the upper and lower values of the image is the width of the fog image), the outer contour of the fog column is displayed in the original image of the fog column image, and the integral output of the fog column image and the measurement and output of the area width of the fog column at a specific distance are realized.
Has the advantages that:
(1) the automatic fog column detection system based on machine vision solves the randomness of manual measurement, greatly saves the cost, can clearly reflect the working condition of the fog column, and has high accuracy and stability. The fog column can be better utilized and controlled, and the working quality and the working efficiency are improved;
(2) the fog column automatic detection system based on the machine vision uses the machine vision as a monitoring detection system, outputs the detection result by utilizing the image and the data table, and adds the calculation result into the original image, so that the detection result is clear and easy to understand and is clear at a glance;
(3) the automatic fog column detection system based on machine vision has the advantages that the automatic fog column measurement platform is simple to operate, clear in feedback and smooth in operation, overcomes the defects of the coverage area and the maximum width detection of a fog column in the prior art, has high industrial utilization value, promotes the automation process of industrial production, and has great application prospects.
Drawings
FIG. 1 is a schematic process flow diagram of the automatic fog column detection system based on machine vision according to the present invention;
FIG. 2 is a schematic structural diagram of a fog column image acquisition module according to the present invention;
FIG. 3 is a schematic structural diagram of a fog column image processing module according to the present invention;
the system comprises a platform 1, a fixing piece 2, a nozzle 3, a water pump 4, an air pump 5, a barometer 6, a light supplement lamp 7, a fog column image acquisition device 8, background cloth 9 and a processing terminal 10.
Detailed Description
The present invention will be described in more detail with reference to the accompanying drawings, in which embodiments of the invention are shown and described, and it is to be understood that the embodiments described are merely illustrative of some, but not all embodiments of the invention.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention.
Example 1
A fog column automatic detection system based on machine vision is shown in figure 1 and comprises a camera calibration module, a fog column image acquisition module, a fog column image processing module, a detection data analysis module and a detection result display module.
The camera calibration module is used for calibrating each image acquisition device in the fog column image acquisition module (the image acquisition devices are calibrated by adopting a Zhang Zhengyou chessboard pattern calibration method) so as to correct image distortion, facilitate subsequent image processing and analyze the internal relation between cameras by utilizing a calibration result.
The fog column image acquisition module is used for acquiring fog column images sprayed by a nozzle, and comprises a platform 1, a fixing part 2, a nozzle 3, a water pump 4, an air pump 5, a barometer 6, a light supplement lamp 7, fog column image acquisition equipment 8, background cloth 9 and a processing terminal 10, wherein the platform 1 is constructed by aluminum alloy and is used for fixing various test equipment, the fixing part 2 is fixed in front of the platform 1 and is used for fixing the nozzle 3, the water pump 4 is used for providing water source for spraying of the nozzle 3, the air pump 5 is used for realizing atomization of the nozzle 3, the fog column image acquisition equipment 8 is fixed at the top of the platform 1 and is used for shooting fog columns sprayed by the nozzle 3, and the barometer 6 is fixed in front of the platform 1 and is used for displaying the current air pressure; the light supplement lamp 7 is fixed below the fog column image acquisition equipment 8 and used for providing a supplement light source for the fog column image acquisition equipment 8; background cloth 9 (black cloth) is located the front lower place of nozzle to other subassemblies are gone into to the fog column image mistake of gathering, reduce follow-up image processing's pressure, air pump 5, water pump 4 and fog column image acquisition equipment 8 are connected with processing terminal 10 through the cable respectively, processing terminal 10 control trigger signal, in order to realize the control to water pump 4, air pump 5 and fog column image acquisition equipment 8, fog column image acquisition equipment 8 receives trigger signal, the fog column image transmission who will shoot carries out follow-up processing to processing terminal 10.
The fog column image processing module is used for processing images of fog columns acquired by the fog column image acquisition module, and specifically comprises an image preprocessing unit, a fog column image splicing unit, an edge detection unit and a contour analysis unit as shown in fig. 3, wherein data acquired by the fog column image acquisition module is processed by the image preprocessing unit, the fog column image splicing unit, the edge detection unit and the contour analysis unit in sequence, and the data processing process of the above units is specifically as follows:
the operation of the image preprocessing unit is as follows:
firstly, distortion correction is carried out on a shot fog column image by utilizing a camera calibration module calibration result, then noise filtering processing is carried out on the image through a median filtering algorithm, then an edge is cut to obtain a target image, and a binary image is obtained through binarization operation;
the operation process of the fog column image splicing unit is as follows:
splicing the fog column images through a SURF \ SIFT algorithm to obtain complete fog column images for subsequent processing;
the operation of the edge detection unit is as follows:
performing edge detection on the binary image through a Canny algorithm;
the operation of the contour analysis unit is as follows:
calculating the area occupied by each water drop contour by setting a threshold value, and filling the contour smaller than the set threshold value as a background color, so as to screen out the outer contour of the spray;
the detection data analysis module is used for acquiring the coverage area and the maximum width of the fog column according to the information acquired by the fog column image processing module, specifically, the boundary line of the outer contour of the fog column is acquired through a polynomial fitting algorithm, then the coverage area and the maximum width of the fog column are acquired, and the detection precision is improved by adopting a statistical pixel method for calculating the width of the fog column, and the specific processing process is as follows:
(1) respectively counting the number of 255 pixel values in the left and right half images by taking the height of the fog image as an index through a Counter function in Python;
(2) obtaining the coefficient value of the fitting function through a polyfit function;
(3) generating a fitting function generated by the left and right half images through a poly1d function, and integrating the two fitting functions to obtain a boundary line of the outer contour of the fog column;
(4) calculating the coverage area of the fog column by utilizing a trapz function in Numpy based on the integral idea of the binarized image, wherein the maximum width of the fog column is the maximum value of the difference between the upper value and the lower value of the outer contour of the fog column;
(5) and (4) completing proportion conversion according to the relation between the pixels of the fog column image and the actual distance, and converting the calculated value in the step (4) into an actual value.
The detection result display module is used for displaying the related results obtained by the detection data analysis module, and the processing process is as follows:
after a fitting function generated by the left and right half images obtained by the detection data analysis module is obtained, the outer contour of the fog column can be obtained by taking the middle scale of the image as an X axis and the fitting value as a Y value through a matplotlib function (the difference between the upper and lower values of the image is the width of the fog image), the outer contour of the fog column is displayed in the original image of the fog column image, and the integral output of the fog column image and the measurement and output of the area width of the fog column at a specific distance are realized.
In addition, the automatic fog column detection system based on machine vision further comprises an abnormal result alarm module, the result is normally detected after the data comes out of the detection data analysis module, if the detected result is normal, the detection result is displayed after entering the detection result display module, and if the detected result is abnormal, the abnormal result alarm module gives an alarm.
Through verification, the automatic fog column detection system based on machine vision solves the randomness of manual measurement, greatly saves the cost, can clearly reflect the working condition of a fog column, and has high accuracy and stability. The fog column can be better utilized and controlled, and the working quality and the working efficiency are improved; the machine vision is used as a monitoring detection system, the detection result is output by utilizing the image and the data table, and meanwhile, the calculation result is added into the original image, so that the detection result is clear and easy to understand and is clear at a glance; the automatic fog column measuring platform is simple to operate, clear in feedback and smooth in operation, overcomes the defects of fog column coverage area and maximum width detection in the prior art, has high industrial utilization value, promotes the process of industrial production automation, and has great application prospect.
Although specific embodiments of the present invention have been described above, it will be appreciated by those skilled in the art that these embodiments are merely illustrative and various changes or modifications may be made without departing from the principles and spirit of the invention.
Claims (10)
1. A fog column automatic detection system based on machine vision is characterized by comprising a camera calibration module, a fog column image acquisition module, a fog column image processing module, a detection data analysis module and a detection result display module;
the camera calibration module is used for calibrating each image acquisition device in the fog column image acquisition module;
the fog column image acquisition module is used for acquiring fog column images sprayed by the nozzle and comprises a plurality of image acquisition devices and background cloth arranged below the nozzle;
the fog column image processing module is used for carrying out image processing on the fog column image acquired by the fog column image acquisition module;
the detection data analysis module is used for acquiring the coverage area and the maximum width of the fog column according to the information acquired by the fog column image processing module, and specifically, the coverage area and the maximum width of the fog column are acquired after the boundary line of the outer contour of the fog column is acquired through a polynomial fitting algorithm;
and the detection result display module is used for displaying the related result obtained by the detection data analysis module.
2. The fog column automatic detection system based on the machine vision is characterized in that the fog column image acquisition module comprises a platform, a fixing part, a nozzle, a water pump, an air pump, a barometer, a light supplement lamp, fog column image acquisition equipment, background cloth and a processing terminal;
the platform is built by aluminum alloy and is used for fixing various test devices;
the fixing piece is fixed in front of the platform and used for fixing the nozzle;
the water pump is used for providing a water source for the spray of the nozzle;
the air pump is used for realizing nozzle atomization;
the fog column image acquisition equipment is fixed at the top of the platform and used for shooting fog columns sprayed by the nozzles;
the barometer is fixed in front of the platform and used for displaying the current air pressure;
the light supplement lamp is fixed below the fog column image acquisition equipment and used for providing a supplement light source for the fog column image acquisition equipment;
the background cloth is positioned in front of and below the nozzle;
the air pump, the water pump and the fog column image acquisition equipment are respectively connected with the processing terminal through cables, the processing terminal controls the trigger signals to realize control over the water pump, the air pump and the fog column image acquisition equipment, and the fog column image acquisition equipment receives the trigger signals and sends shot fog column images to the processing terminal for subsequent processing.
3. The fog column automatic detection system based on machine vision according to claim 1, characterized in that the camera calibration module is used for calibrating the image acquisition device by Zhang Yongyou chessboard lattice calibration method.
4. The fog column automatic detection system based on the machine vision is characterized in that the fog column image processing module comprises an image preprocessing unit, a fog column image splicing unit, an edge detection unit and a contour analysis unit;
data acquired by the fog column image acquisition module are processed by the image preprocessing unit, the fog column image splicing unit, the edge detection unit and the contour analysis unit in sequence.
5. The automatic fog column detection system based on machine vision is characterized in that the image preprocessing unit operates as follows:
firstly, distortion correction is carried out on a shot fog column image by utilizing a camera calibration module calibration result, then noise filtering processing is carried out on the image through a median filtering algorithm, then an edge is cut to obtain a target image, and a binary image is obtained through binarization operation.
6. The fog column automatic detection system based on machine vision as claimed in claim 4, wherein the fog column image stitching unit is operated as follows:
and splicing the fog column images through a SURF/SIFT algorithm to obtain a complete fog column image.
7. The automatic fog column detection system based on machine vision is characterized in that the operation process of the edge detection unit is as follows:
and carrying out edge detection on the binary image by a Canny algorithm.
8. The automatic fog column detection system based on machine vision is characterized in that the operation process of the contour analysis unit is as follows:
and calculating the area occupied by each water drop contour by setting a threshold value, and filling the contour smaller than the set threshold value into a background color, so as to screen out the outer contour of the spray.
9. The automatic fog column detection system based on machine vision is characterized in that the detection data analysis module processes the following steps:
(1) respectively counting the number of 255 pixel values in the left and right half images by taking the height of the fog image as an index through a Counter function in Python;
(2) obtaining the coefficient value of the fitting function through a polyfit function;
(3) generating a fitting function generated by the left and right half images through a poly1d function, and integrating the two fitting functions to obtain a boundary line of the outer contour of the fog column;
(4) calculating by using a trapz function in Numpy to obtain the coverage area of the fog column, wherein the maximum width of the fog column is the maximum value of the difference between the upper value and the lower value of the outer contour of the fog column;
(5) and (4) completing proportion conversion according to the relation between the pixels of the fog column image and the actual distance, and converting the calculated value in the step (4) into an actual value.
10. The automatic fog column detection system based on machine vision is characterized in that the detection result display module performs the following processing procedures:
and after a fitting function generated by the left and right half images obtained by the detection data analysis module is obtained, the outer contour of the fog column can be obtained through a matplotlib function by taking the middle scale of the image as an X axis and the fitting value as a Y value, and the outer contour of the fog column is displayed in an original image of the fog column image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110308263.9A CN113203359B (en) | 2021-03-23 | 2021-03-23 | Fog column automatic check out system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110308263.9A CN113203359B (en) | 2021-03-23 | 2021-03-23 | Fog column automatic check out system based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113203359A true CN113203359A (en) | 2021-08-03 |
| CN113203359B CN113203359B (en) | 2023-02-28 |
Family
ID=77025598
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110308263.9A Active CN113203359B (en) | 2021-03-23 | 2021-03-23 | Fog column automatic check out system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113203359B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001256475A (en) * | 2001-04-27 | 2001-09-21 | Ced System Inc | System for detecting black smoke |
| JP2007315777A (en) * | 2006-05-23 | 2007-12-06 | Ditect:Kk | Three-dimensional shape measurement system |
| JP2010185691A (en) * | 2009-02-10 | 2010-08-26 | Doshisha | Sprayed particle imaging analysis system and analysis method |
| CN102136135A (en) * | 2011-03-16 | 2011-07-27 | 清华大学 | Method for extracting inner outline of cornea from optical coherence tomography image of anterior segment of eye and method for extracting inner outline of anterior chamber from optical coherence tomography image of anterior segment of eye |
| CN103017683A (en) * | 2012-12-31 | 2013-04-03 | 中国人民解放军国防科学技术大学 | Device and method for measuring liquid jet on outermost boundary |
| CN104123531A (en) * | 2013-04-28 | 2014-10-29 | 汉王科技股份有限公司 | Palmprint interest region locating method and apparatus |
| CN104181083A (en) * | 2014-08-27 | 2014-12-03 | 天津商业大学 | Spray characteristic parameter detection device and method |
| CN104634279A (en) * | 2013-11-13 | 2015-05-20 | 中国科学院沈阳计算技术研究所有限公司 | Vision-based automatic aviation oil mist nozzle atomization angle detection device and method |
| CN109816678A (en) * | 2019-02-27 | 2019-05-28 | 青岛伴星智能科技有限公司 | A kind of the nozzle atomization angle automatic checkout system and method for view-based access control model |
| CN110160760A (en) * | 2019-05-05 | 2019-08-23 | 贵州中烟工业有限责任公司 | A kind of nozzle atomization effect detection method |
| CN111353334A (en) * | 2018-12-21 | 2020-06-30 | 富士通株式会社 | Smoke detection method and device |
| CN111735744A (en) * | 2020-04-24 | 2020-10-02 | 昆明理工大学 | Nozzle atomization space distribution evaluation method |
| CN112179641A (en) * | 2020-09-30 | 2021-01-05 | 湖北中烟工业有限责任公司 | Nozzle atomization visual monitoring system |
| CN112453751A (en) * | 2020-11-27 | 2021-03-09 | 上海交通大学 | Pipeline all-position welding back surface online monitoring method based on visual sensing |
-
2021
- 2021-03-23 CN CN202110308263.9A patent/CN113203359B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001256475A (en) * | 2001-04-27 | 2001-09-21 | Ced System Inc | System for detecting black smoke |
| JP2007315777A (en) * | 2006-05-23 | 2007-12-06 | Ditect:Kk | Three-dimensional shape measurement system |
| JP2010185691A (en) * | 2009-02-10 | 2010-08-26 | Doshisha | Sprayed particle imaging analysis system and analysis method |
| CN102136135A (en) * | 2011-03-16 | 2011-07-27 | 清华大学 | Method for extracting inner outline of cornea from optical coherence tomography image of anterior segment of eye and method for extracting inner outline of anterior chamber from optical coherence tomography image of anterior segment of eye |
| CN103017683A (en) * | 2012-12-31 | 2013-04-03 | 中国人民解放军国防科学技术大学 | Device and method for measuring liquid jet on outermost boundary |
| CN104123531A (en) * | 2013-04-28 | 2014-10-29 | 汉王科技股份有限公司 | Palmprint interest region locating method and apparatus |
| CN104634279A (en) * | 2013-11-13 | 2015-05-20 | 中国科学院沈阳计算技术研究所有限公司 | Vision-based automatic aviation oil mist nozzle atomization angle detection device and method |
| CN104181083A (en) * | 2014-08-27 | 2014-12-03 | 天津商业大学 | Spray characteristic parameter detection device and method |
| CN111353334A (en) * | 2018-12-21 | 2020-06-30 | 富士通株式会社 | Smoke detection method and device |
| CN109816678A (en) * | 2019-02-27 | 2019-05-28 | 青岛伴星智能科技有限公司 | A kind of the nozzle atomization angle automatic checkout system and method for view-based access control model |
| CN110160760A (en) * | 2019-05-05 | 2019-08-23 | 贵州中烟工业有限责任公司 | A kind of nozzle atomization effect detection method |
| CN111735744A (en) * | 2020-04-24 | 2020-10-02 | 昆明理工大学 | Nozzle atomization space distribution evaluation method |
| CN112179641A (en) * | 2020-09-30 | 2021-01-05 | 湖北中烟工业有限责任公司 | Nozzle atomization visual monitoring system |
| CN112453751A (en) * | 2020-11-27 | 2021-03-09 | 上海交通大学 | Pipeline all-position welding back surface online monitoring method based on visual sensing |
Non-Patent Citations (2)
| Title |
|---|
| 王廷俊: "基于视觉的航空油雾喷嘴雾化角度自动检测装置", 《中国设备工程》 * |
| 金学民: "基于机器视觉检测精细雾化喷头的装置", 《纺织器材》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113203359B (en) | 2023-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109816678B (en) | Automatic nozzle atomization angle detection system and method based on vision | |
| CN106226325B (en) | A kind of seat surface defect detecting system and its method based on machine vision | |
| CN103454285A (en) | Transmission chain quality detection system based on machine vision | |
| CN109375068B (en) | Target identification method and device based on ultraviolet imaging corona detection | |
| CN103617611A (en) | Automatic threshold segmentation detection method for center and size of light spot | |
| CN110260818B (en) | Electronic connector robust detection method based on binocular vision | |
| CN110472722A (en) | Steel billet counting device and method based on machine vision technique | |
| CN113188633A (en) | Liquid level detection and measurement method based on machine vision | |
| CN113688817A (en) | Instrument identification method and system for automatic inspection | |
| CN113847881A (en) | Free-form surface profile tolerance detection method based on machine vision | |
| CN108830840A (en) | A kind of active intelligent detecting method of circuit board defect and its application | |
| CN113252567A (en) | Method, system, medium and terminal for rapidly detecting multiple defects on surface of aluminum valve plate | |
| CN114280075A (en) | Online visual inspection system and method for surface defects of pipe parts | |
| CN113203359B (en) | Fog column automatic check out system based on machine vision | |
| CN111426693A (en) | Quality defect detection system and detection method thereof | |
| CN109557098A (en) | Metal surface detection system based on machine vision | |
| CN110097540A (en) | The visible detection method and device of polygon workpeace | |
| CN112958957A (en) | Automatic calibration method and system for welding of large steel reinforcement framework | |
| CN115290668B (en) | System and method for detecting defects of finish paint of coated car body | |
| CN116840240A (en) | Visual detection system of power supply distributor | |
| CN205607332U (en) | Measuring device is striden to bridge crane crane span structure based on machine vision | |
| CN111192246B (en) | Automatic detection method for welding spots | |
| Xue et al. | Method of electronic component location, grasping and inserting based on machine vision | |
| CN117218079A (en) | Vehicle body defect detection method based on machine vision | |
| CN210375028U (en) | Remote vision-based laser surface difference detection system |
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 |