CN113588654B - Three-dimensional visual detection method for engine heat exchanger interface - Google Patents
Three-dimensional visual detection method for engine heat exchanger interface Download PDFInfo
- Publication number
- CN113588654B CN113588654B CN202110707026.XA CN202110707026A CN113588654B CN 113588654 B CN113588654 B CN 113588654B CN 202110707026 A CN202110707026 A CN 202110707026A CN 113588654 B CN113588654 B CN 113588654B
- Authority
- CN
- China
- Prior art keywords
- image
- compared
- standard
- heat exchanger
- binarization processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 25
- 230000000007 visual effect Effects 0.000 title claims abstract description 6
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000007547 defect Effects 0.000 claims abstract description 20
- 238000000605 extraction Methods 0.000 claims description 17
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000011179 visual inspection Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 2
- 238000012797 qualification Methods 0.000 abstract description 2
- 238000005070 sampling Methods 0.000 description 4
- 239000000047 product Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 239000011265 semifinished product Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a three-dimensional visual detection method of an engine heat exchanger interface, which is characterized in that a calibrated camera shoots images of standard heat exchanger parts from a plurality of preset acquisition angles and positions with equal viewing distances, binarization processing is carried out, the images after the binarization processing are detected, the foreground and the background are segmented by edges, the edges after error expansion are calculated as characteristic parameters, repeated operation is carried out on the parts to be compared, and the parts to be compared are compared with the characteristic parameters of the standard parts, so that the parts with various defects are screened; the method has the advantages that all parts can be detected one by one quickly and efficiently by the detection method, the classification effect is good, the production efficiency can be greatly improved, and the qualification rate of the parts leaving the factory is obviously improved.
Description
Technical Field
The invention belongs to the field of part defect detection, and particularly relates to a three-dimensional visual detection method for an engine heat exchanger interface.
Background
In the production process of the heat exchanger, the produced heat exchanger is limited by various conditions, and certain defects exist in the produced heat exchanger, such as the problems of angle deviation between the central axis of the heat exchanger input tube and the standard central axis, surface deformation of the heat exchanger input tube, error size of the heat exchanger input tube and the like, and the defects seriously affect the surface quality and the physical and mechanical properties of the product, and finally, the whole part may be disqualified.
At present, the quality detection link of a factory mostly adopts manual detection or off-line sampling detection, and the subjective detection method is to manually measure the finished product or the semi-finished product of the heat exchanger by aid of auxiliary tools such as vernier calipers, and the method is flexible, but has strong dependence on the working capacity and fatigue degree of workers, has the defects of low efficiency, low precision, poor stability and the like, and the labor cost of manual detection occupies a considerable proportion in the production cost, so that great difficulty is brought to the cost control of enterprises; while the off-line sampling detection can obtain high-precision detection data, the off-line sampling detection has the defects of slow reaction, low efficiency, small sampling coverage and the like, and the defects of the heat exchanger are difficult to discover in time.
Disclosure of Invention
The invention aims to provide a three-dimensional visual detection method for an engine heat exchanger interface, which is efficient and flexible in detection process and accurate in detection result.
The technical scheme adopted for solving the technical problems is as follows: a three-dimensional visual inspection method for an engine heat exchanger interface, comprising the steps of:
step 1): calibrating the internal parameters and the external parameters of the camera through a calibration plate to obtain a calibrated camera;
step 2): obtaining images with a plurality of preset acquisition angles and equal viewing distances of a standard heat exchanger through a calibrated camera, dividing an image corresponding to an input tube of the standard heat exchanger in each image with the acquisition angles into standard images corresponding to the acquisition angles, performing image binarization processing on the standard images to obtain standard images subjected to the image binarization processing, and extracting image characteristic parameters of the standard images subjected to the image binarization processing to serve as standard characteristic parameters;
step 3): acquiring images of a plurality of preset acquisition angles of a heat exchanger to be compared through a calibrated camera, dividing an image corresponding to an input tube of the heat exchanger to be compared in the images of each acquisition angle to serve as an image to be compared, performing image binarization processing on the image to be compared to obtain an image to be compared after the image binarization processing, and extracting image characteristic parameters of the image to be compared after the image binarization processing to serve as characteristic parameters to be compared;
step 4): and comparing the characteristic parameters to be compared with the standard characteristic parameters, judging the defect condition of the heat exchanger to be compared corresponding to the comparison result, and finishing the detection process.
The specific process of performing image binarization processing on the standard image in the step 2) is as follows: carrying out Gaussian filtering on the standard image, converting the standard image into a standard binary image through an OTSU algorithm, and finally carrying out closed operation on the standard binary image to obtain a standard image after image binarization processing;
the specific process of performing image binarization processing on the images to be compared in the step 3) is as follows: carrying out Gaussian filtering on the images to be compared, converting the images into binary images to be compared through an OTSU algorithm, and finally carrying out closing operation on the binary images to be compared to obtain images to be compared after the binarization processing of the images;
in the step 2), the standard characteristic parameters comprise vertex coordinates of the standard image after the image binarization, the number of pixels occupied by the standard image after the image binarization and the number of pixels occupied by the standard image after the image binarization with specified error expansion;
in the step 3), the feature parameters to be compared include vertex coordinates of the image to be compared after the image binarization process, the number of pixels occupied by the image to be compared after the image binarization process, and the number of pixels occupied by the image to be compared after the image binarization process after the expansion of the specified error.
In the step 2), the process of extracting the vertex coordinates of the standard image after the image binarization processing is as follows:
firstly, suppressing a pseudo edge caused by noise by using a Canny operator, detecting a pixel-level edge of a standard image after image binarization processing, and obtaining a refined standard edge contour image;
secondly, extracting straight lines at two sides of the part from the thinned standard edge contour image by adopting Hough transformation, and acquiring the central axis of the part according to the straight lines at two sides of the part;
thirdly, acquiring a rotation matrix according to the slope of the standard central axis, acquiring a horizontal image of the part after the central axis is horizontal through the rotation of the thinned standard edge contour image of the rotation matrix, extracting coordinates corresponding to the vertexes of the input tube of the standard heat exchanger in the horizontal image, and taking the coordinates as vertex coordinates of the standard image after the image binarization processing;
the extraction mode of the pixel number occupied by the standard image after the image binarization processing is as follows: filling the inside of the thinned standard edge contour image with white pixels, obtaining the number of pixels of the white pixels and taking the number of pixels of the image corresponding to the input tube of the standard heat exchanger;
the extraction process of the pixel number occupied by the standard image after the image binarization processing after the specified error expansion is as follows:
setting a specified error range, and generating a standard expansion image for edge expansion of the thinned standard edge contour image according to the specified error range;
and secondly, filling white pixels in the standard expansion image to generate a mask image, acquiring the number of pixels of the white pixels in the mask image, and taking the mask image as the standard image after the image binarization processing to specify the number of pixels occupied by the error expansion.
In the step 3), the extraction process of the vertex coordinates of the image corresponding to the input tube of the heat exchanger to be compared is as follows:
firstly, suppressing a false edge caused by noise by using a Canny operator, detecting a pixel-level edge of an image to be compared after image binarization processing, and obtaining a refined edge contour image to be compared;
secondly, extracting straight lines at two sides of the part from the thinned edge profile image to be compared by adopting Hough transformation, and acquiring the central axis of the part according to the straight lines at two sides of the part;
thirdly, acquiring a rotation matrix according to the slope of the axis to be compared, acquiring a horizontal image of the part after the central axis of the part is horizontal through the rotation matrix rotation thinned profile image of the edge to be compared, extracting coordinates corresponding to the vertex of the input tube of the heat exchanger to be compared in the horizontal image, and taking the coordinates as vertex coordinates of the image to be compared after image binarization processing;
the extraction mode of the pixel number occupied by the image to be compared after the image binarization processing is as follows: filling the interior of the thinned edge contour image to be compared with white pixels, obtaining the number of the pixels of the white pixels and taking the number of the pixels as the number of the pixels occupied by the image corresponding to the input tube of the heat exchanger to be compared;
the extraction process of the pixel number occupied by the image to be compared after the image binarization processing after the specified error expansion is as follows:
setting a specified error range, and generating an expanded image to be compared by expanding the edges of the thinned edge profile image to be compared according to the specified error range;
and secondly, filling white pixels in the expansion image to be compared to generate a mask image, obtaining the number of pixels of the white pixels in the mask image, and taking the mask image as the number of pixels occupied by the expansion image to be compared after the binarization processing of the image with specified errors.
The specific process of the step 4) is as follows:
4) -1 marking the vertex coordinates of the standard image after image binarization as (x, y), and marking the vertex coordinates of the image to be compared after image binarization as (x' p ,y′ p ) Let s= | (x' p -x) 2 +(y′ p -y) 2 I, wherein i is absolute value notation, size tolerance error limit is set and noted as δ p When S is less than or equal to delta p Judging that the input pipe of the heat exchanger to be compared is a size qualified piece, if S is more than delta p Judging that the input pipe of the heat exchanger to be compared is a size disqualified piece;
4) -2, the number of pixels occupied by the standard image after the image binarization is denoted as m, and the number of pixels occupied by the image to be compared after the image binarization is denoted as m p Setting the allowable error limit of the surface defect and recording as delta m When |m p -m|≥δ m When it is judged that the surface defect of the input pipe of the heat exchanger to be compared meets the specification, if |m p -m|<δ m Judging that the surface defect of the input pipe of the heat exchanger to be compared does not accord with the specification, wherein the I.
4) -3, marking the number of pixels occupied by the standard image after the image binarization processing after the expansion of the specified error as c, and marking the number of pixels occupied by the image to be compared after the image binarization processing after the expansion of the specified error as c p An angle allowance error limit is set and recorded as delta c When |c p -c|≥δ c When the angle of the input pipe of the heat exchanger to be compared is judged to be in accordance with the specification, when the angle of the input pipe of the heat exchanger to be compared is |c p -c|<δ c And judging that the angle of the input pipe of the heat exchanger to be compared does not accord with the specification, wherein the I.
Compared with the prior art, the method has the advantages that the calibrated camera shoots images of the standard heat exchanger parts from the preset positions with the same acquisition angles and the same viewing distance, binarization processing is carried out, the images after the binarization processing are detected, the edges are used for segmenting foreground and background, the edges after error expansion are calculated as characteristic parameters, repeated operation is carried out on the parts to be compared, and the parts to be compared are compared with the characteristic parameters of the standard parts, so that parts with various defects are screened out; compared with the traditional manual detection, the detection method adopted by the invention can rapidly and efficiently detect all the parts one by one, has good classification effect, can greatly improve the production efficiency, and simultaneously remarkably improves the qualification rate of the parts leaving the factory.
Detailed Description
The present invention is described in further detail below.
A three-dimensional visual inspection method for an engine heat exchanger interface, comprising the steps of:
step 1): and calibrating the internal parameters and the external parameters of the camera through the calibration plate to obtain the calibrated camera.
Step 2): obtaining images with a plurality of preset acquisition angles and equal viewing distances of a standard heat exchanger through a calibrated camera, dividing an image corresponding to an input tube of the standard heat exchanger in each image with the acquisition angles into standard images corresponding to the acquisition angles, performing image binarization on the standard images to obtain standard images subjected to image binarization, and extracting image characteristic parameters of the standard images subjected to image binarization as standard characteristic parameters, wherein the standard characteristic parameters comprise vertex coordinates of the standard images subjected to image binarization, the pixel number occupied by the standard images subjected to image binarization and the pixel number occupied by the standard images subjected to image binarization after the appointed error expansion; the specified error is expanded in detection, namely, 2.5mm is expanded according to the central axis, namely, 2.5/0.094=26.5 pixels, and the edge expansion is carried out by combining the calculation of a specific method formula so as to judge whether the part is incomplete;
the specific process of carrying out image binarization processing on the standard image is as follows: carrying out Gaussian filtering on the standard image, converting the standard image into a standard binary image through an OTSU algorithm, and finally carrying out closed operation on the standard binary image to obtain a standard image after image binarization processing;
the extraction process of the vertex coordinates of the standard image after the image binarization processing is as follows:
firstly, suppressing a pseudo edge caused by noise by using a Canny operator, detecting a pixel-level edge of a standard image after image binarization processing, and obtaining a refined standard edge contour image;
secondly, extracting straight lines at two sides of the part from the thinned standard edge contour image by adopting Hough transformation, and acquiring the central axis of the part according to the straight lines at two sides of the part;
thirdly, acquiring a rotation matrix according to the slope of the standard central axis, acquiring a horizontal image of the part after the central axis is horizontal through the rotation of the thinned standard edge contour image of the rotation matrix, extracting coordinates corresponding to the vertexes of the input tube of the standard heat exchanger in the horizontal image, and taking the coordinates as vertex coordinates of the standard image after the image binarization processing; in the process, the central axis is acquired, the rotation matrix is acquired, the horizontal image is acquired, and the vertex coordinates are obtained by deduction from a mathematical formula of a conventional standard;
the extraction mode of the pixel number occupied by the standard image after the image binarization processing is as follows: filling the inside of the thinned standard edge contour image with white pixels, obtaining the number of pixels of the white pixels and taking the number of pixels of the image corresponding to the input tube of the standard heat exchanger;
the extraction process of the pixel number occupied by the standard image after the image binarization processing after the specified error expansion is as follows:
setting a specified error range, and generating a standard expansion image for edge expansion of the thinned standard edge contour image according to the specified error range;
and secondly, filling white pixels in the standard expansion image to generate a mask image, acquiring the number of pixels of the white pixels in the mask image, and taking the mask image as the standard image after the image binarization processing to specify the number of pixels occupied by the error expansion.
Step 3): obtaining images of a plurality of preset acquisition angles of a heat exchanger to be compared through a calibrated camera, dividing an image corresponding to an input tube of the heat exchanger to be compared in the images of each acquisition angle to serve as an image to be compared, performing image binarization processing on the image to be compared to obtain an image to be compared after the image binarization processing, and extracting image characteristic parameters of the image to be compared after the image binarization processing to serve as the characteristic parameters to be compared, wherein the characteristic parameters to be compared comprise vertex coordinates of the image to be compared after the image binarization processing, the pixel number occupied by the image to be compared after the image binarization processing and the pixel number occupied by the image to be compared after the image binarization processing after the specified error expansion;
the specific process of performing image binarization processing on the images to be compared comprises the following steps: carrying out Gaussian filtering on the images to be compared, converting the images into binary images to be compared through an OTSU algorithm, and finally carrying out closing operation on the binary images to be compared to obtain images to be compared after the binarization processing of the images;
the extraction process of the vertex coordinates of the image corresponding to the input tube of the heat exchanger to be compared is as follows:
firstly, suppressing a false edge caused by noise by using a Canny operator, detecting a pixel-level edge of an image to be compared after image binarization processing, and obtaining a refined edge contour image to be compared;
secondly, extracting straight lines at two sides of the part from the thinned edge profile image to be compared by adopting Hough transformation, and acquiring the central axis of the part according to the straight lines at two sides of the part;
thirdly, acquiring a rotation matrix according to the slope of the axis to be compared, acquiring a horizontal image of the part after the central axis of the part is horizontal through the rotation matrix rotation thinned profile image of the edge to be compared, extracting coordinates corresponding to the vertex of the input tube of the heat exchanger to be compared in the horizontal image, and taking the coordinates as vertex coordinates of the image to be compared after image binarization processing;
the extraction mode of the pixel number occupied by the image to be compared after the image binarization processing is as follows: filling the interior of the thinned edge contour image to be compared with white pixels, obtaining the number of the pixels of the white pixels and taking the number of the pixels as the number of the pixels occupied by the image corresponding to the input tube of the heat exchanger to be compared;
the extraction process of the pixel number occupied by the image to be compared after the image binarization processing after the specified error expansion is as follows:
setting a specified error range, and generating an expanded image to be compared by expanding the edges of the thinned edge profile image to be compared according to the specified error range;
and secondly, filling white pixels in the expansion image to be compared to generate a mask image, obtaining the number of pixels of the white pixels in the mask image, and taking the mask image as the number of pixels occupied by the expansion image to be compared after the binarization processing of the image with specified errors.
In actual detection, four CCD cameras are respectively positioned at 0,90 degrees, 180 degrees and 270 degrees, and the required standard heat exchanger image and the heat exchanger image to be compared are respectively obtained through fixed-angle and fixed-viewing-distance shooting.
Step 4): comparing the characteristic parameters to be compared with the standard characteristic parameters, judging the defect condition of the heat exchanger to be compared corresponding to the comparison result, and completing the detection process, wherein the specific process is as follows:
4) -1 marking the vertex coordinates of the standard image after image binarization as (x, y), and marking the vertex coordinates of the image to be compared after image binarization as (x' p ,y′ p ) Let s= | (x' p -x) 2 +(y′ p -y) 2 I, wherein i is absolute value notation, size tolerance error limit is set and noted as δ p When S is less than or equal to delta p Judging that the input pipe of the heat exchanger to be compared is a size qualified piece, if S is more than delta p Judging that the input pipe of the heat exchanger to be compared is a size disqualified piece;
4) -2, the number of pixels occupied by the standard image after the image binarization is denoted as m, and the number of pixels occupied by the image to be compared after the image binarization is denoted as m p Setting the allowable error limit of the surface defect and recording as delta m When |m p -m|≥δ m When it is judged that the surface defect of the input pipe of the heat exchanger to be compared meets the specification, if |m p -m|<δ m Judging that the surface defect of the input pipe of the heat exchanger to be compared does not accord with the specification, wherein the I.
4) -3, marking the number of pixels occupied by the standard image after the image binarization processing after the expansion of the specified error as c, and marking the number of pixels occupied by the image to be compared after the image binarization processing after the expansion of the specified error as c p An angle allowance error limit is set and recorded as delta c When |c p -c|≥δ c When the angle of the input pipe of the heat exchanger to be compared is judged to be in accordance with the specification, when the angle of the input pipe of the heat exchanger to be compared is |c p -c|<δ c And judging that the angle of the input pipe of the heat exchanger to be compared does not accord with the specification, wherein the I.
Claims (2)
1. The three-dimensional visual detection method of the engine heat exchanger interface is characterized by comprising the following steps of:
step 1): calibrating the internal parameters and the external parameters of the camera through a calibration plate to obtain a calibrated camera;
step 2): obtaining images with a plurality of preset acquisition angles and equal viewing distances of a standard heat exchanger through a calibrated camera, dividing an image corresponding to an input tube of the standard heat exchanger in each image with the acquisition angles into standard images corresponding to the acquisition angles, performing image binarization on the standard images to obtain standard images subjected to image binarization, and extracting image characteristic parameters of the standard images subjected to image binarization as standard characteristic parameters, wherein the standard characteristic parameters comprise vertex coordinates of the standard images subjected to image binarization, the pixel number occupied by the standard images subjected to image binarization and the pixel number occupied by the standard images subjected to image binarization after the appointed error expansion;
the extraction process of the vertex coordinates of the standard image after the image binarization processing is as follows:
firstly, suppressing a pseudo edge caused by noise by using a Canny operator, detecting a pixel-level edge of a standard image after image binarization processing, and obtaining a refined standard edge contour image;
secondly, extracting straight lines at two sides of the part from the thinned standard edge contour image by adopting Hough transformation, and acquiring the central axis of the part according to the straight lines at two sides of the part;
thirdly, acquiring a rotation matrix according to the slope of the standard central axis, acquiring a horizontal image of the part after the central axis is horizontal through the rotation of the thinned standard edge contour image of the rotation matrix, extracting coordinates corresponding to the vertexes of the input tube of the standard heat exchanger in the horizontal image, and taking the coordinates as vertex coordinates of the standard image after the image binarization processing;
the extraction mode of the pixel number occupied by the standard image after the image binarization processing is as follows: filling the inside of the thinned standard edge contour image with white pixels, obtaining the number of pixels of the white pixels and taking the number of pixels of the image corresponding to the input tube of the standard heat exchanger;
the extraction process of the pixel number occupied by the standard image after the image binarization processing after the specified error expansion is as follows:
setting a specified error range, and generating a standard expansion image for edge expansion of the thinned standard edge contour image according to the specified error range;
secondly, filling white pixels in the standard expansion image to generate a mask image, obtaining the number of pixels of the white pixels in the mask image, and taking the mask image as the standard image after the image binarization processing to specify the number of pixels occupied by the error expansion;
step 3): obtaining images of a plurality of preset acquisition angles of a heat exchanger to be compared through a calibrated camera, dividing an image corresponding to an input tube of the heat exchanger to be compared in the images of each acquisition angle to serve as an image to be compared, performing image binarization processing on the image to be compared to obtain an image to be compared after the image binarization processing, and extracting image characteristic parameters of the image to be compared after the image binarization processing to serve as the characteristic parameters to be compared, wherein the characteristic parameters to be compared comprise vertex coordinates of the image to be compared after the image binarization processing, the pixel number occupied by the image to be compared after the image binarization processing and the pixel number occupied by the image to be compared after the image binarization processing after the specified error expansion;
the extraction process of the vertex coordinates of the image corresponding to the input tube of the heat exchanger to be compared is as follows:
firstly, suppressing a false edge caused by noise by using a Canny operator, detecting a pixel-level edge of an image to be compared after image binarization processing, and obtaining a refined edge contour image to be compared;
secondly, extracting straight lines at two sides of the part from the thinned edge profile image to be compared by adopting Hough transformation, and acquiring the central axis of the part according to the straight lines at two sides of the part;
thirdly, acquiring a rotation matrix according to the slope of the axis to be compared, acquiring a horizontal image of the part after the central axis of the part is horizontal through the rotation matrix rotation thinned profile image of the edge to be compared, extracting coordinates corresponding to the vertex of the input tube of the heat exchanger to be compared in the horizontal image, and taking the coordinates as vertex coordinates of the image to be compared after image binarization processing;
the extraction mode of the pixel number occupied by the image to be compared after the image binarization processing is as follows: filling the interior of the thinned edge contour image to be compared with white pixels, obtaining the number of the pixels of the white pixels and taking the number of the pixels as the number of the pixels occupied by the image corresponding to the input tube of the heat exchanger to be compared;
the extraction process of the pixel number occupied by the image to be compared after the image binarization processing after the specified error expansion is as follows:
setting a specified error range, and generating an expanded image to be compared by expanding the edges of the thinned edge profile image to be compared according to the specified error range;
secondly, filling white pixels in the expanded image to be compared to generate a mask image, obtaining the number of pixels of the white pixels in the mask image, and taking the mask image as the number of pixels occupied by the expanded image to be compared after the binarization processing of the image with specified errors;
step 4): comparing the characteristic parameters to be compared with the standard characteristic parameters, judging the defect condition of the heat exchanger to be compared corresponding to the comparison result, and completing the detection process, wherein the specific process is as follows:
4) -1 marking the vertex coordinates of the standard image after image binarization as (x, y), and marking the vertex coordinates of the image to be compared after image binarization as (x' p ,y′ p ) Let s= | (x' p -x) 2 +(y′ p -y) 2 I, wherein i is absolute value notation, size tolerance error limit is set and noted as δ p When S is less than or equal to delta p Judging that the input pipe of the heat exchanger to be compared is a size qualified piece, if s is more than delta p Judging that the input pipe of the heat exchanger to be compared is a size disqualified piece;
4) -2, the number of pixels occupied by the standard image after the image binarization is denoted as m, and the number of pixels occupied by the image to be compared after the image binarization is denoted as m p Setting the allowable error limit of the surface defect and recording as delta m When |m p -m|≥δ m When it is judged that the surface defect of the input pipe of the heat exchanger to be compared meets the specification, if |m p -m|<δ m Judging that the surface defect of the input pipe of the heat exchanger to be compared does not accord with the specification, wherein the I.
4) -3, marking the number of pixels occupied by the standard image after the image binarization processing after the expansion of the specified error as c, and marking the number of pixels occupied by the image to be compared after the image binarization processing after the expansion of the specified error as c p An angle allowance error limit is set and recorded as delta c When |c p -c|≥δ c When the angle of the input pipe of the heat exchanger to be compared is judged to be in accordance with the specification, when the angle of the input pipe of the heat exchanger to be compared is |c p -c|<δ c And judging that the angle of the input pipe of the heat exchanger to be compared does not accord with the specification, wherein the I.
2. The three-dimensional visual inspection method of an engine heat exchanger interface according to claim 1, wherein the specific process of performing image binarization processing on the standard image in the step 2) is as follows: carrying out Gaussian filtering on the standard image, converting the standard image into a standard binary image through an OTSU algorithm, and finally carrying out closed operation on the standard binary image to obtain a standard image after image binarization processing;
the specific process of performing image binarization processing on the images to be compared in the step 3) is as follows: and carrying out Gaussian filtering on the images to be compared, converting the images into binary images to be compared through an OTSU algorithm, and finally carrying out closing operation on the binary images to be compared to obtain the images to be compared after the image binarization processing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110707026.XA CN113588654B (en) | 2021-06-24 | 2021-06-24 | Three-dimensional visual detection method for engine heat exchanger interface |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110707026.XA CN113588654B (en) | 2021-06-24 | 2021-06-24 | Three-dimensional visual detection method for engine heat exchanger interface |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113588654A CN113588654A (en) | 2021-11-02 |
CN113588654B true CN113588654B (en) | 2024-02-02 |
Family
ID=78244544
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110707026.XA Active CN113588654B (en) | 2021-06-24 | 2021-06-24 | Three-dimensional visual detection method for engine heat exchanger interface |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113588654B (en) |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0445697A2 (en) * | 1990-03-07 | 1991-09-11 | Fmc Corporation | Component evaluation system |
JP2002230562A (en) * | 2000-11-29 | 2002-08-16 | Omron Corp | Image processing method and device therefor |
JP2004125525A (en) * | 2002-09-30 | 2004-04-22 | Ishikawajima Harima Heavy Ind Co Ltd | Method and apparatus for measuring rectangular parallelepiped |
CN104568983A (en) * | 2015-01-06 | 2015-04-29 | 浙江工业大学 | Active-omni-directional-vision-based pipeline inside functional defect detection device and detection method |
JP2015178190A (en) * | 2014-03-18 | 2015-10-08 | 株式会社リコー | Image inspection device, image formation system and image inspection method |
CN107014822A (en) * | 2017-02-28 | 2017-08-04 | 深圳市维图视技术有限公司 | A kind of non-woven fabrics gauze mask defective vision detecting system and method |
CN107221006A (en) * | 2017-05-11 | 2017-09-29 | 南京邮电大学 | A kind of communication single pipe tower slant detection method based on unmanned plane imaging platform |
WO2018086299A1 (en) * | 2016-11-11 | 2018-05-17 | 广东电网有限责任公司清远供电局 | Image processing-based insulator defect detection method and system |
CN108176608A (en) * | 2017-12-25 | 2018-06-19 | 中国科学院自动化研究所 | Nut defect inspection method and device based on machine vision |
CN108413892A (en) * | 2018-01-30 | 2018-08-17 | 华侨大学 | A kind of diamond fretsaw complete cycle 3 d surface topography detection method and its detection device |
CN108875719A (en) * | 2018-09-25 | 2018-11-23 | 浙江浙能兴源节能科技有限公司 | Air cooler dust stratification state perception system and calculation method based on deep learning and infrared image identification |
CN108960183A (en) * | 2018-07-19 | 2018-12-07 | 北京航空航天大学 | A kind of bend target identification system and method based on Multi-sensor Fusion |
WO2019120011A1 (en) * | 2017-12-22 | 2019-06-27 | 杭州萤石软件有限公司 | Target detection method and apparatus |
CN111047588A (en) * | 2019-12-26 | 2020-04-21 | 电子科技大学 | Imaging measurement method for size of shaft type small part |
CN112135511A (en) * | 2020-09-28 | 2020-12-25 | 怀化建南机器厂有限公司 | PCB solder paste printing quality inspection method, device and system |
CN112258455A (en) * | 2020-09-28 | 2021-01-22 | 上海工程技术大学 | Detection method for detecting spatial position of part based on monocular vision |
-
2021
- 2021-06-24 CN CN202110707026.XA patent/CN113588654B/en active Active
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0445697A2 (en) * | 1990-03-07 | 1991-09-11 | Fmc Corporation | Component evaluation system |
JP2002230562A (en) * | 2000-11-29 | 2002-08-16 | Omron Corp | Image processing method and device therefor |
JP2004125525A (en) * | 2002-09-30 | 2004-04-22 | Ishikawajima Harima Heavy Ind Co Ltd | Method and apparatus for measuring rectangular parallelepiped |
JP2015178190A (en) * | 2014-03-18 | 2015-10-08 | 株式会社リコー | Image inspection device, image formation system and image inspection method |
CN104568983A (en) * | 2015-01-06 | 2015-04-29 | 浙江工业大学 | Active-omni-directional-vision-based pipeline inside functional defect detection device and detection method |
WO2018086299A1 (en) * | 2016-11-11 | 2018-05-17 | 广东电网有限责任公司清远供电局 | Image processing-based insulator defect detection method and system |
CN107014822A (en) * | 2017-02-28 | 2017-08-04 | 深圳市维图视技术有限公司 | A kind of non-woven fabrics gauze mask defective vision detecting system and method |
CN107221006A (en) * | 2017-05-11 | 2017-09-29 | 南京邮电大学 | A kind of communication single pipe tower slant detection method based on unmanned plane imaging platform |
WO2019120011A1 (en) * | 2017-12-22 | 2019-06-27 | 杭州萤石软件有限公司 | Target detection method and apparatus |
CN108176608A (en) * | 2017-12-25 | 2018-06-19 | 中国科学院自动化研究所 | Nut defect inspection method and device based on machine vision |
CN108413892A (en) * | 2018-01-30 | 2018-08-17 | 华侨大学 | A kind of diamond fretsaw complete cycle 3 d surface topography detection method and its detection device |
CN108960183A (en) * | 2018-07-19 | 2018-12-07 | 北京航空航天大学 | A kind of bend target identification system and method based on Multi-sensor Fusion |
CN108875719A (en) * | 2018-09-25 | 2018-11-23 | 浙江浙能兴源节能科技有限公司 | Air cooler dust stratification state perception system and calculation method based on deep learning and infrared image identification |
CN111047588A (en) * | 2019-12-26 | 2020-04-21 | 电子科技大学 | Imaging measurement method for size of shaft type small part |
CN112135511A (en) * | 2020-09-28 | 2020-12-25 | 怀化建南机器厂有限公司 | PCB solder paste printing quality inspection method, device and system |
CN112258455A (en) * | 2020-09-28 | 2021-01-22 | 上海工程技术大学 | Detection method for detecting spatial position of part based on monocular vision |
Non-Patent Citations (3)
Title |
---|
倒角类冲压零件轮廓缺陷视觉检测;陈海永等;计算机测量与控制(第07期);第41-46页 * |
基于机器视觉的轴承内外圈尺寸检测及分类;范帅等;自动化仪表;第37卷(第11期);第77-80、87页 * |
数字图像处理在顶点识别中的应用研究;向光蓉;控制工程;第10卷(第1期);第94-96页 * |
Also Published As
Publication number | Publication date |
---|---|
CN113588654A (en) | 2021-11-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107798326B (en) | Contour vision detection method | |
CN109900711A (en) | Workpiece, defect detection method based on machine vision | |
CN110503638B (en) | Spiral adhesive quality online detection method | |
CN109523505B (en) | Method for detecting pattern defects on surface of ceramic tile based on machine vision | |
CN110345877B (en) | Method for measuring aperture and pitch of tube plate | |
CN113689415A (en) | Steel pipe wall thickness online detection method based on machine vision | |
CN117649404A (en) | Medicine packaging box quality detection method and system based on image data analysis | |
CN111667470A (en) | Industrial pipeline flaw detection inner wall detection method based on digital image | |
CN114549408A (en) | Position size comparison method based on graphic image | |
CN110554054B (en) | Three-dimensional blade breakage detection system of mechanically-clamped indexable turning tool | |
CN114219802B (en) | Skin connecting hole position detection method based on image processing | |
CN116402792A (en) | Space hole site butt joint method based on three-dimensional point cloud | |
CN116399888A (en) | Method and device for detecting welding spot hollows based on chip resistor | |
CN113588654B (en) | Three-dimensional visual detection method for engine heat exchanger interface | |
CN113762427A (en) | Feeding abnormity detection method in industrial automation detection scene | |
CN113705564A (en) | Pointer type instrument identification reading method | |
CN113592953B (en) | Binocular non-cooperative target pose measurement method based on feature point set | |
CN111539951A (en) | Visual detection method for outline size of ceramic grinding wheel head | |
CN114966238A (en) | Automatic detection and alignment method for antenna phase center | |
CN114963981A (en) | Monocular vision-based cylindrical part butt joint non-contact measurement method | |
CN115578310A (en) | Binocular vision detection method and system for refractory bricks | |
CN114354491A (en) | DCB ceramic substrate defect detection method based on machine vision | |
CN113808150A (en) | Novel edge detection method capable of self-adaptive repairing | |
CN109087278B (en) | Condom front and back recognition method based on improved Canny operator | |
CN112782176A (en) | Product appearance detection method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |