CN112465894B - Method and device for fitting inner diameter and outer diameter of ring, electronic equipment and storage medium - Google Patents
Method and device for fitting inner diameter and outer diameter of ring, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112465894B CN112465894B CN202011342413.XA CN202011342413A CN112465894B CN 112465894 B CN112465894 B CN 112465894B CN 202011342413 A CN202011342413 A CN 202011342413A CN 112465894 B CN112465894 B CN 112465894B
- Authority
- CN
- China
- Prior art keywords
- sampling
- point
- circular ring
- image
- fitting
- 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
- 238000000034 method Methods 0.000 title claims abstract description 98
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000005070 sampling Methods 0.000 claims abstract description 356
- 230000008569 process Effects 0.000 claims description 49
- 238000004422 calculation algorithm Methods 0.000 claims description 23
- 238000007781 pre-processing Methods 0.000 claims description 22
- 238000001914 filtration Methods 0.000 claims description 13
- 230000009467 reduction Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 5
- 230000005855 radiation Effects 0.000 abstract description 24
- 238000012545 processing Methods 0.000 abstract description 6
- 238000009826 distribution Methods 0.000 abstract description 5
- 230000002285 radioactive effect Effects 0.000 description 16
- 238000001514 detection method Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 8
- 230000009466 transformation Effects 0.000 description 8
- 230000000694 effects Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000009776 industrial production Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000005305 interferometry Methods 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—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
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Abstract
The application provides a ring inside and outside diameter fitting method, a ring outside diameter fitting device, electronic equipment and a storage medium, and relates to the technical field of image processing. The method comprises the following steps: determining the boundary of the circular ring from the circular ring image; sampling at least one of horizontal sampling, vertical sampling and radiation sampling on the points of the inner diameter and the outer diameter of the circular ring based on the boundary to obtain a sampling result; and carrying out circle fitting based on the sampling result, and taking the fitting result of the circle as the fitting result of the inner diameter and the outer diameter of the circular ring. According to the method, discrete sampling of data points is carried out through horizontal sampling, vertical sampling and/or radiation sampling, robustness and anti-interference capability are greatly improved, then inner and outer diameter fitting of a fused sample point set is carried out according to sampling results, the data point set is more in accordance with actual data distribution, and fitting efficiency and accuracy are higher.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a method and a device for fitting inner and outer diameters of a circular ring, electronic equipment and a storage medium.
Background
The existing fitting method of the part circle is used for detecting the circle through Hough transformation, the Hough transformation has strong anti-interference capability, but the detection stability is still insufficient when facing to complex workpieces, such as blank steel pipe fittings. Moreover, the Hough transformation can detect that more parameters need to be debugged, and when the Hough transformation faces to a more complex scene, the non-target result is filtered by repeatedly debugging a plurality of parameters, and target circles are filtered together in many cases.
Therefore, the fitting method of the existing part circle has insufficient anti-interference capability when facing a complex environment, and has very high time complexity, especially when facing high-resolution industrial pictures.
Disclosure of Invention
In view of this, an objective of the embodiments of the present application is to provide a method, an apparatus, an electronic device, and a storage medium for fitting inner and outer diameters of a ring, so as to solve the problems of insufficient anti-interference capability when facing a complex environment and insufficient anti-interference capability when facing a complex environment in the prior art.
The embodiment of the application provides a circular ring inside and outside diameter fitting method, which comprises the following steps: determining the boundary of the circular ring from the circular ring image; sampling at least one of horizontal sampling, vertical sampling and radiation sampling on the points of the inner diameter and the outer diameter of the circular ring based on the boundary to obtain a sampling result; and carrying out circle fitting based on the sampling result, and taking the fitting result of the circle as the fitting result of the inner diameter and the outer diameter of the circular ring.
In the implementation manner, discrete sampling of data points is performed through horizontal sampling, vertical sampling and/or radiation sampling, robustness and anti-interference capability are greatly improved, then inner and outer diameter fitting of a fused sample point set is performed according to sampling results, the data point set is more in line with actual data distribution, debugging parameters are required to be less than those in the prior art, and fitting efficiency and accuracy are higher.
Optionally, before the determining the boundary of the ring from the ring image, the method further comprises: acquiring a shooting image of the circular ring; removing irrelevant image parts irrelevant to the fitting of the inner diameter and the outer diameter in the photographed image; intercepting a region-of-interest image containing the circular ring from the photographed image from which the irrelevant image part is removed; and preprocessing the interest domain image, wherein the image output by preprocessing is used as the ring image, and the preprocessing comprises at least one of filtering, graying and binarization.
In the implementation manner, the ring image with fewer interference images is obtained through removing the image part irrelevant to the ring in the shot image and extracting the interest domain image, so that the interference of sundries can be eliminated, and the subsequent fitting precision is improved.
Optionally, the removing the irrelevant image portion of the captured image that is irrelevant to the fitting of the inner diameter and the outer diameter includes: acquiring a background image of the circular ring under the same shooting environment of the shooting image; the captured image is subtracted from the background image to remove the extraneous image portion.
In the implementation mode, the irrelevant image part is removed by simply subtracting the shot image and the background image, so that the calculation complexity is reduced, and the overall efficiency of inside and outside diameter fitting is improved.
Optionally, the step of vertically sampling includes: sequentially sampling the circular ring for a plurality of times based on a specified horizontal direction, wherein the vertical points vertically downwards from the upper boundary or vertically upwards from the lower boundary are sampled for a plurality of times, the sampling of part of the vertical points is overlapped with the inner diameter and the outer diameter of the circular ring for two times respectively, and the sampling step length is reduced from small to large along with the reduction of the included angle in the diameter direction formed by the sampling direction and the sampling points; when the value of the point obtained by each vertical point sampling is smaller than the maximum value of the binarization graph, determining the point obtained by the point sampling as the point outside the circular ring; determining the first point and the last point which are larger than the maximum value of the binarization graph in each vertical point sampling process as outer diameter points; and determining the first point and the last point which are smaller than the maximum value of the binarization graph in each vertical point sampling process as inner diameter points.
In the implementation mode, the sampling process of vertical sampling and the calculation for determining the inner diameter and outer diameter point sets are simple, the inner diameter and outer diameter fitting efficiency is improved, meanwhile, the sampling step length changes along with the reduction of the included angle between the sampling direction and the diameter direction formed by the sampling points, the density of the obtained sampling points is basically the same by adaptive sampling, and the robustness of a fitting algorithm is higher.
Optionally, the step of horizontally sampling includes: sequentially sampling the circular ring from the left boundary to the right or from the right boundary to the left for a plurality of times based on the specified vertical direction, wherein each time of horizontal point sampling is overlapped with the inner diameter and the outer diameter of the circular ring respectively, and the sampling step length is reduced from small to large along with the reduction of the included angle in the diameter direction formed by the sampling direction and the sampling points; determining that the point obtained by sampling the point is a point outside the circular ring when the value of the point obtained by sampling the horizontal point is smaller than the maximum value of the binary image; when the horizontal point sampling direction points to the circle center of the circular ring, determining that the first point larger than the maximum value of the binary image is an outer diameter point and the last point is an inner diameter point in each horizontal point sampling process; when the horizontal point sampling direction is opposite to the circle center of the circular ring, determining that the first point larger than the maximum value of the binary image in each horizontal point sampling process is an inner diameter point, and the last point is an outer diameter point.
In the implementation mode, the sampling process of horizontal sampling and the calculation for determining the inner diameter and the outer diameter point sets are simple, the fitting efficiency of the inner diameter and the outer diameter is improved, meanwhile, the sampling step length changes along with the sampling direction and the proportion of the circular ring in the sampling direction, the density of the obtained sampling points is basically the same by adaptive sampling, and the robustness of a fitting algorithm is higher.
Optionally, the step of radiation sampling includes: generating a sampling ray at each interval angle theta by taking the midpoint of a designated boundary in the boundaries as the center, wherein theta is an included angle with the horizontal coordinate axis of the circular ring image,sampling each sampling ray by a ray point with a fixed sampling step length based on the ray direction; when the value of the point obtained by sampling each time of radioactive points is smaller than the maximum value of the binarization graph, determining the point obtained by sampling the point as the point outside the circular ring; when the direction of the radiation point sampling points to the circle center of the circular ring, determining that the first point which is larger than the maximum value of the binary image in each radiation point sampling process is an outer diameter point, and the last point is an inner diameter point; when the direction of the radioactive point sampling is away from the circle center of the circular ring, determining that the first point which is larger than the maximum value of the binary image in each radioactive point sampling process is an inner diameter point, and the last point is an outer diameter point.
In the implementation mode, the sampling process of radiation sampling and the calculation for determining the inner and outer diameter point sets are simple, and the efficiency of inner and outer diameter fitting is improved.
Optionally, the fitting of the circle based on the sampling result includes: and fitting a circle to the sampling result by adopting a random sampling coincidence algorithm and a least square method.
In the implementation mode, the sampling results are subjected to circle fitting by adopting a random sampling coincidence algorithm and a least square method, the sampling results obtained in three sampling modes of horizontal sampling, vertical sampling and radiation sampling can be fused, and then the circle fitting is performed, so that the method has higher robustness and precision.
The embodiment of the application also provides a device for fitting the inner diameter and the outer diameter of the circular ring, which comprises: the boundary determining module is used for determining the boundary of the circular ring from the circular ring image; the sampling module is used for carrying out at least one of horizontal sampling, vertical sampling and radiation sampling on the points of the inner diameter and the outer diameter of the circular ring based on the boundary to obtain a sampling result; and the fitting module is used for performing circle fitting based on the sampling result, and taking the fitting result of the circle as the fitting result of the inner diameter and the outer diameter fitting of the circular ring.
In the implementation manner, discrete sampling of data points is performed through horizontal sampling, vertical sampling and/or radiation sampling, robustness and anti-interference capability are greatly improved, then inner and outer diameter fitting of a fused sample point set is performed according to sampling results, the data point set is more in line with actual data distribution, debugging parameters are required to be less than those in the prior art, and fitting efficiency and accuracy are higher.
Optionally, the ring inside and outside diameter fitting device further includes: the preprocessing module is used for acquiring a shooting image of the circular ring; removing irrelevant image parts irrelevant to the fitting of the inner diameter and the outer diameter in the photographed image; intercepting a region-of-interest image containing the circular ring from the photographed image from which the irrelevant image part is removed; and preprocessing the interest domain image, wherein the image output by preprocessing is used as the ring image, and the preprocessing comprises at least one of filtering, graying and binarization.
In the implementation manner, the ring image with fewer interference images is obtained through removing the image part irrelevant to the ring in the shot image and extracting the interest domain image, so that the interference of sundries can be eliminated, and the subsequent fitting precision is improved.
Optionally, the preprocessing module is specifically configured to: acquiring a background image of the circular ring under the same shooting environment of the shooting image; the captured image is subtracted from the background image to remove the extraneous image portion.
In the implementation mode, the irrelevant image part is removed by simply subtracting the shot image and the background image, so that the calculation complexity is reduced, and the overall efficiency of inside and outside diameter fitting is improved.
Optionally, the sampling module is specifically configured to: sequentially sampling the circular ring for a plurality of times based on a specified horizontal direction, wherein the vertical points vertically downwards from the upper boundary or vertically upwards from the lower boundary are sampled for a plurality of times, the sampling of part of the vertical points is overlapped with the inner diameter and the outer diameter of the circular ring for two times respectively, and the sampling step length is reduced from small to large along with the reduction of the included angle in the diameter direction formed by the sampling direction and the sampling points; when the value of the point obtained by each vertical point sampling is smaller than the maximum value of the binarization graph, determining the point obtained by the point sampling as the point outside the circular ring; determining the first point and the last point which are larger than the maximum value of the binarization graph in each vertical point sampling process as outer diameter points; and determining the first point and the last point which are smaller than the maximum value of the binarization graph in each vertical point sampling process as inner diameter points.
In the implementation mode, the sampling process of vertical sampling and the calculation for determining the inner diameter and outer diameter point sets are simple, the inner diameter and outer diameter fitting efficiency is improved, meanwhile, the sampling step length changes along with the reduction of the included angle between the sampling direction and the diameter direction formed by the sampling points, the density of the obtained sampling points is basically the same by adaptive sampling, and the robustness of a fitting algorithm is higher.
Optionally, the sampling module is specifically configured to: sequentially sampling the circular ring from the left boundary to the right or from the right boundary to the left for a plurality of times based on the specified vertical direction, wherein each time of horizontal point sampling is overlapped with the inner diameter and the outer diameter of the circular ring respectively, and the sampling step length is reduced from small to large along with the reduction of the included angle in the diameter direction formed by the sampling direction and the sampling points; determining that the point obtained by sampling the point is a point outside the circular ring when the value of the point obtained by sampling the horizontal point is smaller than the maximum value of the binary image; when the horizontal point sampling direction points to the circle center of the circular ring, determining that the first point larger than the maximum value of the binary image is an outer diameter point and the last point is an inner diameter point in each horizontal point sampling process; when the horizontal point sampling direction is opposite to the circle center of the circular ring, determining that the first point larger than the maximum value of the binary image in each horizontal point sampling process is an inner diameter point, and the last point is an outer diameter point.
In the implementation mode, the sampling process of horizontal sampling and the calculation for determining the inner diameter and the outer diameter point sets are simple, the fitting efficiency of the inner diameter and the outer diameter is improved, meanwhile, the sampling step length changes along with the sampling direction and the proportion of the circular ring in the sampling direction, the density of the obtained sampling points is basically the same by adaptive sampling, and the robustness of a fitting algorithm is higher.
Optionally, the sampling module is specifically configured to: generating a sampling ray at each interval angle theta by taking the midpoint of a designated boundary in the boundaries as the center, wherein theta is an included angle with the horizontal coordinate axis of the circular ring image,sampling each sampling ray by a ray point with a fixed sampling step length based on the ray direction; when the value of the point obtained by sampling each time of radioactive points is smaller than the maximum value of the binarization graph, determining the point obtained by sampling the point as the point outside the circular ring; when the direction of the radiation point sampling points to the circle center of the circular ring, determining that the first point which is larger than the maximum value of the binary image in each radiation point sampling process is an outer diameter point, and the last point is an inner diameter point; when the direction of the radioactive point sampling is away from the circle center of the circular ring, determining that the first point which is larger than the maximum value of the binary image in each radioactive point sampling process is an inner diameter point, and the last point is an outer diameter point.
In the implementation mode, the sampling process of radiation sampling and the calculation for determining the inner and outer diameter point sets are simple, and the efficiency of inner and outer diameter fitting is improved.
Optionally, the fitting module is specifically configured to: and fitting a circle to the sampling result by adopting a random sampling coincidence algorithm and a least square method.
In the implementation mode, the sampling results are subjected to circle fitting by adopting a random sampling coincidence algorithm and a least square method, the sampling results obtained in three sampling modes of horizontal sampling, vertical sampling and radiation sampling can be fused, and then the circle fitting is performed, so that the method has higher robustness and precision.
The embodiment of the application also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores program instructions, and the processor executes the steps in any implementation mode when reading and running the program instructions.
Embodiments of the present application also provide a readable storage medium having stored therein computer program instructions which, when read and executed by a processor, perform the steps of any of the above implementations.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for fitting inner and outer diameters of a ring according to an embodiment of the present application.
Fig. 2 is a schematic flow chart of a preprocessing step provided in an embodiment of the present application.
Fig. 3 is a schematic diagram of a sampling manner according to an embodiment of the present application.
Fig. 4 is a schematic block diagram of a circular ring inside and outside diameter fitting device according to an embodiment of the present application.
Icon: 20-fitting the inner diameter and the outer diameter of the circular ring; 21-a boundary determination module; a 22-sampling module; 23-fitting module.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
The applicant researches find that in the actual production environment of a factory, parts are not shielded by original mechanisms of a production line or designed blocking mechanisms and the like in many cases, the existing fitting method of part circles usually carries out circle detection through Hough transformation, the Hough transformation has strong anti-interference capability, but the detection stability is still insufficient when the parts are faced with more complex workpieces, the non-target results of multiple parameter filtering are required to be repeatedly debugged when the shielded parts are faced with more complex scenes, and target circles are filtered out together in many cases, so that the fitting efficiency, precision and robustness are poor.
In order to solve the above-mentioned problems in the prior art, an embodiment of the present application provides a method for fitting an inner diameter and an outer diameter of a ring, please refer to fig. 1, and fig. 1 is a flow chart of the method for fitting an inner diameter and an outer diameter of a ring provided in the embodiment of the present application.
Step S12: the boundary of the circle is determined from the circle image.
It should be understood that, in general, when image processing is performed, the original image obtained by capturing is preprocessed at the beginning, please refer to fig. 2, fig. 2 is a schematic flow chart of a preprocessing step provided in the embodiment of the present application, and the preprocessing step in this embodiment may be as follows:
step S111: and acquiring a shooting image of the circular ring.
In this embodiment, taking a ring as an example of a part in an industrial production line, since the position and the scene where the target part appears in the industrial production line are fixed, a camera for photographing the ring may be fixed at a specific position, and photographing is performed at a fixed position where the ring stays or passes.
Optionally, image parameters such as resolution of the photographed image can be flexibly adjusted according to specific fitting precision requirements.
Step S112: and removing irrelevant image parts irrelevant to the fitting of the inner diameter and the outer diameter in the shot image.
Because the position and the scene that target parts appear in the industrial production line are fixed, can remove "debris" irrelevant with the part detection according to the scene background image that does not have the part, for example supporting mechanism and workstation etc. remove impurity can greatly promote stability and the precision of fitting.
Specifically, the specific manner of removing the extraneous image portion can be as follows: acquiring a background image of a ring in the same shooting environment of a shooting image; the captured image is subtracted from the background image to remove extraneous image portions.
Optionally, the background image is generally obtained by taking the ring part off under the same viewing condition as the same camera that obtains the captured image, so as to ensure consistency of the captured image and the background image.
The subtraction between the images, that is, the subtraction operation is performed on the corresponding pixels between the two images, and the difference information of the two images can be detected by the image subtraction. There are many techniques for implementing image subtraction, such as speckle interferometry, holographic filtering, interference filtering, and grating encoding, and the techniques for implementing image subtraction in this embodiment may be flexibly selected according to the specific requirements of fitting.
Step S113: and intercepting the interest area image containing the circular ring in the photographed image with the irrelevant image parts removed.
The image of the interest domain is intercepted from the shot image based on the fact that the appearance position of the part is fixed, and the picture part contained in the image of the interest domain almost only contains the part of the circular ring part, so that the follow-up processing on the image of the interest domain can avoid the interference of other images, the calculated amount of the image processing is reduced, and the fitting efficiency can be greatly improved.
Step S114: preprocessing the interest domain image, wherein the image output by the preprocessing is used as a circular ring image, and the preprocessing comprises at least one of filtering, graying and binarization.
Optionally, the filtering in this embodiment may be mean shift filtering, where mean shift filtering may perform flat filtering on a color level, and may neutralize colors with similar color distribution, smooth color details, and areas with smaller corrosion area, and most importantly, may better preserve edge information.
In image processing, three components (R: red, G: green, B: blue), that is, three primary colors of Red, green, and Blue are used to represent a true color, the values of the R component, the G component, and the B component are all 0-255, and graying is that when an image is converted into r=g=b, the color represents an image of a gray color, where the value of r=g=b is called a gray value, so that only one byte is needed for each pixel of the gray image to store the gray value (also called intensity value, brightness value), and the gray range is 0-255.
The gray image requires only one byte per pixel to store the gray value, and the gray image for display is typically stored with a non-linear scale of 8 bits per sample pixel, which can be 256 gray levels. Such precision has just been able to avoid visible banding distortion, and is very easy to program or image process while reducing the amount of data.
Image binarization (Image Binarization) is a process of setting the gray value of a pixel point on an image to 0 or 255, that is, displaying a clear black-and-white effect on the whole image. The binarization of the image greatly reduces the data volume in the image, so that the outline of the target can be highlighted, and the identification of the inner diameter and the outer diameter of the subsequent circular ring is more beneficial.
Alternatively, the binarization algorithm in this embodiment may be OTSU (oxford algorithm), kittler algorithm, or other binarization algorithm suitable for this embodiment.
Since the subsequent sampling of points on the inner and outer diameters of the ring is performed, before that, the boundary of the ring part needs to be determined, this embodiment can use contour detection to determine the boundary.
Contour detection refers to the process of extracting the contour of a target by adopting a certain technology and method in a digital image containing the target and the background, ignoring the textures in the background and the target and the influence of noise interference. The existing contour detection methods are two types, one is to detect the target contour by using a traditional edge detection operator, and the other is to extract a mathematical model which can be used from the human visual system to complete the target contour detection. Optionally, in this embodiment, a suitable contour detection method may be selected according to the characteristics of the inner and outer diameter fitting.
Step S14: and (3) performing at least one of horizontal sampling, vertical sampling and radiation sampling on the points of the inner diameter and the outer diameter of the circular ring based on the boundary to obtain a sampling result.
For horizontal sampling, vertical sampling and radiation sampling, please refer to fig. 3, fig. 3 is a schematic diagram of a sampling manner provided in an embodiment of the present application, wherein the schematic diagram of vertical sampling, horizontal sampling and radiation sampling are sequentially performed from left to right, a dashed frame is a boundary, and a straight solid line is a sampling line formed by a point set of each sampling along a straight line.
The essential difference between vertical sampling and horizontal sampling is not that the sampling direction is vertical or horizontal, but that the direction of the sampling line is determined according to the direction relation between the sampling line and the circular ring, the direction of the sampling line can point to opposite boundaries along any boundary, the inner diameter, the outer diameter and the inner diameter of the circular ring contain areas which represent the circular ring, the condition that part of the sampling line passes through the circular ring twice is regarded as vertical sampling, and the condition that the sampling line passes through the circular ring once is regarded as horizontal sampling. It should be understood that vertical sampling and horizontal sampling are just one distinguishing designation for the manner of sampling, and that the designations of the two may be interchanged or changed to other designations.
For example, specific steps of vertical sampling may include:
(1) The rings are sampled sequentially a number of times from vertical points vertically down from the upper boundary or vertically up from the lower boundary based on a specified horizontal direction order.
In the process of sampling multiple vertical points, the track of sampling partial vertical points is overlapped with the inner diameter and the outer diameter of the circular ring twice respectively.
Optionally, multiple vertical point samples are taken from one boundary of the object to the opposite boundary, but since the smaller the included angle between the sampling direction and the sampling point in the diameter direction is when each sampling is closer to a certain boundary of the object, the easier the sampling to the point is, in order to make the sampled points more uniformly distributed on the inner and outer diameters, so as to increase the robustness of subsequent fitting, the sampling step size is set to be from small to large along with the decrease of the included angle between the sampling direction and the sampling point in the diameter direction. For example, the initial step size is set to a and the step size increment is set to α.
(2) And when the value of the point obtained by each vertical point sampling is smaller than the maximum value of the binarization graph, determining that the point obtained by the point sampling is a point outside the circular ring.
In this embodiment, the pixel point exceeding the maximum value of the binary image is the pixel point of the ring in the binary image, the gray value of the ring in the binary image is 255, and the gray value of the other part is 0, and the maximum value of the binary image can be set to values such as 254, 250, etc.
(3) And determining the first point and the last point which are larger than the maximum value of the binarization graph in each vertical point sampling process as outer diameter points.
(4) And determining the first point and the last point which are smaller than the maximum value of the binarization graph in each vertical point sampling process as inner diameter points.
For example, specific steps of horizontal sampling may include:
(1) The circles are sampled sequentially from the left boundary horizontally to the right or from the right boundary horizontally to the left horizontal point a plurality of times based on the specified vertical direction order.
In the process of multiple horizontal point sampling, each horizontal point sampling is respectively overlapped with the inner diameter and the outer diameter of the circular ring once.
The horizontal point sampling is carried out for a plurality of times from one boundary to the opposite boundary of the object, but because the smaller the included angle between the sampling direction and the diameter direction formed by the sampling point is when the sampling point is closer to the boundary of the object in the process from one boundary to the opposite boundary, the sampling point is easier to sample, in order to ensure that the sampled points are more uniformly distributed on the inner diameter and the outer diameter so as to increase the robustness of subsequent fitting, the sampling step length is set to be from small to large along with the reduction of the included angle between the sampling direction and the diameter direction formed by the sampling point, and from large to small after the horizontal point is sampled to the circle center of the circular ring. For example, the initial step size is set to b, the step size increment is set to beta, and the farther the beta is from the center of the circular ring at the horizontal point, the smaller the position is.
(2) And determining that the point obtained by the point sampling is a point outside the circular ring when the value of the point obtained by each time of horizontal point sampling is smaller than the maximum value of the binary image.
(3) When the horizontal point sampling direction points to the circle center of the circular ring, determining that the first point larger than the maximum value of the binary image in each horizontal point sampling process is an outer diameter point, and the last point is an inner diameter point.
(4) When the horizontal point sampling direction is away from the circle center of the circular ring, determining that the first point larger than the maximum value of the binary image in each horizontal point sampling process is an inner diameter point, and the last point is an outer diameter point.
For example, specific steps of radiation sampling may include:
(1) Generating a sampling ray at each interval angle theta by taking the midpoint of a designated boundary in the boundaries as the center, wherein theta is an included angle with the horizontal coordinate axis of the circular ring image,
(2) And sampling the ray points with fixed sampling step sizes on each sampling ray based on the ray direction.
(3) And when the value of the point obtained by each time of radioactive point sampling is smaller than the maximum value of the binarization graph, determining that the point obtained by the point sampling is a point outside the circular ring.
(4) When the direction of sampling the radioactive points to the circle center of the circular ring, determining the first point which is larger than the maximum value of the binary image as an outer diameter point and the last point as an inner diameter point in each radioactive point sampling process.
(5) When the direction of the sampling of the radioactive points is away from the circle center of the circular ring, determining that the first point which is larger than the maximum value of the binary image in each sampling process of the radioactive points is an inner diameter point, and the last point is an outer diameter point.
It should be noted that the sampling of the radial point to a uniform inside and outside diameter point is only required to have a fixed step size (Δθ).
Step S16: and carrying out circle fitting based on the sampling result, and taking the fitting result of the circle as the fitting result of the inner diameter and the outer diameter of the circular ring.
Alternatively, the above-described sampling result may be a combination of any two or three of horizontal sampling, vertical sampling, and radiation sampling. Specifically, the inner diameter points and the outer diameter points obtained by three sampling can be randomly sampled and then fused or combined and then subjected to circle fitting, and the fusion of the three discrete point sampling can improve the robustness of a later algorithm. The effect of fitting the circle by independently using the vertical sampling or the horizontal sampling does not combine the horizontal sampling point and the vertical sampling point together, so that the fitting of the circle is more robust and has higher precision, the effect of radiation sampling and the effect of horizontal and vertical combination are basically the same, and therefore, the results of three sampling modes can be combined in any mode.
Alternatively, the present embodiment may use a random sample consensus algorithm and a least squares method to fit a circle to the sampling results.
A random sample consensus algorithm (RANdomSAmple Consensus, RANSAC) iteratively estimates parameters of a mathematical model from a set of observed data containing outliers. RANSAC is a non-deterministic algorithm that produces a reasonable result at some probability in the sense that more iterations increase this probability. The random sample consensus algorithm assumes that the data contains both correct data and anomalous data (otherwise known as noise). Correct data is denoted as inner points (inliers), and abnormal data is denoted as outer points (outliers). At the same time the RANSAC algorithm also assumes that, given a correct set of data, there is a model that can be calculated to fit these data.
The core idea of the algorithm is randomness and supposition, wherein the randomness refers to that partial data is randomly sampled in a total sample to fit a data model, and the randomness simulation can approximately obtain a correct result according to a large number law. The supposition means that samples selected at random are all correct data, so that a model meeting the sampling data can be obtained, then the model is used for calculating the interior points meeting the model in the whole data set, finally the model subjected to sampling fitting at this time is evaluated by utilizing the interior point rate (all points are removed by the interior points meeting the sampling model at one time), and finally the model with the highest interior point rate or the highest interior point rate before reaching the maximum iteration is returned.
In the scene of the inside and outside diameter fitting, we use the RANSAC algorithm to perform fusion sampling of sampling results, and add least square to perform circular fitting on sampling points.
Least squares is responsible for fitting a circle from randomly sampled points, and is derived from the formula of the circle:
wherein (a, b) is the center of a circle, r is the radius of the circle, namely the parameters to be obtained, x and y are the abscissa and the ordinate of the known sampling point, the unknown parameters are calculated by using a linear least square method, and the above formula is simplified to obtain:
Dx+Ey+F＝-(x 2 +y 2 )
wherein,the linear least squares can be used for directly calculating D, E and F, and indirectly calculating a, b and r. Finally, model parameters conforming to the subset are calculated in the randomly selected samples.
Optionally, the embodiment may further return to the optimal model when the internal point rate of the model parameter is greater than a preset threshold or reaches the maximum iteration number, so as to implement fitting of the ring.
The circular ring inside and outside diameter fitting method provided by the embodiment achieves very high precision and effect in the shielded steel pipe inside and outside diameter fitting experiment, the inside and outside diameter fitting time of the algorithm on a picture with the resolution of 3472A 3648 is 230ms, and the Hough transformation time under the same resolution is more than 800ms. Meanwhile, the robustness and the anti-interference capability are greatly improved, and particularly when oil stains or rust spots exist on parts, the circular ring inside and outside diameter fitting method provided by the embodiment has higher stability than Hough transformation. The time consumed by the hough transform under the same resolution is far longer than that of the circular ring inside and outside diameter fitting method provided by the embodiment, and the result obtained by the hough transform needs further filtering. In addition, the circular ring inside and outside diameter fitting method provided by the embodiment has higher precision, and can reach the precision with the error less than 10 pixels.
In order to match the above-mentioned fitting method for the inner diameter and the outer diameter of the ring provided in this embodiment, the embodiment of the present application further provides a fitting device 20 for the inner diameter and the outer diameter of the ring.
Referring to fig. 4, fig. 4 is a schematic block diagram of an apparatus for fitting inner and outer diameters of a ring according to an embodiment of the present application.
The circular ring inside and outside diameter fitting device 20 includes:
a boundary determining module 21, configured to determine a boundary of the ring from the ring image;
a sampling module 22, configured to sample at least one of a horizontal sampling, a vertical sampling, and a radiation sampling for points of an inner diameter and an outer diameter of the ring based on the boundary, to obtain a sampling result;
and the fitting module 23 is configured to perform fitting of a circle based on the sampling result, and take the fitting result of the circle as the fitting result of the inner diameter and the outer diameter fitting of the circular ring.
Optionally, the ring inside and outside diameter fitting device 20 further includes: the preprocessing module is used for acquiring a shooting image of the circular ring; removing irrelevant image parts irrelevant to fitting of the inner diameter and the outer diameter in the shot image; intercepting a region-of-interest image containing a circular ring from a photographed image from which an irrelevant image part is removed; preprocessing the interest domain image, wherein the image output by the preprocessing is used as a circular ring image, and the preprocessing comprises at least one of filtering, graying and binarization.
Optionally, the preprocessing module is specifically configured to: acquiring a background image of a ring in the same shooting environment of a shooting image; the captured image is subtracted from the background image to remove extraneous image portions.
Optionally, the sampling module 22 is specifically configured to: sequentially sampling the circular ring for a plurality of times based on a specified horizontal direction from an upper boundary vertically downwards or from a lower boundary vertically upwards, wherein part of vertical point sampling is overlapped with the inner diameter and the outer diameter of the circular ring for two times respectively, and the sampling step length is reduced from small to large along with the reduction of a diameter direction included angle formed by the sampling direction and the sampling point; when the value of the point obtained by each vertical point sampling is smaller than the maximum value of the binarization graph, determining that the point obtained by the point sampling is a point outside the circular ring; determining the first point and the last point which are larger than the maximum value of the binarization graph in each vertical point sampling process as outer diameter points; and determining the first point and the last point which are smaller than the maximum value of the binarization graph in each vertical point sampling process as inner diameter points.
Optionally, the sampling module 22 is specifically configured to: sequentially sampling the circular ring from the left boundary to the right or from the right boundary to the left horizontal point for a plurality of times based on the specified vertical direction, wherein each time of horizontal point sampling is overlapped with the inner diameter and the outer diameter of the circular ring respectively, and the sampling step length is reduced from small to large along with the reduction of the included angle of the diameter direction formed by the sampling direction and the sampling point; determining that the point obtained by the point sampling is a point outside the circular ring when the value of the point obtained by each time of horizontal point sampling is smaller than the maximum value of the binary image; when the horizontal point sampling direction points to the circle center of the circular ring, determining that the first point larger than the maximum value of the binarization graph is an outer diameter point and the last point is an inner diameter point in each horizontal point sampling process; when the horizontal point sampling direction is away from the circle center of the circular ring, determining that the first point larger than the maximum value of the binary image in each horizontal point sampling process is an inner diameter point, and the last point is an outer diameter point.
Optionally, the sampling module 22 is specifically configured to: generating a sampling ray at each interval angle theta by taking the midpoint of a designated boundary in the boundaries as the center, wherein theta is an included angle with the horizontal coordinate axis of the circular ring image,sampling each sampling ray by a ray point with a fixed sampling step length based on the ray direction; when the value of the point obtained by sampling the radioactive point is smaller than the maximum value of the binarization graph, determining that the point obtained by sampling the point is a point outside the circular ring; when the sampling direction of the radioactive point points to the circle center of the circular ring, determining that the first point larger than the maximum value of the binary image in each radioactive point sampling process is an outer diameter point, and the last point is an inner diameter point; when the direction of the sampling of the radioactive points is away from the circle center of the circular ring, determining that the first point which is larger than the maximum value of the binary image in each sampling process of the radioactive points is an inner diameter point, and the last point is an outer diameter point.
Optionally, the fitting module 23 is specifically configured to: and (5) fitting a circle to the sampling result by adopting a random sampling coincidence algorithm and a least square method.
The embodiment of the application also provides electronic equipment, which comprises a memory and a processor, wherein the memory stores program instructions, and when the processor reads and runs the program instructions, the processor executes the steps in any one of the method for fitting the inside diameter and the outside diameter of the circular ring provided by the embodiment.
It should be understood that the electronic device may be a personal computer (Personal Computer, PC), tablet computer, smart phone, personal digital assistant (Personal Digital Assistant, PDA), or the like, having a logic computing function.
The embodiment of the application also provides a readable storage medium, wherein the readable storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the steps in the circular ring inside and outside diameter fitting method are executed.
In summary, the method, the device, the electronic device and the storage medium for fitting the inner diameter and the outer diameter of the ring, wherein the method comprises the following steps: determining the boundary of the circular ring from the circular ring image; sampling at least one of horizontal sampling, vertical sampling and radiation sampling on the points of the inner diameter and the outer diameter of the circular ring based on the boundary to obtain a sampling result; and carrying out circle fitting based on the sampling result, and taking the fitting result of the circle as the fitting result of the inner diameter and the outer diameter of the circular ring.
In the implementation manner, discrete sampling of data points is performed through horizontal sampling, vertical sampling and/or radiation sampling, robustness and anti-interference capability are greatly improved, then inner and outer diameter fitting of a fused sample point set is performed according to sampling results, the data point set is more in line with actual data distribution, debugging parameters are required to be less than those in the prior art, and fitting efficiency and accuracy are higher.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus may be implemented in other ways. The apparatus embodiments described above are merely illustrative, for example, block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of devices according to various embodiments of the present application. In this regard, each block in the block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams, and combinations of blocks in the block diagrams, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. The present embodiment therefore also provides a readable storage medium having stored therein computer program instructions which, when read and executed by a processor, perform the steps of any one of the methods of block data storage. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a RanDom Access Memory (RAM), a magnetic disk or an optical disk, or other various media capable of storing program codes.
The foregoing is merely exemplary embodiments of the present application and is not intended to limit the scope of the present application, and various modifications and variations may be suggested to one skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application. It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application.
It should be noted that in this document, terms such as "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
Claims (7)
1. The method for fitting the inner diameter and the outer diameter of the circular ring is characterized by comprising the following steps:
determining the boundary of the circular ring from the circular ring image;
sampling at least one of horizontal sampling and vertical sampling on points of the inner diameter and the outer diameter of the circular ring based on the boundary to obtain a sampling result;
fitting a circle based on the sampling result, and taking the fitting result of the circle as the fitting result of the fitting of the inner diameter and the outer diameter of the circular ring;
wherein the step of vertically sampling comprises:
sequentially sampling the circular ring for a plurality of times based on a specified horizontal direction, wherein the vertical points vertically downwards from the upper boundary or vertically upwards from the lower boundary are sampled for a plurality of times, the sampling of part of the vertical points is overlapped with the inner diameter and the outer diameter of the circular ring for two times respectively, and the sampling step length is reduced from small to large along with the reduction of the included angle in the diameter direction formed by the sampling direction and the sampling points;
when the value of the point obtained by each vertical point sampling is smaller than the maximum value of the binarization graph, determining the point obtained by the point sampling as the point outside the circular ring;
determining the first point and the last point which are larger than the maximum value of the binarization graph in each vertical point sampling process as outer diameter points;
determining the first point and the last point which are smaller than the maximum value of the binarization graph in each vertical point sampling process as inner diameter points;
The step of horizontally sampling includes:
sequentially sampling the circular ring from the left boundary to the right or from the right boundary to the left for a plurality of times based on the specified vertical direction, wherein each time of horizontal point sampling is overlapped with the inner diameter and the outer diameter of the circular ring respectively, and the sampling step length is reduced from small to large along with the reduction of the included angle in the diameter direction formed by the sampling direction and the sampling points;
determining that the point obtained by sampling the point is a point outside the circular ring when the value of the point obtained by sampling the horizontal point is smaller than the maximum value of the binary image;
when the horizontal point sampling direction points to the circle center of the circular ring, determining that the first point larger than the maximum value of the binary image is an outer diameter point and the last point is an inner diameter point in each horizontal point sampling process;
when the horizontal point sampling direction is opposite to the circle center of the circular ring, determining that the first point larger than the maximum value of the binary image in each horizontal point sampling process is an inner diameter point, and the last point is an outer diameter point.
2. The method of claim 1, wherein prior to said determining the boundary of the circle from the circle image, the method further comprises:
acquiring a shooting image of the circular ring;
Removing irrelevant image parts irrelevant to the fitting of the inner diameter and the outer diameter in the photographed image;
intercepting a region-of-interest image containing the circular ring from the photographed image from which the irrelevant image part is removed;
and preprocessing the interest domain image, wherein the image output by preprocessing is used as the ring image, and the preprocessing comprises at least one of filtering, graying and binarization.
3. The method of claim 2, wherein said removing extraneous image portions of the captured image that are not related to the fit of the inner and outer diameters comprises:
acquiring a background image of the circular ring under the same shooting environment of the shooting image;
the captured image is subtracted from the background image to remove the extraneous image portion.
4. The method of claim 1, wherein the fitting of a circle based on the sampling results comprises:
and fitting a circle to the sampling result by adopting a random sampling coincidence algorithm and a least square method.
5. An inside and outside diameter fitting device of a ring, the device comprising:
the boundary determining module is used for determining the boundary of the circular ring from the circular ring image;
The sampling module is used for carrying out at least one of horizontal sampling and vertical sampling on the points of the inner diameter and the outer diameter of the circular ring based on the boundary to obtain a sampling result;
the fitting module is used for performing circle fitting based on the sampling result, and taking the fitting result of the circle as the fitting result of the inner diameter and the outer diameter fitting of the circular ring;
in the process of vertically sampling the points of the inner diameter and the outer diameter of the circular ring based on the boundary to obtain a sampling result, the sampling module is specifically configured to: sequentially sampling the circular ring for a plurality of times based on a specified horizontal direction, wherein the vertical points vertically downwards from the upper boundary or vertically upwards from the lower boundary are sampled for a plurality of times, the sampling of part of the vertical points is overlapped with the inner diameter and the outer diameter of the circular ring for two times respectively, and the sampling step length is reduced from small to large along with the reduction of the included angle in the diameter direction formed by the sampling direction and the sampling points; when the value of the point obtained by each vertical point sampling is smaller than the maximum value of the binarization graph, determining the point obtained by the point sampling as the point outside the circular ring; determining the first point and the last point which are larger than the maximum value of the binarization graph in each vertical point sampling process as outer diameter points; determining the first point and the last point which are smaller than the maximum value of the binarization graph in each vertical point sampling process as inner diameter points;
In the process of horizontally sampling the points of the inner diameter and the outer diameter of the circular ring based on the boundary to obtain a sampling result, the sampling module is specifically configured to: sequentially sampling the circular ring from the left boundary to the right or from the right boundary to the left for a plurality of times based on the specified vertical direction, wherein each time of horizontal point sampling is overlapped with the inner diameter and the outer diameter of the circular ring respectively, and the sampling step length is reduced from small to large along with the reduction of the included angle in the diameter direction formed by the sampling direction and the sampling points; determining that the point obtained by sampling the point is a point outside the circular ring when the value of the point obtained by sampling the horizontal point is smaller than the maximum value of the binary image; when the horizontal point sampling direction points to the circle center of the circular ring, determining that the first point larger than the maximum value of the binary image is an outer diameter point and the last point is an inner diameter point in each horizontal point sampling process; when the horizontal point sampling direction is opposite to the circle center of the circular ring, determining that the first point larger than the maximum value of the binary image in each horizontal point sampling process is an inner diameter point, and the last point is an outer diameter point.
6. An electronic device comprising a memory and a processor, the memory having stored therein program instructions which, when executed by the processor, perform the steps of the method of any of claims 1-4.
7. A readable storage medium, characterized in that the readable storage medium has stored therein computer program instructions which, when executed by a processor, perform the steps of the method according to any of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011342413.XA CN112465894B (en) | 2020-11-25 | 2020-11-25 | Method and device for fitting inner diameter and outer diameter of ring, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011342413.XA CN112465894B (en) | 2020-11-25 | 2020-11-25 | Method and device for fitting inner diameter and outer diameter of ring, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112465894A CN112465894A (en) | 2021-03-09 |
| CN112465894B true CN112465894B (en) | 2024-02-27 |
Family
ID=74808250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011342413.XA Active CN112465894B (en) | 2020-11-25 | 2020-11-25 | Method and device for fitting inner diameter and outer diameter of ring, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112465894B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101144707A (en) * | 2007-09-18 | 2008-03-19 | 湖南大学 | Drinking bottle mouth vision positioning method |
| CN102436659A (en) * | 2011-11-07 | 2012-05-02 | 华中科技大学 | Image analysis method based on yin-yang discrete point sampling model |
| CN102708368A (en) * | 2012-05-04 | 2012-10-03 | 湖南大学 | Method for positioning bottle bodies on production line based on machine vision |
| JP2017010554A (en) * | 2015-06-25 | 2017-01-12 | 株式会社リコー | Curved line detection method and curved line detection device |
| CN106485244A (en) * | 2016-10-12 | 2017-03-08 | 上海联影医疗科技有限公司 | The method of sampling and device |
| CN108876871A (en) * | 2018-06-15 | 2018-11-23 | 广东数相智能科技有限公司 | Image processing method, device and computer readable storage medium based on circle fitting |
| CN109815962A (en) * | 2019-01-17 | 2019-05-28 | 南京信息工程大学 | A method of the green plain cyclic structure of identification ocean eddy marginal convolution |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2572756B (en) * | 2018-04-05 | 2020-05-06 | Imagination Tech Ltd | Sampling for feature detection |
| CN108648201A (en) * | 2018-05-14 | 2018-10-12 | 京东方科技集团股份有限公司 | Pupil positioning method and device, storage medium, electronic equipment |
-
2020
- 2020-11-25 CN CN202011342413.XA patent/CN112465894B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101144707A (en) * | 2007-09-18 | 2008-03-19 | 湖南大学 | Drinking bottle mouth vision positioning method |
| CN102436659A (en) * | 2011-11-07 | 2012-05-02 | 华中科技大学 | Image analysis method based on yin-yang discrete point sampling model |
| CN102708368A (en) * | 2012-05-04 | 2012-10-03 | 湖南大学 | Method for positioning bottle bodies on production line based on machine vision |
| JP2017010554A (en) * | 2015-06-25 | 2017-01-12 | 株式会社リコー | Curved line detection method and curved line detection device |
| CN106485244A (en) * | 2016-10-12 | 2017-03-08 | 上海联影医疗科技有限公司 | The method of sampling and device |
| CN108876871A (en) * | 2018-06-15 | 2018-11-23 | 广东数相智能科技有限公司 | Image processing method, device and computer readable storage medium based on circle fitting |
| CN109815962A (en) * | 2019-01-17 | 2019-05-28 | 南京信息工程大学 | A method of the green plain cyclic structure of identification ocean eddy marginal convolution |
Non-Patent Citations (1)
| Title |
|---|
| 高速自动化灌装线上视觉检验系统研究;国新毅;《中国优秀硕士学位论文全文数据库信息科技辑》(第2010年第05期期);第4章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112465894A (en) | 2021-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dellinger et al. | SAR-SIFT: a SIFT-like algorithm for SAR images | |
| Oakley et al. | Correction of simple contrast loss in color images | |
| EP3115772A1 (en) | Vehicle checking method and system | |
| CN108288264B (en) | Wide-angle camera module contamination testing method | |
| CN110580481B (en) | Light field image key position detection method based on EPI | |
| CN113077459B (en) | Image definition detection method and device, electronic equipment and storage medium | |
| CN113989313A (en) | Edge detection method and system based on image multidimensional analysis | |
| JP2009544090A (en) | Image processing for change detection | |
| CN109447902B (en) | Image stitching method, device, storage medium and equipment | |
| CN114998328A (en) | Workpiece spraying defect detection method and system based on machine vision and readable storage medium | |
| CN111967345B (en) | Method for judging shielding state of camera in real time | |
| CN113298776A (en) | Method for detecting appearance defects of metal closed water pump impeller | |
| Hurník et al. | Circular coded target system for industrial applications | |
| CN112396617A (en) | Anti-interference method of instrument visual reading monitoring system | |
| CN112465894B (en) | Method and device for fitting inner diameter and outer diameter of ring, electronic equipment and storage medium | |
| CN113674220A (en) | Image difference detection method, detection device and storage medium | |
| JP6958743B2 (en) | Image processing device, image processing method and image processing program | |
| CN109741306A (en) | Image processing method applied to hazardous chemical storehouse stacking | |
| CN112819935A (en) | Method for realizing three-dimensional reconstruction of workpiece based on binocular stereo vision | |
| CN112541853A (en) | Data processing method, device and equipment | |
| CN113554688B (en) | O-shaped sealing ring size measurement method based on monocular vision | |
| CN114663681A (en) | Method for reading pointer type meter and related product | |
| Martin-Rodriguez | Testing robustness of camera fingerprint (prnu) detectors | |
| Abdusalomov et al. | Robust shadow removal technique for improving image enhancement based on segmentation method | |
| US10958899B2 (en) | Evaluation of dynamic ranges of imaging devices |
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 |