WO2023124233A1 - 一种圆查找方法、装置、电子设备及存储介质 - Google Patents

一种圆查找方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2023124233A1
WO2023124233A1 PCT/CN2022/118332 CN2022118332W WO2023124233A1 WO 2023124233 A1 WO2023124233 A1 WO 2023124233A1 CN 2022118332 W CN2022118332 W CN 2022118332W WO 2023124233 A1 WO2023124233 A1 WO 2023124233A1
Authority
WO
WIPO (PCT)
Prior art keywords
circle
point
edge
area
identified
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.)
Ceased
Application number
PCT/CN2022/118332
Other languages
English (en)
French (fr)
Inventor
邵骏杰
邓志辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Hikrobot Co Ltd
Original Assignee
Hangzhou Hikrobot Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou Hikrobot Co Ltd filed Critical Hangzhou Hikrobot Co Ltd
Priority to EP22913502.5A priority Critical patent/EP4459564A4/en
Priority to JP2024539659A priority patent/JP7776654B2/ja
Priority to KR1020247025137A priority patent/KR20240122562A/ko
Publication of WO2023124233A1 publication Critical patent/WO2023124233A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
    • G06V10/235—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition based on user input or interaction
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/24—Aligning, centring, orientation detection or correction of the image
    • G06V10/248—Aligning, centring, orientation detection or correction of the image by interactive preprocessing or interactive shape modelling, e.g. feature points assigned by a user
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/469—Contour-based spatial representations, e.g. vector-coding
    • G06V10/471—Contour-based spatial representations, e.g. vector-coding using approximation functions
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20076—Probabilistic image processing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20092—Interactive image processing based on input by user
    • G06T2207/20101—Interactive definition of point of interest, landmark or seed

Definitions

  • the present application relates to the field of information technology, in particular to a circle search method, device, electronic equipment and storage medium.
  • the coordinate position of the object to be recognized is determined by taking the center of the circle pattern on the recognized object to be recognized as a reference point.
  • the user when recognizing circular patterns, the user often needs to make multiple inputs. For example, the user inputs the position of the center of the circle and the radius of the circular pattern by dragging the mouse to calculate the circular area to be recognized. Then, the recognition of the circular pattern is carried out in the area to be recognized, and the operation is complicated.
  • the purpose of the embodiments of the present application is to provide a circle search method, device, electronic equipment and storage medium, so as to solve the problem of complicated operation in the circle pattern recognition process.
  • the specific technical scheme is as follows:
  • the first aspect of the implementation of the present application firstly provides a circle search method, including:
  • a circle is fitted according to the at least three target edge points to obtain a fitted circle.
  • the second aspect of the implementation of the present application provides a circle search device, including:
  • a reference point acquisition module configured to acquire a target reference point in the image to be recognized, wherein the image to be recognized contains a circular pattern, and the target reference point is configured within a preset range of sides of the circular pattern;
  • An edge point selection module configured to perform edge extraction based on the target reference point to obtain at least three target edge points
  • a circle fitting module configured to perform circle fitting according to the at least three target edge points to obtain a fitted circle.
  • an electronic device including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete communication with each other through the communication bus;
  • the processor is used for implementing the steps of any one of the above-mentioned circle search methods when executing the program stored in the memory.
  • Another aspect of the implementation of the present application further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of any one of the above-mentioned circle search methods are implemented.
  • Another aspect of the implementation of the present application also provides a computer program product containing instructions, which, when run on a computer, causes the computer to execute the steps of any one of the above-mentioned circle search methods.
  • a circle search method, device, electronic device, and storage medium provided in the embodiments of the present application can acquire target reference points in an image to be recognized, wherein the image to be recognized contains a circular pattern, and the target reference point configuration Within the preset range of the sides of the circular pattern; edge extraction is performed based on the target reference point to obtain at least three target edge points; and circle fitting is performed according to the at least three target edge points to obtain The fitted circle. Therefore, the circle search can be realized only by the user inputting a point near the edge of a circular pattern, thereby simplifying the user's operation process.
  • FIG. 1 is a schematic flow chart of a circle search method provided in an embodiment of the present application
  • FIG. 2 is a schematic flow chart of a circle search method provided in an embodiment of the present application.
  • FIG. 3 is an example diagram of a circle search method provided in an embodiment of the present application.
  • Fig. 4 is a schematic flow chart of generating an area to be identified provided by the embodiment of the present application.
  • FIG. 5 is another example diagram of the circle search method provided by the embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a circle search device provided in an embodiment of the present application.
  • FIG. 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • Find the circle Locate the specific position of the circle, and give the center position and radius length of the circle.
  • ROI region of interest: A defined area in which the algorithm performs operations.
  • Find point The point near the circumference given by the user is used to find the circle.
  • Checkerboard distance the maximum value of the absolute value of the difference between the abscissa and ordinate of two pixels.
  • RANSAC Random Sample Consensus, Random Sampling Consensus Algorithm
  • the first aspect of the embodiments of the present application provides a circle search method, including:
  • the target reference point in the image to be recognized contains a circular pattern, and the target reference point is arranged within a preset range of the side of the circular pattern (ie, the circumference of the circular pattern);
  • a circle is fitted according to at least three target edge points to obtain a fitted circle.
  • FIG. 1 is a schematic flowchart of a circle search method provided in an embodiment of the present application, including:
  • Step S11 acquiring target reference points in the image to be recognized.
  • the image to be recognized in the embodiment of the present application is an image including a circular pattern
  • the target reference point is a single point, which can be a manually input point. Specifically, it can be marked in the image to be recognized by manual touch or mouse click
  • a point is used as a reference point, and the coordinate position of the reference point can also be input through the keyboard.
  • the target reference point may also be selected manually through a touch screen or the like. In actual use, the user only needs to input a point near the side of a circular pattern as the target reference point. Specifically, the point may or may not be a point on the side.
  • the target reference point can be set on the edge of the circular pattern that needs to be recognized, or can be set within a preset range of the edge of the circular pattern that needs to be recognized.
  • the preset range may be preset, specifically, the preset range may include the target reference point and points on the edge of the circular pattern at the same time.
  • the method in the embodiment of the present application is applied to a smart terminal, and can be implemented through a smart terminal.
  • the smart terminal can be a computer, a mobile phone, a server, or a smart camera.
  • step S12 edge extraction is performed based on the target reference point to obtain at least three target edge points.
  • the image to be recognized includes a circular pattern
  • the target reference point is arranged within a preset range of a side of the circular pattern (ie, a circumference of the circular pattern).
  • the preset range may be a first preset range.
  • edge extraction is performed based on the target reference point to obtain at least three target edge points, including: performing pixel gradient recognition on each pixel point within a first preset range around the target reference point in the image to be recognized to obtain the first Edge points, wherein the pixel gradient of the first edge point is greater than the preset gradient threshold; pixel gradient identification is performed on each pixel point in the second preset range around the first edge point to obtain a plurality of second edge points; from the first At least three target edge points are selected from the edge point and the plurality of second edge points.
  • edge extraction is performed based on the target reference point to obtain at least three target edge points, including: receiving information on the area to be identified by the user, wherein the information on the area to be identified includes the size and position of the area to be identified input by the user;
  • the target reference point is used as a benchmark, and edge extraction is performed in the area to be recognized to obtain at least three target edge points.
  • the preset detection algorithm may be any edge point detection algorithm, such as the canny algorithm (an edge detection algorithm).
  • the pixel gradient recognition is performed on each pixel point within the first preset range around the target reference point in the image to be recognized, and the pixel points with a checkerboard distance of 0, 1, 2... from the target reference point can be searched in turn, and it is judged whether is the edge point until the first edge point is obtained.
  • the first edge point may include multiple pixel points.
  • the size of the first preset range can be set according to actual conditions.
  • the smaller the range of circles to be identified the smaller the first preset range should be, and the larger the range of circles to be identified, the larger the first preset range should be.
  • the range of the image to be recognized is relatively large, but the range of the circular pattern to be recognized is relatively small, only points within a small range around the target reference point can be recognized by setting the first preset range. Therefore, not only can the search of edge points be accelerated, but also the working memory and calculation amount can be reduced. And when the range of the circular pattern to be recognized is relatively large, a relatively large range around the target reference point should be recognized.
  • performing pixel gradient recognition on each pixel point within a first preset range around the target reference point in the image to be recognized to obtain the first edge point including: within the first preset range around the target reference point in the image to be recognized, Each pixel point in multiple preset directions is identified by pixel gradient to obtain the first edge point.
  • pixel gradient recognition is performed on each pixel point in multiple preset directions to obtain the first edge point, including: the target reference point in the image to be recognized Within the first preset range around, select a direction according to the preset reference direction every preset angle span to obtain multiple target directions; perform pixel gradient recognition on each pixel point in the preset reference direction and multiple target directions, and obtain first edge point.
  • the preset direction may refer to four directions of the target reference point, up, down, left, and right, and four directions with a 45° interval between two adjacent directions, and one or more directions in total of eight directions.
  • the size of the second preset range may be the same as or different from that of the first preset range.
  • the first edge point can be used as a starting point to search for other edge points on the circumference contour, and when searching, all edge points can be searched, In order to make the edge points cover all positions of the circle.
  • the pixel gradient identification of each pixel point within the second preset range around the first edge point may be performed by any of the above-mentioned edge point detection algorithms, such as the canny algorithm.
  • pixel gradient identification is performed on each pixel point within a second preset range around the first edge point to obtain a plurality of second edge points, including: within a second preset range around the first edge point, for the second edge point
  • Each pixel point in the clockwise direction and counterclockwise direction of an edge point is identified by pixel gradient to obtain a plurality of second edge points.
  • At least three target edge points are selected from the first edge point and the plurality of second edge points. Since at least three edge points are required to perform circle fitting when performing circle fitting, after obtaining the first edge point and multiple edge points, three edge points need to be selected for circle fitting.
  • the selected at least three target edge points can be a first edge point and a plurality of second edge points, or at least three edge points in the second edge points. Wherein, in selecting at least three target edge points from the first edge point and a plurality of second edge points, three edge points can be selected from the first edge point and a plurality of second edge points as Target edge point.
  • Step S13 performing circle fitting according to at least three target edge points to obtain a fitted circle.
  • the fitting of the circle according to at least three target edge points can be performed by a variety of preset circle fitting methods, for example, the least squares method, or the least squares method based on RANSAC for fitting, to obtain the fitting
  • the parameters of the circle and the fitting circle such as radius and center coordinates, etc.
  • the parameter of the fitted circle is used as the parameter of the circular pattern in the image to be recognized.
  • At least three edge points from the first edge point and a plurality of second edge points can be selected from the first edge point and the plurality of second edge points by downsampling.
  • the edge point is used as the target edge point.
  • selecting at least three target edge points from the first edge point and the plurality of second edge points includes: downsampling the plurality of second edge points to obtain at least three third sampling edge points; according to at least Performing circle fitting on three target edge points to obtain a fitted circle includes: performing circle fitting according to at least three third sampling edge points to obtain a fitted circle. Because the number of the third edge points after downsampling is smaller than the number of the second edge points.
  • down-sampling may be performed according to the distance between the third edge points, so that the third edge points obtained by sampling may be evenly distributed on the fitting circle as much as possible. Therefore, the number of second edge points that need to be calculated and saved can be reduced by downsampling, thereby reducing memory consumption and subsequent calculation, and improving fitting efficiency.
  • the first edge point and multiple second edge points can be automatically identified only by the user inputting a target reference point, so that the circle can be defined by identifying the first edge point and the second edge point. Fitting to obtain the parameters of the circle in the image to be recognized, thereby simplifying the user's operation process.
  • the parameters of the fitted circle include the position coordinates of the fitted circle, and the circle is fitted according to at least three target edge points.
  • the above method further includes:
  • Step S21 generating an area to be identified according to the position coordinates of the fitted circle
  • step S22 the circle is recognized in the area to be recognized, and a recognition result is obtained, wherein the recognition result includes parameters of the recognized circle.
  • the position coordinates of the fitted circle include the center coordinates of the fitted circle and the radius of the fitted circle
  • the region to be identified is generated according to the position coordinates of the fitted circle, including: calculation based on the radius of the fitted circle
  • the region to be recognized with the preset shape to be generated may include the entire fitted circle, for example, when the preset shape is a circle, the radius of the circle corresponding to the area to be recognized in the preset shape is greater than the radius of the fitted circle.
  • the calculated area to be recognized in the preset shape The corresponding circle can be 5.
  • the length and width of the rectangle corresponding to the area to be recognized in the calculated preset shape are both greater than twice the radius of the fitting circle, for example, when the radius of the fitting circle is At 4 o'clock, the length and width of the rectangle corresponding to the region to be recognized in the preset shape can be 9 and 10 respectively.
  • the aforementioned area to be identified may be an area of various shapes, for example, the area to be identified may be a circle, a ring, a square, a rectangle, and the like.
  • the range of the region to be recognized should include the range of the circular pattern in the image to be recognized.
  • identify the circle in the area to be identified and obtain the identification result, including: comparing the size of the area of the area to be identified with the fitted circle; when the ratio of the area to be identified to the area of the fitted circle is greater than the preset
  • an updated to-be-recognized area is generated according to the size of the target reference point and the preset area; circles are identified in the updated to-be-identified area to obtain a recognition result.
  • the smaller the range of circles to be identified the smaller the first preset range should be, and the larger the range of circles to be identified, the larger the first preset range.
  • the range of the image to be recognized is large, but the range of the circular pattern to be recognized is small, only points within a small range around the target reference point can be recognized by setting the first preset range. Therefore, not only can the search of edge points be accelerated, but also the working memory and calculation amount can be reduced. And when the range of the circular pattern to be recognized is relatively large, a relatively large range around the target reference point should be recognized.
  • the above preset recognition method may be various methods for image recognition, for example, RANSAC and the like.
  • a higher-precision circle search can be performed in the ROI.
  • the region to be recognized can be generated according to the position coordinates of the fitted circle, and then the circle is recognized in the region to be recognized, and the recognition result is obtained, so that by performing circular pattern in the region to be recognized
  • the recognition can not only obtain the recognition result, improve the accuracy of the recognized circle parameters, but also find the circle in the area to be recognized by selecting the recognition area, without searching in the entire image, thereby reducing the amount of calculation , to improve computational efficiency.
  • the position coordinates of the fitted circle include the center coordinates of the fitted circle and the radius of the fitted circle, and the region to be identified is generated according to the position coordinates of the fitted circle, including:
  • Step S211 according to the coordinates of the center of the fitted circle and the radius of the fitted circle, calculate the inner diameter and outer diameter of the ring-shaped area to be identified;
  • Step S212 according to the characteristic parameters, with the center coordinates of the fitted circle as the center, and according to the inner diameter and outer diameter of the annular area to be identified, generate an annular area to be identified;
  • Step S22 performs circle recognition in the area to be recognized, and obtains the recognition result, including:
  • step S221 the circle is recognized in the ring-shaped area to be recognized, and the recognition result is obtained.
  • the inner and outer diameters of the ring-shaped area to be recognized are calculated, including: calculating the sum of the radius of the fitted circle and the width of the preset annular area , to obtain the outer diameter of the area to be identified; calculate the difference between the radius of the fitted circle and the width of the preset annular area, and obtain the inner diameter of the area to be identified.
  • the inner diameter and outer diameter of the circular area to be generated can be calculated, and the inner diameter of the circular area to be generated can be obtained by subtracting a preset value from the radius of the circular pattern. Add the preset value to the radius of the pattern to get the outer diameter of the circular area to be generated.
  • the preset value can be set according to the actual situation. In one example, the size of the preset value corresponds to the radius of the circle. The larger the radius of the circle, the larger the preset value can be. Smaller, the preset value can be smaller. Then, centering on the coordinates of the center of the fitted circle, an annular area to be identified is generated according to the inner and outer diameters of the area to be identified.
  • the generated circular area includes all edge points of the circular pattern.
  • the circle is recognized in the ring-shaped area to be identified to obtain a recognition result
  • the recognition result can be obtained by performing recognition of a circular pattern in the ring-shaped area to be identified by the above-mentioned preset recognition method.
  • the recognition of the circular pattern can be carried out in the circular to-be-recognized area by image recognition methods such as the above-mentioned RANSAC.
  • the recognition result may include parameters such as the radius of the circle and the coordinates of the center of the circle. Since the circular area includes all edge points of the circular pattern, and the area of the circular area is small, the area to be recognized is small, so the recognition efficiency is higher.
  • the inner diameter and outer diameter of the ring-shaped area to be recognized can be calculated according to the center coordinates of the fitted circle and the radius of the fitted circle, centered on the center coordinates of the fitted circle, According to the inner diameter and outer diameter of the ring-shaped area to be identified, a ring-shaped area to be identified is generated, and a circle is recognized in the ring-shaped area to be identified to obtain a recognition result, thereby reducing the area to be identified and improving the efficiency of identification.
  • FIG. 5 is another example diagram of the circle search method provided by the embodiment of the present application, including:
  • Image edge extraction when the image to be detected is large, and the diameter of the circle to be searched is relatively small, which only occupies a small part of the entire image area, only the area near the search point set by the user can be extracted to reduce the working memory and Calculations.
  • the second aspect of the embodiment of the present application provides a circle search device, see Figure 6, including:
  • the reference point acquisition module 601 is configured to acquire a target reference point in the image to be recognized, wherein the image to be recognized contains a circular pattern, and the target reference point is arranged within a preset range of a side of the circular pattern;
  • the edge point selection module 602 is used to extract the edge based on the target reference point to obtain at least three target edge points;
  • the circle fitting module 603 is configured to perform circle fitting according to at least three target edge points to obtain a fitted circle.
  • the edge point selection module 602 includes:
  • the first edge point detection module is configured to perform pixel gradient identification on each pixel point in the first preset range around the target reference point in the image to be recognized to obtain the first edge point, wherein the pixel gradient of the first edge point is greater than the preset gradient threshold;
  • the second edge point detection module is used to perform pixel gradient identification on each pixel point within a second preset range around the first edge point to obtain a plurality of second edge points;
  • a target edge point acquisition module configured to select at least three target edge points from the first edge point and the plurality of second edge points.
  • the parameters of the fitted circle include the position coordinates of the fitted circle, and the above device also includes:
  • An area to be identified generation module used for generating an area to be identified according to the position coordinates of the fitted circle
  • the area to be identified identification module is configured to identify circles in the area to be identified to obtain an identification result, wherein the identification result includes parameters of the identified circle.
  • the position coordinates of the fitted circle include the center coordinates of the fitted circle and the radius of the fitted circle
  • the region-to-be-recognized generation module includes:
  • the characteristic parameter calculation module is used to calculate the characteristic parameters of the region to be recognized in the preset shape to be generated according to the radius of the fitted circle, wherein the preset shape is a circle or a rectangle, and the characteristic parameter is the radius of a circle or a rectangle Length and width;
  • the characteristic parameter generation module is used to generate the region to be recognized based on the characteristic parameters, with the coordinates of the center of the fitted circle as the center of the region to be recognized.
  • the position coordinates of the fitted circle include the center coordinates of the fitted circle and the radius of the fitted circle
  • the region-to-be-recognized generation module includes:
  • the inner and outer diameter calculation sub-module is used to calculate the inner diameter and outer diameter of the ring-shaped area to be identified according to the center coordinates of the fitted circle and the radius of the fitted circle;
  • the ring-shaped area generation submodule is used to generate the ring-shaped area to be identified according to the inner diameter and outer diameter of the ring-shaped area to be identified with the center coordinates of the fitted circle as the center;
  • the area to be identified identification module is specifically used to identify circles in the annular area to be identified to obtain identification results.
  • the inner and outer diameter calculation sub-module is specifically used to calculate the sum of the radius of the fitted circle and the width of the preset annular area to obtain the outer diameter of the area to be identified; calculate the radius of the fitted circle and the preset annular area The difference between the area widths, to obtain the inner diameter of the area to be identified;
  • the second edge point detection module is specifically configured to perform pixel gradient identification on each pixel point in the clockwise and counterclockwise directions of the first edge point within a second preset range around the first edge point, to obtain multiple second edge points.
  • the first edge point detection module is specifically configured to perform pixel gradient recognition on each pixel point in multiple preset directions within a first preset range around the target reference point in the image to be recognized to obtain the first edge point.
  • the first edge point detection module includes:
  • the direction selection sub-module is used to select a direction according to the preset reference direction at intervals of a preset angle span within the first preset range around the target reference point in the image to be recognized, so as to obtain multiple target directions;
  • the pixel recognition sub-module is used to perform pixel gradient recognition on each pixel point in the preset reference direction and multiple target directions to obtain the first edge point.
  • the target edge point acquisition module is specifically configured to down-sample a plurality of second edge points to obtain at least three third sampled edge points;
  • the circle fitting module is specifically configured to perform circle fitting according to at least three third sampling edge points to obtain a fitted circle.
  • the area identification module to be identified includes:
  • the area comparison sub-module is used to compare the size of the area of the area to be identified and the fitted circle;
  • the area update submodule is used to generate an updated area to be identified according to the target reference point and the size of the preset area when the ratio of the area of the area to be identified to the area of the fitted circle is greater than a preset threshold;
  • the update area recognition sub-module is used to perform circle recognition in the updated to-be-recognized area to obtain a recognition result.
  • the edge point selection module 602 includes:
  • the area information receiving sub-module is used to receive the information of the area to be identified by the user, wherein the information of the area to be identified includes the size and position of the area to be identified input by the user;
  • the area edge extraction sub-module is used for performing edge extraction in the area to be identified based on the target reference point to obtain at least three target edge points.
  • the user only needs to input a point near the side of a circular pattern to realize the circle search, thereby simplifying the user's operation process.
  • the embodiment of the present application also provides an electronic device, as shown in FIG. complete the mutual communication,
  • Memory 703 used to store computer programs
  • the image to be recognized contains a circular pattern, and the target reference point is a point whose distance from the side of the circular pattern is less than a preset distance threshold;
  • a circle is fitted according to at least three target edge points to obtain a fitted circle.
  • the communication bus mentioned above for the electronic device may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus or the like.
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • the communication bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.
  • the communication interface is used for communication between the electronic device and other devices.
  • the memory may include a random access memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-Volatile Memory, NVM), such as at least one magnetic disk memory.
  • RAM Random Access Memory
  • NVM non-Volatile Memory
  • the memory may also be at least one storage device located far away from the aforementioned processor.
  • the above-mentioned processor can be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; it can also be a digital signal processor (Digital Signal Processor, DSP), a dedicated integrated Circuit (Application Specific Integrated Circuit, ASIC), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • CPU Central Processing Unit
  • NP Network Processor
  • DSP Digital Signal Processor
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • a computer-readable storage medium is also provided, and a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any of the above-mentioned circle search methods is implemented. A step of.
  • a computer program product including instructions is also provided, and when it is run on a computer, it causes the computer to execute any of the circle search methods in the above embodiments.
  • all or part of them may be implemented by software, hardware, firmware or any combination thereof.
  • software When implemented using software, it may be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application will be generated in whole or in part.
  • the computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices.
  • the computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website, computer, server or data center Transmission to another website site, computer, server, or data center by wired (eg, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (eg, infrared, wireless, microwave, etc.).
  • the computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device such as a server or a data center integrated with one or more available media.
  • the available medium may be a magnetic medium (for example, a floppy disk, a hard disk, or a magnetic tape), an optical medium (for example, DVD), or a semiconductor medium (for example, a Solid State Disk (SSD)).
  • SSD Solid State Disk
  • each embodiment in this specification is described in a related manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments.
  • the description is relatively simple, and for relevant parts, please refer to part of the description of the method embodiments.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)
  • User Interface Of Digital Computer (AREA)
  • Collating Specific Patterns (AREA)

Abstract

一种圆查找方法、装置、电子设备及存储介质，应用于信息技术领域，可以获取待识别图像中的目标参照点，其中，所述待识别图像中包含圆形图案，所述目标参照点配置在所述圆形图案的边的预设范围内；以所述目标参照点为基准进行边缘提取，得到至少三个目标边缘点；根据所述至少三个目标边缘点进行圆的拟合，得到拟合的圆。从而实现仅需要用户输入一个圆形图案的边的附近的点就可以实现圆的查找，从而简化用户的操作流程。

Description

一种圆查找方法、装置、电子设备及存储介质
本申请要求于2021年12月31日提交中国专利局、申请号为202111683480.2发明名称为“一种圆查找方法、装置、电子设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及信息技术领域，特别是涉及一种圆查找方法、装置、电子设备及存储介质。
背景技术
在机器视觉领域中，通过对圆形图案的识别，可以根据识别结果进行定位、测量等。例如，以识别到的待识别物体上圆形图案的圆心为基准点确定待识别物体的坐标位置。
然而，目前在进行圆形图案的识别时，往往需要用户进行多次输入，例如，通过用户输入圆心的位置，以及通过拖拽鼠标等方式输入圆形图案的半径，计算圆形待识别区域，然后在待识别区域中进行圆形图案的识别，操作复杂。
发明内容
本申请实施例的目的在于提供一种圆查找方法、装置、电子设备及存储介质，用以解决圆形图案识别过程中操作复杂的问题。具体技术方案如下：
本申请实施的第一方面，首先提供了一种圆查找方法，包括：
获取待识别图像中的目标参照点，其中，所述待识别图像中包含圆形图案，所述目标参照点配置在所述圆形图案的边的预设范围内；
以所述目标参照点为基准进行边缘提取，得到至少三个目标边缘点；
根据所述至少三个目标边缘点进行圆的拟合，得到拟合的圆。
本申请实施的第二方面，提供了一种圆查找装置，包括：
参照点获取模块，用于获取待识别图像中的目标参照点，其中，所述待识别图像中包含圆形图案，所述目标参照点配置在所述圆形图案的边的预设 范围内；
边缘点选取模块，用于以所述目标参照点为基准进行边缘提取，得到至少三个目标边缘点；
圆形拟合模块，用于根据所述至少三个目标边缘点进行圆的拟合，得到拟合的圆。
本申请实施的另一方面，还提供了一种电子设备，包括处理器、通信接口、存储器和通信总线，其中，处理器，通信接口，存储器通过通信总线完成相互间的通信；
存储器，用于存放计算机程序；
处理器，用于执行存储器上所存放的程序时，实现上述任一圆查找方法步骤。
本申请实施的另一方面，还提供了一种计算机可读存储介质，所述计算机可读存储介质内存储有计算机程序，所述计算机程序被处理器执行时实现上述任一圆查找方法步骤。
本申请实施的另一方面，还提供了一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行上述任一圆查找方法步骤。
本申请实施例有益效果：
本申请实施例提供的一种圆查找方法、装置、电子设备及存储介质，可以获取待识别图像中的目标参照点，其中，所述待识别图像中包含圆形图案，所述目标参照点配置在所述圆形图案的边的预设范围内；以所述目标参照点为基准进行边缘提取，得到至少三个目标边缘点；根据所述至少三个目标边缘点进行圆的拟合，得到拟合的圆。从而仅需要用户输入一个圆形图案的边附近的点就可以实现圆的查找，从而简化用户的操作流程。
当然，实施本申请的任一产品或方法并不一定需要同时达到以上所述的所有优点。
附图说明
为了更清楚地说明本发明实施例和现有技术的技术方案，下面对实施例 和现有技术中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本申请实施例提供的圆查找方法的一种流程示意图；
图2为本申请实施例提供的圆查找方法的一种流程示意图；
图3为本申请实施例提供的圆查找方法的一种实例图；
图4为本申请实施例提供的生成待识别区域的一种流程示意图；
图5为本申请实施例提供的圆查找方法的另一种实例图；
图6为本申请实施例提供的圆查找装置的一种结构示意图；
图7为本申请实施例提供的电子设备的一种结构示意图。
具体实施方式
为使本发明的目的、技术方案、及优点更加清楚明白，以下参照附图并举实施例，对本发明进一步详细说明。显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
首先，对本申请实施例中可能使用的名词进行解释：
单点：像素坐标中的一个点。
查找圆：定位到圆的具体位置，给出圆的圆心位置和半径长度。
ROI(region of interest，感兴趣区域)：一个限定的区域，算法在此区域中执行操作。
查找点：用户给出的圆周附近的点，用于查找圆。
棋盘距离：两个像素点横坐标差绝对值与纵坐标差绝对值的最大值。
RANSAC(Random Sample Consensus，随机抽样一致算法)：采用迭代的方式从一组包含离群的被观测数据中估算出数学模型的参数。
为了解决现有技术中，在进行圆形图案的识别时，需要用户进行多次输入，操作复杂的问题。
本申请实施例的第一方面，提供了一种圆查找方法，包括：
获取待识别图像中的目标参照点，其中，待识别图像中包含圆形图案，目标参照点配置在圆形图案的边(即圆形图案的圆周)的预设范围内；
以目标参照点为基准进行边缘提取，得到至少三个目标边缘点；
根据至少三个目标边缘点进行圆的拟合，得到拟合的圆。
可见，通过本申请实施例的方法，仅需要用户输入一个圆形图案的边附近的点就可以实现圆的查找，从而简化用户的操作流程。
具体的，参见图1，图1为本申请实施例提供的圆查找方法的一种流程示意图，包括：
步骤S11，获取待识别图像中的目标参照点。
本申请实施例中的待识别图像为包括圆形图案的图像，目标参照点为单点，可以为人工输入的点，具体的，可以通过人工触控或鼠标点击的方式在待识别图像中标注一个点作为参照点，也可以通过键盘输入参照点的坐标位置等方式。当本申请实施例的方法应用于智能手机等设备时，也可以通过人工通过触屏等方式选取目标参照点。在实际使用过程中，用户只需要输入一个圆形图案的边的附近的一个点作为目标参照点即可，具体的，该点可以是边上的点也可以不是边上的点。在实际使用过程中目标参照点可以设置在需要进行识别的圆形图案的边缘上，也可以设置在需要进行识别的圆形图案的边缘的预设范围内。该预设范围可以预先设定，具体的，该预设范围可以同时包括目标参照点和圆形图案的边缘上的点。
传统方法在进行查找圆过程中，一般需要将参照点放在圆心和圆周上，才可以确定圆心坐标以及半径，从而根据确定的圆心和半径进行找圆。然而，由于用户的操作误差往往无法准确将参照点放在圆心上，导致往往需要多次操作，操作复杂并且存在误差，而本申请实施例的方法则仅需要将参照点放在圆周的预设范围内就可以实现目标参照点的选取，从而简化操作流程，提 高用户体验。
本申请实施例的方法，应用于智能终端，可以通过智能终端来实施，具体的该智能终端可以是电脑、手机、服务器或智能相机等。
步骤S12，以目标参照点为基准进行边缘提取，得到至少三个目标边缘点。
其中，待识别图像中包含圆形图案，目标参照点配置在圆形图案的边(即圆形图案的圆周)的预设范围内。具体的，该预设范围可以为第一预设范围。可选的，以目标参照点为基准进行边缘提取，得到至少三个目标边缘点，包括：对待识别图像中目标参照点周围第一预设范围内的各像素点进行像素梯度识别，得到第一边缘点，其中，第一边缘点的像素梯度大于预设梯度阈值；对第一边缘点周围第二预设范围内的各像素点进行像素梯度识别，得到多个第二边缘点；从第一边缘点和多个第二边缘点中选取至少三个目标边缘点。可选的，以目标参照点为基准进行边缘提取，得到至少三个目标边缘点，包括：接收用户待识别区域信息，其中，待识别区域信息包括用户输入的待识别区域的大小和位置；以目标参照点为基准，在待识别区域中进行边缘提取，得到至少三个目标边缘点。
对待识别图像中目标参照点周围第一预设范围内的各像素点进行像素梯度识别，得到第一边缘点。其中，第一边缘点的像素梯度大于预设梯度阈值。本申请实施例中对待识别图像中目标参照点周围第一预设范围内的各像素点进行像素梯度识别，可以通过预设检测算法对待识别图像中目标参照点周围第一预设范围内的各像素点进行像素值的识别，然后根据识别到的像素值计算该像素点对应的像素梯度。实际使用过程中，可以通过计算Sobel算子(索贝尔算子)，计算各像素点的像素梯度。具体的，该预设检测算法可以是任一边缘点检测算法，如，canny算法(一种边缘检测算法)。一个例子中，对待识别图像中目标参照点周围第一预设范围内的各像素点进行像素梯度识别，可以依次搜索距离目标参照点棋盘距离为0，1，2…的像素点，并判断是否为边缘点，直至得到第一边缘点。其中，第一边缘点可以包括多个像素点。
其中，第一预设范围的大小可以根据实际情况进行设定。一个例子中，需要识别的圆的范围越小，该第一预设范围应该越小，需要识别的圆的范围越大，该第一预设范围则应该越大。例如，如果待识别图像的范围较大，而 需要识别的圆形图案的范围较小，可以通过第一预设范围的设定只识别目标参照点周围一个小范围内的点就可以。从而不但可以加快边缘点的查找，还可以减少工作内存和计算量。而当需要识别的圆形图案的范围较大，则应当识别目标参照点周围一个较大的范围。
可选的，对待识别图像中目标参照点周围第一预设范围内的各像素点进行像素梯度识别，得到第一边缘点，包括：对待识别图像中目标参照点周围第一预设范围内，多个预设方向上的各像素点进行像素梯度识别，得到第一边缘点。可选的，对待识别图像中目标参照点周围第一预设范围内，多个预设方向上的各像素点进行像素梯度识别，得到第一边缘点，包括：在待识别图像中目标参照点周围第一预设范围内，根据预设基准方向每间隔预设角度跨度选取一个方向，得到多个目标方向；对预设基准方向和多个目标方向上的各像素点进行像素梯度识别，得到第一边缘点。一个例子中，预设方向可以是指目标参照点的上下左右四个方向，以及相邻两个方向间隔45°的四个方向，共八个方向中的一个或多个方向。
对第一边缘点周围第二预设范围内的各像素点进行像素梯度识别，得到多个第二边缘点。第二预设范围的大小可以与第一预设范围的大小相同或不同。在查找第一边缘点周围第二预设范围内的多个第二边缘点时，可以以第一边缘点为起点搜索圆周轮廓上的其它边缘点，在搜索时，可以搜索全部的边缘点，以便让边缘点布满圆周的各个位置。对第一边缘点周围第二预设范围内的各像素点进行像素梯度识别，可以通过上述任一边缘点检测算法，如，canny算法进行识别。
可选的，对第一边缘点周围第二预设范围内的各像素点进行像素梯度识别，得到多个第二边缘点，包括：在第一边缘点周围第二预设范围内，对第一边缘点的顺时针和逆时针方向上的各像素点进行像素梯度识别，得到多个第二边缘点。其中，当圆形图案的半径比较大时，可以对这些边缘点进行采样，仅保留采样的边缘点，从而减少内存的消耗和后续的计算量。
从第一边缘点和多个第二边缘点中选取至少三个目标边缘点。由于在进行圆的拟合时，至少需要三个边缘点才可以进行圆的拟合，因此，在获取第一边缘点和多个边缘点之后，需要选择三个边缘点进行圆的拟合。选择的至 少三个目标边缘点可以是第一边缘点和多个第二边缘点，也可以是第二边缘点中的至少三个边缘点。其中，在从第一边缘点和多个第二边缘点中选取至少三个目标边缘点，可以通过随机选取的方法，从第一边缘点和多个第二边缘点中选取三个边缘点作为目标边缘点。
步骤S13，根据至少三个目标边缘点进行圆的拟合，得到拟合的圆。
其中，根据至少三个目标边缘点进行圆的拟合，可以通过多种预设圆的拟合方法进行拟合，例如，最小二乘法，或基于RANSAC的最小二乘法进行拟合，得到拟合的圆和拟合圆的参数，如，半径和圆心坐标等。然后将该拟合圆形的参数作为待识别图像中圆形图案的参数。
在从第一边缘点和多个第二边缘点中选取至少三个边缘点作为目标边缘点时，可以通过下采样的方法，从第一边缘点和多个第二边缘点中选取至少三个边缘点作为目标边缘点。可选的，从第一边缘点和多个第二边缘点中选取至少三个目标边缘点，包括：对多个第二边缘点进行下采样，得到至少三个第三采样边缘点；根据至少三个目标边缘点进行圆的拟合，得到拟合的圆，包括：根据至少三个第三采样边缘点进行圆的拟合，得到拟合的圆。由于下采样后的第三边缘点的数量小于第二边缘点的数量。在下采样时，可以根据第三边缘点之间的距离进行下采样，以使采样得到的第三边缘点在拟合圆上尽量均匀分布。因此，通过下采样可以减少需要计算和保存的第二边缘点的数量，从而可以减少内存的消耗和后续的计算量，提高拟合效率。
可见，通过本申请实施例的方法，仅需要用户输入一个目标参照点就可以自动识别出第一边缘点和多个第二边缘点，从而通过识别第一边缘点和第二边缘点进行圆的拟合，得到待识别图像中圆的参数，从而简化用户的操作流程。
可选的，参见图2，拟合的圆的参数包括拟合的圆的位置坐标，根据至少三个目标边缘点进行圆的拟合，得到拟合的圆之后，上述方法还包括：
步骤S21，根据拟合的圆的位置坐标生成待识别区域；
步骤S22，在待识别区域中进行圆的识别，得到识别结果，其中，识别结果包括识别到的圆的参数。
可选的，拟合的圆的位置坐标包括拟合的圆的圆心坐标和拟合的圆的半径，根据拟合的圆的位置坐标生成待识别区域，包括：根据拟合的圆的半径计算得到待生成的预设形状的待识别区域的特征参数，其中，预设形状为圆形或矩形，特征参数为圆的半径或矩形的长和宽；以拟合的圆的圆心坐标为待生成的待识别区域的中心，生成待识别区域。其中，在根据根据拟合的圆的半径计算得到待生成的预设形状的待识别区域的特征参数时，该待生成的预设形状的待识别区域可以包含整个拟合的圆，例如，当预设形状为圆形时，预设形状的待识别区域对应的圆的半径大于拟合的圆的半径，例如，当拟合圆的半径为4时，计算得到的预设形状的待识别区域对应的圆的可以为5。再例如，当拟合圆的半径为4时，计算得到的预设形状的待识别区域对应的矩形的长和宽均大于该拟合圆的半径的两倍，如，当拟合圆的半径4时，预设形状的待识别区域对应的矩形的长和宽可以分别为9和10。
其中，上述待识别区域可以是多种形状的区域，例如，待识别区域可以是圆形、环形、正方形、长方形等。在生成待识别区域时，待识别区域的范围应当包括待识别图像中圆形图案的范围。
可选的，在待识别区域中进行圆的识别，得到识别结果，包括：对比待识别区域和拟合的圆的面积的大小；当待识别区域与拟合的圆的面积的比例大于预设阈值时，根据目标参照点和预设区域的大小生成更新后的待识别区域；在更新后的待识别区域中进行圆的识别，得到识别结果。一个例子中，需要识别的圆的范围越小，该第一预设范围应该越小，需要识别的圆的范围越大，该第一预设范围可以越大。例如，如果待识别图像的范围较大，而需要识别的圆形图案的范围较小，可以通过第一预设范围的设定只识别目标参照点周围一个小范围内的点就可以。从而不但可以加快边缘点的查找，还可以减少工作内存和计算量。而当需要识别的圆形图案的范围较大，则应当识别目标参照点周围一个较大的范围。
本申请实施例中，通过预设识别方法，在待识别区域中进行圆形图案的识别时，上述预设识别方法可以是多种进行图像识别的方法，例如，RANSAC等。本申请实施例中，参见图3，根据圆形图案的参数生成ROI后，可以在ROI中进行更高精度的圆的查找。
可见，通过本申请实施例的方法，可以根据拟合的圆的位置坐标生成待识别区域，然后在待识别区域中进行圆的识别，得到识别结果，从而通过在待识别区域中进行圆形图案的识别，不但可以得到识别结果，提高识别到的圆形的参数的精度，还可以通过识别区域的选取，在待识别区域中查找圆，而无需在整个图像中进行查找，从而减小计算量，提高计算效率。
可选的，参见图4，拟合的圆的位置坐标包括拟合的圆的圆心坐标和拟合的圆的半径，根据拟合的圆的位置坐标生成待识别区域，包括：
步骤S211，根据拟合的圆的圆心坐标和拟合的圆的半径，计算得到环形待识别区域的内径和外径；
步骤S212，根据所述特征参数，以拟合的圆的圆心坐标为中心，根据环形待识别区域的内径和外径，生成环形待识别区域；
步骤S22在待识别区域中进行圆的识别，得到识别结果，包括：
步骤S221，在环形待识别区域中进行圆的识别，得到识别结果。
可选的，根据拟合的圆的圆心坐标和拟合的圆的半径，计算得到环形待识别区域的内径和外径，包括：计算拟合的圆的半径和预设环状区域宽度之和，得到待识别区域的外径；计算拟合的圆的半径和预设环状区域宽度之差，得到待识别区域的内径。
根据圆形图案的半径和预设长度，计算得到待生成圆环形区域的内径和外径，可以通过圆形图案的半径减去一个预设值得到待生成圆环形区域的内径，圆形图案的半径加上该预设值得到待生成圆环形区域的外径。具体的，该预设值可以根据实际情况进行设定，一个例子中，该预设值的大小与圆的半径相对应，圆的半径越大，该预设值可以越大，圆的半径越小，该预设值可以越小。然后以拟合的圆的圆心坐标为中心，根据环形待识别区域的内径和外径，生成环形待识别区域。本申请实施例中，所生成的圆环形区域包括圆形图案的所有边缘点。
在环形待识别区域中进行圆的识别，得到识别结果，可以通过上述预设识别方法，在圆环形待识别区域中进行圆形图案的识别，得到识别结果。具体的，可以是通过上述RANSAC等图像识别方法，在圆环形待识别区域中进 行圆形图案的识别。本申请实施例中，识别结果可以包括圆的半径和圆心坐标等参数。由于圆环形区域包括圆形图案的所有边缘点，并且，圆环形区域的区域面积较小，需要识别的区域较小，因此，识别效率更高。
可见，通过本申请实施例的方法，可以根据拟合的圆的圆心坐标和拟合的圆的半径，计算得到环形待识别区域的内径和外径，以拟合的圆的圆心坐标为中心，根据环形待识别区域的内径和外径，生成环形待识别区域，在环形待识别区域中进行圆的识别，得到识别结果，从而可以减小需要识别的区域，提高识别的效率。
参见图5，图5为本申请实施例提供的圆查找方法的另一种实例图，包括：
1、设置圆周附近查找点；本申请中的查找点位于圆形图案的圆周附近。
2、图像边缘提取；当待检测的图像较大，而需要查找的圆直径比较小，只占整个图像区域的一小部分，可以只提取用户设置的查找点附近的区域，以减少工作内存和计算量。
3、搜索最近边缘点；具体的，可以依次搜索距离查找点棋盘距离为0，1，2…的点，或，沿着固定的8个方向(相邻两个方向间隔45°)来搜索，得到圆周上的点。
4、沿着边缘搜索其他边缘点；从顺时针和逆时针两个方向进行搜索，然后保存搜索到的边缘点。可选的，如果待搜索圆的半径比较大，可以对这些边缘点进行采样，仅保留采样的边缘点，可以减少内存的消耗和后续的计算量。
5、边缘点圆拟合；对保留下来的边缘点进行圆拟合，圆拟合时可以有多种不同的方式，如最小二乘法或者基于RANSAC的最小二乘法等，最终便得到此单点查找圆的结果。
本申请实施例的第二方面，提供了一种圆查找装置，参见图6，包括：
参照点获取模块601，用于获取待识别图像中的目标参照点，其中，待识别图像中包含圆形图案，目标参照点配置在圆形图案的边的预设范围内；
边缘点选取模块602，用于以目标参照点为基准进行边缘提取，得到至少 三个目标边缘点；
圆形拟合模块603，用于根据至少三个目标边缘点进行圆的拟合，得到拟合的圆。
可选的，边缘点选取模块602，包括：
第一边缘点检测模块，用于对待识别图像中目标参照点周围第一预设范围内的各像素点进行像素梯度识别，得到第一边缘点，其中，第一边缘点的像素梯度大于预设梯度阈值；
第二边缘点检测模块，用于对第一边缘点周围第二预设范围内的各像素点进行像素梯度识别，得到多个第二边缘点；
目标边缘点获取模块，用于从第一边缘点和多个第二边缘点中选取至少三个目标边缘点。
可选的，拟合的圆的参数包括拟合的圆的位置坐标，上述装置还包括：
待识别区域生成模块，用于根据拟合的圆的位置坐标生成待识别区域；
待识别区域识别模块，用于在待识别区域中进行圆的识别，得到识别结果，其中，识别结果包括识别到的圆的参数。
可选的，拟合的圆的位置坐标包括拟合的圆的圆心坐标和拟合的圆的半径，待识别区域生成模块，包括：
特征参数计算模块，用于根据拟合的圆的半径计算得到待生成的预设形状的待识别区域的特征参数，其中，预设形状为圆形或矩形，特征参数为圆的半径或矩形的长和宽；
特征参数生成模块，用于根据所述特征参数，以拟合的圆的圆心坐标为待生成的待识别区域的中心，生成待识别区域。
可选的，拟合的圆的位置坐标包括拟合的圆的圆心坐标和拟合的圆的半径，待识别区域生成模块，包括：
内外径计算子模块，用于根据拟合的圆的圆心坐标和拟合的圆的半径，计算得到环形待识别区域的内径和外径；
环形区域生成子模块，用于以拟合的圆的圆心坐标为中心，根据环形待识别区域的内径和外径，生成环形待识别区域；
待识别区域识别模块，具体用于在环形待识别区域中进行圆的识别，得到识别结果。
可选的，内外径计算子模块，具体用于计算拟合的圆的半径和预设环状区域宽度之和，得到待识别区域的外径；计算拟合的圆的半径和预设环状区域宽度之差，得到待识别区域的内径；
可选的，第二边缘点检测模块，具体用于在第一边缘点周围第二预设范围内，对第一边缘点的顺时针和逆时针方向上的各像素点进行像素梯度识别，得到多个第二边缘点。
可选的，第一边缘点检测模块，具体用于对待识别图像中目标参照点周围第一预设范围内，多个预设方向上的各像素点进行像素梯度识别，得到第一边缘点。
可选的，第一边缘点检测模块，包括：
方向选取子模块，用于在待识别图像中目标参照点周围第一预设范围内，根据预设基准方向每间隔预设角度跨度选取一个方向，得到多个目标方向；
像素识别子模块，用于对预设基准方向和多个目标方向上的各像素点进行像素梯度识别，得到第一边缘点。
可选的，目标边缘点获取模块，具体用于对多个第二边缘点进行下采样，得到至少三个第三采样边缘点；
圆形拟合模块，具体用于根据至少三个第三采样边缘点进行圆的拟合，得到拟合的圆。
可选的，待识别区域识别模块，包括：
面积比较子模块，用于对比待识别区域和拟合的圆的面积的大小；
区域更新子模块，用于当待识别区域与拟合的圆的面积的比例大于预设阈值时，根据目标参照点和预设区域的大小生成更新后的待识别区域；
更新区域识别子模块，用于在更新后的待识别区域中进行圆的识别，得到识别结果。
可选的，边缘点选取模块602，包括：
区域信息接收子模块，用于接收用户待识别区域信息，其中，待识别区域信息包括用户输入的待识别区域的大小和位置；
区域边缘提取子模块，用于以目标参照点为基准，在待识别区域中进行边缘提取，得到至少三个目标边缘点。
可见，通过本申请实施例的装置，可以实现仅需要用户输入一个圆形图案的边附近的点就可以实现圆的查找，从而简化用户的操作流程。
本申请实施例还提供了一种电子设备，如图7所示，包括处理器701、通信接口702、存储器703和通信总线704，其中，处理器701，通信接口702，存储器703通过通信总线704完成相互间的通信，
存储器703，用于存放计算机程序；
处理器701，用于执行存储器703上所存放的程序时，实现如下步骤：
获取待识别图像中的目标参照点，其中，待识别图像中包含圆形图案，目标参照点为与圆形图案的边的距离小于预设距离阈值的点；
以目标参照点为基准进行边缘提取，得到至少三个目标边缘点；
根据至少三个目标边缘点进行圆的拟合，得到拟合的圆。
上述电子设备提到的通信总线可以是外设部件互连标准(Peripheral Component Interconnect，PCI)总线或扩展工业标准结构(Extended Industry Standard Architecture，EISA)总线等。该通信总线可以分为地址总线、数据总线、控制总线等。为便于表示，图中仅用一条粗线表示，但并不表示仅有一根总线或一种类形的总线。
通信接口用于上述电子设备与其他设备之间的通信。
存储器可以包括随机存取存储器(Random Access Memory，RAM)，也可以包括非易失性存储器(Non-Volatile Memory，NVM)，例如至少一个磁盘存 储器。可选的，存储器还可以是至少一个位于远离前述处理器的存储装置。
上述的处理器可以是通用处理器，包括中央处理器(Central Processing Unit，CPU)、网络处理器(Network Processor，NP)等；还可以是数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。
在本申请提供的又一实施例中，还提供了一种计算机可读存储介质，该计算机可读存储介质内存储有计算机程序，所述计算机程序被处理器执行时实现上述任一圆查找方法的步骤。
在本申请提供的又一实施例中，还提供了一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机执行上述实施例中任一圆查找方法。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时，全部或部分地产生按照本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质(例如固态硬盘Solid State Disk(SSD))等。
需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、 “包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
本说明书中的各个实施例均采用相关的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于装置、电子设备、存储介质及计算机程序产品实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
以上所述仅为本申请的较佳实施例，并非用于限定本申请的保护范围。凡在本申请的精神和原则之内所作的任何修改、等同替换、改进等，均包含在本申请的保护范围内。

Claims (15)

  1. 一种圆查找方法，包括：
    获取待识别图像中的目标参照点，其中，所述待识别图像中包含圆形图案，所述目标参照点配置在所述圆形图案的边的预设范围内；
    以所述目标参照点为基准进行边缘提取，得到至少三个目标边缘点；
    根据所述至少三个目标边缘点进行圆的拟合，得到拟合的圆。
  2. 根据权利要求1所述的方法，其中，所述以所述目标参照点为基准进行边缘提取，得到至少三个目标边缘点，包括：
    对所述待识别图像中目标参照点周围第一预设范围内的各像素点进行像素梯度识别，得到第一边缘点，其中，所述第一边缘点的像素梯度大于预设梯度阈值；
    对所述第一边缘点周围第二预设范围内的各像素点进行像素梯度识别，得到多个第二边缘点；
    从所述第一边缘点和所述多个第二边缘点中选取至少三个目标边缘点。
  3. 根据权利要求2所述的方法，其中，所述拟合的圆的参数包括所述拟合的圆的位置坐标，所述根据所述至少三个目标边缘点进行圆的拟合，得到拟合的圆之后，所述方法还包括：
    根据所述拟合的圆的位置坐标生成待识别区域；
    在所述待识别区域中进行圆的识别，得到识别结果，其中，所述识别结果包括识别到的圆的参数。
  4. 根据权利要求3所述的方法，其中，所述拟合的圆的位置坐标包括所述拟合的圆的圆心坐标和拟合的圆的半径，所述根据所述拟合的圆的位置坐标生成待识别区域，包括：
    根据所述拟合的圆的半径计算得到待生成的预设形状的待识别区域的特征参数，其中，所述预设形状为圆形或矩形，所述特征参数为圆的半径或矩形的长和宽；
    根据所述特征参数，以所述拟合的圆的圆心坐标为待生成的待识别区域的中心，生成待识别区域。
  5. 根据权利要求3所述的方法，其中，所述拟合的圆的位置坐标包括所述拟合的圆的圆心坐标和拟合的圆的半径，所述根据所述拟合的圆的位置坐标生成待识别区域，包括：
    根据所述拟合的圆的圆心坐标和拟合的圆的半径，计算得到环形待识别区域的内径和外径；
    以所述拟合的圆的圆心坐标为中心，根据所述环形待识别区域的内径和外径，生成环形待识别区域；
    所述在所述待识别区域中进行圆的识别，得到识别结果，包括：
    在所述环形待识别区域中进行圆的识别，得到识别结果。
  6. 根据权利要求5所述的方法，其中，所述根据所述拟合的圆的圆心坐标和拟合的圆的半径，计算得到环形待识别区域的内径和外径，包括：
    计算所述拟合的圆的半径和预设环状区域宽度之和，得到待识别区域的外径；计算所述拟合的圆的半径和预设环状区域宽度之差，得到待识别区域的内径。
  7. 根据权利要求2所述的方法，其中，所述对所述第一边缘点周围第二预设范围内的各像素点进行像素梯度识别，得到多个第二边缘点，包括：
    在所述第一边缘点周围第二预设范围内，对所述第一边缘点的顺时针和逆时针方向上的各像素点进行像素梯度识别，得到所述多个第二边缘点。
  8. 根据权利要求2所述的方法，其中，所述对所述待识别图像中目标参照点周围第一预设范围内的各像素点进行像素梯度识别，得到第一边缘点，包括：
    对所述待识别图像中目标参照点周围第一预设范围内，多个预设方向上的各像素点进行像素梯度识别，得到第一边缘点。
  9. 根据权利要求8所述的方法，其中，所述对所述待识别图像中目标参照 点周围第一预设范围内，多个预设方向上的各像素点进行像素梯度识别，得到第一边缘点，包括：
    在所述待识别图像中目标参照点周围第一预设范围内，根据预设基准方向每间隔预设角度跨度选取一个方向，得到多个目标方向；
    对所述预设基准方向和所述多个目标方向上的各像素点进行像素梯度识别，得到第一边缘点。
  10. 根据权利要求2所述的方法，其中，所述从所述第一边缘点和所述多个第二边缘点中选取至少三个目标边缘点，包括：
    对所述多个第二边缘点进行下采样，得到至少三个第三采样边缘点；
    所述根据所述至少三个目标边缘点进行圆的拟合，得到拟合的圆，包括：
    根据所述至少三个第三采样边缘点进行圆的拟合，得到所述拟合的圆。
  11. 根据权利要求3所述的方法，其中，所述在所述待识别区域中进行圆的识别，得到识别结果，包括：
    对比所述待识别区域和所述拟合的圆的面积的大小；
    当所述待识别区域与所述拟合的圆的面积的比例大于预设阈值时，根据所述目标参照点和预设区域的大小生成更新后的待识别区域；
    在所述更新后的待识别区域中进行圆的识别，得到识别结果。
  12. 根据权利要求1所述的方法，其中，所述以所述目标参照点为基准进行边缘提取，得到至少三个目标边缘点，包括：
    接收用户待识别区域信息，其中，所述待识别区域信息包括用户输入的待识别区域的大小和位置；
    以所述目标参照点为基准，在所述待识别区域中进行边缘提取，得到至少三个目标边缘点。
  13. 一种圆查找装置，包括：
    参照点获取模块，用于获取待识别图像中的目标参照点，其中，所述待 识别图像中包含圆形图案，所述目标参照点配置在所述圆形图案的边的预设范围内；
    第一边缘点检测模块，用于对所述待识别图像中目标参照点周围第一预设范围内的各像素点进行像素梯度识别，得到第一边缘点，其中，所述第一边缘点的像素梯度大于预设梯度阈值；
    第二边缘点检测模块，用于对所述第一边缘点周围第二预设范围内的各像素点进行像素梯度识别，得到多个第二边缘点；
    目标边缘点获取模块，用于从所述第一边缘点和所述多个第二边缘点中选取至少三个目标边缘点；
    圆形拟合模块，用于根据所述至少三个目标边缘点进行圆的拟合，得到拟合的圆。
  14. 一种电子设备，包括处理器、通信接口、存储器和通信总线，其中，处理器，通信接口，存储器通过通信总线完成相互间的通信；
    存储器，用于存放计算机程序；
    处理器，用于执行存储器上所存放的程序时，实现权利要求1-12任一所述的方法步骤。
  15. 一种计算机可读存储介质，所述计算机可读存储介质内存储有计算机程序，所述计算机程序被处理器执行时实现权利要求1-12任一所述的方法步骤。
PCT/CN2022/118332 2021-12-31 2022-09-13 一种圆查找方法、装置、电子设备及存储介质 Ceased WO2023124233A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP22913502.5A EP4459564A4 (en) 2021-12-31 2022-09-13 Circle search method and device, electronic device and storage medium
JP2024539659A JP7776654B2 (ja) 2021-12-31 2022-09-13 円検出方法、装置、電子機器および記憶媒体
KR1020247025137A KR20240122562A (ko) 2021-12-31 2022-09-13 원 검색 방법, 디바이스, 전자 기기 및 저장 매체

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111683480.2 2021-12-31
CN202111683480.2A CN114359548B (zh) 2021-12-31 2021-12-31 一种圆查找方法、装置、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2023124233A1 true WO2023124233A1 (zh) 2023-07-06

Family

ID=81104978

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/118332 Ceased WO2023124233A1 (zh) 2021-12-31 2022-09-13 一种圆查找方法、装置、电子设备及存储介质

Country Status (5)

Country Link
EP (1) EP4459564A4 (zh)
JP (1) JP7776654B2 (zh)
KR (1) KR20240122562A (zh)
CN (1) CN114359548B (zh)
WO (1) WO2023124233A1 (zh)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116977642A (zh) * 2023-08-03 2023-10-31 江苏军尚智能科技有限公司 一种无序堆叠运动的圆形工件的识别、分拣方法和装置
CN118196171A (zh) * 2024-05-20 2024-06-14 法奥意威(苏州)机器人系统有限公司 一种检测圆的方法、装置、存储介质及电子设备
CN118297940A (zh) * 2024-05-30 2024-07-05 泰山石膏(宜宾)有限公司 一种石膏板生产线质量管控方法、装置、设备及介质
CN118354010A (zh) * 2024-06-17 2024-07-16 北京蓝耘科技股份有限公司 一种gpu输出数据加密方法、系统及存储介质
CN118424149A (zh) * 2024-07-05 2024-08-02 东华隆（广州）表面改质技术有限公司 一种压延辊轮廓检测的方法及系统
CN118799350A (zh) * 2024-09-13 2024-10-18 昆山华恒工程技术中心有限公司 一种管板焊接中管孔识别方法
CN118941711A (zh) * 2024-07-15 2024-11-12 杭州云甲数字技术有限公司 特征方向信息获取方法及装置、计算机程序产品
CN119394228A (zh) * 2024-10-17 2025-02-07 赛力斯汽车有限公司 孔类信息提取方法、系统、电子设备及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114359548B (zh) * 2021-12-31 2025-11-04 杭州海康机器人股份有限公司 一种圆查找方法、装置、电子设备及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100067805A1 (en) * 2006-12-18 2010-03-18 Fraunhofer-Gesellschaft Zur Foerderung Der Angewandten Forschung E.V. Device, method and computer program for identifying a traffic sign in an image
CN102236894A (zh) * 2010-04-30 2011-11-09 西门子公司 圆检测方法及装置
CN106251352A (zh) * 2016-07-29 2016-12-21 武汉大学 一种基于图像处理的罐盖缺陷检测方法
CN106447683A (zh) * 2016-08-09 2017-02-22 上海柏楚电子科技有限公司 一种圆的特征提取算法
CN109815822A (zh) * 2018-12-27 2019-05-28 北京航天福道高技术股份有限公司 基于广义Hough变换的巡检图零部件目标识别方法
CN114359548A (zh) * 2021-12-31 2022-04-15 杭州海康机器人技术有限公司 一种圆查找方法、装置、电子设备及存储介质

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005333116A (ja) * 2004-04-21 2005-12-02 Nikon Corp 位置検出装置及び方法、位置調整装置及び方法、並びに露光装置及び方法
JP2011227748A (ja) 2010-04-21 2011-11-10 Seiko Epson Corp 画像処理装置、画像処理方法、画像処理プログラム、及び欠陥検出装置
WO2016133924A1 (en) * 2015-02-18 2016-08-25 Siemens Healthcare Diagnostics Inc. Image-based tube slot circle detection for a vision system
CN106503704B (zh) * 2016-10-21 2018-03-23 河南大学 一种自然场景中圆形交通标志定位方法
CN112534469B (zh) * 2019-06-27 2024-07-19 京东方科技集团股份有限公司 图像检测方法、图像检测装置、图像检测设备及介质
JP2021096652A (ja) 2019-12-17 2021-06-24 富士通株式会社 画像識別装置、方法、及びプログラム
CN112508009A (zh) * 2020-11-23 2021-03-16 北京配天技术有限公司 圆形特征检测方法、装置及存储装置
CN113712665B (zh) * 2021-11-01 2022-04-22 北京柏惠维康科技有限公司 基于定位标志物的定位方法、装置及计算机存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100067805A1 (en) * 2006-12-18 2010-03-18 Fraunhofer-Gesellschaft Zur Foerderung Der Angewandten Forschung E.V. Device, method and computer program for identifying a traffic sign in an image
CN102236894A (zh) * 2010-04-30 2011-11-09 西门子公司 圆检测方法及装置
CN106251352A (zh) * 2016-07-29 2016-12-21 武汉大学 一种基于图像处理的罐盖缺陷检测方法
CN106447683A (zh) * 2016-08-09 2017-02-22 上海柏楚电子科技有限公司 一种圆的特征提取算法
CN109815822A (zh) * 2018-12-27 2019-05-28 北京航天福道高技术股份有限公司 基于广义Hough变换的巡检图零部件目标识别方法
CN114359548A (zh) * 2021-12-31 2022-04-15 杭州海康机器人技术有限公司 一种圆查找方法、装置、电子设备及存储介质

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
GUO, CHENGCHENG ET AL.: "Effective Extraction Method of Oval Objects in Image", ELECTRONIC MEASUREMENT TECHNOLOGY, no. 04, 15 April 2017 (2017-04-15), XP009547539 *
See also references of EP4459564A4

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116977642A (zh) * 2023-08-03 2023-10-31 江苏军尚智能科技有限公司 一种无序堆叠运动的圆形工件的识别、分拣方法和装置
CN118196171A (zh) * 2024-05-20 2024-06-14 法奥意威(苏州)机器人系统有限公司 一种检测圆的方法、装置、存储介质及电子设备
CN118297940A (zh) * 2024-05-30 2024-07-05 泰山石膏(宜宾)有限公司 一种石膏板生产线质量管控方法、装置、设备及介质
CN118354010A (zh) * 2024-06-17 2024-07-16 北京蓝耘科技股份有限公司 一种gpu输出数据加密方法、系统及存储介质
CN118424149A (zh) * 2024-07-05 2024-08-02 东华隆（广州）表面改质技术有限公司 一种压延辊轮廓检测的方法及系统
CN118941711A (zh) * 2024-07-15 2024-11-12 杭州云甲数字技术有限公司 特征方向信息获取方法及装置、计算机程序产品
CN118799350A (zh) * 2024-09-13 2024-10-18 昆山华恒工程技术中心有限公司 一种管板焊接中管孔识别方法
CN119394228A (zh) * 2024-10-17 2025-02-07 赛力斯汽车有限公司 孔类信息提取方法、系统、电子设备及存储介质

Also Published As

Publication number Publication date
EP4459564A4 (en) 2025-04-16
KR20240122562A (ko) 2024-08-12
CN114359548B (zh) 2025-11-04
JP7776654B2 (ja) 2025-11-26
EP4459564A1 (en) 2024-11-06
JP2024547167A (ja) 2024-12-26
CN114359548A (zh) 2022-04-15

Similar Documents

Publication Publication Date Title
WO2023124233A1 (zh) 一种圆查找方法、装置、电子设备及存储介质
WO2020114320A1 (zh) 点云聚类方法、图像处理设备及具有存储功能的装置
CN103645890B (zh) 一种用于在图形用户界面中定位控件的方法和装置
WO2021196698A1 (zh) 待侦测物体储量确定方法、装置、设备及介质
CN109165657A (zh) 一种基于改进sift的图像特征检测方法及装置
CN113344994B (zh) 图像配准方法、装置、电子设备及存储介质
CN103077528A (zh) 基于DCCD-Laplace和SIFT描述符的快速影像匹配方法
CN111565356A (zh) 一种基站位置检测方法及装置
CN113689526B (zh) 地图中无效区域的划分方法及装置、电子设备
CN108229583B (zh) 一种基于主方向差分特征的快速模板匹配的方法及装置
CN115631229A (zh) 一种电池片定位方法、装置、电子设备及存储介质
CN111813984A (zh) 一种利用单应矩阵实现室内定位的方法、装置及电子设备
CN108648156A (zh) 点云数据中杂散点标记方法、装置、电子设备及存储介质
CN115115857A (zh) 一种图像匹配方法、装置及计算机设备
CN111880776A (zh) 一种层级关系获得方法、装置及电子设备
CN108133206B (zh) 静态手势识别方法、装置及可读存储介质
CN112508009A (zh) 圆形特征检测方法、装置及存储装置
CN117218100B (zh) 工件圆拟合方法、装置、视觉检测系统及电子设备
CN111880721A (zh) 数据处理方法及装置、电子设备、存储介质
CN111951349A (zh) 一种图形顶点类型的调整方法、装置及电子设备
CN113627143B (zh) 一种表格创建方法、装置、电子设备及存储介质
CN117739809B (zh) 一种瓶口尺寸测量方法、计算机设备及介质
CN113096182A (zh) 一种移动对象的定位方法、装置、电子设备及存储介质
CN111814869B (zh) 一种同步定位与建图的方法、装置、电子设备及存储介质
CN110399892B (zh) 环境特征提取方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22913502

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2024539659

Country of ref document: JP

ENP Entry into the national phase

Ref document number: 20247025137

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2022913502

Country of ref document: EP

Effective date: 20240731