19 results about "Circle fitting" patented technology

The invention discloses an underground mine pipeline type point cloud completion method based on axial slicing, which relates to the technical field of point cloud data processing, is used for performing data completion on pipeline type point clouds, and comprises the steps of axially slicing preprocessed pipeline point cloud data, performing dimension reduction on three-dimensional point clouds to two-dimensional plane processing, and calculating related geometric parameters of pipelines. The method comprises the following steps: extracting a pipeline center line based on improved DBSCAN clustering and least square circle fitting, constructing a skeleton model under geometric topology constraints, combining local geometric features and global topology constraints, realizing geometric reconstruction of a missing region through rotating surface generation and a local interpolation algorithm, and realizing robust repair of the missing region. According to the method, a convex hull and an RANSAC method are combined to extract a pipeline center line and geometric parameters, pipeline point cloud data complementation is realized through a continuous rotation correction method, and the pipeline point cloud complementation quality is remarkably improved.

The application discloses a point-circle distance visual measurement method based on weighted circle fitting and uncertainty evaluation, comprising the following steps: S10, initial circle estimation and local region of interest (ROI) definition; S20, adaptive weighted circle fitting based on measurement point guidance; S30, point-circle distance calculation and uncertainty evaluation. The application realizes higher point-circle distance measurement precision and robustness than traditional methods; significantly reduces measurement errors caused by edge occlusion, noise and non-ideal circle deformation; provides quantitative evaluation (uncertainty) of the reliability of each distance measurement result; while ensuring high precision, maintains or improves calculation efficiency, so that it is suitable for online detection.

This invention discloses a method for estimating the rotor position of a robot servo motor based on circle fitting. The method includes: in each control cycle of the robot servo motor, using a Hall sensor to detect the absolute position of the servo motor rotor in real time and outputting two Hall signals; using a fitted Taubin circle and its parameters to perform debiasing and normalization processing on the two Hall signals output in each control cycle, and calculating the corrected rotor position angle for each control cycle using an arctangent function; wherein the Taubin circle is constructed based on data digitization and robust fitting using the RANSAC algorithm. This invention improves the accuracy of robot joint motor position detection and control performance by fitting a Taubin circle based on data digitization and the RANSAC algorithm, correcting the Hall signals in real time, and calculating the rotor position angle.

The invention discloses a target grid calligraphy practicing method based on a Chinese character circular structure model. The method comprises the following steps: a) extracting a Chinese character structure circle; b) constructing a target lattice; c) mapping strokes; the invention relates to the technical field of calligraphy teaching, by introducing a Chinese character circular structure model, the system breaks through the neglect of a traditional rectangular grid system on geometrical characteristics of Chinese characters, and by means of target grids constructed by golden proportion concentric circles and equally-divided radial lines, curvature, retraction and density changes of the Chinese characters can be quantified more accurately, so that the accuracy of calligraphy teaching is improved. The scientificity and aesthetic feeling of the writing composition are improved; an RANSAC circle fitting algorithm and an error quantification feedback mechanism are adopted, quantifiable deviation indexes are provided for teachers and students, subjective evaluation in the teaching process is reduced, and teaching efficiency and evaluation objectivity are improved; moreover, through a standardized target lattice template and an image registration technology, the problem that different teaching materials and teachers are inconsistent in definition of'gravity center 'and'middle palace' is solved.

This invention belongs to the field of integrated radar signal processing technology, specifically involving a two-stage clutter suppression method based on the space-time domain, which solves the problem of clutter suppression in complex low-altitude environments. First, the first stage, based on CLAM (Clear-and-Field Analysis), eliminates the dependence on the radial velocity difference between the target and clutter, directly and accurately shielding clutter from the physical space dimension, efficiently eliminating strong static ground object interference while preserving the energy of low-speed UAVs without loss. Second, the second stage, with its candidate angle traversal and circle fitting algorithm, accurately estimates and reduces the DC bias caused by residual static clutter, successfully overcoming the blind spot problem when the target and clutter spatial angles are close, enabling accurate extraction of weak, low-speed UAV targets at close range.

The invention discloses a centroid-offset-resistant multi-circle special-shaped target and a binocular vision positioning method thereof, and belongs to the technical field of industrial vision measurement and precise positioning, the target comprises a white background substrate and seven symmetrically distributed black circles, a large circle is arranged in the center, standard perfect circle small circles are arranged right above and right below respectively, and a large circle is arranged in the middle of the black circles. The four corners are respectively provided with special small circles which are designed according to a cylindrical surface nonlinear projection formula. The positioning method comprises the steps that a binocular camera collects a target image, and two-dimensional circle center coordinates are extracted; calculating a three-dimensional point cloud through stereo matching; extracting a cylindrical space axial vector and constructing a normal plane, and orthogonally projecting the three-dimensional feature points to the normal plane for two-dimensional circle fitting; and calculating the reference point coordinates of the internal anchoring column center and the surface highest axis through inverse coordinate transformation. According to the method, positioning errors caused by curvature deformation, space inclination and rotation around the axis of the cylinder are effectively overcome, and positioning robustness and universality under complex working conditions are remarkably improved.

The application discloses a circle fitting method and device and a storage medium. The circle fitting method comprises the following steps: performing edge detection processing on a to-be-fitted circular target in a target image to obtain edge detection points; selecting target detection points in the edge detection points to perform iterative fitting processing to obtain an iterative fitting circle; determining fitting weights corresponding to the target detection points according to the fitting matching degrees of the iterative fitting circle and the target detection points; and performing weighted iterative fitting processing according to the fitting weights and the target detection points to obtain target circular parameters of the to-be-fitted circular target. The above scheme can improve the circle fitting precision when the circular target is recognized.

The invention discloses a robot servo motor rotor position estimation method based on circle fitting, and the method comprises the steps: detecting the absolute position of a servo motor rotor in real time through employing a Hall sensor in each control period of a robot servo motor, and outputting two paths of Hall signals; performing debiasing and normalization processing on the two Hall signals output in each control period by using the fitted Taubin circle and the parameters thereof, and calculating the corrected rotor position angle in each control period through an arc tangent function; wherein the Taubin circle is constructed based on robust fitting of data centralization and an RANSAC (Random Sample Consensus) algorithm. Through the fitting Taubin circle based on data centralization and the RANSAC algorithm, the Hall signal is corrected in real time, the rotor position angle is calculated, and the robot joint motor position detection precision and the control performance are improved.

The invention discloses a vision measurement method based on STP model coordinate calibration, which comprises the following steps of: analyzing geometric features of an STP model to extract a measurement datum point and import tolerance information of the features, and then constructing a unified transformation relationship among an STP model coordinate system, a movement mechanism coordinate system and a camera coordinate system by adopting multi-point calibration, mapping from a model coordinate to an actual measurement coordinate and a measured feature under a camera pixel coordinate system is realized, and a detection path and a camera photographing pose are planned based on the model feature, so that automatic vision measurement of multiple features on a workpiece is realized; in the image processing stage, gray threshold segmentation is carried out by using the standard height of geometric features, the bottom surface and the feature surface of a workpiece are distinguished, the dimensions, heights and other parameters of template features are obtained by combining Blob region growth median feature extraction, circle fitting, plane fitting and other algorithms, and finally, the measurement result is compared with the standard tolerance of the model, so that the accuracy of the measurement result is improved. And outputting a detection report and deviation statistics.

The invention provides a method and device for detecting a cylinder in a point cloud and electronic equipment, and the method comprises the steps: projecting a three-dimensional point in the point cloud to a projection plane perpendicular to an axis through detecting the axis of the cylinder in the point cloud, and obtaining a projection point; and performing down-sampling processing on the projection points, and setting a mark number corresponding relation for each projection point after down-sampling. According to the invention, multiple circle fitting operations are executed, and each circle fitting is executed by using the projection point on the circle during the previous circle fitting, so that the precision of circle fitting is improved, and the precision of final cylinder detection is further improved. Besides, the mark number corresponding relation is established, so that the three-dimensional points before projection can be directly found based on the mark number corresponding relation under the condition that the circle is detected, the points on the cylindrical surface can be accurately positioned, the implementation process is more simplified, and the detection result is more accurate.

This invention relates to the field of precision measurement technology, and more particularly to a method and system for measuring the diameter of a test tube. The method includes: acquiring point cloud data of the cross-sectional profile of the test tube and splitting it into a test tube surface point set and a label surface point set; calculating the diameter of the test tube after performing optimal circle fitting using an improved bee colony algorithm. The optimal circle fitting using the improved bee colony algorithm includes: A10, defining the objective function and initializing the food source population and parameters; A20, sequentially executing the hired bee stage and the observation bee stage, updating the food sources and their corresponding stagnation counts; A30, entering the scout bee stage, checking the stagnation count of each food source, initializing food sources with stagnation counts exceeding the abandonment threshold according to a mixing strategy, and updating the food source population; A40, incrementing the current iteration count by 1 and returning to step A20, until the iteration termination condition is met. This invention improves the accuracy of test tube diameter measurement.

The application discloses a multi-class circle special-shaped target resisting heart drift and a binocular vision positioning method thereof, and belongs to the technical field of industrial vision measurement and precision positioning. The target comprises a white background substrate and seven symmetrical black circles, wherein a large circle is arranged at the center, a standard normal small circle is arranged above and below the large circle respectively, and four specially-made class circles are arranged at four corners respectively. The specially-made class circles are designed according to a cylindrical surface nonlinear projection formula. The positioning method comprises the following steps: a binocular camera collects a target image and extracts two-dimensional circle center coordinates; three-dimensional point clouds are solved through stereo matching; a cylindrical space axial vector is extracted and a normal plane is constructed, and three-dimensional feature points are orthogonally projected to the normal plane for two-dimensional circle fitting; and the coordinates of an internal anchor cylinder center and a surface highest axial reference point are solved through coordinate inverse transformation. The application effectively overcomes positioning errors caused by cylindrical curvature deformation, space inclination and rotation around an axis, and significantly improves the positioning robustness and universality under complex working conditions.

The invention relates to a borehole video image expansion method and device, and the method comprises the steps: carrying out the denoising and edge enhancement processing of a borehole image through a deep learning model, and obtaining a processed image; performing circle fitting on the basis of the drilling hole edge data points in the processed image to obtain a fitting circle, and determining the circle center and the radius of the fitting circle; calculating the distance between the center of the fitting circle and each boundary of the processed image, and determining the minimum value of all the distances; the image expansion area is an annular area, namely the annular area with the radius as the inner diameter and the minimum value as the outer diameter; and converting each coordinate point in the annular region into a coordinate point corresponding to the rectangular expanded image, and determining the pixel value of the coordinate point corresponding to the rectangular expanded image according to the pixel value of each coordinate point in the annular region. According to the method, denoising and edge extraction are carried out on the drilling video image, and when drilling hole circle fitting is carried out, an accurate image expansion result can be obtained based on an interior point majority principle.

The invention relates to a multi-arc-segment symmetric structural member measurement system, method and device and a storage medium. The system comprises an OCT image acquisition device, a contour extraction module, a curve analysis module and a circle fitting module, the OCT image acquisition device is used for acquiring an original tomographic image of a to-be-detected sample by utilizing an OCT imaging technology, and the contour extraction module is used for extracting surface contour features of the preprocessed image by adopting morphology and a connected region processing algorithm; the curve analysis module is used for performing curvature analysis and segmental arc identification on the surface contour features based on a differential geometry principle and a multi-scale analysis method, and the circle fitting module is used for performing geometric analysis on segmental arc segmentation results by combining algebraic fitting and geometric fitting algorithms, judging the opening direction of each segmental arc and generating circle fitting parameters. According to the invention, an end-to-end automatic measurement process is formed by using an integrated design, the operation cost and time consumption are reduced, and the measurement precision, efficiency and reliability are improved.

This invention relates to a method and system for extracting anchor drill hole contours based on contour geometric constraints. The method includes: acquiring an image of an anchor drill hole on a steel strip using a camera; preprocessing the image; determining the image edge information of the preprocessed anchor drill hole image using the Canny edge detection method; determining the upper and lower edge straight line information of the steel strip in the image based on the image edge information and using the Hough line detection method, and taking the upper and lower edge straight line information of the steel strip in the image as the region of interest; determining a circular contour within the region of interest using a circle fitting method; and determining the anchor drill hole contour based on the circular contour and contour geometric constraints. The contour geometric constraints are a functional relationship between the distance between the camera and the steel strip and the radius of the anchor drill hole. This invention can improve the accuracy of anchor drill hole contour extraction.

The application discloses an axial slice-based underground mine pipeline point cloud completion method, relates to the technical field of point cloud data processing, and is used for data completion of pipeline point cloud, and comprises the following steps: slicing a pipeline point cloud data after preprocessing along an axial direction, reducing three-dimensional point cloud to two-dimensional plane processing, calculating related geometric parameters of the pipeline, extracting a pipeline center line based on improved DBSCAN clustering and least square circle fitting, constructing a skeleton model under geometric topological constraints, combining local geometric features and global topological constraints, realizing geometric reconstruction of a missing area through a rotary surface generation and local interpolation algorithm, and realizing robust repair of the missing area. The application extracts the pipeline center line and geometric parameters in combination with a convex hull and a RANSAC method, realizes completion of the pipeline point cloud data through a continuous rotation correction method, and significantly improves the completion quality of the pipeline point cloud.

This invention discloses an automatic detection and sorting process for ball track dimensional defects within a ball cage shell, relating to the field of ball track dimensional defect detection. The process includes: acquiring an original contour point cloud dataset; obtaining a robust ball track contour dataset using random sampling circular arc fitting; establishing a spatial radial dimension compensation model to obtain the radial dimension correction value at the bottom of the ball track and the corrected ball track contour coordinates; obtaining the compensation value for the ball track arc radius based on a least-squares circle fitting algorithm; calculating the angular deviation and straightness error of each ball track to generate a multi-dimensional dimensional defect feature vector; and sorting the workpieces into qualified, reworkable, or scrap bins using a pneumatic sorting mechanism based on the comparison results. The advantages of this invention are: by combining anomaly point suppression and clamping posture calibration compensation, the influence of surface interference and clamping errors on measurement accuracy is eliminated, achieving high-precision automatic detection and reliable grading and sorting of ball track dimensions within the ball cage shell.

The invention relates to the technical field of machine tools, and provides a lathe tool setting method which is based on a tool setting gauge installed on a spindle box of a lathe, and the lathe tool setting method comprises the steps that a current moment image of a tool nose part of a lathe tool is obtained; extracting a tool nose contour value of the lathe tool from the image at the current moment; least square circle fitting is carried out according to the contour values of the tool noses, so that the tool center position of the lathe tool at the current moment is obtained; and according to the tool center position at the current moment and the target tool center position, the relative position of the lathe tool and the spindle box is adjusted, so that tool setting operation of the lathe tool is completed. In this way, the least square circle fitting mode can integrate information of all tool nose contour values, interference of local tool abrasion or image noise on the tool center position determination result is effectively reduced, the accuracy and stability of the determined tool center position are improved, then the tool setting accuracy is improved, and the tool setting accuracy is improved. The problem that the tool setting precision is poor when the lathe tool is set in the prior art is solved.

A complex structure workpiece drilling parameter measurement method based on a shrinking neighborhood circle boundary point clustering algorithm, applying computer vision and machine learning technology, proposes a shrinking neighborhood circle boundary point clustering algorithm, improves the accuracy of boundary point clustering, and an iterative circle fitting method based on fitting degree improves the accuracy of drilling recognition and fitting, so that the constructed three-dimensional measurement model can be used for workpiece drilling parameter acquisition, and the measurement error is less than 0.05mm, meeting the engineering requirements.