18 results about "Subpixel edge detection" patented technology

The invention relates to the technical field of vertical shaft guide detection, in particular to an industrial intelligent visual detection and diagnosis system for a vertical shaft guide. The coal dust shadow quantization unit extracts a coal dust region by adopting a double-peak self-adaptive threshold segmentation combined region growing algorithm, and introduces a space weight factor to calculate an average gray value and a coverage area proportion, and the dynamic coupling calibration unit depends on a three-dimensional lookup table calibrated by multiple working conditions and nonlinear interpolation; the optimal deviation compensation coefficient of the jitter and coal dust combination is matched, a dynamic gray segmentation threshold value is generated, and a defect diagnosis decision unit accurately calculates the abrasion depth through partition self-adaptive segmentation, multi-scale morphological filtering and denoising and gradient amplitude and curvature double-constrained sub-pixel edge detection. A hierarchical control instruction is output according to the real-time depth and the historical trend, coupling interference is eliminated, the cage guide abrasion detection accuracy is improved, and a reliable basis is provided for safe operation and maintenance.

This invention provides a machine vision-based method and system for measuring the dimensions of circular threads. First, it achieves complete coverage of the entire thread profile by acquiring multiple local images, overcoming the limitation of a single field of view in capturing the entire thread. Second, it extracts the contours of each image frame through sub-pixel edge detection and performs in-depth analysis of feature points within each frame. Subsequently, a feature-constrained stitching model is established to achieve precise alignment and global optimization of data from different fields of view, reducing the error amplification effect caused by geometric mismatch and viewing angle deviation, and suppressing nonlinear errors in parameter accuracy within the measurement range. This method can comprehensively and accurately measure key parameters of circular threads (such as taper, pitch, thread profile variation, and minimum effective connection length). This method not only significantly improves the overall accuracy and reliability of thread measurement but also provides a solid technical guarantee for the safety and durability of oil well pipeline connections, and has important reference value for research and application in related fields.

This invention relates to the field of pharmaceutical automation equipment and discloses an intelligent sampling robot suitable for drug production. The robot includes a multi-sensor fusion positioning system, a force control coordination system, and a cleanroom structure design. The multi-sensor fusion positioning system comprises a 3D laser positioning module, a binocular vision module, a sub-pixel edge detection module, and a sensor fusion algorithm. The force control coordination system includes a hybrid RNN-LSTM (Recurrent Short-Term Memory) and CNN (Convolutional Neural Network) network, an airbag gripper, a six-dimensional force sensor, and an underactuated rotation mechanism. The cleanroom structure design includes a mechanical gripper, a nano-sterile coating, and a stainless steel IP69K sealing structure. By employing a fusion algorithm combining extended Kalman filtering and fuzzy evidence theory, efficient fusion of multi-sensor data is achieved. Dynamic threshold adjustment is realized through the hybrid RNN-LSTM and CNN network, reducing force control fluctuations and lowering production costs.

The invention discloses a transverse image distance measuring device and method for transformer replacement traction, and belongs to the technical field of power equipment maintenance. The device comprises a transverse visual image deviation measuring system, a mounting frame, a quick clamping device and an image processing host, the visual deviation measuring system is arranged above a main transformer transfer trolley track wheel carrier through the mounting frame and the quick clamping device, and the visual angle of the visual deviation measuring system is adjusted to be perpendicular to a track; the system collects images of track wheels and tracks; the method comprises the following steps of: based on an image, extracting a track and a wheel rim edge through a sub-pixel edge detection algorithm which comprises image preprocessing and is based on a Zernike moment, and calculating a transverse deviation amount; according to the method, traditional manual plumb line measurement is replaced with non-contact image measurement, the measurement precision is greatly improved, uninterrupted continuous monitoring is achieved, the rail gnawing risk is effectively eradicated, and the operation safety and universality are remarkably improved.

The invention discloses a method and a device for measuring the motion idle stroke and the overall flexibility of a flapping-wing aircraft mechanism, and relates to the field of miniature aircrafts, and the method comprises the steps: loading an aircraft wing rod on a high-speed camera measurement platform, and recording an image of the wing rod in a motion period; after the recorded image is optimized and denoised, an optical flow method is used for capturing a moving wing rod, a sub-pixel edge detection method is used for recognizing a gray level image of wing rod movement, then the edge is optimized and corrected based on the geometrical characteristics of the wing rod, and edge calibration is carried out on the gray level image of wing rod movement; then, the angular displacement of the wing rod is recognized according to the wing rod motion gray level image after coordinate calibration is completed, meanwhile, the distribution load of the wing rod is reconstructed, and inversion is conducted on the bending moment of the wing rod through recognized coordinate information and a Tikhonov regularization method; and finally, drawing an angular displacement-bending moment curve graph of the wing rod and extracting the idle stroke and the overall flexibility of the aircraft. According to the method, the motion idle stroke and the overall flexibility of the mechanism on the flapping-wing air vehicle are effectively extracted with high precision, and the method has great guiding significance in design, test and function research of the flapping-wing air vehicle.

The application discloses a kind of based on edge feature direction code matching's hydraulic hoist tower structure deformation measurement method, belong to computer vision measurement field, this method includes the following steps: using subpixel edge detection method to the detection area image is handled, obtain subpixel edge line position and subpixel edge direction;Based on subpixel edge direction, using direction code encoding method to the edge direction angle is handled, obtain the edge direction code of discretization, and based on the edge direction code of discretization the edge direction code of left and right camera image is calculated;Based on binocular stereo vision system, using template matching method and parallax principle to the edge direction code of left and right camera image is matched, calculate the spatial three-dimensional coordinates of detection area matching coefficient maximum point;Based on the spatial three-dimensional coordinates change of same detection point before and after structure deformation, obtain the deformation of hydraulic hoist tower structure.

The present application relates to the vertical shaft cage detection technical field, specifically, it relates to a kind of industrial intelligent vision detection and diagnosis system for vertical shaft cage, acquisition unit synchronously obtains cage flange surface image and cage car pitch angle, coal dust shadow quantization unit uses bimodal adaptive threshold segmentation combined with region growing algorithm to extract coal dust area, introduce space weight factor to calculate average gray value and coverage area proportion, dynamic coupling calibration unit relies on three-dimensional look-up table and nonlinear interpolation of multi-working condition calibration, match the optimal deviation compensation coefficient of the combination of jitter and coal dust, generate dynamic gray scale segmentation threshold, defect diagnosis decision unit is through zoned adaptive segmentation, multiscale morphological filtering denoising, combined with gradient amplitude and curvature double-constraint subpixel edge detection accurately calculate wear depth, according to real-time depth and historical trend output grading control instruction, eliminate coupling interference, improve cage wear detection accuracy, provide reliable basis for safe operation.

The application relates to a multi-camera large-size visual measurement method and system, which comprises the following steps: installing a plurality of cameras for large-size measurement; marking a group of three-coordinate marker points in the visual field of each camera on a calibration whiteboard by using a three-coordinate measuring machine, and recording the three-coordinate positions and sequence of each three-coordinate marker point; acquiring images of the three-coordinate marker points in the visual field of each camera on the calibration whiteboard by the camera, and obtaining the center positions of the regions where the three-coordinate marker points are located; obtaining the pose transformation matrix of all the cameras; adopting a sub-pixel edge detection algorithm based on Gaussian fitting on the images collected by the camera to obtain an edge point set, and fitting an edge straight line by using the edge point set; obtaining a straight line intersection point based on the edge straight line; converting the straight line intersection point to a world coordinate system based on the obtained pose transformation matrix; and obtaining a size based on the converted position. The application is used for high-precision large-size visual measurement.

The invention discloses a bridge expansion joint disease monitoring method and system based on time sequence image analysis, and belongs to the technical field of bridge structure health monitoring, and the method comprises the steps: installing fixed industrial cameras at the two sides of an expansion joint, regularly collecting high-resolution images, and synchronously obtaining temperature data; accurate registration of images in different periods is realized through feature point matching; identifying diseases such as rubber strip aging, profile steel warping, foreign matter blockage and concrete damage by adopting a deep convolutional neural network; a sub-pixel edge detection algorithm is utilized to measure the seam width, and a seam width-temperature response curve is established to identify abnormal deformation; according to the method, automatic detection, high-precision measurement and trend early warning of expansion joint diseases are realized, and the method is suitable for remote intelligent supervision of expressway bridge groups.

The application discloses an oil saw guide plate flatness and groove wear image measurement method and system, relates to the technical field of machine vision image measurement, and the method obtains guide plate multi-source fusion image data through the cooperative collection of a line laser projection and coaxial light source illumination, calculates the flatness deviation by using three-dimensional point cloud reconstruction and reference plane fitting, adopts sub-pixel edge detection and multi-section statistical measurement to quantize groove wear parameters, fuses the flatness and groove wear indexes to calculate a comprehensive wear index and output a grading maintenance suggestion, and automatically generates a detection report, thereby providing an objective quantitative basis for oil saw guide plate quality detection.

The invention discloses a foaming rate detection method and device, electronic equipment and a storage medium, and relates to the technical field of image processing, and the method comprises the steps: obtaining a product image containing a foaming region in a to-be-detected product, carrying out the sub-pixel edge detection, and obtaining a sub-pixel edge point sequence, the product image is an image acquired after the foaming area of the to-be-detected product is sliced under the ultraviolet rays with the preset wavelength; determining a first positioning contour area containing at least two sub-pixel edge points in the product image according to the sub-pixel edge point sequence; determining a candidate image area in the product image according to a preset pixel dynamic threshold value, and determining a second positioning contour area with bubbles according to the first positioning contour area and the candidate image area; and determining a first image region representing the bubbles in the second positioning contour region, determining an optimal circumcircle corresponding to the first image region, and determining the foaming rate of the bubbles in the foaming region according to the optimal circumcircle. The foaming rate detection efficiency is improved.

The application discloses a kind of fusion improved YOLO and subpixel extraction's slope deformation visual detection method, belong to image data processing technical field, including constructing slope dataset;Improved YOLO model is constructed;Improved YOLO network is trained with slope dataset, and improved YOLO model is obtained;In real monitoring point, image in video is carried out key point detection with improved YOLO model, and key point prediction pixel level coordinates are output;Subpixel edge detection method of Zernike matrix is used to generate the subpixel coordinates of key point, and cumulative displacement monitoring is carried out based on subpixel coordinates.The application keeps the advantages of YOLOv8 algorithm deployment efficiency and model light weight, significantly improves the precision of highway slope displacement monitoring, breaks through the pixel level limit and pursues the displacement perception ability of submillimeter level, easy to deploy intelligent highway slope displacement real-time monitoring, effectively prevent disasters.

This invention discloses a high-precision online visual inspection system and method for LED carrier tape based on a dual-station setup. The inspection system in this invention features an adjustable dual-station configuration to meet the requirements for inspecting the planar appearance and thickness dimensions of the LED carrier tape. The structural design fully considers compatibility, inspection speed, and the maximum permissible operating speed of the carrier tape. Furthermore, addressing the challenges of miniaturized carrier tapes and high precision requirements, a least-squares sub-pixel edge detection algorithm is proposed. This algorithm can effectively detect various feature dimensional parameters on the LED carrier tape, achieving high-speed, high-precision positioning and recognition of feature points on the carrier tape image. To address the issue of defocus blurring when the carrier tape moves beyond the lens's depth of field, a linear compensation algorithm is proposed. This algorithm provides real-time feedback of inspection data, quickly guiding the camera and enabling rapid on-site debugging in industrial settings, ensuring the system can be truly applied in industrial production environments.

The application provides a camera calibration method and device, which comprises the following steps: collecting defocus images of a ring calibration board at different angles, and performing sharpening processing on the defocus images at different angles to obtain sharpened defocus images; performing edge detection on the sharpened defocus images based on a sub-pixel edge detection algorithm to obtain an edge detection image; performing edge abnormal point elimination operation on the edge detection image to obtain a target defocus image, so that the ring edge data is more accurate; determining a point array corresponding to the projection center of a plurality of rings on the ring calibration board on the target defocus image; performing normalization processing on the point array to obtain a point matrix of a normal focus image corresponding to the target defocus image. Finally, the camera is calibrated based on the point matrix of the normal focus image, and the problem that the feature point coordinates cannot be accurately extracted and the error is large in the camera calibration process in the ultra-large result and long-distance computer vision measurement process of the existing calibration method is solved.

The invention discloses a slope deformation visual detection method fusing improved YOLO and sub-pixel extraction, and belongs to the technical field of image data processing, and the method comprises the steps: constructing a slope data set; an improved YOLO model is constructed; training the improved YOLO network by using the slope data set to obtain an improved YOLO model; carrying out key point detection on an image in a video at a real monitoring point by using an improved YOLO model, and outputting a key point prediction pixel-level coordinate; and a Zernike moment sub-pixel edge detection method is used to generate sub-pixel coordinates of the key points, and accumulated displacement monitoring is carried out based on the sub-pixel coordinates. On the basis of keeping the advantages of deployment high efficiency and model lightweight of the YOLOv8 algorithm, the precision of road slope displacement monitoring is remarkably improved, the pixel-level limitation is broken through, the submillimeter-level displacement sensing capacity is pursued, intelligent road slope displacement real-time monitoring of actual deployment is facilitated, and disasters are effectively prevented.

The application discloses a fruit and vegetable image sub-pixel edge detection method based on Gaussian modeling. In view of the situation that the left and right sides of the approximate Gaussian curve are not equal in the conventional sub-pixel edge detection, the introduction of a cubic fitting factor helps to change the original Gaussian modeling curve symmetry structure and adjust the height range of the left and right wings to make it closer to the actual data curve characteristics. By constructing a fruit and vegetable image sub-pixel edge detection error function, the Gaussian curve fitting coefficient optimization value, the Gaussian curve fitting median optimization value, the Gaussian curve fitting standard deviation optimization value and the cubic fitting factor optimization value are determined. The gradient amplitude of the pixel point can give the corresponding fruit and vegetable image sub-pixel edge detection Gaussian curve fitting value to judge whether it is a sub-pixel edge point, so as to complete the fruit and vegetable image sub-pixel edge detection.

The invention discloses a sub-pixel edge detection method and device and a storage medium in the technical field of computer vision and image processing, and the method comprises the steps: carrying out the weighted total least square straight line fitting based on a joint weight, and obtaining a local main direction straight line; calculating an orthogonal residual error of the candidate sample based on the local main direction straight line, calculating a Huber type robust weight according to the size of the orthogonal residual error, and carrying out primary reweighting and refitting based on the Huber type robust weight and a joint weight to obtain a stable main direction straight line; and carrying out linear interpolation type smooth updating based on the current position and the target position of the sub-pixel point, carrying out chaining according to direction continuity and geometric adjacency, and outputting a sub-pixel edge curve set. According to the invention, the technical problems of positioning jitter, wrong connection / disconnection and outlier traction in a scene with complex texture and low signal-to-noise ratio in the existing sub-pixel edge detection technology can be solved.

This invention relates to a high-precision weld joint inspection method and system, comprising: acquiring photographs of a circular plate-like part to be inspected; determining the center and diameter of the circular plate-like part; performing image preprocessing and coarse positioning on the photographs to obtain candidate baselines and candidate circles; filtering the candidate baselines and candidate circles to obtain measurement baselines and measurement circles; constructing baseline measuring calipers and circular measuring calipers; employing a sub-pixel edge detection algorithm to extract sub-pixel edge points; fitting straight lines and ellipses and calculating distances to achieve weld joint defect detection. This invention automatically filters and measures the inspection results, eliminating manual intervention and achieving high-precision automatic weld joint measurement.