27 results about "Hough transforms" patented technology

The application discloses a high-precision moon tracking method based on image processing, which comprises the following steps: according to local GPS information, the height angle and the azimuth angle of the moon relative to the local position are calculated by using an astronomical algorithm and are sent to an execution module for pre-adjustment, so that the moon is preliminarily tracked; the moon target in the gray-scale image is recognized by using a Hough transform, the position of the moon center in the image and the moon radius are obtained, the weight of each pixel point in the image to the moon brightness is calculated, the weighted center is obtained, the accurate position of the moon brightness center is obtained, the azimuth deviation and the pitch angle deviation of the moon brightness center and the optical axis are calculated, and if the deviation data exceeds a preset threshold value, the deviation data is sent to the execution module for correction and adjustment. The moon image is collected in real time by using a CCD, the moon center and the radius are recognized by using an image processing method, the accurate position of the moon brightness center and the deviation of the moon brightness center and the optical axis are calculated by using parameters, the high-precision real-time tracking of the moon is realized, and the method has the advantages of high precision, rapid response and the like.

This invention discloses a video tracking and recognition method for the spatial trajectory of hoisted objects based on multi-source data fusion, belonging to the field of machine vision monitoring technology. The method includes acquiring pre-loaded physical boundary constants of the tower crane and simultaneously collecting multi-source data during tower crane operation. Based on the physical boundary constants, kinematic calculations are performed on the multi-source data to obtain the relative vertical displacement, the three-dimensional absolute spatial coordinates of the luffing trolley center point, and the absolute coordinates and three-dimensional rotation matrix of the camera's optical center in the global three-dimensional coordinate system. Edge detection is performed on the temporally aligned color video frame matrix to extract candidate wire rope contours and generate a binary edge pixel matrix. Collinear edges are mapped to polar coordinate space using Hough transform. This invention reduces the uncertainty of monocular vision depth scale and improves stability and accuracy under conditions of large-amplitude lifting and complex swinging.

This invention provides a method for synchronous measurement and data fusion of surface coordinates, position degree, and step difference in a wind tunnel, belonging to the field of surface technology in wind tunnels. This invention acquires raw point clouds by deploying a laser displacement sensor array and a 3D scanner in the wind tunnel test section. A refraction field prediction model is established using temperature and pressure data, and optical path deviations are corrected using a ray tracing algorithm. The point cloud is divided into surface regions and step difference regions using octree spatial indexing and region growing segmentation. The position degree deviation is calculated using the moving least squares method for the surface regions, and sub-pixel-level step difference measurement is achieved for the step difference regions through morphological operations, double-threshold hysteresis tracking, and Hough transform. Finally, a multi-source data fusion weight allocation function is established based on measurement uncertainty to generate a comprehensive measurement report. This invention solves the technical problem of the inability to synchronously and accurately measure the three types of geometric parameters—surface coordinates, position degree, and step difference—under high-speed airflow conditions in wind tunnels.

This invention relates to a dynamic scanning compensation method and DNA synthesis device based on inkjet printing, belonging to the field of DNA synthesis. By applying threshold segmentation, connected component analysis, and circular Hough transform to a standard analysis image, a circular region for each reaction site is obtained. Based on the distance of all edge points of each reaction site from the center of the circular boundary, it is determined whether each reaction site meets the roundness requirements, thus obtaining information on missing reaction sites. Simultaneously, to address potential inaccuracies after the circular Hough transform, the results are calibrated using the YOLO target detection model based on a convolutional neural network, achieving high-precision detection of missing reaction sites suitable for industrial applications. Furthermore, by adding recognition weights for defective reaction sites such as those with "partially excessive distances from the center" during YOLOv6 model training, the compatibility between the two is further improved, enhancing detection accuracy and meeting the requirements of high-precision DNA synthesis.

The present application relates to a kind of suspension bridge pin joint type sling rotation angle measurement method, comprising the following steps: S1, selecting the two places of sling of suspension bridge around lower pin shaft rotation site are carried out transverse marking and longitudinal marking;S2, the marked part of rotation site is videoed and frame is extracted, and the image sequence after frame extraction is obtained;S3, the image gray scale of image sequence after frame extraction is carried out using self-defined single channel method;S4, after the pre-processing of gray-scale image, all straight lines of image are identified using Hough transform, and the long straight line located at the edge of transverse marking and longitudinal marking is extracted;S5, the angle between long straight line respectively located at the edge of transverse marking and longitudinal marking is calculated, and the angle value of sling around pin shaft rotation with time variation in acquisition time period is obtained.The method proposed in the present application can realize the measurement of sling around pin shaft rotation angle, and provide reliable data basis for sling rotation law and related damage mechanism research.

This invention discloses a deep learning-based intelligent detection and classification method for wafer defects, belonging to the field of computer vision technology. First, a multi-scale pyramid decomposition is performed on the original wafer grayscale image. Then, a Fast Fourier Transform is performed on each layer of the image in the frequency domain. An adaptive sliding window detector and Hough transform are used to accurately identify and locate frequency peaks representing periodic background. Next, an adaptive notch filter is constructed and applied to suppress these periodic background frequencies, and non-periodic defect signals are explicitly enhanced by calculating frequency domain residuals. Finally, the multi-scale processed defect enhancement residual maps are fused to generate the final defect enhancement map, which serves as the input to the deep learning detection network. This invention solves the problem in existing technologies where low-contrast micro-defects are easily obscured by the strong periodic background texture of the wafer, leading to low detection accuracy and poor model generalization ability.

This invention relates to the field of infrastructure engineering technology, specifically to a machine vision-based method and system for locating spraying areas. The method includes: using a depth camera to capture the original point cloud of the beam surface, segmenting and selecting target planes on the beam surface using the RANSAC algorithm; converting the image to two dimensions, extracting line features using Hough transform and edge detection, inversely mapping back to three dimensions, and selecting the uppermost point of the line; moving the camera upwards to capture the point cloud of the upper part of the beam, removing interference to extract two target planes; calculating the normal vectors of the two planes, comparing the point cloud to obtain the coordinates of the calibration points, constructing a new three-dimensional coordinate system and generating a rotation matrix; and planning the robot spraying path based on the beam surface design parameters. The system includes: a depth camera, point cloud segmentation, two-dimensional mapping and feature extraction, three-dimensional coordinate recovery and key point selection, spatial calibration, and path planning modules, which work together to implement the above method, eliminate point cloud blind spots, improve positioning accuracy, and meet the requirements for precise spraying of beam surfaces.

This invention relates to a data processing method for single-event multi-track detection based on a time projection chamber, belonging to the field of particle track analysis technology. The method includes the following steps: S1: Denoising preprocessing of the original points; S2: Reconstructing and correcting all tracks in the event using three-dimensional iterative Hough transform and weighted least squares method, outputting the linear equation of each track; S3: For a given straight line, calculating the distance from all points in the event to the straight line, setting a distance threshold, and considering points less than the threshold as points located on the straight line, thereby achieving track splitting; S4: Overfitting processing of the split tracks. This invention improves the processing effect of time projection chamber and other particle track detectors on single-event multi-track detection, providing a practical solution for high-energy particle multi-track detection and identification.

The application discloses a borehole multi-source cooperative imaging method based on a cable drilling rod in a coal mine underground, comprising the following steps: acquiring a stratum original state image in a drilling process through an imaging unit integrated at the tail end of the drilling rod, and simultaneously purifying an imaging area by using a cleaning module arranged on the drilling rod; transmitting the acquired stratum original state image to a ground control system, and then identifying a fissure through a Bi-PTI model; detecting a straight line feature of a fissure area by using an optimized Hough transform, and outputting a detection report containing geological annotation after calculating a fissure width and a fissure dip angle. The application can save a secondary detection process in the while-drilling imaging, improve a single-hole detection time, adapt to complex working conditions such as steeply inclined coal seams and curved holes, and meanwhile, can realize lens self-cleaning and image intelligent analysis, and improve detection precision.

This invention discloses a method and apparatus for calibrating a telecentric structured light system based on the geometric center of a checkerboard pattern. The method includes: selecting test calibration board images from a set of calibration board images; performing image edge detection and binarization based on the Sobel operator to obtain a binarized edge map; performing line detection based on the Hough transform, calculating the rotation correction angles corresponding to the vertical lines of the checkerboard pattern, and constructing a rotation matrix using the rotation correction angles; constructing a standard checkerboard pattern template based on ROI selection and edge expansion processing of the test calibration board images; performing normalization processing on each calibration board image, and then performing template matching and sub-pixel-level center localization with the standard checkerboard pattern template to finally determine the center coordinates of the checkerboard pattern in the corresponding calibration board image as feature point coordinates; and using the rotation matrix to perform attitude correction on the feature point coordinates of each calibration board image, thereby calibrating the telecentric structured light system. This invention can significantly improve calibration accuracy and stability.

This invention discloses a method and apparatus for detecting and guiding irregular stripe noise removal in nighttime light remote sensing images. The method includes: dividing the original image into areas with strong light sources, no light, and areas to be processed, and enhancing the edges to obtain an enhanced image; performing iterative detection of stripe noise based on the enhanced image using frequency domain analysis and multi-constraint Hough transform to obtain a stripe mask; aligning the stripe mask with the binary image of the original image based on morphological operations and then performing inter-band filtering to obtain a noise-free mask; obtaining the noise target region based on the noise-free mask and the original image; performing progressive noise correction on the noise target region based on a dynamic window and an adaptive correction algorithm to obtain an initial result; and performing residual correction based on the initial result and the strong light source region to obtain a destriped image.

This invention discloses a TBD (Target Breakdown Dictation) method for weak targets under range ambiguity combined with sparse representation, belonging to the field of data processing technology. It acquires ambiguity-inducing sensor range measurement data and performs sparse decomposition and reconstruction using sparse representation to initially estimate the ambiguity of the target's position. The ambiguity track is initiated using the Hough Transform TBD algorithm, and range deambiguity is achieved by combining the Chinese Remainder Theorem. The pulse interval increment is modeled as a Markov chain, predicted using a Long Short-Term Memory (LSTM) network, and the state prediction value is deambigued based on the predicted value. This prediction is then correlated with the current unambiguous measurement and filtered to complete the track update. Track management is performed, including canceling failed tracks and initiating new tracks, and this process is repeated until tracking ends. This invention achieves effective target detection, stable tracking, and continuous management in scenarios with sensor range ambiguity and low signal-to-noise ratio, improving deambiguity accuracy and tracking robustness, and is suitable for complex detection scenarios such as weak targets.

This invention discloses a system for identifying and judging fractured surrounding rock at the tunnel face. This invention relates to the field of tunnel and underground engineering geological exploration technology, solving the technical problem that existing technologies struggle to simultaneously achieve both high accuracy and real-time judgment of fractures in complex construction environments. The system includes an image acquisition module, a main control module, a storage module, and a display module. The main control module performs multi-scale decomposition of the image, uses a lightweight deep convolutional neural network to coarsely locate fracture regions in low-resolution images to generate a mask, and performs adaptive threshold edge detection, connected component morphological filtering, Hough transform linear fitting, and local edge connection on the target region of high-resolution sub-image blocks. The fracture traces are then fused with the mask to verify the output result. This invention combines deep learning localization with traditional edge extraction, reducing computational complexity while ensuring fracture identification accuracy, achieving a unified high-precision identification and real-time judgment of fractures at the tunnel face in complex construction environments.

The application provides a sea-sky line detection method based on semantic segmentation and Hough transformation, and specific steps are as follows: S1: inputting a visible light image of a water traffic scene, and preparing a data set of the water traffic image; S2: establishing a Mo-SegNet network model of the water traffic image as a semantic segmentation model, and performing pixel-by-pixel segmentation on the input test set of the water traffic image to output a semantic segmentation image; S3: performing edge detection on the semantic segmentation image output by S2 by using a Canny detection algorithm, and outputting a binary image containing only the edge contour of the sea-sky line and a background; and S4: performing Hough transformation on the binary image, fitting the edge pixels of the edge contour of the sea-sky line, and obtaining a sea-sky line detection result. The Mo-SegNet network model is used as the semantic segmentation model, and the Hough transformation is used to fit the sea-sky line, so that accurate detection of the sea-sky line in a complex water traffic scene is realized.

This invention provides a method and system for controlling carbon monoxide concentration in sintering flue gas based on the preparation of dust-collecting ash pellets, relating to the field of metallurgical solid waste treatment technology. The method includes: S1, obtaining raw materials for dust-collecting ash pellet preparation and mixing the raw materials; S2, using an improved visual recognition model to perform image segmentation and particle size calculation of the dust-collecting ash pellets to obtain the dust-collecting ash pellets; S3, using a combined edge contour and Hough transform detection method to calculate the particle size of the dust-collecting ash pellets; S4, controlling the carbon monoxide concentration during the sintering process through the dust-collecting ash pellets. This invention, through the identification of dust-collecting ash pellet particle size and standardized control of the pelletizing process, ensures that the pelletizing particle size is concentrated within the target range; simultaneously, it establishes the relationship between pellet particle size and carbon monoxide concentration, clarifying the influence of particle size on carbon monoxide emissions; and through the synergistic regulation of the dust-collecting ash ratio and pellet particle size on carbon monoxide concentration, it solves the problem of dust-collecting ash accumulation pollution in the steel manufacturing process.

This invention belongs to the technical field of inertial navigation systems, specifically relating to a transfer alignment method based on Hough transform. The method includes the following steps: listing several parameter sets, transmitting acceleration and angular velocity readings, calculating the matching degree, determining whether coarse alignment is complete, relisting the parameter sets, transmitting acceleration and angular velocity readings, calculating the matching degree, and determining whether precise alignment is complete. This invention does not require a dedicated mathematical model of the inertial navigation system and can universally measure the installation angle and delay time of various inertial navigation systems to achieve transfer alignment. Its outstanding advantage is its good versatility.

This invention relates to a machine vision-based method for automatic wafer flipping and positioning. A panoramic area scan camera is mounted on the back side of the load port to acquire wafer images and transmit them to a host PC. The system employs traditional algorithms such as Gray-Level Co-occurrence Matrix (GLCM), Canny edge detection, and Hough transform, combined with a Convolutional Neural Network (CNN), to achieve wafer front and back recognition, contour localization, and grinding quality assessment. When the robot grasps the wafer, the system automatically identifies the grasping surface. If it is the front side, the system controls the robot to adjust the wafer orientation via a flipping mechanism, ensuring that the wafer enters the subsequent process with the back side facing up. This method enables automatic wafer inspection, positioning, and quality monitoring before and after grinding, with a positioning accuracy of ±0.01mm and a front and back recognition accuracy of ≥99.8%, significantly improving the automation level and production efficiency of semiconductor manufacturing.

A method for rapidly detecting a straight line, a plane and a hyperplane in a multi-dimensional space. The new method has two important advantages: firstly, the model corresponds to a total least square fitting algorithm and has better tolerance to data noise, so as to solve the problem of the precision of detecting a target on a parameter space segmentation line by means of fast Hough transform being too low; and secondly, in the integrated fast Hough transform, targets that are close to each other in a data space are gathered together in a parameter space, and a calculation process in the parameter space can be displayed by using a visual graph, thereby rapidly determining the number of targets, guiding the setting of system parameters, and distinguishing a target that is repeatedly recognized.

This invention discloses a robust imaging method and system for maneuvering targets based on Hough transform and coherent cumulative phase function. It primarily addresses the problems of high computational complexity and the susceptibility to image quality issues caused by multi-target cross-terms in existing target imaging methods. The solution includes: receiving echoes and performing range pulse compression; correcting range migration using Hough+SOKT transform; extracting the echoes in the range cells after range migration correction and establishing a delay cross-correlation function for order reduction; jointly estimating the coefficients of the second and third terms using the CICPF algorithm; constructing an azimuth matched filter to pulse-compress the echoes after range migration correction; and processing the pulse-compressed echo data using range IFFT and azimuth FFT to obtain a precisely focused target image. This invention avoids joint parameter search and avoids cross-terms between multiple targets by first correcting migration and then extracting cell order reduction, thus improving imaging quality. It can be used for the reconnaissance of maneuvering targets such as ships and aircraft.

The invention discloses a DNA synthesis equipment dynamic scanning compensation method based on ink-jet printing and DNA synthesis equipment, and belongs to the field of DNA synthesis. Threshold segmentation, connected domain analysis and circular Hough transform are carried out on a standard analysis image, a circular area of each reaction site is obtained, whether each reaction site meets the roundness requirement or not is judged according to the circle center position from all edge points of each reaction site to the circular boundary of each reaction site, and if yes, the roundness of the reaction site is judged. And acquiring information of the deletion reaction site. And meanwhile, aiming at possible inaccuracy after circular Hough transform, a target detection model YOLO based on a convolutional neural network is combined to calibrate a result, so that high-precision detection of a deletion reaction site suitable for industrial application can be obtained. Furthermore, by increasing the recognition weights of defect reaction sites such as'the distance between part of edge points and the circle center is too large 'in YOLOv6 model training, the suitability of the defect reaction sites and the recognition weights is further improved, the detection precision is improved, and the high-precision DNA synthesis requirement can be met.

This invention discloses a method and system for optical character recognition of printed Burmese text based on deep learning, belonging to the field of optical character recognition technology. The method first preprocesses scanned images of printed Burmese documents, using Hough transform to segment table and character regions and extract target character regions. Then, it constructs an image dataset and builds a Burmese OCR recognition model. The model is trained using a stochastic gradient descent optimizer with momentum, and parameters are optimized through 4-fold cross-validation to obtain a high-precision recognition model. Finally, the segmented character regions are input into the model to complete detection and classification, outputting text information and importing it into a data table. This invention can accurately segment Burmese characters within tables, improve model recognition accuracy, has low deployment costs, and can be used for detecting duplicate voter registration in Burmese elections, effectively improving the efficiency of Burmese document digitization and information extraction.

The application discloses a kind of based on DAS and dynamic threshold highway low-speed event monitoring method and system, comprising: obtaining the DAS signal of target highway section;DAS signal is pretreated;Vehicle trajectory signal enhancement and vehicle trajectory signal separation are carried out to the feature image after pretreatment, and the vehicle trajectory separation feature map of different direction is obtained;The vehicle trajectory separation feature map of different direction is respectively divided into section, and a plurality of section feature maps are obtained;Edge detection and hough transform are carried out to section feature map respectively, the coordinates of the vehicle trajectory straight line segment of each vehicle in each section are obtained, and the average speed of all vehicles in each section is obtained according to it;According to the average speed of all vehicles in each section and the dynamic baseline threshold of this section, whether this section exists low-speed event is judged respectively;If yes, then alarm is carried out.The application can reduce the false negative rate and false alarm rate of low-speed event.

The application discloses a sea surface stereo matching and depth measurement method based on wave main direction correction, and aims to solve the feature degradation and mismatch caused by the consistency of the transverse sea wave texture and the matching search direction. The method first denoises and enhances the image and extracts the texture, calculates the global flow direction by using the block Hough transform, and adaptively starts the rotation optimization; secondly, an ambiguity scoring model based on normalized cross correlation (NCC) is constructed to filter the optimal rotation angle, the image is synchronously rotated and cropped, and the transverse repeated texture is reconstructed into a periodic structure with high gradient change; then, feature points are extracted in the rotated image domain, the RANSAC algorithm is combined to filter and estimate the fundamental matrix to complete the epipolar rectification, the prior disparity search range is locked according to the distribution of the homonymic points, and the semi-global matching (SGM) algorithm is used to generate the initial disparity; finally, the real depth is recovered through reverse correction, the point cloud is generated, and the three-dimensional surface of the sea wave is reconstructed. The application fundamentally eliminates the matching confusion caused by the transverse texture, significantly improves the three-dimensional reconstruction accuracy, and is suitable for application scenes such as marine wave monitoring and disaster warning.

This invention discloses a livestock point cloud segmentation and denoising method based on adaptive parameter Hough transform. The method involves acquiring livestock point cloud data, preprocessing the point cloud data to obtain two point cloud datasets containing livestock and fences on one side, extracting feature vectors from the point cloud data, inputting these feature vectors into an adaptive Hough transform parameter model for fence detection to obtain potential fence lines, using these fence lines as a reference for denoising and segmenting the livestock point cloud to obtain a one-sided livestock point cloud, and finally performing point cloud registration to output a complete livestock point cloud. This invention constructs a parameter adaptive model based on a limited amount of labeled data, employs transfer learning and few-shot learning techniques to address the problem of scarce labeled data, establishes a nonlinear mapping from the point cloud feature space to the Hough parameter space, and adapts to adaptive parameter adjustments for different scenarios.

This application relates to the field of test strip image processing technology, specifically a method and system for identifying dichlorvos colloidal gold tomography bands based on multi-feature fusion. The method includes: acquiring a macro image of the color development area of ​​the test strip, extracting the A channel of the Lab color space and constructing a chromaticity attenuation gradient field, and obtaining edge seed points through multi-scale Gaussian convolution and second-derivative zero-crossing detection; establishing a virtual temporal cumulative development model, simulating the spatial accumulation of color development particles with anisotropic thermal diffusion, and generating a probability connectivity graph of discontinuous segments based on the overlap of diffusion fronts; semantically completing the gaps between bands through an edge prediction model to obtain a continuous edge probability map, and generating a smooth edge map through non-maximum suppression and distance confidence attenuation compensation; extracting straight line segments using Hough transform and combining position prior to screen matching bands, and calculating the regional integral optical density to realize the restoration and identification of discontinuous bands.