65 results about "Minimum bounding rectangle" patented technology

The invention provides a textile surface defect detection method and system based on image features, and relates to the technical field of textile surface defect detection.The method comprises the steps that an RGB image of a to-be-detected textile is obtained and zoomed to 512 * 512 pixels, and then at least five semantic tags are output through a semantic segmentation model; the method comprises the following steps: adopting hyperspectral imaging with the wavelength of 400-1700 nm and the resolution of 10 nm, calculating the pixel reflectivity through a reflectivity formula, comparing the reflectivity of 5-8 characteristic wavebands, marking as a pollutant if the average deviation exceeds a threshold value, matching the type and position of a stain with a spectral angular distance, and after a standard sample and a semantic region are converted into an LAB color space, extracting a minimum rotation enclosing rectangle and dividing a grid, invalid pixels are filled with 3 * 3 neighborhood effective pixel weighted mean values, and a grid LAB mean value is calculated. A grid pollutant pixel corresponding to an image to be detected is filled with a standard sample in a mean value mode, then channels A and B are clustered through a sliding window, a pilling area is preliminarily judged according to the standard deviation of a channel L, and the pilling area is confirmed by combining the structured light three-dimensional point cloud and comparing with a threshold value.

The invention relates to the technical field of image processing, and provides a power equipment installation inclination degree identification method and system, a medium and equipment, and the method comprises the steps: obtaining a power equipment inspection image, and carrying out the segmentation of a power equipment box through a deep learning instance segmentation method, and obtaining a box mask image; based on the box body mask image, carrying out box body minimum enclosing rectangle fitting by adopting an equal-interval rotation search method to obtain an inclination angle of the box body; wherein the equal-interval rotation searching method comprises the following steps: continuously rotating a box mask image for multiple times in the same direction, increasing the rotation angle at equal intervals, recording the minimum enclosing rectangle of the box mask image in each rotation, and calculating the area of the minimum enclosing rectangle obtained in each rotation; and finally, the minimum enclosing rectangle corresponding to the minimum area is selected as the minimum enclosing rectangle obtained by fitting, and the rotation angle of the minimum enclosing rectangle obtained by fitting is taken as the inclination angle of the box body, so that the calculation amount and the calculation complexity are effectively reduced.

The invention discloses a ship 3D target detection method and system based on image and laser radar fusion in the field of ship navigation intellectualization, and the method comprises the steps: obtaining a two-dimensional bounding box set of an object in a camera image through a Yolov11 detection frame, converting the eight vertex sets of a three-dimensional bounding box into a camera coordinate system, obtaining the minimum bounding rectangle coordinate of a plane coordinate set, and obtaining the minimum bounding rectangle coordinate of the plane coordinate set; calculating an IOU value for each minimum enclosing rectangle and a two-dimensional bounding box in the two-dimensional bounding box set, projecting a plane coordinate of the three-dimensional bounding box before the minimum enclosing rectangle is converted to a two-dimensional plane, and obtaining a three-dimensional detection frame and category information; information such as the position and the size of an object existing in the navigation direction is obtained in real time through a laser radar and fused with a camera picture; the improved DBSCAN clustering algorithm is designed, the core block is confirmed through the point cloud density in the local point cloud data block, the core point in the core block is searched, the clustering processing time is shortened, the algorithm complexity is reduced, and the operation efficiency of 3D target detection is improved.

The invention discloses an online real-time editing method and device supporting million-level vector data and a medium, and relates to the technical field of spatial data co-processing, and the method comprises the steps: carrying out the dynamic rendering of a standardized element sequence based on a real-time state notification, rendering the operable standardized elements into green, and carrying out the dynamic rendering of the standardized element sequence; the standardized elements operated by multiple users are rendered to be yellow, and the standardized elements which cannot be operated are rendered to be red; when the standardized element of the user operation is yellow or red, real-time interception is carried out, a prompt is pushed, and a structured operation log is generated; and verifying the adjacency, connectivity and conflict-free inclusion relationship between the element change coordinates in the structured operation log and the topological snapshot index, generating a processing patch by identifying topological breaking points and executing spatial interpolation connection, marking an element coordinate set needing to be processed, and outputting coordinates of a reprocessing region by calculating a minimum bounding rectangle. According to the method, the memory occupancy essential optimization is realized through a density self-adaptive streaming processing mechanism.

The invention provides an outdoor power transmission channel hidden danger identification method and system based on semantic segmentation, and the method comprises the steps: marking a small target region in long-tail distribution from an outdoor power transmission channel image, carrying out the geometric transformation after cutting out the small target region, and carrying out the cross-image migration to generate a migration image; performing illumination correction on the migrated image to generate an enhanced image; constructing a semantic segmentation model for hidden danger recognition, and inputting the enhanced image into the semantic segmentation model to extract each semantic region and corresponding mask in the enhanced image; screening out abnormal masks from the masks and deleting the abnormal masks, and then removing existing cavity areas to obtain residual masks; and clustering and merging the remaining masks to generate a minimum enclosing rectangle with a rotation angle as a final detection frame. Based on the method, the invention also provides an outdoor power transmission channel hidden danger identification system based on semantic segmentation. According to the method, the outdoor power transmission channel hidden danger identification precision and efficiency are remarkably improved, and safe and stable operation of a power transmission line is ensured.

The invention relates to the technical field of liquid level detection, and discloses a liquid level detection method and system based on image processing, and the method comprises the steps: obtaining to-be-processed original liquid level image data; preprocessing the data of the original liquid level image, wherein the preprocessing comprises the steps of extracting a red channel from the original liquid level image, carrying out binarization processing on the image based on double thresholds, carrying out expansion on a binary image by using a square structure element, carrying out opening operation and closing operation on the expanded image, carrying out corrosion operation on the image subjected to the closing operation, and carrying out iteration for three times; and carrying out feature extraction on the preprocessed image, calculating a minimum bounding rectangular frame, drawing a rectangular frame in the original liquid level image, and judging the liquid level height according to the height of the rectangular frame. Compared with the prior art, dual threshold segmentation and multi-scale morphological processing are innovatively combined, and the detection robustness under the complex illumination condition is improved.

The invention discloses a bulk cargo cabin real-time fusion detection method based on a laser point cloud, and the method comprises the steps: obtaining a real-time three-dimensional scene point cloud of a port scene, and obtaining a deck plane equation and a normal vector; projecting the three-dimensional scene point cloud to a two-dimensional deck plane, and constructing an intensity image taking point cloud intensity as information and a depth image taking projection distance as information; obtaining an intensity mask image from the intensity image; acquiring a depth edge image according to the depth image, and fusing the depth edge image and the intensity mask image to obtain a fused edge image; contour extraction is carried out on the fused edge image, polygon fitting is carried out, a quadrangle in the fused edge image is reserved as a candidate cabin, and a minimum enclosing rectangle of the quadrangle is obtained; and obtaining four vertex coordinates of the minimum bounding rectangle, and back-projecting the four vertex coordinates to the three-dimensional space to obtain three-dimensional space rectangular coordinate points of the final cabin. The method is suitable for a complex environment and a dynamic scene in a port operation area, and the cabin in the dynamic scene can be obtained in real time.

This invention discloses a method and system for quality monitoring and defect localization in a selected area laser melting process. The invention involves real-time acquisition of molten pool images during the selected area laser melting process; extraction of molten pool contours from images belonging to the same printing layer, calculating the molten pool area and the center point of the minimum bounding rectangle of the molten pool contour; creation of a blank image of the same size as the molten pool images, and marking the center point of the minimum bounding rectangle of each molten pool contour at the corresponding position in the blank image; grid division of the blank image, filling the marked grid with the corresponding molten pool area value to generate a grid matrix; segmentation of the grid matrix, converting each segment into a grayscale sub-image; and inputting the grayscale sub-images into a trained neural network model to obtain quality classification results.

The present invention relates to an imaging prior-driven, progressive, intelligent recognition method for small spatial targets, comprising the following steps: using a threshold-embedded minimum bounding rectangle algorithm to preliminarily locate a motion-blurred spatial target, obtaining a preliminarily located image; extracting degradation features from the preliminarily located image, and calculating the residual between the preliminarily located image and the degradation features to obtain a deblurred spatial target image; using a trained improved enhanced super-resolution generative adversarial network to extract features from the deblurred spatial target image, obtaining a sharpened spatial target image; and using a trained residual network to perform target recognition on the sharpened spatial target image, obtaining the spatial target type. This recognition method first preliminarily locates the spatial target, then deblurs and sharpens the located spatial target image, and finally uses the residual network for target recognition, thereby improving the accuracy of spatial target recognition in wide-format images.

This invention discloses a method and system for accurate counting of dense copper sheets based on semantic segmentation and image processing. The method includes: acquiring a large field-of-view image of dense copper sheets; labeling and cropping the copper sheets in the image, and inputting the cropped image and labels into a Unet semantic segmentation network for training to obtain a trained Unet network model; setting the input image of the trained Unet network model to the original image size, and performing inference on the original image to obtain a preliminary inference map; performing an opening operation on the preliminary inference map to filter out small imperfections, and performing dilation to obtain large columns of copper sheets; correcting the angle of the minimum bounding rectangle of the large columns of copper sheets; and forming a peak-and-valley image through affine transformation, projection integration, and filtering, and counting the number of copper sheets in all large columns of copper sheets in the image by counting the number of peaks. This invention effectively solves the problem of achieving high-precision counting in scenes with mottled and densely arranged copper sheets.

The present invention relates to an image processing method, comprising: acquiring a visible light image, a near-infrared image, and a fluorescence image of the same tooth region to obtain a multimodal image; inputting the multimodal image into a segmentation network, wherein a spatial attention module is embedded in the skip connection between the encoder and decoder of the segmentation network, and the segmentation network outputs a binary mask of the tooth region; extracting the contours of individual teeth from the binary mask, determining the minimum bounding rectangle and geometric center of gravity of each contour; assigning an FDI tooth position code to each contour based on the horizontal coordinate of the geometric center of gravity; cropping the corresponding individual tooth image block from the multimodal image based on the minimum bounding rectangle; inputting the individual tooth image block into a multi-branch convolutional neural network to obtain a unified feature vector; inputting the unified feature vector into a fully connected classification network, which outputs probability values ​​corresponding to different categories. The present invention also relates to image processing devices, media, computer program products, and tooth recognition systems.

This invention discloses a method and system for small target detection in remote sensing images based on multi-scale features. The method involves: acquiring a remote sensing image to be detected; performing dehazing and brightness enhancement processing on the remote sensing image; inputting the brightness-enhanced image into a trained remote sensing image small target detection model to obtain the small target detection result; and the working principle of the trained remote sensing image small target detection model includes: extracting multi-scale features from the brightness-enhanced remote sensing image; performing feature fusion and feature enhancement on the extracted multi-scale features to obtain a feature map; fixing the size of regions of interest of different sizes in the feature map to obtain proposed candidate boxes for the target; applying non-maximum suppression to the extracted proposed candidate boxes to obtain the predicted bounding box coordinates of the target; drawing the minimum bounding rectangle of the target's region; and using the minimum bounding rectangle as the predicted bounding box of the target to obtain the target detection result in the remote sensing image.

The invention discloses a face dynamic feature detection method and system based on continuous frames. The method comprises the following steps: performing face detection on a preprocessed video frame by adopting a RetinaFace model of a quantized adaptive edge device NPU to obtain a face bounding box with the highest confidence coefficient; inputting the adjusted face image into the quantized PFLD model, extracting 98 key points and mapping the key points back to an original image space; eye and mouth key points are extracted according to a predefined index, and three sub-regions are obtained through minimum enclosing rectangle expansion cutting; inputting the sub-region images into a quantized ResNet binary classifier, and outputting eye opening and closing and mouth closing / yawning states; n frames of results are recorded through a sliding window, facial dynamic features and fatigue levels are judged according to a majority voting aggregation state, and finally the results are packaged into a JSON format and transmitted in real time through a UDP protocol. The method is light in weight, high in real-time performance, capable of accurately detecting the face dynamic features and adaptive to edge device deployment.

The invention provides a time sequence ROI multiplexing human body posture serial detection method and device, equipment and a medium, and the method comprises the steps: carrying out the full-image target detection of a key frame of an input video sequence, outputting the coordinates of a human body bounding box through a lightweight target detection algorithm, and filtering a redundant box with the confidence lower than a preset threshold value; then executing local posture estimation on the human body bounding box area, outputting 35 key joint point coordinate sets and confidence degrees thereof, and filtering low-confidence-degree joint points of which the confidence degrees are lower than a preset joint point threshold value; performing local attitude estimation on an extended ROI (Region of Interest) region of a previous frame multiplexed by an adjacent non-key frame, wherein the extended ROI region is obtained through equal-proportion extension based on a minimum bounding rectangle of effective articulation points of the key frame; sequentially processing the video frame sequence according to a preset key frame interval N, and upgrading the current frame into a key frame when a full-image detection triggering condition is met; ensuring; on the premise that the precision is not sacrificed basically, the processing speed of human body target detection and posture estimation in the video stream is greatly improved.

The application discloses a kind of supporting million-level vector data online real-time editing method, equipment and medium, it is related to spatial data collaborative processing technical field, including, based on real-time state notification to the dynamic rendering of standardization element sequence, renderable standardization element is rendered to green, standardization element of multiple-user operation is rendered to yellow, render standardization element that cannot be operated to red;When the standardization element of user operation is yellow or red, real-time interception is carried out and push prompt is pushed, and structured operation log is generated;The adjacency, connectivity and conflict-free containing relationship of element change coordinates in structured operation log and topological snapshot index are verified, processing patch is generated by identifying topological fracture point and executing spatial interpolation connection, while marking the element coordinate set needing to be processed, the minimum bounding rectangle is calculated to output reprocessing area coordinates.The application realizes memory occupation essential optimization by density adaptive streaming processing mechanism.

The invention discloses a building spacing intelligent calculation method based on a spacing standard analysis model. The building spacing intelligent calculation method comprises the following steps: S1, normalizing a designed building scheme general plan; s2, calculating an effective building height; s3, extracting an effective building outline range, removing parts which do not need to participate in building spacing calculation from the building outline range, and extracting an effective building outline range which is reserved to be included in spacing calculation; s4, generating a convex hull of the effective building contour; s5, generating a minimum bounding rectangle corresponding to the convex hull according to the convex hull generated in the step S4; s6, determining a minimum spacing standard under different conditions; s7, calculating the minimum distance of the building under different conditions in the design scheme; and S8, a calculation result is generated, if the minimum building distance obtained through calculation in the step S7 is larger than or equal to the corresponding minimum distance standard in the step S6, the distance meets the standard requirement, and otherwise, the design does not meet the standard requirement.

This invention provides a method and system for identifying and segmenting mixed-issue documents. The method includes the following steps: after detecting the documents, multiple mask data of individual documents are obtained; the mask data is filtered according to a set threshold to obtain mask data that meets certain conditions; after merging the mask data that meets the conditions, the minimum bounding rectangle is calculated; and the positions of the obtained minimum bounding rectangle are segmented using an array method. This method for identifying and segmenting mixed-issue documents detects different documents without missing any, achieving high accuracy and effectively improving the efficiency and accuracy of document classification while saving manpower, thus possessing significant application value.

This invention discloses an adaptive template registration method based on image grayscale. First, FAST corner points are extracted from the image to be registered. Then, the corner points are clustered, and the minimum bounding rectangle of each set is extracted. The region enclosed by the minimum bounding rectangle in the image to be registered is used as the template to complete adaptive template extraction. Next, a normalized cross-correlation algorithm is used for matching in subsequent image sequences. Finally, the affine transformation coefficients of the image are calculated using the coordinates before and after template matching, and the image to be registered is subjected to an affine transformation to achieve image registration. This invention, through its grayscale-based adaptive template image registration method, provides an adaptive template selection method under different background conditions, solving the problems of fixed template position and limited template information in previous methods, improving the template matching accuracy, and showing good application prospects.

The present invention discloses a chip pin measurement method and device based on an adaptive rectangular frame, wherein the method includes: obtaining an image of the chip to be measured; based on the obtained image of the chip to be measured, determining a first region of interest and solving the minimum bounding rectangle of the first region of interest; calculating the four corner points of the minimum bounding rectangle and sequentially sorting the four corner points, wherein the pins on any side of the first region of interest correspond to two of the sorted four corner points; selecting all target pins on any side of the first region of interest, and drawing an adaptive measurement rectangular frame for the target pins based on the positions of the two corner points corresponding to the target pins and the reference parameter values ​​of the target pins; based on the adaptive measurement rectangular frame, determining a second region of interest and solving the pin edges within the second region of interest; and obtaining data of the target pins based on the pin edges. This method can reduce measurement difficulty, reduce calculation complexity, and improve the reliability and stability of measurement results.

The invention provides a block chain data query method, device and equipment, a medium and a program product, and is applied to the technical field of information security, the method comprises the following steps: obtaining industrial chain information sent by a data producer, and inputting the industrial chain information into a block chain, the industrial chain information comprising spatial data and one-dimensional data except the spatial data; based on a minimum boundary rectangle MBR and a hash value of the spatial data, constructing a spatial data index structure, and storing the spatial data index structure in the block chain; based on the transaction attribute and the hash value of the one-dimensional data, constructing a one-dimensional data index structure, and storing the one-dimensional data index structure in the block chain; under the condition that a query request sent by a client is received, based on the query request, the one-dimensional data index structure and the spatial data index structure, determining a query result from the block chain; and sending the query result to the client. Through the method, the data query efficiency can be improved.

The present invention provides a method, system, and computing storage medium for extracting text content from an image, comprising the following steps: S1, obtaining the minimum bounding rectangle of each image region on an image; S2, intercepting each image region by perspective transformation; S3, calculating a third rotation angle of each image region; performing non-cropping rotation and straightening on each intercepted image region according to the third rotation angle; S4, performing a first splicing on the text content of each text box in each image region; S5, calculating a standard rotation angle of the image, and performing non-cropping rotation and straightening on the image; S6, performing a second splicing on the text content of each image region after the first splicing; and S7, outputting the text content after the second splicing. The present invention intelligently reads the text content of multiple image regions on an image, thereby improving the accuracy of post-processing of the image text content.

A method for determining a spatial two-tuple is performed by a computer device. The method comprises: obtaining a given spatial distance and multiple spatial objects, wherein each spatial object belongs to a first spatial object set or belongs to a second spatial object set (101); determining a global area according to a minimum bounding rectangle (MBR) and an extended minimum bounding rectangle (EMBR) corresponding to the first spatial object set and an MBR and an EMBR corresponding to the second spatial object set (102); performing subspace division on the global area to obtain multiple subspaces (103); partitioning the multiple spatial objects according to a positional relationship between each spatial object and each subspace to determine spatial objects comprised in each subspace (104); and according to a spatial distance between the spatial objects of each subspace, determining a spatial two-tuple comprised in each subspace that matches the given spatial distance (105).

This application belongs to the field of digital twin basic data management technology. This application provides an automated method and apparatus for generating spatial identity codes for basic geographic entities. The embodiments of this disclosure acquire the geometric and classification information of basic geographic entities under a unified spatiotemporal reference, automatically calculate the minimum bounding rectangle / minimum outer cube, adaptively select the minimum grid level that can contain the geometric range, and generate two-dimensional or three-dimensional location codes level by level according to the BeiDou grid location code rules. These are combined with classification codes and sequence codes to form a standard field; then, a proprietary identification field is formed by combining this field with root identifier codes and special codes, and extended fields are added as needed to achieve interaction with external codes. This can realize the automated generation, verification, parsing, and traceability of spatial identity codes in scenarios such as provincial, municipal, and county collaborative production updates, two-dimensional / three-dimensional integrated database construction, semantic association, and service publishing, providing unified support for the data organization and management of basic geographic entities and cross-industry interconnection.

This invention provides a method, computer device, and storage medium for processing geometric data of layout files. The method includes acquiring a layout file of a 3D chip, extracting polygonal entities and layer information, assigning polygonal entities to corresponding layer containers, and creating an independent R-tree index for each layer; performing connectivity analysis on the polygonal entities, returning a set of connected components and performance analysis statistics; when creating an independent R-tree index for each layer, acquiring data for all polygonal entities in a single layer, generating a minimum bounding rectangle for each polygonal entity, constructing R-tree indexes in parallel for different layers using multiple threads, and determining whether the number of node entries in the R-tree index exceeds a splitting threshold; if so, splitting the node; and verifying the consistency between the created R-tree index and the original data. The computer device and storage medium are capable of implementing the above method. This invention can improve the efficiency of geometric data processing of layout files.

This invention provides a method, apparatus, electronic device, and storage medium for determining GeoHash codes. First, the minimum bounding rectangle of the region to be identified is determined. Next, the GeoHash codes corresponding to the vertex grids containing any three vertices of the minimum bounding rectangle are determined. Then, based on the GeoHash codes of the three vertex grids, a preset character table is looked up multiple times to determine the GeoHash codes of all grids within the minimum bounding rectangle. Finally, from the GeoHash codes of all grids, the GeoHash codes of each target grid that overlaps with the region to be identified are selected. In this invention, the preset character table includes 32 characters from a Base32 encoding table, and the positions of these 32 characters in the preset character table are determined based on the encoding principle of GeoHash codes. Therefore, the GeoHash codes of all grids within the minimum bounding rectangle can be determined by looking up the table. Compared to the multiple encoding conversions in existing technologies, this invention uses a table lookup method, reducing the computational load and improving the computational speed.

The application discloses an intelligent chessboard control method and device based on an ink screen, equipment and a medium, and relates to the fields of electronic display technology and chess game equipment. The method comprises the following steps: detecting a chess game state change event, determining a logical grid with a state change; calculating a minimum bounding rectangle based on the mapping relationship between the logical grid and the pixel; expanding the minimum bounding rectangle into a final refresh rectangle containing the affected logical grid according to a preset chess rule; dynamically configuring driving waveform parameters according to the area ratio of the final refresh rectangle; and performing a local refresh operation only on the display area corresponding to the final refresh rectangle. Through rule-aware local refresh and waveform adaptive adjustment, the application significantly reduces refresh delay and screen flicker, prolongs the service life of the equipment, optimizes system power consumption, and improves the user's playing experience.

The invention discloses a laser bar center extraction method, which comprises the following steps of: 1) training a segmentation module so that the segmentation module can segment a laser bar in a to-be-measured image, and outputting a Mask binary image; 2) inputting a to-be-tested image into a segmentation module, outputting a corresponding Mask binary image, screening foreground connected domains, and obtaining a reasoning Mask binary image; 3) performing morphological processing, extracting a connected domain, and obtaining a minimum bounding rectangle as an ROI region; 4) respectively acquiring F1, F2 and F3 by utilizing the ROI of the image to be detected, and then judging whether the ROI is a good area or a non-good area; and 5) for a good area, directly utilizing the ROI area corresponding to the image to be measured to perform light stripe center extraction, and for a non-good area, utilizing the ROI area corresponding to the reasoning Mask binary image to perform light stripe center extraction, and acquiring coordinates of a laser stripe central point. According to the method, the precision can be ensured, external interference can be effectively reduced, and the robustness is relatively high.

This application discloses a method and apparatus for constructing a ciphertext spatial index based on hierarchical order-preserving encryption, relating to the field of ciphertext spatial index construction. The method includes: embedding a security policy into the nodes of an R+ tree index to obtain an AR+ tree index; generating multi-level keys based on the AR+ tree index; using the multi-level keys to perform hierarchical order-preserving encryption on the plaintext index data, mapping the plaintext index data to ciphertext intervals; parsing the query statement to obtain a query rectangle and user access permissions; performing hierarchical order-preserving encryption on the query rectangle based on the AR+ tree index and multi-level keys, and finding the intersection with the minimum bounding rectangle of each layer's nodes; verifying user access permissions and filtering out all data IDs that meet the conditions; determining the original data ciphertext based on the filtered data IDs; and decrypting the original data ciphertext using the encryption algorithm used when encrypting the original data to obtain the plaintext data. This application enables fast retrieval and querying of spatial indexes in ciphertext mode.

The present invention claims protection for an electronic signature correction technology based on eigenvalue decomposition, which relates to the field of electronic signature technology. The technology comprises the following steps: obtaining a signature stroke position sequence to establish a covariance matrix; performing eigenvalue decomposition on the covariance matrix, projecting the coordinates of all stroke points in the direction of the eigenvector to obtain the signature sequence coordinates, and obtaining the corrected coordinates of the stroke points based on the eigenvalue decomposition; obtaining a minimum bounding rectangle based on the convex hull of the stroke point set, calculating the stroke rotation angle based on the minimum bounding rectangle, and rotating the stroke points according to the angle to obtain the corrected coordinates of the stroke points based on the minimum bounding rectangle; and fusing the two corrected coordinates to obtain the corrected position coordinates of the signature strokes. This method can be widely applied in electronic signature verification scenarios.