87 results about "Vector graphics" patented technology

The invention discloses a defect multi-angle detection and fusion method based on a vector graph and affine transformation, and relates to the technical field of image processing, and the method comprises the steps: collecting a plurality of sub-images with overlapping regions at a single angle; constructing a collision map at the angle, wherein the view field of each grid corresponds to a sub-image; extracting defect contours from the sub-images and converting the defect contours into defect vector graphs; according to the defect vector set of all the sub-images at the angle, collision detection and cross-sub-image defect fusion are carried out based on the collision map at the angle, and a defect set at the angle is obtained; one angle is selected as a reference angle, other angles are selected as target angles, a defect set of the target angles is transformed to a reference angle coordinate system based on affine transformation, collision detection and cross-angle fusion are carried out on the transformed defect set and the defect set of the reference angles, and a final optical assembly defect set is obtained. And integrated detection of large-area coverage, high-precision alignment and high-efficiency fusion is realized.

The invention belongs to the technical field of intelligent processing of nuclear power engineering design drawings, and particularly relates to an intelligent analysis system and method for a nuclear power CAD flow chart based on multi-modal data fusion. Comprising a multi-modal feature extraction module, a cross-modal alignment module, a joint analysis module and a dynamic graph generation module, and the multi-modal feature extraction module analyzes a vector graph, a text label and an attribute table to generate standardized features; the cross-modal alignment module is used for establishing space-semantic association among the heterogeneous data; the joint analysis module cooperatively deduces equipment types, reconstructs a connection relation and fuses parameters; and the dynamic graph generation module constructs a spatio-temporal topological graph and optimizes and verifies the spatio-temporal topological graph, and data are transmitted among the modules through standardized interfaces to form a closed-loop optimized link. The method has the beneficial effects that the space-semantic model is constructed, the correlation strength is quantified through the distance attenuation weighting function, and the dynamic decision tree verification method is combined, so that the space automatic alignment is realized, and the alignment confidence is provided.

The invention discloses an SVG vector diagram-based primitive matching and intelligent recognition system and method, and relates to the technical field of computer graphic processing and mode recognition. The system stores a PDF file through SHA-256 Hash duplicate removal, format conversion is achieved through a tool, an 800DPI PNG image is generated, and the resolution is verified; the affine transformation matrix is analyzed, coordinate normalization and graphic element classification conversion are executed, and complex paths are split, deduplicated and merged; detecting a character area, and deleting corresponding character elements in the SVG; geometric features are extracted to construct a multi-dimensional index, and a template topological structure is analyzed; and selecting anchor points according to priorities, adapting to multiple rotation directions, matching non-anchor point elements through dynamic tolerance, verifying connection points in combination with adaptive topology tolerance, and finally outputting a matching result containing confidence. The system realizes efficient identification and accurate matching of technical drawings through standardization processing and an intelligent matching algorithm, and is suitable for scenes such as industrial drawing analysis and document digitization.

The invention relates to an image processing method, a map generation method, electronic equipment and a storage medium. The image processing method comprises the following steps: extracting image features from an environment image to obtain a feature map of the environment image; segmenting the feature map through at least two different types of geometric element models to obtain different types of geometric element maps; fusing the geometric element diagrams of different categories to obtain a first fused diagram; and performing vectorization processing on geometric elements in the first fusion image to obtain a structured vector graph corresponding to the environment image.

The invention discloses a building vector graph multi-scene intelligent simplification method and system, and belongs to the technical field of geographic information systems. Comprising the following steps: establishing a four-level data system comprising an original data layer, an engineering cache layer, a display cache layer and a terminal view layer; monitoring data change and user interaction events through an event bus; the event is responded, the current application scene is intelligently recognized, and the corresponding simplified parameter configuration is dynamically loaded; based on the configuration, executing simplification logic on the target building vector graph; querying a topological relation to carry out cooperative processing on the contours of the adjacent buildings; and synchronously updating a processing result to the four-level data system. Through four-stage data caching, dual-drive triggering and scene self-adaptive judgment, efficient, high-quality and self-adaptive processing of building simplification in multiple scenes such as cartographic integration, real-time display and spatial analysis is realized, and the system flexibility, the resource utilization rate and the user experience are improved.

The invention discloses an icon-related XML format recognition method, an icon format recognition method and a server, and the method comprises the steps: obtaining an XML document according to an icon file path in an installation package, and extracting a tag name of a root element; when the tag name is identified as a vector graph type or an adaptive icon type, reading attribute information or child node information of a root element, and executing structural integrity verification; and finally determining the icon format type according to the structure verification result and the tag name. According to the method and the device, through a dual detection mechanism of extension shunting and content deep analysis, and in cooperation with a main and standby analysis fault-tolerant strategy, accurate identification in an environment without Android running is realized, the problem of misjudgment of an XML icon format is effectively solved, and the consistency of icon display is ensured.

The application provides a geometric figure processing method and device, equipment and a storage medium. The method comprises the following steps: acquiring a to-be-recognized image, and recognizing and cutting the to-be-recognized image to determine an initial geometric illustration; performing optimization processing on the initial geometric illustration to determine a target geometric illustration; performing denoising processing on the target geometric illustration to obtain a denoised geometric illustration, acquiring image features of the denoised geometric illustration, classifying the image features to determine a target geometric element, and determining a first vector element according to the target geometric element and a geometric element relationship obtained by disassembling the target geometric element; editing a to-be-edited vector element in the first vector element based on an editing instruction, determining a vector figure according to the to-be-edited vector element and a non-editing vector element, and exporting the vector figure to a figure resource library in a standard format. Thus, high-precision recognition is performed on the geometric figure, and the subsequent labor cost for adjusting the geometric figure is greatly reduced.

This invention relates to the field of drawing recognition technology, and discloses a method, apparatus, device, and readable storage medium for beam span recognition in vector graphics. The method includes: acquiring a target vector graphic and its corresponding matrix representation; identifying key beam span points from the matrix representation; determining the beam span type based on these key points; and mapping the positions of the key beam span points to the target vector graphic to obtain beam span elements corresponding to the beam span type in the target vector graphic. By implementing this invention, the recognition of beam span elements is not limited by the drawing method, ensuring the accuracy of beam span element recognition. This enables accurate identification of the positional information of beam elements, further guaranteeing accurate identification and attribute matching of beam elements.

The present disclosure relates to systems, non-transitory, computer-readable media, and methods for the three-dimensional rotation of vector graphics. In particular, in some embodiments, the disclosed systems provide a two-dimensional vector graphic in a first orientation for display via a graphical user interface of a client device. Additionally, in some embodiments, the disclosed systems receive user input to rotate the two-dimensional vector graphic in a three-dimensional space to a second orientation. Furthermore, in some embodiments, the disclosed systems generate a new two-dimensional graphic using a neural diffusion network, which represents the two-dimensional vector graphic rotated according to the user input. Finally, in some embodiments, the disclosed systems provide the new two-dimensional graphic in the second orientation for display via the graphical user interface.

This application provides a storyboard script generation method. The method includes obtaining a reference image used to generate a storyboard script; obtaining an element of the reference image and element vector information of the element; obtaining a vector element matching the element; and generating the storyboard script by setting the vector element on a specified canvas based on the element vector information. According to the storyboard script generation method provided in this application, the element in the reference image is identified, and the matched vector element is correspondingly set on the specified canvas, to obtain the storyboard script in a form of a vector graph. Therefore, it is more efficient and easier to produce the storyboard script, and user experience is effectively improved.

The invention provides a city texture unit optimization and integration method based on set operation, electronic equipment and a storage medium aiming at the problems of massive texture unit combination modes, low manual screening efficiency, high subjectivity and the like in city updating. The method comprises the following steps: acquiring and numbering spatial data of N texture units of a target area, and constructing a basic database; calculating the number of all pairwise combinations, and screening combinations with intersecting boundaries through vector graphic analysis to form a set Z; selecting texture units from the Z, and combining the texture units according to rules to generate a new texture unit set ZB; based on indexes such as the area, the entrance position and the space quality, weighted quantitative scoring is carried out on the ZB; and outputting an optimal scheme according to the score sequence. According to the method, texture combinations are converted into mathematical set operation, so that massive combinations can be calculated, automatic processing and objective quantitative evaluation are realized, modern function requirements are met while urban historical textures are inherited, and the method is suitable for scenes such as historical block updating.

A method, apparatus, non-transitory computer readable medium, and system for image generation include obtaining a noise input and an input prompt comprising a pattern element. A coordinate frame of the noise input is shifted based on a diffusion step to obtain a shifted coordinate frame. A synthetic image is generated, using an image generation model, by denoising the noise input based on the input prompt and the shifted coordinate frame. The synthetic image comprises a repetition of the pattern element.

A combined sensing and projection apparatus includes a LIDAR sensor, a scan module, a unified processor and a mechanical mounting. The LIDAR sensor is configured to detect light and sense a physical property of an object or environment. The scan module has a micro-electromechanical system (MEMS) mirror configured to deflect one or more laser beams to project vector graphic content related to the physical property of the object. The unified processor is configured to reduce processing delays by fusion of processing of both vector graphic content and determination of the physical property of the object. The scan module and sensor are attached to the mechanical mounting.

The application discloses a high-speed train carriage modeling method, which is used to solve the problem that the prior art cannot accurately simulate network of high-speed train carriage. The method comprises the following steps: obtaining a high-speed train line on which a to-be-modeled high-speed train carriage runs; determining a car body model of the to-be-modeled high-speed train carriage, and determining a carriage width of the to-be-modeled high-speed train carriage according to the car body model; establishing a corresponding planar vector graph of the to-be-modeled high-speed train carriage in simulation software according to the carriage width and the high-speed train line; determining a carriage height of the to-be-modeled high-speed train carriage according to the car body model; and establishing a corresponding 3D model of the to-be-modeled high-speed train carriage in the simulation software according to the carriage height and the planar vector graph.

This invention belongs to the field of image enhancement technology, specifically to a method and system for automatic optimization and reconstruction of vector graphics based on image enhancement. It includes collecting full-dimensional original feature data and partition quality index data of the image to be processed. Different abnormal scenarios are identified, and corresponding reconstruction collaborative error data is constructed by combining the current reconstruction processing stage and image attribute state. An optimized reconstruction strategy is formulated based on preset vector reconstruction quality requirements. The set of parameters to be corrected is marked in the optimized reconstruction strategy according to the reconstruction collaborative error data, and adjustments are made to obtain a refined optimized reconstruction strategy. The distribution stability index of the partition quality index data of each structural region after optimized reconstruction is collected in real time. Processing nodes that fail the evaluation in the refined optimized reconstruction strategy are defined as error nodes, and an iterative correction strategy pointing to the error nodes is generated. This invention can improve reconstruction accuracy, make reconstruction results more stable, and enhance anomaly detection and scene recognition capabilities.

The application discloses a polygonal plate splicing method, system, device and medium based on machine vision, relates to the technical field of plate splicing, and comprises the following steps: acquiring plate outlines of each plate to be spliced through a vector path extraction algorithm of a graph convolution network; converting the plate outlines into each vector graph, and calculating a priority score of each vector graph; performing a preliminary arrangement to form a preset splicing graph based on the priority score; determining the layout result with the lowest hole rate formed by multiple preliminary arrangements as a target layout; identifying and acquiring a vector graph of a gap in the target layout, and acquiring a vector graph of a plate to be spliced which has not been laid out; putting the vector graph of the plate to be spliced which has not been laid out into each vector graph of the gap one by one until the vector graph of each gap cannot be put in, so that a final layout of the preset splicing graph is obtained; and the problems of low secondary splicing efficiency of the excess material, serious warehouse backlog, low utilization rate of the excess material and the like in the background art are solved.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate data-bound vector images from input raster images. In some embodiments, the disclosed systems receive, from a client device, a data file and a raster image depicting at least one raster object within a scene. Additionally, the disclosed systems generate at least one scalar vector graphic object from the at least one raster object of the raster image and bind the at least one scalar vector graphic object to data from the data file. Further, the disclosed systems generate a scalar vector graphic image depicting the at least one scalar vector graphic object within the scene based on the data bound to the at least one scalar vector graphic object. The disclosed systems provide the scalar vector graphic image for display on a graphical user interface.

This invention proposes a lossless extraction method, device, and computer-readable medium for chart vector graphics in PDF, relating to the field of computer technology. Responding to a chart vector graphics extraction request, the method involves: acquiring target PDF data based on the request and converting the target PDF data into target markup language (TRAIL) data; obtaining the position information of one or more target chart vector graphics based on preset chart vector graphics tags in the TRIL data, confirming the corresponding target candidate box range based on the position information of the target chart vector graphics, and generating a candidate box statistics table; calling and retrieving the target candidate box range from the candidate box statistics table, selecting the chart vector graphics data to be extracted based on the chart type of the target chart vector graphics, and performing lossless extraction to obtain the final chart vector graphics data; and converting the TRIL data corresponding to the final chart vector graphics data into the target chart vector graphics.

A method of generating a three-dimensional (3D) structure model from a two-dimensional (2D) drawing file, which includes one or more illustrations of a structure, using a data processing device includes importing the 2D drawing file to the data processing device, converting the 2D drawing file into a raster graphics file, converting the raster graphics file into a vector graphics file, extracting one or more graphical projections representative of the structure from the vector graphics file, converting the one or more projections into a tagged data graphics file, forming a 3D structure model representative of the structure by connecting the plurality of cartesian points of the tagged data graphics file, and generating an electronic output file including the 3D structure model.

The invention discloses a method and a device for quickly establishing a 2D character model based on artificial intelligence, a terminal and a medium, and the method comprises the steps: collecting a preset number of 2D character images and related data, and building a data set; constructing a 2D character reconstruction model based on a deep learning technology, and inputting the data set into the 2D character reconstruction model to carry out model training of a preset round; obtaining a target 2D figure image, inputting the target 2D figure image into the trained 2D figure reconstruction model for feature extraction, and reconstructing the 2D figure model based on the extracted features; and outputting the reconstructed 2D character model to a preset format. According to the method and the device, the 2D character reconstruction model is constructed and trained, so that the animation 2D character reconstruction model can be automatically reconstructed and generated according to the input target 2D character image, and then the image file or the vector graphic file is output, so that the method and the device can be applied to the fields of game development, virtual reality, animation production and the like, and the animation creation efficiency and the animation production capacity are improved.

The invention discloses a quality inspection method and device for a flood analysis model grid structure, equipment and a medium. The quality inspection method comprises the steps of collecting an element data set included in the flood analysis model grid structure; according to the identification number and the associated element number corresponding to each element data, verifying the association relationship between each element data, and obtaining successfully verified target element data; and generating a grid vector layer based on the target element data through a vector graph generation engine, and determining a quality inspection result of the grid structure according to a generation result of the grid vector layer. According to the technical scheme of the embodiment of the invention, the time cost and the labor cost consumed in the quality inspection process of the flood analysis model grid structure can be saved, omission errors are avoided, and the quality inspection efficiency and the accuracy of quality inspection results are improved.

The application relates to the technical field of vector graphics rendering, in particular to a vector graphics rendering method based on a rendering engine, which comprises the following steps: in the rendering engine initialization stage, a rendering kernel and a multilingual adaptation layer independently running are built, color font analysis logic is built in the kernel, color composite data is analyzed through an improved font table traversal algorithm, and glyph description information is stored in an independent glyph cache pool; a rendering request in an upper layer is converted into an instruction stream through the adaptation layer, a target glyph is extracted, a vector path is precompiled, an intermediate representation of hardware acceleration adaptation is generated, and pixel cache-aware rasterization calculation is performed to generate a raster image. The method can stably analyze color glyph data, glyph storage and calling are more efficient, the rendering kernel and the multilingual interface are more adaptable, hardware acceleration matching is higher, rasterization calculation and cache resource adaptation are more coordinated, and the overall rendering process is smoother.

A method comprises receiving, at a client device 202, a command corresponding to an input delta 208, to a vector path for a graphical design, the command including a component defining a type of vecto

The invention relates to the technical field of document processing and automation, in particular to a graphical tool and bidding document generation system and method based on a large model, and the method comprises the steps: obtaining a natural language description or bidding document template document input by a user, and recognizing a graph in the document to generate placeholders; the input information is sent to a large language model for semantic analysis and reasoning, and structured graphic data conforming to predefined JSON Schema is output; based on the data, calculating a non-overlapping and cross-minimized graphic element space layout through an automatic layout algorithm, driving a vector graphic library to generate a standard vector graphic and converting the standard vector graphic into a bitmap format; finally, the bitmap is automatically inserted into the position of a placeholder corresponding to the bidding document, map note adding and format adjusting are completed, and a complete bidding document of an integrated graphical representation is output. According to the method, end-to-end automatic generation from a natural language to a professional graphical representation is realized, and the bidding document compiling efficiency and the graphical representation quality are remarkably improved.

The invention provides an aircraft interactive line manual system fusing configuration control and maintenance implementation. The aircraft interactive line manual system comprises an electrical configuration library, a line library, a maintenance information library, a standard implementation library and a data module construction subsystem, and the data module construction subsystem is used for obtaining an XML-form circuit diagram carrying maintenance information and standard implementation information by adopting a vector graph construction mode based on the electrical configuration library, the circuit library, the maintenance information library and the standard implementation library, and the XML-form circuit diagram has an interaction function. According to the interactive circuit manual, the comprehensive and unified circuit configuration library and the circuit information library are established, repeated construction of redundant data is avoided, the manual development cost is reduced, meanwhile, related maintenance implementation information of the circuit is associated with the circuit information, and the functionality of the interactive circuit manual and the economical efficiency of circuit maintenance work are effectively improved.

The application relates to the technical field of image processing, in particular to a smooth transformation display method of a visual training stimulation vector graph, which comprises the following steps: acquiring a vector image of a user visual area, calculating line distribution disorder degrees of local areas in the vector image according to the distribution state of lines in the local areas; analyzing the difference between the local areas at the same positions before and after the movement of the user visual area, and calculating background change degrees; calculating stripe complexity increase degrees of the movement of the user visual area according to the distribution state of the background change degrees of the local areas; comparing the stripe complexity increase degrees of the movement of the user visual area before and after the current time, and acquiring a refresh rate of the current movement of the user visual area. The application aims to improve the rendering effect of the vector graph by adjusting the refresh rate, and ensure that the rendering effect meets the visual perception habit of the user.

The invention provides a carton multi-process processing method and device, and relates to the technical field of industrial automation. The method comprises the steps that a vector graphic file of a carton to be processed is obtained; the vector graphic file is analyzed to determine the machining process type of each graphic element and the first coordinate and the second coordinate in the drawing, and the machining process types comprise punching, line cutting, line pressing and grooving; according to preset mechanical center line coordinates and drawing center line coordinates, each first coordinate is processed to determine a first target coordinate, and the first target coordinate is the coordinate of a target machining assembly corresponding to the machining process type of each graphic element; determining a second target coordinate of each processing action according to the mechanical distance of each processing assembly, the target processing assembly of each graphic element and the second coordinate; and the paperboard is conveyed to the second target coordinate, and the target machining assembly located at the first target coordinate is driven to execute the corresponding machining action.

A combined sensing and projection apparatus includes a RADAR sensor, a scan module, a unified processor and a mechanical mounting. The RADAR sensor is configured to detect electromagnetic waves and sense a physical property of an object or environment. The scan module has a micro-electromechanical system (MEMS) mirror configured to deflect one or more laser beams to project vector graphic content related to the physical property of the object. The unified processor is configured to reduce processing delays by fusion of processing of both vector graphic content and determination of the physical property of the object. The scan module and sensor are attached to the mechanical mounting.

The present application relates to the technical field of laser marking test, and more particularly to a marking test method, device and equipment; user-defined parameters are processed according to a preset filling algorithm and a preset scanning direction to obtain a plurality of effective filling line segments; the plurality of effective filling line segments are processed based on a preset shortest idle stroke strategy, a preset clipping algorithm and a preset single maximum processing range to obtain a plurality of sub-vector graphics and a plurality of overlapping areas; the plurality of overlapping areas and the plurality of sub-vector graphics are subjected to marking test; real-time scanning points are analyzed according to a preset pulse frequency calculation formula, a preset laser beam incidence direction vector, a preset dynamic compensation algorithm and user-defined parameters to obtain marking test results, relevant strategies are used to split and adapt sub-vector graphics and construct overlapping areas, real-time scanning points are integrated for multi-core element analysis, reliable marking results are generated, processing efficiency and quality are taken into account, and accurate laser processing is supported.

The invention relates to the technical field of data processing, and discloses a building remote sensing interpretation method and device and electronic equipment, and the method comprises the steps: obtaining multi-source heterogeneous geographic data in a target region, dividing the multi-source heterogeneous geographic data into a plurality of target sub-rectangular regions based on a preset reference coordinate system, generating a multi-band sample of each target sub-rectangle in parallel; performing AI model reasoning on the multi-band sample to obtain an interpretation result of each target sub-rectangular grid; the grid interpretation result comprises a graphic grid and an attribute grid; converting the grid interpretation result into vector graphs, and fusing the vector graphs located at the boundaries of the target sub-rectangles to obtain a geometrically complete vector graph; and carrying out attribute assignment on the geometrically complete vector graph based on the attribute grids, and generating an attribute vector interpretation result of the target region. According to the method, the problem of engineering bottleneck of low reasoning speed when massive high-resolution remote sensing data is processed in the prior art is effectively solved.