57 results about "Geometric primitive" patented technology

The invention relates to the technical field of three-dimensional model design of molds, and provides a mold three-dimensional high-precision modeling method and system based on multi-modal data fusion, and the method comprises the steps: collecting an RGB image, a high dynamic range image and a structured light depth image of an entity mold, and carrying out the reconstruction to obtain a globally consistent dense point cloud; denoising and semantic segmentation are carried out on the point cloud, and a cavity function area, a core function area and a runner function area are recognized; performing differential parametric modeling based on an identification result: performing geometric primitive fitting on regular geometric features, performing NURBS curved surface reconstruction on a free-form surface, and performing swept volume or rotator fitting on a flow channel to obtain a parameterized geometry, a parameterized curved surface and a parameterized channel model; and applying boundary continuity constraint to fuse the parameterized geometry, the parameterized curved surface and the parameterized channel model, and constructing a hybrid parameterized three-dimensional model. According to the method, rapid reconstruction of a high-precision, high-semantic and full-parameterized three-dimensional model of an entity mold can be realized.

The invention discloses an industrial design-oriented drawing semantic analysis and structured conversion method and system. The method comprises the following steps: acquiring an input image, carrying out different-scale coding on image features through an image coding backbone network, selecting a specific layer to extract a multi-scale feature map, and fusing to generate multi-scale features; inputting the multi-scale features into a geometric primitive detection network and an other element detection network, respectively identifying geometric primitives and non-geometric primitives, and carrying out positioning and classification; analyzing mutual relations between geometric elements and other elements contained in the graph through an element relation graph network, and generating formalized language description based on a matching rule; a Prompt template is constructed, geometric information is supplemented by using a multi-modal large model, the rationality of the supplemented information is verified through a geometric attribute relationship verifier, and complete formalized language description is obtained. According to the method, the industrial drawing image containing the complex constraint relation can be efficiently and accurately converted into machine-readable structured data.

The invention provides a virtual model generation method and device, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the steps of determining description information for generating a virtual model in response to a received generation instruction of the virtual model, and generating a grid model based on the description information; determining a distance field set corresponding to the grid model, and performing structure sensing alignment processing on the grid model based on the distance field set to obtain a first model, the first model comprising a plurality of first geometric primitives; determining a first distance field subset corresponding to each first geometric primitive from the distance field set, and trimming the first model based on each first distance field subset to obtain a second model; and determining a plurality of target components based on the second model, constructing a target model based on the plurality of target components, and outputting the target model. According to the method and the device, efficient generation and accurate optimization of the virtual model can be realized, so that the quality and the efficiency of model generation are improved.

The invention relates to the technical field of image recognition, in particular to a wheel rim sundry visual detection system for railway axle counting, and the system comprises a wheel track feature preliminary extraction module which is used for receiving an axle counting point image, traversing the image to calculate the gradient magnitude of each pixel point, screening the pixel points with the gradient magnitude exceeding a preset threshold value, obtaining a discrete feature point set of a wheel track, and obtaining a wheel track feature point set; in the discrete feature point set of the wheel track, dividing the point set into a linear feature point cluster and an arc feature point cluster, and establishing a preliminary wheel track geometric primitive; according to the method, after an axle counting point image is received, edge information screening is completed according to a pixel gradient magnitude, non-significant boundary areas are eliminated through gradient threshold limitation, the accuracy of feature extraction is improved, and after a feature point set is formed, two types of feature point clusters of straight lines and arcs are divided, and geometric structure fitting is performed, so that the accuracy of feature extraction is improved. And the morphological structure of the wheel rail is expressed in a parameter form, so that the region definition stability is improved.

The present disclosure provides an object positioning method, device, equipment, medium and program product, and relates to the technical field of image processing. The method converts scene data reflecting the geometric information of the surface of an object into a set of local geometric primitives rich in spatial position, geometric type and characteristic parameters, calculates the geometric affinity between the primitives to represent the possibility that they belong to the same object, and then uses a clustering algorithm to realize instance segmentation, thereby solving the technical problem of low precision and poor robustness of traditional object positioning methods caused by occlusion, background interference and a large number of object types in a complex environment, realizing automatic object instance segmentation and positioning based on geometric clues without a large amount of manual annotation, and achieving the effects of improving the recognition accuracy of objects with complex geometric structures, enhancing the generalization ability of the method in real scenes, and significantly reducing the dependence on pre-training data and manual annotation.

The application provides a robot environment perception method based on multi-sensor fusion, comprising the following steps: performing space-time synchronization processing on original multi-sensor data to generate synchronized perception data; judging whether there is a semantic landmark matching the original or synchronized data in a topological map, wherein the matching condition is that the geometric primitive of the semantic landmark in the topological map and the same geometric primitive existing in the data are matched; when it is confirmed that there is a matching landmark, selecting the matching landmarks to form a set; based on the set, performing pose correction on the original multi-sensor data, fusing different pose constraints in the matching landmarks into the original data, and obtaining corrected data for robot path planning. The application can improve the consistency of multi-sensor data and the accuracy of robot environment perception, and provides reliable correction data for path planning.

The invention discloses a laser cutting path optimization method of laser cutting equipment, and relates to the technical field of cutting path optimization. According to the laser cutting path optimization method of the laser cutting equipment, geometric primitive data of a to-be-cut workpiece is obtained, contour analysis processing is carried out, and a contour geometric data set of the to-be-cut workpiece is extracted; cutting sequence planning processing is conducted on the contour geometric data set of the to-be-cut workpiece based on a genetic algorithm, and an initial cutting path of the to-be-cut workpiece is generated; multi-target collaborative optimization processing is conducted on the initial cutting path of the to-be-cut workpiece, and the optimized cutting path of the to-be-cut workpiece is obtained.According to the method, the optimized cutting path of the to-be-cut workpiece is verified, the optimized verification cutting path of the to-be-cut workpiece is generated, and therefore the machining efficiency is remarkably improved while the machining precision is guaranteed; therefore, the reliability of the cutting process is comprehensively improved.

Techniques applicable to a ray tracing hardware accelerator for traversing a hierarchical acceleration structure with reduced round-trip communications with a processor are disclosed. The reduction of round-trip communications with a processor during traversal is achieved by having a visibility mask that defines visibility states for regions within a geometric primitive available to be accessed in the ray tracing hardware accelerator when a ray intersection is detected for the geometric primitive.

The invention relates to a method, a system, equipment and a medium for constructing a three-dimensional model based on geometric primitive hierarchy, and the method comprises the following steps: generating basic geometric primitives based on user input; determining a mapping rule type and an input parameter based on the generated basic geometric primitive; automatically executing a mapping algorithm to generate an initial three-dimensional grid model based on the determined mapping rule type and the input parameters; and adjusting and optimizing the initial three-dimensional grid model according to user requirements to obtain a final three-dimensional grid model. According to the method, basic geometric primitives are subjected to formalized description through a mathematical expression, a hierarchical structure capable of being driven by parameters is constructed, and systematic organization and precise control of a three-dimensional model are achieved. Thus. The method can be widely applied to the technical field of computer graphics and three-dimensional modeling.

Approaches presented herein provide for the clustering of geometric primitives, such as triangular faces, of a mesh representation that is advantageous for downstream processing. In at least one embodiment, clustering can be performed based in part on the spatial locations of the geometric primitives, such as to minimize the surface area of bounding boxes around clustered primitives or minimize the overlap between bounding boxes. Other factors such as connectivity within, or across, clusters can also be considered. A cost function can be used that includes weighted combination of cost terms, where those cost terms can be selected based in part upon a type of downstream processing to be performed, or requirements / optimizations of hardware to perform the processing.

The present disclosure relates to a multi-view image generation apparatus and method, and a graphics processing unit. Waves are constructed according to primitive information and vertex information of geometric primitives to generate a plurality of waves for parallel processing, and the waves are scheduled by a wave management unit for execution, which can improve execution efficiency. Since the primitive information of the geometric primitives is stored in a first cache unit, data sharing between waves can be implemented. During the parallel processing of the waves, vertex information in a second cache unit is updated in real time according to vertex address information outputted by the waves, so that a raster processing unit can read the latest vertex information from the second cache unit. Finally, through an image generation unit, a multi-view image is generated according to image colors obtained by executions of the waves and views corresponding to pixel points.

The invention discloses a wheeled inspection robot and a camera motion understanding method and system thereof. Displacement, video stream data and pose data are acquired in real time through a data acquisition module; the camera motion classification module performs motion classification and visual detection on the video frames, outputs geometric primitive and semantic primitive tags and an equipment state detection result, and maps the geometric primitive and semantic primitive tags and the equipment state detection result to a reference frame; the SfM-VLM fusion inference module extracts geometric parameters of camera motion through an SfM algorithm, fuses visual features and then inputs the fused visual features into a VLM model to generate natural language semantic description; the structured annotation module generates double-track annotations of a tag layer and a subtitle layer based on geometric primitives, semantic primitive tags and natural language semantic description; the multi-modal decision module fuses geometric primitive and semantic primitive tags, equipment state detection results and data acquired by the data acquisition module to generate an inspection decision; the problems of motion decoupling, target tracking, data annotation and multi-modal decision making in a dynamic environment are solved, and the routing inspection reliability and the intelligent level are improved.

The approaches presented here involve clustering geometric primitives, such as triangular areas, within a mesh representation, which is advantageous for downstream processing. In at least one embodiment, clustering can be partially based on the spatial positions of the geometric primitives, for example, to minimize the surface area of ​​bounding boxes around clustered primitives or to minimize the overlap between bounding boxes. Other factors, such as connectivity within or between clusters, can also be considered. A cost function can be used that comprises a weighted combination of cost terms, where these cost terms can be selected partly based on the type of downstream processing to be performed or on hardware requirements / optimizations for performing the processing.

The invention discloses a three-dimensional point cloud data segmentation model training and application method and device and a medium, and relates to the technical field of three-dimensional point cloud data segmentation, and the method comprises the steps: constructing an implicit fitting module, for each type of geometric primitive type, obtaining a first data set corresponding to the geometric primitive type, training an implicit fitting module by using the first data set to obtain a post-training implicit fitting module corresponding to the geometric primitive type, and forming an initial three-dimensional point cloud data segmentation model by using the segmentation module, the clustering module and the post-training implicit fitting module corresponding to each type of geometric primitive type, and training the initial three-dimensional point cloud data segmentation model to obtain a three-dimensional point cloud data segmentation model, and completing three-dimensional point cloud data segmentation by using the three-dimensional point cloud data segmentation model. According to the three-dimensional point cloud data segmentation method and the three-dimensional point cloud data segmentation system, the primitive geometric loss information is introduced by adopting the trained post implicit fitting module with the same structure and different parameters, so that the accuracy and robustness of the three-dimensional point cloud data segmentation model can be improved.

This invention relates to a depth completion method for non-cooperative spatial targets based on geometric primitive constraints, belonging to the field of 3D structure reconstruction technology for spatial targets. The method includes: establishing local depth constraint equations based on the target's geometric primitives; constructing a multi-task depth completion neural network model and incorporating the local depth constraint equations into the network loss function; establishing a sample dataset and training the multi-task depth completion neural network model; and embedding the trained model into the information processing unit of a spaceborne platform for target depth and pose prediction. This method addresses the problems of low accuracy and interpretability in the fine structure recovery of existing neural network-based target depth completion models, offering advantages such as high accuracy, fast speed, and strong interpretability of prediction results, thus achieving accurate recovery of the 3D fine structure of spatial targets under structural constraints.

The invention discloses a drawing update identification method and system, and the method comprises the following steps: S1, analyzing drawing files of new and old versions, and extracting multi-dimensional information including geometric primitives, layers and text annotations, S2, comparing the extracted multi-dimensional information of new and old versions, and identifying difference items, S3, based on a preset rule base, analyzing the identified difference items, and carrying out the identification of the new and old versions of the new and old versions of the new and old versions of the new and old versions of the new and old versions. The method comprises the following steps of S1, comparing and analyzing a drawing version, S2, automatically judging the change type and the influence level of the drawing version, S4, automatically generating a visual change report on the basis of a comparison and analysis result, highlighting a change area in a graphical mode by the report, and attaching a structured change list.According to the method, a traditional drawing version management mode is thoroughly innovated through an automatic, multi-dimensional and intelligent technical means; accurate, efficient and intelligent change identification is realized, project risks are effectively reduced, and cooperation efficiency and management level are improved.

Methods, devices, and data streams are provided for generating, transmitting, and decoding scene descriptions of an augmented reality scene. According to the present principles, a scene description graph links nodes and includes information indicating how a proximity trigger has to be evaluated to trigger an action on a virtual object. Conditions regarding proximity are based on the set of geometric primitives plus boundary values that change related 3D regions.

The application discloses a kind of instance segmentation and structured topological reconstruction methods of complex geometric building, it is related to three-dimensional model generation technical field, comprising the following steps: S1, building point cloud instance segmentation: using SoftGroup network to the semantic analysis of unmanned aerial vehicle LiDAR point cloud, output contains the independent component instance of each building component semantic label, the fine segmentation of each building component is realized by point cloud instance mask;S2, geometric primitive extraction: according to semantic label, group instance point cloud is carried out, and differential geometric fitting is executed, the application is realized by semantic-geometric coupling modeling The unified expression of irregular structure and regular component, solve the segmentation and parameterization bottleneck in complex building scene in traditional method, also adopt the boundary expression of elliptic curve segment simplification conical top or hemispherical top and support structure, reduce the complexity of calculation, while guarantee the integrity of building skeleton.

The application discloses a wheeled inspection robot and a camera motion understanding method and system thereof, wherein displacement, video stream data and pose data are acquired in real time through a data acquisition module; a camera motion classification module classifies motion and detects vision for a video frame, outputs geometric primitives and semantic primitive labels and device state detection results, and maps to a reference frame; an SfM-VLM fusion inference module extracts geometric parameters of camera motion through an SfM algorithm, inputs a VLM model after fusing visual features to generate natural language semantic description; a structured annotation module generates double-track annotations of a label layer and a subtitle layer based on geometric primitives, semantic primitive labels and natural language semantic description; and a multi-modal decision module fuses geometric primitives and semantic primitive labels, device state detection results and data collected by the data acquisition module to generate an inspection decision; the problems of motion decoupling, target tracking, data annotation and multi-modal decision in a dynamic environment are solved, and the inspection reliability and intelligent level are improved.

This invention relates to the field of computer vision and image processing, and proposes a method and system for automatic 3D modeling of 2D engineering drawings. The method includes the following steps: inputting 2D engineering drawings; parsing the context, generating a feature to-do list, and establishing a cross-view spatial mapping coordinate system; extracting the component types from the feature to-do list; obtaining parameterized topological constraint rules for the component types from a preset knowledge base; adopting goal-oriented active probing to search for geometric contours matching the features in the three views, obtaining the geometric primitives and their spatial poses corresponding to each feature; reading the dimension annotations, attaching the dimension values ​​as logical variables to the corresponding geometric primitives, and generating an enhanced structured feature list; constructing an instruction compiler, inputting the enhanced structured feature list, mapping each feature to a feature class calling function in the engineering knowledge base, and synthesizing a Python source code sequence to generate a parameterized 3D model.

The approaches presented here involve clustering geometric primitives, such as triangular areas, within a mesh representation, which is advantageous for downstream processing. In at least one embodiment, clustering can be partially based on the spatial positions of the geometric primitives, for example, to minimize the surface area of ​​the bounding boxes around clustered primitives or to minimize the overlap between bounding boxes. Other factors, such as connectivity within or between clusters, can also be considered. A cost function can be used that comprises a weighted combination of cost terms, where these cost terms can be selected, in part, based on the type of downstream processing to be performed or on hardware requirements / optimizations for performing the processing.

The application relates to the technical field of architectural model design, and discloses a curtain wall simulation design method and system based on BIM, which comprises the following steps: obtaining architectural point cloud data containing complex curved surface features; combining various geometric features of the point cloud data to improve a traditional region growing algorithm to segment the point cloud data; fitting geometric primitives to the segmented point cloud data and constructing an architectural BIM model to complete curtain wall simulation design. The application aims to improve the accuracy of region growing algorithm in edge segmentation of different architectural planar point cloud data.

The invention discloses a multi-target object rapid identification and sorting method, and relates to the technical field of computer vision, and the method comprises the steps: carrying out the instance segmentation of a multi-target object in a visual field based on multi-modal image data and three-dimensional point cloud data, extracting a sub-pixel geometric primitive from the edge contour of each target object, and obtaining a sub-pixel geometric primitive of the edge contour of each target object; generating a sub-pixel geometric feature set; on the basis of the sub-pixel geometric feature set, in combination with corresponding timestamp information, analyzing a spatial pose change relationship of each target object in a continuous time dimension, and forming a dynamic pose prediction sequence; time hedging compensation is carried out on the spatial poses of the target objects according to the time offset of the target objects from completion of pose calculation to sorting execution, and high-precision spatial pose information of the target objects at the future execution moment is solved; and on the basis of the high-precision spatial pose information, the corresponding sorting control instruction is generated, so that the operation frequency of multi-target continuous sorting and the system robustness are improved.

This invention discloses a spatiotemporal data indexing query method, system, medium, and device based on GPU ray tracing, belonging to the field of spatial data indexing technology. The method includes responding to a point query request, obtaining the query coordinates, query time, and target object identifier from the point query request, emitting a vertical ray along a preset direction starting from the query coordinates and starting height, performing GPU ray traversal of the nearest intersection point on the vertical ray using a pre-established spatiotemporal index structure, and returning the intersecting geometric primitive with the smallest ray parameter, whose object identifier matches the target object identifier, and is a valid data record, as the query result of the point query request. This invention achieves hardware acceleration of spatiotemporal indexing query by uniformly mapping two-dimensional spatial coordinates and time dimension to a three-dimensional coordinate system and utilizing a bounding volume hierarchy and its corresponding geometric acceleration structure.

The invention provides a product assembly stage identification method based on point cloud geometric primitive information, and belongs to the technical field of computer-aided assembly and simulation. The method comprises the following steps: respectively acquiring a model point cloud corresponding to a workpiece model in each assembly stage, and acquiring an actual point cloud corresponding to an actual workpiece; geometric primitives are utilized to divide and construct an actual primitive library and a plurality of model primitive libraries, all the model primitive libraries are utilized to construct a model point cloud picture corresponding to each model point cloud, and the actual primitive library is utilized to construct an actual point cloud picture; coarse registration of each model point cloud and the actual point cloud is completed; and according to all coarse registration results, fine registration is carried out on the actual point cloud and each model point cloud, and the assembly stage of the actual workpiece is identified according to all fine registration results. According to the invention, the method can achieve the precise recognition of the assembly stage of an unmarked product.

The invention discloses an intelligent image recognition system for a paper ruler regulation drawing operation, and the system comprises an image input module which receives an optical scanning signal of the paper ruler regulation drawing operation, and forms an original image digital signal; the image feature extraction module performs self-adaptive preprocessing operation on the original image digital signal to generate a feature topology signal containing geometric primitives and a spatial distribution relation of the geometric primitives; the semantic recognition module analyzes the feature topology signal based on a built-in cartographic specification knowledge base, and generates a primitive association signal with a semantic tag by combining a spatial relationship and a specification rule; the structure reconstruction module establishes a hierarchical semantic structure according to the primitive association signal and generates a structured vector signal; and the output module converts the structured vector signal into a digital engineering drawing file in a target computer aided design format. According to the intelligent image identification system for the paper ruler regulation drawing operation, the problems of shaking, line breaking and dense labeling of hand-drawn lines in the traditional paper ruler regulation drawing operation can be solved.

The present disclosure relates to an image reconstruction method, an electronic device and a storage medium, the image reconstruction method comprising: performing a first coordinate system conversion from a world coordinate system to a camera coordinate system on original primitive parameters of three-dimensional geometric primitives in a scene captured by an input image to obtain first primitive parameters of the three-dimensional geometric primitives, the primitive parameters of the three-dimensional geometric primitives being used to describe spatial attributes of the corresponding three-dimensional geometric primitives in the scene; applying directional distortion to the first primitive parameters of the three-dimensional geometric primitives to obtain second primitive parameters of the three-dimensional geometric primitives; performing a second coordinate system conversion from the camera coordinate system to the world coordinate system on the second primitive parameters of the three-dimensional geometric primitives to obtain target primitive parameters of the three-dimensional geometric primitives; and performing image rendering based on the target primitive parameters of the three-dimensional geometric primitives to obtain a target image after reconstruction. Through directional distortion, the target image is consistent with the input image in distortion parameters.

The application provides a product assembly stage recognition method based on point cloud geometric primitive information, and belongs to the technical field of computer-aided assembly and simulation. The method comprises the following steps: acquiring model point clouds corresponding to workpiece models of each assembly stage respectively, and acquiring actual point clouds corresponding to an actual workpiece; constructing an actual primitive library and a plurality of model primitive libraries by using geometric primitive division; constructing model point cloud graphs corresponding to each model point cloud by using all the model primitive libraries, and constructing an actual point cloud graph by using the actual primitive library; completing coarse registration of each model point cloud and the actual point cloud respectively; performing fine registration of the actual point cloud and each model point cloud according to all coarse registration results, and recognizing the assembly stage of the actual workpiece according to all fine registration results. The application can realize accurate recognition of the assembly stage of a product without identification.

The application relates to the technical field of automatic driving positioning, and particularly discloses a laser radar SLAM method, device and system for an automatic driving vehicle, which comprises the following steps: acquiring laser radar original point cloud data, and obtaining feature information after adaptive roughness evaluation and feature screening of the laser radar original point cloud data; performing dynamic outlier detection on the feature information to screen out outlier feature points and obtain effective feature information; performing pose estimation on the effective feature information according to a double-peak geometric primitive constraint mechanism to obtain a six-degree-of-freedom pose, wherein the double-peak geometric primitive constraint mechanism is obtained by constructing corresponding feature information in a local map according to feature information of a current frame; sequentially performing local map construction and global map construction according to the six-degree-of-freedom pose to obtain positioning information of the automatic driving vehicle. The laser radar SLAM method for the automatic driving vehicle can improve the precision and reliability of laser radar SLAM.

The application relates to a three-dimensional object detector construction method and system, point feature, edge feature, surface feature and line feature of collected point cloud data are extracted, and N seed points are obtained; a first layer geometry perception module is used to learn four-channel weighted graphs of four types of features and to calculate weighted features, a first layer context perception module is used to construct the relationship between the seed points; three convolution layers are used to extract three kinds of geometric primitives; a second layer context perception module is used to establish the relationship between the features of the three kinds of geometric primitives, that is, the region blocks, and to obtain weighted features by using a second layer geometry perception module to learn three-channel weighted graphs of the three kinds of geometric primitives and to calculate the weighted features; a proposal generation module is used to obtain region proposals of objects, and a three-dimensional object detector construction task is completed. The application improves the precision of three-dimensional object detection and improves the multi-scale object detection precision of an indoor scene.