893 results about "Plane map" patented technology

The invention discloses a BIM-based two-dimensional data and three-dimensional model verification matching method and system. The system comprises a 2D drawing processing module, a 3D model processing module, a difference detection module and a report generation module. In the 2D drawing processing module, a user imports a process pipeline plan and a profile map, and through preprocessing and image semantic analysis, pipeline elevation labeling information is extracted and numbered. And the 3D model processing module loads a target BIM model, locates a process pipeline area, analyzes pipeline parameters and a space state, analyzes a pipeline topological relation and performs conflict verification. And the difference detection module binds the 2D drawing with a corresponding pipeline object in the 3D model, establishes a mapping relation, compares differences, and performs labeling and classification. And the report generation module is used for carrying out visual annotation in the 2D drawing and the 3D model based on the annotation difference, automatically generating a difference comparison table and outputting a report, so that efficient and accurate verification and matching of the two-dimensional data and the three-dimensional data are realized, the examination period is shortened, and the rapid collaborative correction efficiency of the construction team is improved.

The invention provides an intelligent inventory robot path optimization method based on environment modeling and collaborative optimization, and relates to the technical field of intelligent warehouse management, and the method comprises the steps: scanning a warehouse region through an unmanned plane platform, and generating three-dimensional warehouse point cloud data; after point cloud denoising, plane fitting, shelf boundary extraction and channel detection processing, a two-dimensional storage plane graph is generated and transmitted to a robot data base; generating an initial inventory planning path by adopting an A * algorithm, optimizing the initial path through a simulated annealing algorithm, and generating a target inventory planning path; based on the dynamic obstacle influence factors, the RFID signal intensity and the robot residual electric quantity are combined, and a target path is corrected through a mixed algorithm of multi-target optimization and PSO dynamic weight; and the operation end checks the checking progress through the AR equipment and manually adjusts the target path, so that the checking path of the intelligent checking robot can be optimized in real time in a dynamic environment, and the checking efficiency, the coverage rate and the cruising ability of the robot are improved.

The invention discloses a space identification method and system based on a YOLO model, a terminal and a medium, and the method comprises the steps: obtaining a CAD drawing, carrying out the space segmentation and coordinate conversion of the CAD drawing, obtaining a PNG image corresponding to a specified space region in the CAD drawing and a label file corresponding to the PNG image, and determining a training data set based on the PNG image and the label file; building a Python operation environment, installing a YOLOv8-seg model and a related dependency library thereof, and carrying out end-to-end training on the training data set based on a training script of the YOLOv8-seg model to obtain a YOLO space segmentation model; and based on the YOLO space segmentation model, carrying out space segmentation on the building plane drawing, outputting a segmentation result, and carrying out automatic labeling on a space region. According to the method, the YOLO space segmentation model is adopted, high-precision space recognition and classification are achieved, and the generalization ability is high.

Methods, systems, and bitstream syntax are described for a scalable 3D scene representation. A general framework presents a dual-layer architecture where a base layer provides a baseline scene representation, and an enhancement layer provides enhancement information under a variety of scalability criteria. The enhancement information is coded using a trained neural field. Example systems are provided using a PSNR criterion and a baseline multi-plane image (MPI) representation. Examples of bitstream syntax for metadata information are also provided.

The invention discloses a three-dimensional curved surface pattern layering processing method based on parameterized segmentation, and aims to solve the problem of high-precision pattern processing on the surface of a curved surface by using a laser scanning galvanometer. The method comprises the following steps: firstly, importing a three-dimensional model, and carrying out parameterization processing to obtain a two-dimensional parameter domain; positioning a to-be-processed plane pattern in the two-dimensional parameter domain to form a complete two-dimensional geometric grid covering a pattern area, generating a three-dimensional pattern grid attached to a curved surface, and calculating a center normal vector of the three-dimensional pattern grid; then, generating an equidistant plane group on the surface of the curved surface, and calculating an intersection line of the plane and the three-dimensional pattern grid as a laser scanning track; and the five-axis linkage platform-galvanometer system is started for machining. Through the parameterization domain, distortion of curved surface pattern machining is effectively solved, machining uniformity is improved, and the method is particularly suitable for laser machining of large-scale or high-complexity curved surface patterns.

The invention provides a thermal simulation analysis method, device and equipment for PCB design and a storage medium, and the method comprises the steps: obtaining a finite element model of a PCB, the finite element model being obtained through modeling according to the electrical parameters of components, the typesetting parameters of the components and the structural layout parameters of a substrate; controlling the finite element model to operate under a preset power load to obtain a simulation heat diagram of the finite element model; partially hiding the finite element model to respectively obtain a component plane graph and a substrate plane graph; inputting the component planar graph into a preset image recognition model to obtain a first annotation graph, and inputting the substrate planar graph into the preset image recognition model to obtain a second annotation graph; and inputting the simulation heat map, the first annotation map and the second annotation map into a preset image scoring model, annotating a thermal anomaly region and thermal anomaly information, and using the thermal anomaly region and the thermal anomaly information to guide optimization of a finite element model.

The invention discloses a path planning method and system for curved surface integrated conformal jet printing, and belongs to the field of additive manufacturing. According to the method, the geometric data of the non-deployable curved surface are obtained and converted into the discretized grid model, then the plane pattern is designed and mapped to the three-dimensional curved surface, the mapped pattern is locally optimized, and the complete printing area model is generated. Path planning is divided into initial jet printing path generation and five-axis linkage motion path planning, conformal characteristics are achieved through an adaptive interpolation algorithm and NURBS curve optimization, five-axis motion parameters are calculated based on an inverse kinematics algorithm, and the positioning relation between a jet printing head and a curved surface is kept through the RTCP technology. The method solves the problems of precision and path planning efficiency in complex curved surface manufacturing, and is suitable for manufacturing heterogeneous complex curved surface functional structures in the fields of aerospace, medical instruments and the like.

The invention provides an effective room identification method, device and equipment and a storage medium, and the method comprises the steps: converting wall elements in an architectural plan into a line segment set, and carrying out the intersection detection and topology analysis to obtain an undirected weighted graph structure; determining an influence area in response to a user editing operation, and performing incremental updating on the influence area to obtain a locally updated graph structure; performing ring detection processing on the locally updated graph structure by applying a minimum ring basis algorithm to obtain a minimum ring basis containing a basic ring in the influence region; and identifying the effectiveness of the rings according to the geometric features and the topological features of each ring in the minimum ring basis, and identifying the effective rings as effective rooms. According to the method, through incremental updating and local processing, the calculation overhead of full-amount reconstruction is avoided, the calculation efficiency and real-time performance of room recognition are remarkably improved, and the method is suitable for interactive design scenes of large complex architectural planar graphs.

A splat generation system and associated methods generate a splat representation of a three-dimensional (3D) model with varying detail based on an unequal or non-uniform capture of the 3D model. The system receives the 3D model. The system analyzes variation in the position or visual characteristics of the 3D model primitives, attributes different levels-of-importance to different surfaces or regions of the 3D model based on the variation, and defines a non-uniform placement of virtual cameras around the 3D model according to the different levels-of-importance that are attributed to the different surfaces or regions of the 3D model. The system generates the splats for the splat representation that reconstruct the different surfaces or regions with differing amounts of detail that match the detail captured for the different surfaces or regions in images generated from the non-uniform placement of the virtual cameras.

The present invention relates to the technical field of intelligent evacuation. Provided are a method and system for intelligently generating an emergency evacuation scheme. The method comprises: performing geographic information scene creation and data association on the basis of a park plane map, so as to obtain a digital visual map; sensing and marking the type, occurrence location, severity degree and influence range of an incident in real time, and performing initial information configuration on an evacuation scheme; determining an evacuation mode; automatically and manually creating or modifying evacuation routes, automatically merging the generated evacuation routes, and automatically supplementing unselected evacuation routes, so as to obtain an optimal evacuation path; and automatically generating key information of the evacuation scheme, so as to obtain an emergency evacuation scheme. The present invention reduces the evacuation design command difficulty of a complex incident site, improves and ensures the feasibility of all evacuation schemes, eliminates the misoperation possibly caused by human factors in the case of a large number of manual plans, and ensures the correctness of an evacuation indication direction, thereby making intelligent evacuation more reliable and safe.

The invention discloses a distributed urban and rural planning decision support method and system, and relates to the technical field of data analysis, and the method comprises the following steps: S100, drawing a planar graph of a to-be-planned region, dividing the planar graph of the region according to a Morse decomposition method, and constructing a region matrix, S200, calculating the coverage rate of the region matrix, and S300, calculating the coverage rate of the region matrix. And planning the surveying and mapping path. According to the method, planning units and surveying and mapping grids are unified into the same quadrilateral matrix through Morse complex, repeated zoning and edge matching errors are effectively avoided, the edge weight is inversely proportional to the building coverage rate, an unmanned aerial vehicle and a surveying and mapping vehicle automatically and preferentially encrypt a high built-up area, field working hours are saved, the data precision of a core construction area is guaranteed, and the construction efficiency is improved. The regional matrix naturally corresponds to edge nodes, and each node only communicates with an adjacent unit, so that the MST and the local route can be locally solved, the communication complexity is reduced, and the method is suitable for large-scale regional surveying and mapping.

The invention provides a virtual hotel guide customization system based on intelligent optimization and multi-mode interaction. The virtual reality and intelligent navigation system comprises a user preference acquisition module used for acquiring user preference data; the scene sensing module is used for outputting the short-time congestion degree weight of each interest point through a space-time diagram convolutional network congestion prediction model according to the hotel indoor plane graph and the real-time people flow data; and the path optimization module is used for generating a tour guide route which meets the time budget and has the minimum congestion degree and updating the tour guide route in real time. According to the virtual hotel guide customization system based on intelligent optimization and multi-modal interaction, not only can a crowded area be dynamically avoided within a second level and smooth and redundancy-free guide be ensured, but also the journey can be adjusted in real time according to the remaining time and interest preference of the user, and on-demand accurate service for different guest groups is realized.

The invention relates to the technical field of image recognition, in particular to a building plane element recognition model construction method based on a convolutional neural network, and the method comprises the following steps: obtaining an input APN sample; elements in the APN sample are labeled, and a labeled file is generated; converting the annotation file into a format required by YOLO, and normalizing the annotation file; performing data enhancement on the APN sample, expanding the training data volume, and outputting to obtain an element detection result and a feature vector; installing dependency and carrying out data configuration; setting command line model parameters and customizing training scripts; and carrying out model training and model reasoning. According to the method, the plane layout is abstracted based on the machine learning method, and the vector data type has high flexibility and deformation capability, so that the vector output which keeps the original plane image form unchanged can be converted into various objects according to the purpose of a user. And classifying and identifying the plane elements by using the GNN.

The invention provides a hub-oriented dynamic flexible adaptive space reconstruction method and system, and the method comprises the steps: constructing a hub space plane graph of a to-be-constructed hub space in a preset coordinate system, and determining boundary coordinates, obstacle coordinates, entrance coordinates and exit coordinates of the hub space plane graph; determining a first route by adopting a first algorithm based on the boundary coordinates, the obstacle coordinates, the entrance coordinates and the exit coordinates of the hub space plane graph, and determining a first path based on the first route; if the hub space is a preset key area, updating the first route by adopting the second algorithm to obtain a second route, and determining a second path based on the second route; and determining a path boundary in the first path or the second path, arranging the spatial reconstruction units along the path boundary, determining coordinates of the spatial reconstruction units, and matching the coordinates with the corresponding spatial reconstruction units.

Methods and devices for generated multiplane images from a representation of a 3D scene are disclosed. When an MPI is generated by the system, an image of the accumulation of the alpha values is computed. A convolutional networked is trained with a penalization function that penalizes MPIs with high values of accumulated alpha according to a parameter selected or trained to reduce the redundancy of information between layers of the MPI. When generating a MPI from a subset of the views of a new captured 3D scene, a first MPI is generated with the trained CNN with the associated parameter. An error is calculated between the other views and corresponding synthesized with the first MPI. This error is used to modify the parameter. Then, a second MPI is generated with the trained CNN with the new parameter.

The invention relates to a circuit board back drilling hole nondestructive testing method and system, and belongs to the technical field of multi-layer circuit board manufacturing. Comprising the following steps: acquiring position information and depth data of each back drilling hole in a circuit board to be detected; scanning the position of the back drilling hole according to the position information, and constructing a three-dimensional scanning image; wherein the three-dimensional scanning image comprises an XZ plane image; according to the XZ plane image, taking the bottom of the copper column reserved on the circuit board to be detected as a reference layer, and calculating the height of the copper column; measuring the thickness of the circuit board to be measured, and calculating the drilling depth of the back drilling hole according to the thickness and the height of the copper column; the drilling depth is compared with the depth data, and whether the height of the copper column is within a preset range or not is judged; when the drilling depth exceeds a preset range, judging that the drilling depth is abnormal; and when the drilling depth is within a preset range, determining that the drilling depth is normal. According to the invention, nondestructive and complete detection of the back drilling hole is realized, and the drilling depth and the drilling quality of the back drilling hole on the corresponding detected circuit board can be fed back.

The invention discloses a pixel-level accurate texture generation method based on a multi-view artistic work. The method comprises the following steps: inputting an image file; performing multi-view projection on the 3d model for a plurality of views corresponding to the plane image to construct a texture space; aiming at coexisting points on the surface of the 3d model in the multiple visual angles, calculating a dot product of each visual angle direction and a normal of the surface of the 3d model so as to construct an initial texture map corresponding to the 3d model; projecting all contour points of the 3d model into a texture space to obtain corresponding texture information, and comparing the texture information with contour points contained in the initial texture map to construct a mask area; generating a shielding texture map corresponding to the mask area through a diffusion model; and carrying out rendering processing on the 3d model based on the initial texture map and the sheltered texture map so as to output a high-quality model with texture information. The invention further provides a pixel-level accurate texture generation device. According to the method provided by the invention, the high-quality texture can be generated for the grid, and meanwhile, the pixel-level consistency with the reference art is ensured.

The invention provides a gear tooth surface precision detection method based on a deep learning network, a medium and equipment, and mainly solves the problem of insufficient model generalization ability caused by scarcity of real labeled data and domain difference in an existing method. The method comprises the following steps: collecting a plane workpiece image marked with a roughness level as a source domain data set, and pre-training an intelligent detection model; based on a gear shaping machining meshing motion relation, establishing a tooth surface morphology geometric simulation model, and generating virtual gear tooth surface images of different roughness grades; extracting a real gear tooth surface area image as a target domain sample; a domain adaptation method based on clustering optimal transmission is adopted, the feature distribution difference between a source domain and a target domain is calculated and minimized, model parameters are optimized, and self-adaptive migration of a feature space from a plane image to a gear tooth surface is achieved. According to the method, virtual sample generation and a domain adaptation technology are combined, so that the data acquisition cost is effectively reduced, and the detection precision and the model generalization ability under the small sample condition are remarkably improved.

The invention relates to the technical field of image detection, can be applied to business system platforms of financial science and technology, medical health and the like, and discloses a method, a device, equipment and a medium for generating a three-dimensional scene based on a planar graph, and the method comprises the steps: obtaining a data set, and carrying out the multi-modal feature extraction and preprocessing of the data set, and obtaining structural data; performing modal alignment on the structured data to obtain fusion data in a unified feature space; performing three-dimensional scene prediction on the fused data by using a preset autoregression converter architecture to obtain a three-dimensional scene prediction result; carrying out loss calculation and parameter optimization iteration on the autoregression converter architecture according to a three-dimensional scene prediction result to obtain an optimization model; and constructing the preset plane graph into a three-dimensional scene by using the optimization model. The problems of accuracy and efficiency in generation of a three-dimensional scene based on a planar graph in the prior art are solved.

The invention relates to the technical field of light field image super-resolution reconstruction, in particular to a light field image spatial super-resolution method based on a multi-scale large kernel attention mechanism, which comprises the following steps: inputting a target light field image into a trained spatial super-resolution reconstruction model, and outputting a spatial super-resolution reconstruction image of the target light field image; in the spatial super-resolution reconstruction model, performing feature extraction on an input light field image through a shallow feature extraction network to generate a shallow feature map; respectively extracting angle features, spatial features and epipolar plane image features from the macro-pixel image of the shallow feature map, the sub-aperture image for generating the macro-pixel feature map and the epipolar plane image of the shallow feature map through a large kernel feature extraction network, and fusing to generate a 4D light field feature map; and performing up-sampling reconstruction on the 4D light field feature map through an up-sampling reconstruction network to generate a spatial super-resolution reconstruction image of the input light field image. According to the invention, the reconstruction quality of the spatial super-resolution of the light field image can be improved.

The invention relates to a robot time optimal speed planning method comprising the following steps: giving a determined Cartesian space robot end motion path, and realizing path parameterization and discretization through a path parameter s; a kinematics model and a dynamics model of the robot are established, a more accurate dynamics model is obtained through dynamics parameter identification, and therefore joint speed, moment and jerk constraints are introduced to guarantee the feasibility of motion; relocating the constraints in the joint space to Cartesian space using a Jacobian matrix and its derivative; the reduction of the motion time is taken as an optimization target, a phase plane graph of path parameters is solved by adopting nonlinear optimization iteration, and speed planning with optimal time is carried out according to correlation calculation of a Jacobian matrix. The method is high in universality, the working time of the robot can be effectively shortened, the smooth and stable joint value, speed and acceleration curve of the robot are obtained, the working efficiency is improved, meanwhile, the service life of the robot is prolonged, and the working precision of the robot is improved.

The invention discloses a method for generating a route of an autonomous inspection channel of an unmanned aerial vehicle, and the method is characterized in that the method comprises the steps: S1, channel selection and vectorization; s2, elevation processing mode decision making: calculating an elevation standard deviation in a frame selection area according to the imported DEM elevation data; dynamically adjusting the terrain clearance of the unmanned aerial vehicle according to the calculated elevation standard deviation; s3, automatic route planning comprises the steps of generating an initial waypoint, self-adaptive waypoint density and multi-angle coverage in a channel vector range; and S4, generating and verifying an air route file, wherein the air route file comprises standardized packaging and three-dimensional visual verification. An unmanned aerial vehicle inspection channel route is quickly generated through a two-dimensional plane map, and efficient and safe autonomous flight is realized by combining intelligent elevation processing and route optimization.

The invention provides an unmanned aerial vehicle navigation method and system fusing reinforcement learning and model prediction. The method comprises the following steps: collecting environment information by using a laser radar through autonomous exploration and establishing a map; extracting a two-dimensional plane map of the projection of the global map at the height of the target point; searching an optimal global path on the global two-dimensional map; using a deep reinforcement learning algorithm to obtain a smooth trajectory with the position, speed and attitude information of the unmanned aerial vehicle; and realizing trajectory tracking of the unmanned aerial vehicle by an optimized method through model predictive control. The technical problems that collision is likely to happen in unmanned aerial vehicle planning and the system control stability is poor are solved.

The invention discloses a casting part multi-mode intelligent cost accounting method and system, and relates to the technical field of casting engineering and intelligent cost accounting. The casting part multi-mode intelligent cost accounting method comprises the steps that process information in casting engineering is extracted and processed in a structured mode, and missing information of a plane drawing is automatically supplemented; matching a target casting process route and key parameters based on the process information subjected to the structured processing; and calculating the basic total cost according to the target casting process route, and correcting the basic total cost in combination with the historical data deviation, the real-time market data and the order variables to obtain the corrected total cost. Unified automatic analysis of the plane drawing and the three-dimensional drawing is achieved, the problem that information of the plane drawing is incomplete is solved through image recognition and rule completion, and the limitation that only a single drawing type is supported is broken through; the casting process constraint extracted from the three-dimensional drawing is directly used as a core parameter of process matching, and the plane drawing indirectly maps process requirements through feature recognition, so that quantitative association of drawing information-process parameter-cost is realized.

The invention discloses a front-wheel steering vehicle autonomous exploration method and system suitable for a complex terrain, and the method comprises the steps: 1, obtaining a global rasterized terrain plane map according to original point cloud data; step 2, carrying out trafficability cost evaluation on the global rasterized terrain plane map to obtain a global trafficability cost map and a leading edge point; step 3, dividing a set direction area according to the orientation and steering capability of the vehicle, calculating leading edge gathering points in the set direction by using a geometric analysis algorithm, and obtaining a sparse topological graph of the leading edge points; step 4, local planning: selecting a frontier aggregation point with the lowest navigation comprehensive cost from local frontier aggregation points in the frontier point sparse topological graph as a local planning target point of the current period, and obtaining an initial path by using an improved A * algorithm; and 5, performing global planning. According to the method, the interaction between the vehicle and the terrain can be fully considered, a real local terrain traversal map is generated, and the vehicle can completely and autonomously explore a large outdoor unknown area.

The invention discloses a CTC station graph automatic drawing method based on image recognition. The method comprises the steps that centralized management and maintenance are conducted on all primitive objects related to station yard graphs; image recognition is carried out according to the station yard graph of the interlocking upper computer interface, the in-station railway signal object element type and the in-station signal equipment connection relation of the to-be-drawn station are obtained, and the in-station signal equipment connection relation is mapped and associated to in-station graph elements corresponding to the in-station railway signal object elements of the to-be-drawn station; outputting the connection relation of the in-station signal equipment according to the connection relation table of the station yard basic primitives; primitive objects are selected, primitives of the selected primitive objects are automatically spliced, and then a station yard plane graph preliminarily meeting the requirement of a CTC station graph is obtained; primitives in the drawn station yard plane graph and static attributes of the primitives are stored on the basis of a database, and statistics, verification and output are conducted on data of the primitives. The invention further discloses a system, electronic equipment and a computer readable storage medium.

The invention relates to a navigation method for a bodybuilding robot in a large-scale environment and a storage medium. The method comprises the following steps: firstly, dividing an environment map of a plurality of environments into a plurality of sub-maps, and constructing a hierarchical topological map based on a satellite navigation map and a building floor planar graph; and then, planning a path of the body-equipped robot based on the hierarchical topological map. And then controlling the robot with the body to start from the starting node, and when the robot with the body arrives at the switching node, switching the sub-map of the current environment to the sub-map of the next environment according to the cross-environment navigation strategy until the robot with the body arrives at the destination node. According to the method, complex space navigation is simplified into a graph search problem of node connection, so that the calculation complexity of path planning is greatly reduced, and the navigation path of the robot with the body has continuity and smoothness during cross-environment, so that the navigation efficiency of the robot with the body in a large-scale environment is improved.

The invention relates to the technical field of building decoration supervision, and discloses an intelligent building decoration construction supervision method and system based on artificial intelligence. The method comprises the following steps: acquiring real-time construction data through sensing equipment deployed at a construction site, and inputting the real-time construction data into a pre-trained building decoration quality analysis model; according to a quality evaluation result output by the model, generating a digital construction plane graph containing a construction abnormal region mark; automatically generating a recheck instruction set for the abnormal region based on the abnormal region coordinates; the recheck instruction set is distributed to the corresponding construction terminal equipment, and the terminal equipment is triggered to execute secondary data collection of the designated area; and dynamically adjusting a detection threshold parameter of the building decoration quality analysis model according to a deviation value between the data of the secondary data acquisition and a preset construction standard. The method can achieve the real-time and precise supervision of the building decoration construction process, optimizes the supervision process, improves the construction supervision efficiency and quality, and meets the demands of the building decoration industry for construction supervision.

A method to align a constellation of access points of a wireless local area network to, e.g., a floorplan, includes generating a representation of a constellation of access points of a wireless local area network area using inter-access point range finding, wherein data from the inter-access range finding is filtered based on a quality indicator associated with respective links between the access points, matching the representation of the constellation of access points to features of a map of a predetermined space, and identifying a location for each access point in the representation of the constellation of access points based on location information associated with the map.