340 results about "Vector map" patented technology

The invention relates to the technical field of navigation and positioning, in particular to an intelligent positioning and navigation early warning system and method for ships and boats. The method comprises the following steps: collecting and carrying out sea condition sensing and positioning signal evaluation according to a multi-source sensor synchronous data set to obtain a sensor reliability score table; performing target motion situation analysis according to the sensor reliability score table to obtain a fusion situation vector diagram; performing target motion state judgment according to the fused situation vector diagram to obtain a target motion state judgment result; performing multi-target collision risk assessment according to the target motion state judgment result to obtain a risk degree assessment matrix; performing navigation maneuvering performance constraint according to the risk assessment matrix to obtain a route planning maneuvering constraint rule set; and performing route trajectory search according to the route planning manipulation constraint rule set to obtain a navigation trajectory scheme. According to the invention, through the positioning navigation early warning technology, the positioning precision, the navigation safety and the early warning system practicability of the ship in a complex environment are obviously improved.

The invention relates to a remote sensing image ground feature recognition method based on deep learning, and the method comprises the steps: carrying out the data collection and preprocessing of a ground surface target region, eliminating the position deviation through geometric correction, processing the illumination difference through combination with radiation equalization, and generating a ground feature registration image; performing multi-dimensional feature fusion processing on the image, performing tensor fusion on vegetation spectral features, earth surface texture features, point cloud data features and linear ground feature features, and constructing a ground feature fusion matrix; a bilateral convolutional neural network is adopted to extract spectral response characteristics and spatial correlation characteristics, and characteristic interaction is realized through an attention mechanism to generate a ground feature probability distribution diagram; and finally, carrying out noise filtering, boundary refining and vectorization conversion processing on a classification result, and outputting a ground feature classification vector diagram. According to the method, three technical bottlenecks of insufficient cooperative utilization of multi-source heterogeneous data, insufficient spectrum-space feature fusion and poor GIS compatibility are solved, and the operation efficiency of territorial investigation, disaster monitoring and other scenes can be remarkably improved.

Disclosed are embodiments for facilitating generative artificial intelligence to generate multiple autonomous vehicle future trajectories. In some aspects, an embodiment includes receiving input data to a generative pre-trained transformer (GPT)-based trajectory generation model, wherein the input data comprises vector map representations, nearby actor history, and autonomous vehicle (AV) history of an AV; generating map tokens from the vector map representations and generating agent tokens from the nearby actor history and the AV history; inputting a concatenated set of the map tokens and the agent tokens into an encoder transformer of the GPT-based trajectory generation model; outputting, by the encoder transformer, an output embedding that is representative of a scene of the AV; and determining, by a decoder of the GPT-based trajectory generation model, a sequence of AV waypoint predictions for the AV based on the output embedding.

The embodiment of the invention provides a scoliosis Cobb angle determination method and device based on Mama, equipment and a storage medium. The method is applied to the scoliosis prediction field. The method comprises the following steps: acquiring image information, and preprocessing the acquired image information to obtain an original image; performing multi-level local feature extraction on the original image through an encoder to obtain a first feature map; performing global feature capture on the first feature map through a Mama module to obtain a second feature map; decoding the second feature map through a decoder to obtain a target feature map; generating, by a prediction module, a central heat map, an offset map and a centripetal vector map based on the target feature map; according to the central heat map, the offset map and the centripetal vector map, extracting central point coordinates of the centripetal body, and according to the central point coordinates of the centripetal body, determining four angular point coordinates of the centripetal body; the Cobb angle is determined through a geometric algorithm according to the coordinates of the four angular points of the cone, and the measurement precision of the Cobb angle is improved.

The invention belongs to the technical field of automatic driving, and particularly relates to an automatic driving local vector map construction method based on a standard precise map and fusion perception. The method comprises the following steps: preprocessing standard precise map information, and constructing a fusion sensing network; in the standard and precise map information preprocessing, original standard and precise map data are processed into vectorization expression suitable for model input; the fusion sensing network comprises a feature extraction backbone network, a BEV (aerial view) view conversion network, a multi-mode BEV feature fusion network and a map element decoding module; in the map element decoding module, the processed standard precise map elements are interacted with BEV aerial view features of the sensor; in local map model training, query denoising is introduced as an additional training task, and query sorting selection is introduced to accelerate the model convergence speed. According to the method, higher accuracy, better robustness and higher operation efficiency can be achieved, and the influence of environmental factors is smaller.

The invention provides a method for generating multi-dimensional landform vector data based on remote sensing image semantic segmentation, and belongs to the technical field of remote sensing image ground object recognition and artificial intelligence, and the method comprises the steps: training a landform recognition deep learning model based on a remote sensing image, adjusting a pre-training weight to optimize an image encoder, and generating a classification result; the landform recognition deep learning model comprises an encoder formed by a multi-layer convolutional network and a decoder of an up-sampling and feature fusion architecture; extracting a single-band label corresponding to each landform type from the classification result, and generating a binary raster image with the single-band labels; and converting the binary raster image with the single-band label into a vector diagram, and combining the vector diagram with the elevation information to generate multi-dimensional geographic data.

The invention provides a basement scene automatic vector map construction method and system, and the method comprises the steps: carrying out the IPM conversion of a plurality of ground-oriented top view images, carrying out the splicing, obtaining a bird's-eye view, carrying out the semantic segmentation of the bird's-eye view, extracting semantic elements, and converting the semantic elements into point cloud data; providing IMU and vehicle wheel speed data, combining with the point cloud data to construct a local map, and correcting to obtain a semantic point cloud map; preprocessing the semantic point cloud map, and clustering the point cloud data in the semantic point cloud map according to the similarity semantic point cloud to obtain clustered point cloud data; and based on the semantic point cloud map, combining the clustering point cloud data, constructing boundaries on two sides of a road, generating a lane center line and a boundary line, obtaining a vector map, embedding parking space information, and performing curve optimization on the center line and the boundary line, so as to obtain a basement scene automatic vector map. Vector representation of the complex environment of the underground garage is achieved, and high-quality basic map data support is provided for applications such as vehicle navigation and path planning.

The invention relates to the field of city updating, and discloses a city updating decision-making method based on public participation, which comprises the following steps: acquiring city space basic data including a vector map, remote sensing image data and historical, cultural and geographic information data of a city; on the basis of the acquired spatial data, a public participation base map is constructed, and the base map comprises information of a road network, land use types and historical and cultural areas of the city; collecting opinion data of the public on facility site selection through an interactive platform on the public participation base map; and according to the collected public opinion data, constructing a multi-subject scoring model. According to the method, a decision-making method based on public participation is adopted, space basic data and public opinions of cities are combined, facility site selection is evaluated through a multi-subject scoring model, and the opinions of different subjects can be integrated by the system by setting weight values of the public, experts and the government, so that the diversity and fairness of site selection schemes are ensured.

The invention provides an online vector map construction method fusing a large language model and thermodynamic diagram attention and electronic equipment, and the method comprises the steps: obtaining an image collected by multiple cameras, extracting a feature map of the image, converting the feature map into BEV features, and optimizing the BEV features through pooling operation; dynamic objects and static objects are separated from the optimized BEV features, semantic categories are marked, BEV semantic features are obtained, and semantic enhancement is conducted on the BEV semantic features in combination with a knowledge base of a large language model; generating a thermodynamic diagram by using the BEV semantic features after semantic enhancement, generating query points in the thermodynamic diagram, and constructing a vector map by using the BEV semantic features and the query points; and performing quality evaluation on the vector map and performing error optimization based on an evaluation result. According to the method, for a complex dynamic environment, a high-precision vector map can be constructed by optimizing the feature fusion capability of the multi-view image, accurately distinguishing a static object from a dynamic object and improving the semantic understanding capability of the environment.

The invention provides a graphical high-efficiency navigation positioning method and system based on multi-sensor fusion, a high-precision grid map is quickly generated through a pre-drawn vector map, or a known grid map is directly used for navigation, so that the navigation efficiency is improved. Meanwhile, an improved error Kalman filtering algorithm for dynamically adjusting covariance of process noise and observation noise is designed and is used for high-precision fusion positioning of UWB / IMU. Besides, local path planning and dynamic obstacle avoidance are performed in combination with a low-cost one-dimensional laser radar, so that the navigation precision, real-time performance and robustness of the system are remarkably improved, the hardware cost and the calculation complexity are effectively reduced, and an efficient and reliable solution is provided for application of multi-sensor fusion navigation positioning in a complex environment.

The invention relates to the technical field of intelligent monitoring of wild animals, and provides a wild animal channel monitoring method based on infrared induction and AI identification, which comprises the following steps: triggering high-resolution infrared image acquisition when an infrared induction module detects that the change of heat in a channel exceeds a threshold value; an animal target in the image sequence is identified through an AI target detection model, a motion area is extracted, and a transverse / longitudinal motion vector diagram is generated; motion intensity distribution is calculated based on the vector diagram, and a dynamic weight map is generated in combination with a species activity mode database; and carrying out space-time fusion on the dynamic weight map and the infrared images of the current frame and the historical frame, outputting a monitoring result with species classification and an activity track, and uploading the monitoring result to a data center. According to the invention, precise monitoring, intelligent analysis and real-time early warning of wild animal activities can be realized, and the automation level and data value of wild animal channel monitoring are improved.

The invention relates to the technical field of embedded maps, and provides a vector map display method under a VxWorks system, which comprises the following steps: S1, analyzing a vector map source file through an MITAB library, and extracting geometric space topological data, geographic coordinate system parameters, style attributes and projection parameters; s2, constructing a hierarchical storage structure based on SQLite3, and storing vector map information including a spatial data table, a style configuration table and a metadata table into a geographic information database; s3, creating a map display control MapWidget inherited from a QGraphics View class based on a Qt framework, loading the geographic information database through a dynamic configuration interface, and initializing a coordinate system conversion module, a multi-level view window module and a covering management system; and S4, dynamically rendering and outputting an interactive vector map interface through a layer priority scheduling strategy in a VxWorks real-time operating system. Through the design of the cross-platform data middle layer, the extensible general symbology system and the resource efficiency optimization, the data compatibility problem of the embedded system and the commercial GIS software is solved.

The invention discloses an unmanned aerial vehicle tilt video and vector map real-time projection sleeving method, which comprises an unmanned aerial vehicle body, and is characterized in that a video data acquisition module and a video preprocessing module for preprocessing the tilt video acquired by the video data acquisition module are arranged in the unmanned aerial vehicle body; a map data processing module is further arranged in the unmanned aerial vehicle body, an improved ORB algorithm is adopted in the feature extraction and matching module, and a posture correction and projection transformation module used in cooperation with the video data acquisition module is installed in the unmanned aerial vehicle body. And a real-time display module in the unmanned aerial vehicle body displays the sleeved video and vector map on terminal equipment in real time through a signal module arranged in the unmanned aerial vehicle body. The problems that the real-time performance is poor, the nesting precision is reduced, and long-time high-precision nesting cannot be achieved during working in an existing unmanned aerial vehicle tilt video and vector map fusion technology at present are solved.

The invention discloses a robust online vector map construction method for space-time simplified query, and relates to the technical field of automatic driving perception, and the method comprises the steps: fusing multi-view features into a unified bird's-eye view for representation; matching instance features of the current frame and the historical frame based on time association; updating query features and optimizing query representations; a high-quality vector map construction model is used as a teacher model, a map construction model focused on taking an instance as a center is used as a student model, and features of a teacher network are adaptively distilled to a student network; and designing a loss function to evaluate the student model, performing training optimization, and if the output requirement is not met, further optimizing the student model through a middle distance perception mechanism. According to the method, the robustness, the precision and the efficiency of online vector map construction are remarkably improved, especially the performance in a dynamic environment and a complex scene, and by means of the mode, multi-view, space-time correlation and complex 3D target detection tasks can be better processed.

The invention discloses a microplastic transportation path prediction method, device and equipment based on a complex hydrodynamic environment and a medium, and relates to the technical field of environment monitoring and water pollution governance, and the method comprises the steps: integrating a watershed digital elevation model, a river channel vector diagram, microplastic attributes and real-time hydrological data; a dynamic adjacency matrix is used for capturing water flow direction changes, multi-modal feature fusion is combined for modeling micro-plastic physical attributes and topographic resistance, the problem of monitoring data scarcity is solved through a cross-basin transfer learning strategy, a micro-plastic transfer path is accurately predicted, high-precision simulation of micro-plastic transfer in a complex hydrodynamic environment is achieved, and high-precision simulation of micro-plastic transfer in a complex hydrodynamic environment is achieved. The pollution prevention and control efficiency is improved.

The invention discloses a method for constructing a computable road network. Road data in the vector map are extracted, line string data or line segments obtained by splitting the line string data are used as connecting edges, geographic feature codes containing Geohash information are given to starting points and ending points of the connecting edges, and therefore a basic road network map is constructed. And extracting a middle vertex set of the basic road network diagram and an edge attribute set of middle vertex connection edges, and carrying out road network vertex optimization based on edge attributes to obtain an optimized computable road network. Geographic feature codes adopted by the method comprise spatial geographic information and have the characteristics of graph vertex coding, and the constructed road network graph can be used for graph calculation and verification and restoration of road connection relations. Furthermore, in combination with a representation point acquisition scheme provided by the invention, a road network map fusing facilities and equipment can be constructed, so that the application range of the computable road network is expanded. The computable road network constructed by the method is high in operation efficiency and suitable for different production environments.

The invention discloses a GIS spatial data processing system and method, and relates to the field of geographic information systems, and the system comprises a data obtaining module which obtains original vector map data from a plurality of data sources and carries out format conversion; the data cleaning module is used for detecting and removing abnormal data points by utilizing geometric analysis; the multi-scale processing module is used for performing multi-level processing on the data through Laplace multi-scale decomposition; the geometric optimization module is used for carrying out geometric structure optimization on the vector data based on curvature analysis; the topology analysis module is used for carrying out topological feature extraction and continuous coherence analysis on the data by utilizing algebraic topology; and the data storage module is used for compressing and storing the optimized data and constructing a query index at the same time. The method is used for solving the problem of low quality and efficiency of manual processing of complex geographic data, greatly improves the efficiency and quality of GIS spatial data processing, and is suitable for complex GIS data processing scenes.

The invention discloses a building height change identification method, device and equipment based on remote sensing spatio-temporal information, and a storage medium. The method comprises the following steps: acquiring a building bottom contour by using a vector map; building top contours at different moments are obtained through the multi-temporal high-resolution optical remote sensing images; according to the Euclidean distance between the geometric center point of the bottom contour of the building and the geometric center point of the top contour of the building, obtaining projection displacement of the top and bottom contours of the building; calculating a multi-building relative projection displacement ratio and a single-building absolute projection displacement ratio of different buildings according to the top and bottom contour projection displacements of the buildings at different moments; calculating a satellite inclination angle tangent ratio according to the satellite observation angles at different moments; and according to the multi-building relative projection displacement ratio, the single-building absolute projection displacement ratio and the satellite dip angle tangent ratio, identifying the height change of the building. According to the invention, the accuracy of building height change identification can be improved.

According to the emergency safety management GIS big data vector slicing service map, the vector data are thinned and simplified under each level by using the optimized global constraint algorithm, and the simplified and thinned vector data are cut and sliced and are published in a service form. The style of the tile is designed, and the client renders and visualizes the requested vector tile according to the specified style. And designing a cutting thought, and cutting point, line and surface elements in the vector data. And organizing and storing the generated tiles by using a quadtree index. A cache strategy of a client is designed, existing WMS and WMTS service standards are expanded, a vector tile map style is designed, and vector tiles are published in a service form. According to the method, a prototype system is created, static and dynamic slicing services of the vector map are realized, loading and rendering are carried out at a client, and particularly, when the emergency safety management quantity is huge and the quality is poor, the map precision and efficiency advantages are obvious.

The embodiment of the invention provides a vector map construction method based on autoregression depth estimation and a related device, and relates to the technical field of computers. The method comprises the steps that a depth image corresponding to a scene image is obtained according to the scene image obtained through a camera and a pre-trained autoregressive depth estimation model, and the loss used by the depth estimation model in the training process is calculated based on depth prediction maps of different scales and corresponding second target depth maps; the second target depth map is a map obtained after the residual feature of the first target depth map is enhanced, the first target depth map is a fixed-size map obtained by processing a real depth image, and the residual feature is calculated based on the first target depth map and the obtained depth prediction map; and constructing a vector map according to the scene image and the depth image. Therefore, the corresponding depth information can be accurately estimated based on the scene image shot by the camera, and then the vector map is constructed.

The invention relates to a model training method, a map data fusion method and related equipment, and relates to the technical field of automatic driving. The model training method comprises the following steps: acquiring at least two local vector maps and global map data; extracting the at least two local vector maps to obtain category data and coordinate data of a plurality of map elements; performing feature extraction on the category data and the coordinate data by using the initial map data fusion model to obtain vector map features; performing rasterization processing based on the coordinate data to obtain raster map features; performing feature fusion and feature extraction on the vector map features and the grid map features to obtain extracted map features; decoding and predicting the extracted map features to obtain global map prediction data; and training the initial map data fusion model based on the global map prediction data and the global map data to obtain a map data fusion model. According to the invention, an accurate fusion result can be obtained, and the fusion efficiency is high.

The invention relates to the field of homogenizer intelligence, and discloses a homogenizer intelligent pressure increasing and reducing control system based on servo synchronous transmission, which comprises the following steps: extracting the operation inertia difference of each plunger mechanism under a multi-pump parallel structure, generating a synchronous offset vector map, and calculating the pressure increasing and reducing of the homogenizer based on the synchronous offset vector map. Calling a slip registration algorithm and an inertia field decoupling network, extracting reconstructed plunger stroke and pressure response mapping data, constructing a three-dimensional flow-path-stress tensor model, judging whether fluctuation-wear coupling sensitive points exist or not, activating a frequency conversion regulation and control strategy set of a servo driving layer based on a disturbance window and the coupling sensitive points, and carrying out the control of the servo driving layer. And judging whether structural thermal drift feedback unbalance exists or not, dynamically adjusting servo redundancy and a buffer response strategy in combination with a preset life curve and an abnormal response backtracking channel, and outputting a synchronous regulation and control instruction set. The method has the advantage of improving the long-term operation reliability of the homogenizer.

The invention relates to a semantic vector map robust construction method and device, a storage medium and a program product, which are applied to the technical field of automatic driving perception, and the method comprises the following steps: obtaining a multi-exposure original image; preprocessing the multi-exposure original image to obtain a high dynamic range image; bEV feature extraction and enhancement are carried out on the high dynamic range image to obtain a multi-scale BEV feature and an enhanced BEV feature; processing the enhanced BEV features to obtain a mixed query, and processing the mixed query and the multi-scale BEV features through a multi-layer mask activated instance decoder to obtain an embedded query and a coordinate query; processing the enhanced BEV features through a mask feature construction unit to obtain binary mask features, determining local block features based on coordinate query, and adjusting lane point coordinates based on the local block features, embedded query and a multi-layer perceptron to obtain a semantic vectorization map. The method has the effect of improving the accuracy and robustness of map construction.

The invention relates to the technical field of information processing, and particularly discloses an automatic mapping method and system for an autonomous vehicle. An automatic mapping method for an autonomous vehicle comprises the following steps: constructing a generation and preprocessing model of a point cloud map, and fusing image, point cloud and position information to obtain a complete lane line map; single-frame lane information extraction is carried out on the lane line map, lane information around the vehicle at each moment in the vehicle driving process is calculated, and the lane information comprises lane line information and lane center line information; and carrying out multi-frame lane association and post-processing on the lane line information and the lane center line information, and carrying out inter-frame matching association and alignment on the lane information generated by a single frame to obtain a vector map for an automatic driving vehicle. The existing lane line information in the display environment is given, and the concept of lanes and the topological connection relation between the lanes can be represented.

The invention provides a coal mine roadway point cloud segmentation method based on an interactive grouping linear attention mechanism, and relates to the technical field of computer vision. Constructing a local coordinate system to describe three angle features between the normal vector of the query point and the normal vector of the reference point, and distance features between the query point and the reference point; carrying out high-dimensional feature coding to construct a high-dimensional feature vector; introducing an interactive grouping linear vector attention mechanism to divide channels of value vectors mapped by the high-dimensional feature vectors into a plurality of groups, and applying linear change in each group and interaction of high-dimensional features among the groups to obtain a target feature vector; and performing semantic segmentation by using a multi-layer perceptron to obtain a segmentation category of the point cloud data of the coal mine tunnel. Therefore, efficient and accurate segmentation of the point cloud data in the complex scene of the coal mine tunnel is realized without increasing equipment and computing power in the coal mine tunnel.

The embodiment of the invention provides a vector map construction model training method and device based on knowledge distillation, and relates to an automatic driving perception technology method.The method comprises the steps that a teacher model is constructed by constructing a first vector map, and a student model is constructed by constructing a second vector map; determining Bayesian loss of the first vector map construction teacher model for training, determining intermediate layer feature loss and optimal weight loss of the trained first vector map construction teacher model and the second vector map construction student model, and determining first loss of each intermediate layer feature of the second vector map construction student model, and adjusting parameters of the second vector map construction student model based on the intermediate layer feature loss, the optimal weight loss and the first loss so as to train the second vector map construction student model, and constructing a map based on the second vector map construction student model. The cost of map construction can be reduced.

The invention relates to a defect detection method and device, equipment and a storage medium. Acquiring image data of the surface of the to-be-detected object; determining a normal vector diagram and a reflectivity diagram of the surface of the to-be-detected object according to the image data and light source information of a light source adopted when the image data is acquired; inputting the reflectivity graph into a defect detection model to obtain first defect information of the surface of the to-be-detected object; performing image analysis on the normal vector diagram to obtain second defect information of the surface of the to-be-detected object; and determining target defect information of the surface of the to-be-detected object according to the first defect information and the second defect information. At least three images with different brightness distributions on the surface of the to-be-detected object are obtained, so that high-quality imaging on the surface of the to-be-detected object is realized, and the object surface defect detection accuracy is improved; the defect information of the surface of the to-be-detected object is determined through the detection model and image analysis, so that the determined defect information is more accurate, and the object surface defect detection accuracy is further improved.

The invention discloses an indoor navigation positioning precision improving method and system based on a filtering algorithm, and relates to the technical field of signal processing. The method comprises the following steps: suppressing signal fluctuation and multipath interference by adopting a Bluetooth positioning technology in combination with a segmented power law regression model and Kalman filtering; ultrasonic-assisted positioning is introduced, the distance is calculated through the time difference between pulses and Bluetooth, and the anti-interference capability is improved in cooperation with temperature correction and spectral analysis; multi-mode dynamic fusion is carried out, when shielding is little, Bluetooth positioning is corrected through high-precision ultrasonic waves, when shielding is serious, Bluetooth data is smoothed through moving average, and positioning coordinates are optimized in combination with a least square method; a base station and a reference object are marked through a vector map, the position of a terminal is dynamically displayed, and positioning reliability is visually presented through an error semitransparent circle; a positioning base station array, a mobile terminal and a rear-end processing module are integrated, and low-power-consumption multi-mode fusion positioning is achieved. The method reduces the positioning error in a complex indoor environment, and is suitable for scenes such as personnel / equipment real-time tracking.

The invention belongs to the field of material tower weighing and metering, and provides a material tower weight calculation method and a material tower weighing system, and the method comprises the steps: determining that a part of sensors are in a damaged state based on weight signals transmitted by the sensors; calculating the layer number of the current weight of the material tower in a pre-constructed three-dimensional weighing vector map by using other sensors; reconstructing a weight value which should be output by the damaged state sensor according to the map data of the layer and the upper layer in combination with the position of the damaged state sensor; and calculating the weight of the material tower according to the weight value which should be output by the damaged state sensor and the weight values output by other sensors. The method has the advantages that the three-dimensional weighing vector map of the material tower is established, the weight value which should be output by the damaged sensor at present is calculated by utilizing the weight values of other sensors working normally and combining the position of the damaged sensor, so that the weight of the material tower is obtained, the precision required by production is kept during weighing of the material tower, and the production efficiency is improved. Therefore, the sensor does not need to be stopped for maintenance immediately after being damaged.