118 results about "Coordinate projection" patented technology

The invention discloses a charger shell screw hole rapid positioning method based on three-dimensional point cloud identification, and the method comprises the steps: collecting a polarization structured light three-dimensional point cloud, carrying out the preprocessing, building a workpiece coordinate system, and obtaining a steady point cloud; calculating a homology bar chart in the neighborhood of the point cloud, screening candidate areas according to a threshold value, and generating candidate masks and topology confidence; performing principal component analysis and polar coordinate projection on the candidate region, and outputting a local point cloud; projecting and correcting a local point cloud to obtain a complemented point cloud and implicit field features; solving a hole axis by adopting random sampling consistency, and carrying out Gaussian mixture fitting on an output center and a hole diameter; fusing topology and geometric scores as joint confidence, and judging whether to enter execution or not; and mapping the center and the axis to a robot coordinate system, and compensating and updating a parameter output result during assembly. According to the invention, through three-dimensional point cloud identification and multi-stage geometric topology analysis, rapid and accurate positioning and assembly adaptive correction of the charger shell screw holes are realized.

The invention discloses a multi-sensor fusion-based obstacle detection and recognition method for a wharf unmanned vehicle, and relates to the technical field of intelligent driving, and the method comprises the steps: setting a maximum threshold value and a minimum threshold value, comparing a sensor coverage rate with the maximum threshold value and the minimum threshold value, executing a sensor increase and decrease strategy, and carrying out the time synchronization of sensor data; obtaining an internal parameter matrix, a distortion coefficient and an external parameter matrix, projecting three-dimensional point coordinates of the point cloud data into two-dimensional coordinates of an image plane, and converting the two-dimensional coordinates in the image data into three-dimensional coordinates in a global coordinate system; labeling the sensor data to obtain a two-dimensional bounding box and a three-dimensional bounding box, and obtaining the category and pose label of an obstacle; building a multi-modal fusion perception model, and training the multi-modal fusion perception model by taking the sensor data and the categories and pose labels of the obstacles as training data; and deploying the optimized multi-modal fusion perception model, and outputting the category and pose information of the obstacle, so that the method is suitable for a complex driving environment.

The invention discloses a multi-source data fusion indoor positioning method and system based on deep learning, and relates to the technical field of indoor positioning, and the method comprises the steps: obtaining a wireless signal, inertial sensor data, a timestamp and an indoor map topology; processing the signal through a deep learning model to obtain a preliminary positioning coordinate, and mapping the preliminary positioning coordinate to a map path edge for topological constraint; calculating a displacement and a time interval in combination with the coordinate sequence and the timestamp, fusing the speed and the steering angle of the inertial data, and constructing a spatial-temporal feature vector; calculating a reconstruction error of the vector by using an auto-encoder model to obtain an abnormal confidence coefficient score; if the score exceeds a threshold value, calculating a moving direction according to sensor data, screening a candidate path edge through direction similarity matching, and projecting the coordinate to the edge for correction; otherwise, receiving the original coordinates; and finally outputting the corrected positioning track or the positioning track formed by the original coordinates. The method can ensure that the positioning track better conforms to the actual motion state, and the self-adaptive capability of the positioning system is enhanced.

The invention discloses an agricultural robot laser strike positioning method and device based on a virtual mapping surface, and the method comprises the following steps: S1, constructing a virtual mapping surface for the projection of a coordinate system of a visual system through a calibration board in a to-be-operated scene, establishing a mapping function between projection coordinates on the virtual mapping surface and instruction coordinates of the laser galvanometer through data fitting; s2, dynamically compensating target coordinates acquired in real time according to a built-in attitude sensor of the visual system; and S3, projecting the target coordinate after dynamic compensation to the virtual mapping surface, converting the target coordinate into a preliminary instruction coordinate of the laser galvanometer according to the mapping function, and performing dynamic compensation on the preliminary instruction coordinate to obtain a final instruction coordinate to control the laser galvanometer to act. The calibration process is simple, the coordinate conversion calculation amount is small, and fluctuation generated in the robot movement process can be dynamically compensated to ensure the positioning accuracy.

The invention relates to a virtual power plant resource flexible aggregation method and device based on linear programming projection, and the method comprises the steps: constructing a linear state equation corresponding to each to-be-aggregated resource according to the resource characteristic data of each to-be-aggregated resource, and carrying out the linear transformation; aggregating the energy use flexible feasible region of each to-be-aggregated resource, and solving a coordinate projection problem to obtain a preliminary aggregated energy use feasible region; constructing a network security constraint and embedding a solution process of the preliminary aggregation energy use feasible region to obtain an aggregation energy use feasible region considering the network security constraint; and constructing a multi-parameter planning model, and fusing an aggregation cost function into a solving process of an aggregation energy use feasible region considering network security constraints to obtain a virtual power plant resource flexibility aggregation result. Therefore, the problems that in the prior art, energy use feasible regions and adjustment cost of massive heterogeneous resources cannot be aggregated at the same time, network security constraints cannot be embedded, and high-dimensional aggregation errors are large are solved, and higher calculation efficiency and compatibility are achieved.

The invention relates to the technical field of marine monitoring, in particular to a marine video multi-target tracking and behavior recognition method and device.The method comprises the steps that firstly, a coordinate transformation matrix is constructed based on camera equipment parameters, and frequency domain denoising, illumination compensation and false target filtering are conducted on an original video; super-resolution reconstruction enhancement is carried out on the small-scale target; detecting the optimized video frame by using a deep learning model, and outputting a target bounding box and identity features; a single-view-angle local track is generated in combination with Kalman filtering and a Hungary algorithm; when the target crosses the view field, re-identification is carried out through coordinate projection and cross-view-angle feature invariants, and a cross-view-angle global unique track is generated through fusion; and finally, track motion features are extracted and logically compared with a marine management rule threshold value, and an abnormal behavior judgment result is output. According to the method, the small target detection precision under the complex sea condition is effectively improved, the problem of cross-view target identity breakage is solved, and global continuous tracking and illegal behavior intelligent early warning are realized.

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

The invention relates to the technical field of medical image processing, in particular to a DICOM sequence intelligent normalization and sorting method and system, and the method comprises the steps: obtaining an original DICOM file; analyzing a key DICOM tag of the original DICOM file to obtain a direction tag and body position information, and based on the direction tag, realizing normalization based on a patient coordinate system and performing direction correction; projecting the coordinates of all the slices to a normal vector direction to reconstruct a layer sequence, and counting a slice interlayer spacing sequence to estimate a real interlayer spacing based on adjacent projection difference values; identifying and rejecting abnormal slices based on the abnormal comparison target label and the slice interlayer spacing sequence; and for a multi-sequence set of the same check, extracting a sorting feature vector corresponding to each sequence, and selecting a sorting rule in combination with scene complexity to obtain a final sorting key for representing a sorting result of the phase dimension and / or the time dimension. The method has the effect of solving the problems that existing DICOM sequences are inconsistent in direction, disordered in layer sequence, difficult in time phase recognition and the like.

The invention relates to the technical field of image generation, in particular to a medical beauty 3D model construction method and system based on an image large model, and the method comprises the following steps: obtaining rasterized image data based on a 3D full-head point cloud model through space coordinate projection and pixel mapping, judging connectivity and a missing region, screening region features, and generating texture guidance parameters; and screening textures according to partition features, determining a multi-region fitting index, and outputting a continuous boundary fusion region. According to the invention, through carrying out multi-angle spatial reconstruction and fine pixel mapping on the three-dimensional point cloud data, texture coverage is not limited to a single view angle, spatial feature partitioning and target attribute identification, so that accurate supplementation of the texture of the missing region is realized; the locally generated texture content and the original input region are highly fused in the aspects of color structure and detail representation, and region mutation is effectively eliminated through spatial adaptation and boundary adaptive processing, smooth connection of multi-part texture splicing presentation, color transition and gradient fusion.

The invention provides a large-scale rotary equipment blade measurement system calibration method based on LM algorithm optimization, and belongs to the technical field of blade three-dimensional measurement. Points in a world coordinate system are converted to a rotary table coordinate system, are rotated in the rotary table coordinate system, and then are converted to the world coordinate system; and projecting the rotated world coordinate to a pixel coordinate system to obtain a theoretical pixel coordinate, comparing the theoretical pixel coordinate with an actual pixel coordinate, and calculating a re-projection error. Constructing a target function by using the re-projection error, and iteratively optimizing the axis parameters of the rotary table through an L-M algorithm until convergence; and outputting the optimized rotary table axis for blade point cloud splicing. According to the method, the problem of linear axis calculation errors on the basis of mark point position tracking is solved, nonlinear optimization of the rotary table rotating shaft is achieved, and technical support is provided for follow-up rotary splicing and all-topography measurement of blade point clouds.

The invention discloses an industrial safety detection method combining time alignment and motion consistency, and belongs to the technical field of industrial safety monitoring. According to the method, through seven steps of multi-camera data acquisition and preprocessing, target feature extraction, coordinate projection, instantaneous speed estimation, multi-dimensional similarity fusion, soft matching optimization and model training and target trajectory generation, the problem of space-time inconsistency during multi-camera cooperative detection in an industrial scene is solved. A camera clock offset parameter is innovatively introduced to correct a cross-camera time difference, appearance, geometry and time prior multi-dimensional similarity are fused, a multi-loss function optimization model is constructed, and cross-camera target accurate matching and long-time trajectory tracking are realized. High-precision technical support is provided for personnel safety monitoring and equipment abnormal behavior detection in an industrial scene, and the industrial production safety protection capability is improved.

The invention discloses a method for detecting the flatness of a concrete wall surface. The method comprises the following steps: step 1, collecting point cloud data of a to-be-detected concrete wall area, shooting a high-definition RGB image, and obtaining an initial corresponding relation between original point cloud data and image pixels and internal and external parameters of a camera; 2, preprocessing the original point cloud data; step 3, performing wall fitting by using a second-order polynomial curved surface model through a least square method; step 4, calculating point cloud deviation and identifying defect points; 5, establishing an accurate mapping relation between a three-dimensional point cloud coordinate system and a two-dimensional image pixel coordinate system, and projecting the three-dimensional coordinates of the identified defect points to the corresponding two-dimensional RGB images; and step 6, carrying out visual output on the detection result, and generating a visual report. According to the method, the detection accuracy is improved, effective simplification of a flat region and lossless retention of a defect feature region are realized, and the processing efficiency and the information fidelity are improved.

The invention discloses a six-degree-of-freedom object pose estimation system and method in an industrial scene and a medium, and the system comprises a multi-modal data preprocessing module, a shared encoder feature extraction module, a comparative learning and attention fusion module, a pose regression and rotation decoupling module, and a simulation driving-based data enhancement module. The multi-modal data preprocessing module is used for receiving and processing an original RGB image and a depth map, and outputting a pixel-level space aligned RGB-D data pair through filtering and denoising and coordinate projection transformation based on camera internal reference; and the shared encoder feature extraction module is used for extracting features from the aligned RGB-D data pairs and carrying out adaptive weighted fusion through a channel attention mechanism so as to output a shared feature fused with appearance and geometric information. According to the method, the estimation precision can be improved, the ADD index is improved by 12.8% and the rotation error is reduced by 21.4% in a 70% shielding or light reflection scene, and the method has strong robustness for depth noise, shielding and light reflection and has strong practicability.

The invention relates to the technical field of construction progress monitoring, in particular to a construction progress multi-dimensional dynamic monitoring method based on the Internet of Things and BIM, and the method comprises the following steps: obtaining a component number and a planned time period through the BIM, collecting an action label, a three-dimensional coordinate and space projection matching time, and generating a component behavior set through DBSCAN clustering; the method comprises the following steps: slicing an action sequence to calculate frequency and coverage proportion; classifying component states to generate progress deviation; matching the deviation with a Hungary algorithm to calculate a coupling map; extracting a mechanical track and path included angle, normalizing and correcting the included angle to generate a deviation sequence, and grading track segments to generate a dynamic monitoring index set. According to the method, time-space association is established based on component numbers and coordinate projection, a classification model is constructed by using time slice coverage to identify progress deviation, task chain coupling is analyzed through bidirectional matching, a deviation sequence is generated through included angle correction, a delay amount and coverage rate evaluation system is established, and progress deviation tracing and abnormal early warning are achieved.

The invention relates to the technical field of robot control, in particular to a motion control method and device of a parallel 3RRS robot, the parallel 3RRS robot and a medium, and the robot comprises a base platform, a movable platform and three RRS branch chains connecting the base platform and the movable platform. The method comprises the following steps: acquiring target attitude information and target position information of a mobile platform; based on the structure parameters of the RRS branch chain in the zero position state, the target attitude information and the target position information, calculating the center coordinate of a first plane figure formed by the center of the spherical hinge joint of the movable platform; calculating the center coordinate of the spherical hinge joint; projecting the central coordinate of the spherical hinge joint into a second plane figure determined by the first connecting rod of the corresponding branch chain and the Z axis of the coordinate system of the base; solving a target rotation angle of each first rotation joint based on the projection point coordinates; and finally, all joints are driven to enable the movable platform to move to the target pose. Complex space problems are converted into plane geometry solution, so that calculation is simple, and high-precision and high-efficiency real-time control is facilitated.

The invention discloses a spherical domain magnetotelluric non-structural vector finite element inversion method capable of automatically modeling, which comprises the following steps of: automatically establishing a spherical domain initial model through global topographic data, and performing spatial discretization by using a non-structural tetrahedral mesh to realize three-dimensional magnetotelluric non-structural finite element solution of two polarization modes in a spherical domain; constructing a spherical domain magnetotelluric three-dimensional regularization inversion objective function according to the actual observation data and the prediction data; adopting adjoint forward modeling to solve a Jacobian matrix and a product of transpose and a vector of the Jacobian matrix, and utilizing a nonlinear conjugate gradient method to realize iterative inversion of spherical domain magnetotelluric, so as to obtain a final inversion model and complete spherical domain magnetotelluric non-structural vector finite element inversion. According to the method, spherical domain magnetotelluric non-structural vector finite element inversion is realized, errors caused by coordinate projection can be avoided, and a large-scale inversion result is more accurate and more conforms to a real earth model.

The invention provides a click event mapping method, device and equipment based on vehicle-machine interaction and a medium, and the method comprises the steps: responding to a click event on a target image in a vehicle-machine window, and determining a first two-dimensional coordinate at a click position, the target image comprising a super-resolution rendering image; according to a coordinate mapping function from the target image to an original image, the first two-dimensional coordinate is converted, a second two-dimensional coordinate on the original image is obtained, the original image comprises a three-dimensional image, and the conversion frequency of the first two-dimensional coordinate is the same as the image processing frequency from the original image to the target image; constructing a coordinate projection matrix corresponding to the original image, and converting the second two-dimensional coordinates to obtain three-dimensional coordinates on the original image; and determining a target object corresponding to the click event according to the three-dimensional coordinate and a preset object mapping configuration. In combination with multi-level coordinate reverse mapping and a three-dimensional view angle calibration mechanism, the problem of dislocation between the click position and the 3D object is effectively prevented, and the interaction experience of the user is improved.

The invention belongs to the technical field of image processing, and relates to an image video rain removal method based on local perception modeling and multi-stage span fusion, which adopts parallel branch networks with three level scales to respectively and sequentially carry out feature extraction, feature extraction and multi-stage span fusion on raining images with corresponding resolution sizes, performing high-level semantic information mining on the input raining image to obtain a high-dimensional feature map; high-resolution image reconstruction: adopting a local set perception implicit representation module, mapping the high-dimensional feature map to a continuous RGB color space through linear coordinate projection, and compensating continuous textures and edges sheltered by rain in the image to obtain a reconstructed image; and cross-scale feature fusion: carrying out information fusion between stages and scales on the image through double branches, and aligning and enhancing multi-scale semantics to obtain a high-resolution rain-removed image. According to the method, artifacts of a raining image can be suppressed in a multi-domain and multi-scale level, and sharpness and consistency are enhanced.

The invention discloses a glasses combined image quality detection method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining a calibration image collected by a binocular camera, wherein the calibration image comprises a left eye image and a right eye image; performing coordinate extraction on the left eye image and the right eye image to obtain a left eye corner pixel coordinate and a right eye corner pixel coordinate which are matched with each other; for each group of matched left eye corner point pixel coordinates and right eye corner point pixel coordinates, performing coordinate projection on the left eye corner point pixel coordinates or the right eye corner point pixel coordinates based on parameters of the binocular camera to obtain a group of projected target corner point pixel coordinates and reference corner point pixel coordinates; and determining the glasses combination quality of the intelligent glasses according to each group of target angular point pixel coordinates and reference angular point pixel coordinates, thereby solving the problems of low glasses combination precision judgment accuracy, manpower resource consumption and the like, improving the combination precision judgment accuracy, being free of manual participation, being capable of realizing automation, and being objective and accurate in detection result.

This invention discloses a quantum entangled light spatial correlation imaging method based on iterative deconvolution, belonging to the field of quantum information. The method includes the following steps: illuminating the target sample with a position-momentum entangled light source, and acquiring multiple frames of entangled light carrying sample information using a single-photon camera; performing statistical operations on the acquired multi-frame images to remove irrelevant background noise and obtain a joint probability distribution image of the sample; extracting the correlation width using the spatial distribution image of the joint probability distribution through differential coordinate projection to construct the point spread function of the optical system; using the point spread function for forward convolution projection and backward error projection, updating the image estimate through iterative calculation until the convergence condition is met to obtain the target sample image. This invention utilizes a camera to image with a position-momentum entangled light source under low illumination conditions, which can obtain high-contrast target imaging and has potential advantages in imaging light-sensitive samples.

The invention relates to capturing an image of a spherical site. An image processing server for transforming an image to project onto a media plane of a venue, the image processor comprising: a memory configured to store instructions; and a processor configured to execute instructions that, when executed by the processor, configure the processor to project three-dimensional coordinates of a plurality of pixels of a media plane onto two-dimensional coordinates of an image space of an image to provide a plurality of two-dimensional points projected onto the image, the color information of the plurality of pixels of the image is interpolated based on the color information of the plurality of pixels of the media plane, and the color information of the plurality of pixels is provided to the field so that the image is projected onto the media plane.

The invention provides a course rapid initial alignment method and device for vehicle-mounted integrated navigation, and relates to the technical field of navigation calibration, and the method comprises the following steps: based on three-axis acceleration data, eliminating a component of gravitational acceleration in a horizontal direction through attitude compensation, and obtaining a horizontal longitudinal acceleration measurement value; carrying out plane coordinate projection based on the GNSS positioning data to obtain a track point sequence; determining the horizontal displacement length of the current track point and other track points in the track point sequence; on the basis of the horizontal longitudinal acceleration measurement value and the track point sequence, the motion direction is judged through the speed change trend and the horizontal acceleration direction, the current track angle is corrected, and a corrected course angle is obtained; and based on the corrected course angle and the Z-axis angular velocity of the gyroscope measured by the IMU module, estimating the course angle error and the zero offset of the gyroscope by adopting an adaptive Kalman filtering algorithm, and outputting the corrected course angle. According to the invention, fast and accurate course initialization of combined navigation in a low-speed equipment operation scene can be realized.

This application provides a method, device, electronic device, and storage medium for displaying a target plane. The method includes: acquiring a first coordinate group of P markers attached to the patient's body surface in a CT coordinate system based on CT images; tracking a second coordinate group of the P markers in an optical coordinate system using an optical tracking device; registering the first and second coordinate groups to obtain a first real-time transformation matrix from the CT coordinate system to the optical coordinate system; calculating second real-time coordinates of the needle tip and needle tail in the CT coordinate system based on the first real-time transformation matrix, the first real-time needle tip coordinates, and the first real-time needle tail coordinates in the optical coordinate system; and displaying the positions of the needle tip, needle tail, and target point in the target plane based on the coordinates projected onto the target plane from the second real-time needle tip coordinates, the coordinates projected onto the target plane from the second real-time needle tail coordinates, and the target point coordinates in the CT coordinate system. This method can avoid harm to the patient caused by puncture surgery.

The invention provides a semantic grid map optimization method and system based on multi-task road surface information, and belongs to the technical field of automatic driving navigation, and the method comprises the steps: processing an obtained road environment image to obtain a lane line segmentation result and a drivable region segmentation result; establishing a coordinate projection relation from an OCC space to a pixel coordinate system based on a rotation translation matrix between the sensors; projecting a surface grid center point of the semantic grid map to a pixel coordinate system based on the coordinate projection relationship, and supplementing lane line information according to a projection result; performing semantic correction on the drivable area based on the coordinate projection relation and the drivable area segmentation result; performing instance extraction and semantic association processing on an unknown obstacle; and outputting the optimized three-dimensional semantic grid map. Based on the method, the invention further provides a semantic grid map optimization system based on the multi-task road surface information. According to the method, the quality and practicability of the semantic map are improved on the premise that the system burden is not obviously increased.

A device for calibrating a camera of a vehicle includes: a first camera for acquiring a first image, a second camera for acquiring a second image, and a processor that extracts a first class of interest from the first image, and extracts a second class of interest from the second image. The processor projects pixel coordinates of the first class of interest onto the second image to convert the pixel coordinates, and corrects parameters of the second camera such that a difference between the converted pixel coordinates of the first class of interest and pixel coordinates of the second class of interest is minimized.

The invention discloses a multi-mode environment sensing system for automatic driving and a method thereof, and belongs to the technical field of intelligent network connection automobiles. The system comprises a vehicle-mounted imaging subsystem, an AMSR-T image enhancement module, a 77GHz millimeter wave radar subsystem and the like, and environment perception is realized through multi-modal data acquisition, image enhancement, target extraction and tracking, BEV transformation, cross-modal fusion and semantic judgment. The method comprises the steps of data acquisition, image enhancement, target processing, coordinate projection, feature fusion and result output. According to the multi-mode environment sensing system and method, the defects of single-mode sensing in low-light, rain and fog scenes and the like are overcome, the problems that an existing fusion scheme is high in cost and time delay are solved, end-to-end low delay and low power consumption are achieved through a heterogeneous computing platform, and the multi-mode environment sensing system and method are suitable for automatic driving environment sensing.

The present application relates to motor drive control and hardware ring simulation test technical field, specifically to a kind of motor operating state simulation test system.It includes: signal acquisition module, for collecting the control instruction issued by measured controller, and obtains the environmental parameter and load parameter of test setting;Manifold space construction module, for reflecting the high-dimensional riemann manifold space of motor energy state, and change into the metric tensor of manifold space;Dynamic curvature evolution unit, for mapping external load disturbance and multi-physical field coupling effect into the dynamic change of metric tensor, geodesic trajectory represents the evolution path of motor operating state, to solve the operating state of motor next time;Physical quantity reconstruction module, for projecting the geodesic trajectory coordinates on manifold space back to Euclidean space, restore as electric signal physical quantity, and feedback to measured controller, form closed loop test.The present application significantly improves the physical authenticity and confidence of motor running simulation under high temperature or magnetic saturation state.

The application provides a semantic grid map optimization method and system based on multi-task road surface information, and belongs to the technical field of automatic driving navigation. The method comprises the following steps: processing a road environment image to obtain lane line segmentation results and drivable area segmentation results; establishing a coordinate projection relationship from an OCC space to a pixel coordinate system based on a rotation and translation matrix between sensors; projecting surface layer grid center points of a semantic grid map to the pixel coordinate system based on the coordinate projection relationship, and supplementing lane line information according to a projection result; performing semantic correction on a drivable area based on the coordinate projection relationship and the drivable area segmentation results; performing instance extraction and semantic association processing on unknown obstacles; and outputting an optimized three-dimensional semantic grid map. Based on the method, the application further provides a semantic grid map optimization system based on multi-task road surface information. The application improves the quality and practicability of a semantic map without significantly increasing the burden of a system.