116 results about "Point projection" patented technology

The invention discloses a dual-path non-cooperative spacecraft pose estimation method based on uncertainty perception, and belongs to the technical field of spacecraft pose estimation. According to the method, a dual-path prediction framework based on a shared backbone network is constructed and comprises a geometric reasoning path and a global context sensing path. In the training stage, prediction results of the two paths are aligned through a geometric consistency loss function, and joint optimization is carried out by combining multi-task losses such as key point regression, classification, rotation and translation regression and the like. In the inference stage, the pose estimation result is adaptively fused according to the predicted variance output by each path, when the variance is low, the output of the global context sensing path is directly adopted, otherwise, the key point projections of the two paths are combined, and the final pose is recovered. The method has higher estimation precision, robustness and interpretability in complex space environments such as shielding, illumination variation and large-scale variation, and provides reliable visual navigation support for on-orbit autonomous tasks.

The invention discloses a building detail extraction method and device based on oblique photography and composite modal features, and the method comprises the steps: calculating a tilt parameter of a midpoint of a point cloud model based on the point cloud model of oblique photography data of a target building, and converting the tilt parameter into a color parameter; projecting points on the point cloud model to a target building view area of a two-dimensional plane to obtain a plurality of superpixel blocks, inputting features of the superpixel blocks into a variational auto-encoder, and performing optimization to obtain encoder optimization weight data; and inputting the features of the super-pixel blocks into an encoder to obtain corresponding optimized latent variables, clustering the super-pixel blocks based on the optimized latent variables, and mapping a clustering result to the three-dimensional model of the target building to obtain details of the target building. By adopting the technical scheme, the three-dimensional features and the color features are compounded, and the structure details and the distribution characteristics of the complex building are captured by utilizing the relevance between the features; an encoder of a pre-trained variational auto-encoder is used for aggregation, so that the accuracy of an aggregation result is improved.

The invention relates to the technical field of robots, and discloses an obstacle sensing method and a storage medium, and the method comprises the steps: obtaining image data of an environment in front of a mobile robot and three-dimensional point cloud data generated through laser radar scanning; pixel-level semantic segmentation is carried out on the image data, and a semantic segmentation map with each pixel having a semantic tag is generated; projecting each three-dimensional point in the three-dimensional point cloud data to a semantic segmentation map based on a calibration relationship between a camera and a laser radar, and generating a semantic point cloud with a semantic tag; for a detection blind area of the laser radar in front of the robot, generating a virtual three-dimensional point cloud in the detection blind area by using obstacle semantic information corresponding to an image area of the detection blind area in the semantic segmentation map; and determining the obstacle point cloud based on the three-dimensional point cloud of which the semantic label is the obstacle category in the semantic point cloud and the virtual three-dimensional point cloud. According to the invention, the obstacle detection precision in a complex environment can be improved.

The application relates to the chip detection technical field, in particular to a semiconductor packaging workpiece identification detection method and device and a cutting and sorting integrated machine, wherein the method comprises the following steps: acquiring a surface image of a workpiece to be detected; the surface image comprises an identification for marking a workpiece type of the workpiece to be detected; the workpiece type is a good material type or a bad material type; image skeleton extraction is performed on the surface image to obtain a skeleton line corresponding to a pattern in the surface image; for each pixel point on the skeleton line, if the minimum distance between the pixel point and a preset identification reference line is less than a first preset distance, the pixel point is projected onto the identification reference line; the identification reference line is drawn in the surface image according to the identification shape corresponding to the bad material type; and the identification corresponding to the workpiece type on the workpiece to be detected is determined according to the proportion of the area of the identification reference line projected by the skeleton line. The application can solve the problems of low identification detection precision and weak anti-interference capability of the identification on the workpiece to be detected.

The invention provides a method and a device for generating a process track. The method comprises the following steps: acquiring a group of discrete three-dimensional reference track points and original point cloud data for representing the three-dimensional shape of a workpiece; generating a group of three-dimensional intermediate target points with corresponding process forms through waveform interpolation based on the group of discrete three-dimensional reference track points; for each three-dimensional middle target point, according to the original point cloud data around the three-dimensional middle target point, fitting through a moving least square method to obtain a corresponding local three-dimensional curved surface; the three-dimensional middle target point is projected to the local three-dimensional curved surface, final three-dimensional track point coordinates and normal vector postures thereof on the local three-dimensional curved surface are obtained, the process track is generated based on the multiple final three-dimensional track point coordinates and the corresponding normal vector postures thereof, and it is ensured that the generated process track is attached to the real surface of the workpiece. And meanwhile, the method has process adaptability and high fidelity.

The invention relates to the field of image processing, and provides an image generation method, electronic equipment and a vehicle, and the method comprises the steps: obtaining a fisheye image corresponding to the current position of the vehicle, projecting each pixel point in the fisheye image to a preset spherical model, and determining a first projection point corresponding to each pixel point; projecting each first projection point to a preset cylinder model to obtain a second projection point corresponding to each first projection point; and obtaining target internal and external parameter data corresponding to the fisheye image, and performing texture mapping processing on all the second projection points according to the target internal and external parameter data to obtain a planetary visual angle top view corresponding to the current position of the vehicle. The fisheye image is sequentially projected twice through the spherical model and the cylinder model, alignment of ground textures is achieved due to the fact that the radius of the bottom face of the cylinder is large, points far away from the center can be compressed through vertex transformation of the spherical model, and therefore the problem that far ground points are seriously stretched is avoided, and the accuracy of ground texture alignment is improved. And the accuracy of the planetary view angle top view is improved.

The invention provides a method for checking light leakage of a sun shield, which is used for effectively adjusting and optimally avoiding the conditions of upper light leakage or left light leakage of the sun shield, the sun shield, a ceiling boundary, an A column boundary and a front windshield black edge in the driving process of a driver and passengers. By taking the left limit point or the upper limit point of the left eye ellipse as a projection center, projecting a point on the sun shield onto the curved surface of the front windshield, projecting a point on the left A column onto the curved surface of the front windshield, and projecting a point on the ceiling onto the curved surface of the front windshield; and then processing the data. According to the method, the optimized result can be quantitatively presented, a model or an organizing person is not needed for review, and high efficiency and low cost are achieved.

The application discloses a kind of unmanned aerial vehicle based on BIM and perceives house safety appraisal management system and method, it is related to data processing technical field;The application is generated by training U-Net++ model, based on three-dimensional BIM model of house, by space grid sampling algorithm is combined with convex hull optimization algorithm, generates preset track;Unmanned aerial vehicle carries dual-mode sensing pod and flies along preset track, collects image virtual list and metadata;Image sequence is carried out denoising enhancement processing, utilizes BIM feature point projection to guide SIFT feature bidirectional matching to realize precision alignment, after Euclidean distance threshold verification, input pre-training U-Net++ model generates crack binary mask, and is converted into physical crack parameter;Through SfM point cloud and ICP registration technology, the angle of inclination of wall is calculated;Integrate crack parameter, inclination angle and BIM attribute, and automatically trigger graded early warning through risk rule base;Realize the full-process automation from data acquisition, crack identification to risk assessment, significantly improve detection accuracy and efficiency, effectively reduce high-risk missed detection rate.

The application relates to a landmark point matching method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining a scanning point cloud obtained by shooting a calibration object under a current scanning visual angle; the calibration object comprises a landmark point; matching the calibration object point cloud with the scanning point cloud to obtain a first matching point pair; the first matching point pair comprises a calibration object matching point and a matching scanning matching point; projecting the scanning matching point to an image coordinate system of a camera to obtain an image mapping point; obtaining a calibration object image obtained by shooting the calibration object by the camera; matching the image mapping point with the landmark point on the calibration object image to obtain a second matching point pair; the second matching point pair comprises a scanning matching point and a matching landmark point on the calibration object image; for the camera, determining a target matching point pair of the landmark point on the calibration object image and the landmark point on the calibration object based on the first matching point pair and the second matching point pair. The method can obtain more accurate target landmark point pairs and optimize unstable factors of the equipment.

The invention relates to a panoramic image splicing method and system based on the real-time attitude of a ship body, and the method comprises the steps: synchronously collecting an original image, a rolling angle data and a pitch angle data through arranging a plurality of fisheye cameras in the circumferential direction of the ship body in combination with inertial navigation equipment; hardware-level clock synchronization is realized by using a second pulse signal of a global positioning system, and alignment of an image and attitude data is completed through a timestamp matching algorithm; the method comprises the following steps: acquiring internal and external parameters of a camera by adopting a Zhang's calibration method, performing de-preprocessing on an image, constructing a rotation matrix based on a real-time attitude, projecting pixel points to a stable world coordinate system, and generating a projection image; for an overlapping region between adjacent projection images, dynamically calculating a fusion weight according to an attitude angle change rate, and realizing adaptive weighted splicing; and finally, a seamless panoramic image is generated and coded and output to a display terminal and a storage device, panoramic image splicing in a ship body shaking scene is realized, and real-time performance, robustness and environmental adaptability are considered.

Systems and techniques are described herein for occlusion detection. For instance, a method for occlusion detection is provided. The method may include generating a plurality of voxels in a voxel space based on a point-cloud representation of a scene; generating an annotation point in the voxel space based on sensor data representative of an object in the scene; projecting a ray from a sensor position in the voxel space to the annotation point; and determining whether the annotation point is occluded based on the ray and the plurality of voxels.

The application is a method for installing, measuring, controlling and checking large-curvature pipe sections, which comprises checking the posture of the immersed tube during the installation of the immersed tube pipe sections and checking the through measurement accuracy after the installation of the immersed tube pipe sections; the checking the posture of the immersed tube during the installation of the immersed tube pipe sections specifically comprises: GPS-RTK accuracy comparison, total station synchronous monitoring, pulling and closing systems, and diving and pulling measurement; the checking the through measurement accuracy after the installation of the immersed tube pipe sections specifically comprises: combined cavity tooth measurement and point projection measurement. The application can be applied to the installation, measurement, control and checking of large-curvature pipe sections, the accuracy of the measurement and control system is verified through diving, pulling and closing and RTK, the initial posture measurement of the pipe sections is verified through combined cavity measurement and manhole point projection measurement, the accuracy of the measurement and control system and the through measurement is verified from multiple angles, the risk of pipe section docking is reduced, and data basis is provided for subsequent pipe section linear control.

The application discloses a projection figure distortion prediction compensation correction method of a laser scanning projection system, and comprises the following steps: carrying out laser scanning projection system projection; acquiring projection figure distortion data, establishing a neural network training data set and a test data set; establishing an initial topological structure, weights and thresholds of a BP neural network; optimizing the weights and thresholds of the BP neural network based on a particle swarm optimization algorithm; carrying out deviation compensation on the coordinate positions of each projection point according to the training output of the PSO-BP neural network; selecting feature points in each part of a to-be-projected plane; projecting the feature points by using a distortion deviation correction projector based on the PSO-BP neural network; acquiring feature point projection coordinate values; subtracting the ideal projection point coordinates without distortion from the corrected feature point projection coordinates; judging whether the difference value meets an error interval; if yes, it is determined that the projection coordinate value distortion error has been corrected and compensated; if no, returning to step three for feedback type multiple iterations until the difference value meets the error interval.

The invention relates to an SLAM back-end optimization method based on sparse matrix factorization and a hardware accelerator architecture, and the method comprises the steps: constructing a Hessian matrix through employing a binary sparse coding mechanism according to the actual observation coordinates of feature points on an image plane and the predicted coordinates of road sign points projected to a camera coordinate system; performing Schel elimination processing on the Hessian matrix based on binary sparse coding to obtain a linear equation set only containing a camera pose variable; and carrying out extended Kalman filtering on a linear equation set only containing a camera pose variable to realize incremental updating of a state pose and a road sign point coordinate. According to the method, the overall delay of SLAM rear-end optimization can be remarkably reduced, and the real-time requirement in a high-speed moving scene is met.

The application provides a close operation robot, an obstacle avoidance method and a control unit thereof, and belongs to the technical field of robots.The method comprises the following steps: acquiring a color image of an operation scene and depth information corresponding to each pixel point in the color image; identifying a workpiece target in the color image based on a pre-trained instance segmentation model to obtain a workpiece mask; performing inflation processing on the workpiece mask to obtain a safe workpiece area; based on the safe workpiece area, screening the pixel points in the depth information, projecting the retained pixel points into three-dimensional space points to construct an obstacle point cloud; updating an obstacle avoidance map according to the obstacle point cloud; based on the updated obstacle avoidance map, performing collision detection and trajectory planning on a close operation process of the robot, and controlling the robot to perform an obstacle avoidance operation.The obstacle avoidance method, the control unit and the close operation robot provided by the application can effectively distinguish workpieces from obstacles in a close operation scene, and improve the reliability of online obstacle avoidance.

The application provides a road sign point cloud generation method and device. The road sign point cloud generation method comprises: acquiring a plurality of first road images on a target road; acquiring an image road plane of each first road image in a point cloud coordinate system and road sign pixel points on each first road image; fitting based on the image road planes of the plurality of first road images to obtain a fitted road plane; and projecting the road sign pixel points on each first road image to the fitted road plane to obtain a road sign point cloud in the point cloud coordinate system. The application can improve the accuracy of road sign point cloud generation.

This invention discloses a method, apparatus, and medium for spatial coordinate unfolding and reconstruction, comprising: extracting spatial expression points labeled as target tissue types from spatial group data to generate a standardized binary image; performing a closing operation and smoothing edges, extracting multiple contour regions and merging them into a main contour, and performing an image skeletonization algorithm on the main contour to generate a skeleton path map; selecting the longest path from the shortest paths as the central main path; backprojecting the central main path in the image coordinates to the original spatial coordinate system to determine the central main path and its starting and ending points; constructing a tangent-normal coordinate system and calculating the distance from the spatial expression points to a first reference point; generating edge reference lines; projecting all spatial expression points to the unfolded coordinate system to determine the projection target; and projecting according to the projection target to obtain the unfolded coordinates. This invention automatically generates complete skeleton paths and highly smooth edge curves, effectively restoring the true spatial positions of the host and / or microorganisms and spatial expression points.

There is a need for new technologies that enable real-time, high-precision spatial measurement. [Solution] Multiple laser beams or sound waves are emitted into space at different oscillation angles, and the distance to the intersection is calculated with high precision by applying the Law of Sines to the point where they intersect. Furthermore, it is equipped with a viewpoint synchronization aiming system and an IMU (Inertial Measurement Unit), and is equipped with the user's eyes. By acquiring the movement and focus data of a sphere and temporarily controlling the oscillation angle via the viewpoint synchronization aiming system, the intersection is automatically synchronized with the user's viewpoint. In addition, by integrating it into devices such as smart glasses, VR goggles, and drones, it is possible to cooperate with moving objects and adapt to dynamic environments, solving the problems of conventional technologies.

The invention discloses an intracranial artery balloon dilatation axial stress monitoring system and method based on curvature ratio quantitative analysis, and belongs to the field of intelligent medical treatment. The system comprises an image acquisition and processing module, a curvature ratio calculation and mechanical inversion module, a risk assessment and early warning module and a visual interaction module. On the basis of the principles of film mechanics and contact mechanics, a mechanical causal chain of a balloon-plaque contact interface from geometric asymmetry to axial stress is completely disclosed; asymmetric plaques cause non-uniform stretching of balloons on two sides of the lowest point; according to the method, the curvature ratio R is defined to be equal to C / D to quantify the stretching degree, the curve length C is a path (left side) from a left end point A to a lowest point L and a path (right side) from the lowest point L to a right end point B in an effective analysis area, and the linear distance D is the Euclidean distance from mark points M1 and M2 to a projection point P of the lowest point; the difference value delta R of the curvature ratios of the two sides is equal to | Rleft-Rright |, and the stretching unevenness is directly quantized; intra-membrane tangential tension unbalance is caused by uneven stretching, a couple trend for promoting a balloon to move is generated, the trend is balanced by static friction force, and the counter-acting force is the axial force acting on plaques and is a direct reason for complications such as interlayers and shedding. The axial stress direction points to the same side with the large curvature ratio side, and the relative size is represented by delta R. The system automatically calculates delta R through real-time image processing and carries out dynamic risk assessment, and visual early warning is provided for an operator in a visual graphic form.

The application provides a semantic label fusion method and device, electronic equipment and a storage medium, and aims at improving the problem that the accuracy of semantic labels obtained in semantic segmentation is low. The method comprises the following steps: obtaining point cloud data scanned for a target object and multiple target images shot from different perspectives; for each target image in the multiple target images, performing semantic segmentation on each two-dimensional pixel point in the target image to obtain the category label of the two-dimensional pixel point; performing semantic segmentation on each three-dimensional pixel point in the point cloud data to obtain the category label of the three-dimensional pixel point; and fusing the category label of the three-dimensional pixel point and the category label of the projected pixel point according to the projection distance of the projected pixel point of the three-dimensional pixel point projected onto the target image to obtain the fused semantic label.

The invention discloses an acupuncture point positioning method, device and equipment and a medium, and the method comprises the steps: obtaining a position relation between a target acupuncture point and a preset reference point on the body surface of a human body target part, obtaining a mapping point of the target acupuncture point on a body surface tangent plane at the preset reference point, and projecting the mapping point to a three-dimensional grid model of the target part, a target intersection point is obtained, the target intersection point serves as a candidate point, the matching degree of the candidate point and the target acupoint is evaluated according to the position of the candidate point on the three-dimensional grid model and a preset geometric constraint term, and if the evaluation result does not meet a preset termination condition, a grid point is selected from a preset grid area with the target intersection point as the center, and taking the grid point as a candidate point, returning to execute the step of obtaining the position of the candidate point on the three-dimensional grid model until a preset termination condition is met, obtaining a target point, and positioning the target acupuncture point on the body surface of the target part according to the target point. And the accuracy of acupoint positioning is improved.

The invention discloses a ground wire operation behavior identification method and system based on visual detection, and relates to the technical field of computer vision, and the method comprises the steps: projecting a skeleton key point to an image plane, calculating a Hamming distance between a binary descriptor and a skeleton projection point, and calculating an intersection-union ratio of a refined bounding box and a projection box; screening the intersection-to-parallel ratio and the Hamming distance to generate a target feature set, inputting the target feature set into a Bi-LSTM model to generate an optimized state sequence, and outputting an action category and probability through a 1D-CNN (1D-Convolutional Neural Network); by adopting a dynamic bounding box adjustment and quadtree recursive division technology, a self-adaptive action area grid is generated, the accuracy of action detail capture is enhanced, multi-scale time sequence feature extraction and optical flow feature map enhancement are combined, a fine-grained feature set is constructed, the accuracy of action recognition is improved, and the real-time processing capacity of ground wire operation behavior recognition is improved.

The invention provides a fragment penetration target contour recognition method, device and equipment and a storage medium, and relates to the technical field of ammunition engineering. The method comprises the following steps: acquiring fragment hole coordinates of a target surface to obtain fragment points; according to the fragment hole coordinates, fragment points are projected to a projection plane, and projection points corresponding to the fragment points are obtained; determining a minimum convex polygon surrounding the projection points to obtain a projection two-dimensional contour line; generating rays perpendicular to the projection plane for the projection points on the projection two-dimensional contour line, and determining intersection points of the rays and the target surface; and connecting the intersection points to obtain a three-dimensional contour, and performing curved surface optimization on the three-dimensional contour based on the fragment points to obtain a three-dimensional contour curved surface of the surface of the fragment penetration target. The problem that the three-dimensional contour of the surface of the fragment penetration target cannot be correctly and effectively identified in the prior art can be solved.

A method for calibrating a vehicle cabin camera having: a pitch, yaw and roll angle; and a field of view capturing vehicle cabin features which are symmetric about a vehicle longitudinal axis comprises: selecting points from within an image of the vehicle cabin and projecting the points onto a 3D unit circle in accordance with a camera projection model. For each of one or more rotations of a set of candidate yaw and roll rotations, the method comprises: rotating the projected points with the rotation; flipping the rotated points about a pitch axis; counter-rotating the projected points with an inverse of the rotation; and mapping the counter-rotated points back into an image plane to provide a set of transformed points. A candidate rotation which provides a best match between the set of transformed points and the locations of the selected points in the image plane is selected.

The application discloses a geometric optical phenomenon restoration method based on a kernel density estimation algorithm, and relates to the technical field of three-dimensional optics, and comprises the following steps: projecting three-dimensional space discrete light ray hitting points to a two-dimensional plane through coordinate conversion; mapping continuous two-dimensional plane coordinates to pixel indexes through affine transformation to obtain a two-dimensional pixel grid; converting discrete points into continuous intensity distribution through a plurality of kernel function diffusion methods; performing nonlinear compression on the kernel function diffusion result through an inverse tangent function to obtain final intensity values; displaying the final intensity values through single-channel to RGB pseudo-color mapping; performing light ray tracing to construct a light ray refraction model; and performing light ray direction to imaging plane coordinate mapping based on the light ray refraction model and the pseudo-color mapping rule to obtain a data set; the smoothness and dynamic range of light ray density distribution are remarkably improved, and high-fidelity visualization of complex refraction phenomena is realized.

The invention provides a tunnel section point cloud generation method utilizing virtual scanning light reconstruction, which comprises the following steps of: firstly, extracting an obtained tunnel point cloud by utilizing a tunnel section slice point generation algorithm to obtain a tunnel section point cloud slice; secondly, points on the tunnel section point cloud slices are projected to a plane where the tunnel section is located, virtual scanning points in the plane of the tunnel section are calculated, and virtual scanning light corresponding to any scanning point is obtained; and finally, dividing points in the whole tunnel section plane according to an angle differential unit, removing miscellaneous points in the tunnel section point cloud, and generating section point cloud data for tunnel deformation analysis. According to the method, the problems of low automation degree, high indoor work labor intensity and the like of existing section extraction and processing based on three-dimensional laser scanning are solved, the influence of a large number of random targets contained in the laser scanning data is overcome, the tunnel point cloud indoor work processing and section generation speed is increased, and the method has the characteristics of reducing the indoor work labor intensity, being high in automation degree and the like.

The application discloses a camera external parameter calibration method, comprising the following steps: acquiring a first image collected by a camera and extracting first corner points of a preset reference object from the first image; acquiring an internal parameter matrix, an initial external parameter matrix and a point cloud of the preset reference object of the camera; projecting each point in the point cloud onto a second image with the same size as the first image based on the internal parameter matrix and the initial external parameter matrix and extracting second corner points of the preset reference object from the second image; registering the first corner points and the second corner points to obtain a transformation matrix; and obtaining an external parameter conversion matrix of the camera by using the internal parameter matrix, the initial external parameter matrix and the transformation matrix. The application further discloses a system, a computer device and a readable storage medium. The scheme provided by the application does not need a special calibration board to be deployed on a road by a calibration personnel, a manual intervention is not needed in a calibration process, and the calibration efficiency can be greatly improved and the labor cost can be saved.

The high-rise building inclination monitoring method disclosed by the application is suitable for high-precision inclination monitoring of irregular building structures, and the relative position change of the monitoring point is measured to obtain the inclination change value of the building body. The high-rise building inclination monitoring method of the application is based on high-precision edge and corner measurement results of a total station, and uses non-contact measurement. Compared with the point projection method, the measurement cooperation personnel are dispensed with, the labor cost is saved, the reading error is reduced, the precision and reliability of the monitoring results are improved, compared with displacement measurement inclination monitoring, the observation pier is not needed to be built, the control measurement link is dispensed with, the labor and material resources are greatly saved, and the on-site work is more flexible and the high-precision inclination change of the target position of the building body is more easily obtained.

The invention relates to the technical field of optical element precision manufacturing, in particular to an optical element three-dimensional modeling method based on normal projection inverse transformation. Comprising the steps of establishing an ideal curved surface parameterization vector expression according to optical design parameters, and determining a curved surface body coordinate system and a vector height function; solving the gradient of the rise function to obtain gradient information of each point of the curved surface and calculating a unit normal vector; projecting the three-dimensional curved surface points to a preset reference plane along the normal direction of the curved surface, establishing a forward geometric mapping relation from the three-dimensional coordinates of the curved surface body coordinate system to the measurement coordinates of the interferometer, and obtaining an explicit expression of the measurement coordinates; two-dimensional normal error distribution data of the optical element are collected, errors are overlaid in the normal direction to construct an actual curved surface expression containing manufacturing errors, and the corresponding relation between three-dimensional normal errors and measurement data is established; and on the basis of forward mapping relation numerical value inverse transformation, the measurement coordinates are inversely calculated into curved surface body coordinates, and the curved surface body coordinates are substituted into an actual curved surface expression to obtain a complete three-dimensional curved surface model containing manufacturing errors.