677 results about "Point cloud segmentation" patented technology

A three-dimensional point cloud segmentation method and apparatus based on a locally weighted curvature and a two-point method, which method and apparatus relate to the field of point cloud processing. The segmentation method comprises: calculating a normal vector of each sample point in a three-dimensional point cloud image (S101); calculating a locally weighted curvature of each sample point on the basis of the normal vector, and comparing the locally weighted curvature with a preset curvature threshold value, so as to obtain a comparison result (S102); when the comparison result indicates that the locally weighted curvature of the sample point is greater than or equal to the preset curvature threshold value, marking the sample point as a boundary feature point, so as to obtain a boundary feature point set (S103); fitting a point cloud planar model on the basis of the boundary feature point set, and performing iterative calculation on the point cloud planar model, so as to obtain a target inner point set (S104); and segmenting the three-dimensional point cloud image on the basis of the boundary feature point set and the target inner point set (S105).

The present application discloses a point cloud segmentation method and apparatus, a storage medium, and an electronic device. The method comprises: for a target sample point in a spatial point cloud, determining a curvature feature of a local plane corresponding to the target sample point in the spatial point cloud; on the basis of the curvature feature, determining a local density corresponding to the local plane; on the basis of candidate relative distance values between a plurality of other sample points and the target sample point, determining a target relative distance value corresponding to the target sample point, wherein the plurality of other sample points are sample points other than the target sample point in the spatial point cloud; and on the basis of the local density and the target relative distance value, segmenting the spatial point cloud to obtain a spatial point cloud segmentation result.

The invention relates to the technical field of power detection, and discloses a vegetation risk hidden danger detection method and system based on sparse point cloud segmentation, and the method comprises the steps: collecting image data of a monitoring region at different angles, generating sparse point cloud data, and carrying out the preprocessing of the sparse point cloud data; and performing point cloud segmentation on the sparse point cloud data through a neural network, dividing the monitoring region according to region types, analyzing a spatial relationship between vegetation and power equipment in a target region, performing risk assessment, and generating an early warning signal in combination with multi-modal data. According to the method, the sparse point cloud data is precisely segmented, the three-dimensional space characteristics of the tree are extracted, and the potential risk of the tree and the power transmission facility can be dynamically monitored in real time by precisely calculating the space relation between the tree and the power transmission facility; according to the multi-modal fusion data, multi-level early warning information is generated, so that the efficiency and precision of power transmission line inspection are greatly improved, and the pre-judgment and timely treatment of hidden dangers are realized.

The invention relates to the technical field of image processing, in particular to a feature point automatic labeling method and system based on point cloud data. The method comprises the following steps: acquiring regional multi-source point cloud data, and performing multi-modal data fusion to obtain point cloud fusion data; performing shoreline structure ground point cloud segmentation based on the point cloud fusion data to obtain a ground point cloud segmentation data set; performing edge detection on the ground point cloud segmentation data set, and identifying geometric salient points according to an edge detection result so as to obtain a feature point candidate set; performing ground feature type classification based on the feature point candidate set to obtain a target classification data set; distributing a symbolic pattern for the target classification data set and binding a point cloud feature attribute to obtain a symbolic data set; and performing multi-level symbol dynamic adjustment and interactive labeling based on the symbolized data set to obtain a symbol dynamic view. The method is helpful for improving the accuracy and efficiency of symbolization expression of the shore feature points, and has strong interactivity.

The invention discloses a multi-scale attention aggregation-based target point cloud segmentation method for a battery replacement robot, and the method comprises the steps: 1, collecting an RGB image, a depth image and three-dimensional point cloud data of a target fastener through a binocular structured light depth camera, and carrying out the fusion to generate a FastSeg3D data set; 2, a two-stage preprocessing method is provided, noise points are removed through radius filtering, and background point clusters far away from a target are removed through DBSCAN density clustering; 3, the network encoder uses a local feature aggregation module to extract geometric features, and the calculation complexity is reduced in combination with a random sampling strategy; 4, embedding a multi-scale attention aggregation module into the jump connection of the encoder and the decoder, fusing the features through a channel and a space attention unit, and achieving the self-adaptive weight weighting of the features of each layer of the encoder; and 5, recovering the resolution of the original point cloud by adopting nearest neighbor interpolation up-sampling, outputting a segmentation semantic tag, and obtaining a high-quality point cloud target. According to the method, the operation time of the battery replacement robot is shortened, and the balance problem of large-scale target point cloud segmentation speed and precision is solved.

The invention provides a laser radar point cloud analysis method based on transform. The method relates to the technical field of laser radar point cloud segmentation. The method comprises the following steps: synchronously acquiring a scene laser radar point cloud and an RGB image through a laser radar and a camera, and carrying out filtering processing on the laser radar point cloud; constructing a sparse depth map of the RGB image by using the laser radar point cloud; the pre-trained depth estimation model converts the RGB image of the scene into a dense depth map under the conditions of the internal reference of the camera, the relative attitude of the camera collecting the RGB image and the sparse depth map, and ensures that the generated dense depth map is aligned with the laser radar point cloud; the dense depth map and the laser radar point cloud which are matched with each other are provided for a Unet architecture point cloud segmentation model based on a Transform block, and the Unet architecture point cloud segmentation model supplements dense depth map features into laser radar point cloud features to realize laser radar point cloud segmentation.

The invention provides a sheep body size measuring method and device based on three-dimensional reconstruction and point cloud segmentation, a medium and a program product, and relates to the technical field of computer vision. The method comprises the following steps: acquiring a sheep image of a to-be-detected sheep, and preprocessing the sheep image to obtain a multi-view sheep target point cloud; performing point cloud registration processing on the multi-view sheep target point cloud to obtain a sheep three-dimensional model; performing point cloud segmentation processing based on the body size measurement key points and the sheep three-dimensional model to obtain key point region point clouds; based on the key point region point cloud, determining a region point cloud projection space, performing attitude normalization on the interval point cloud, and determining an attitude normalized key point region point cloud; and calculating the body size data of the to-be-measured sheep based on the point cloud of the key point region subjected to attitude normalization. According to the embodiment of the invention, through three-dimensional reconstruction of the body surface point cloud of the sheep, non-contact measurement of the body size data of the sheep is realized, and the measurement efficiency and accuracy are improved.

The invention discloses an automatic stacking method and device, a terminal and a storage medium, and the method comprises the steps that package information of a to-be-stacked package is obtained according to an acquisition device, and an optimal stack type is matched for the to-be-stacked package in combination with historical stack type data of an automatic stacking system; carrying out point cloud segmentation on the tray with the stacked parcels through a preset segmentation model to obtain a segmentation result, calculating a tray gap in combination with the optimal stack type and a preset path planning algorithm, and generating a stacking path; the flexible clamping jaw device is controlled to grab the parcels to be stacked, the grabbing posture is corrected in real time in combination with feedback of the torque sensor, and the mechanical arm is controlled to execute stacking according to the stacking path; and when the segmentation result of the tray is matched with the optimal stack type, a stacking three-dimensional model is generated, the stacking three-dimensional model is bound with the AGV below the tray, and the AGV is controlled to be automatically put in storage. According to the method, stacking and warehousing are completed through stack type matching and path planning, and the adaptability and the space utilization rate of a stacking system are improved.

A point cloud cylinder segmentation processing method and apparatus, and an electronic device. The present invention relates to the technical field of computers, and in particular, to the technical field of three-dimensional point cloud segmentation. The method comprises: acquiring a plurality of sample points comprised in a point cloud corresponding to a target object; determining neighbor points of the plurality of sample points within respective preset neighborhood ranges; on the basis of the neighbor points of the plurality of sample points within respective preset neighborhood ranges, obtaining normal vectors respectively corresponding to the plurality of sample points; performing clustering processing on the plurality of sample points on the basis of the normal vectors respectively corresponding to the plurality of sample points to obtain a clustering result; and performing cylinder segmentation on the target object on the basis of the clustering result to obtain a cylinder segmentation result of the target object.

The invention discloses a wheat organ three-dimensional point cloud segmentation method based on dynamic voxel and category perception. Three-dimensional reconstruction is carried out on a wheat sample based on a three-dimensional Gaussian splash method, and dense point cloud data are obtained; performing data amplification on the dense point cloud data by adopting a dynamic voxel rasterization random sampling method combining dynamic voxel division and a random farthest point sampling strategy, and performing standardized point cloud quantity processing to obtain a standard point cloud data set; and based on the standard point cloud data set, carrying out key organ segmentation by adopting a category perception segmentation network. According to the data enhancement method, key geometric features are maintained while data diversity is expanded, a feature extraction module of the category perception segmentation network solves the problem of ignoring important points during sampling by fusing DCA and a weighted farthest point sampling strategy, and an improved loss function combining a point cloud space structure and information is adopted to improve the accuracy of data enhancement. And the segmentation precision of the wheat complex point cloud data is effectively improved.

The invention provides a shield muck three-dimensional point cloud segmentation and volume calculation method based on deep learning, and belongs to the technical field of deep learning and shield, and the method comprises the steps: S1, point cloud data collection, preprocessing and sample labeling; s2, constructing and training a deep learning segmentation model; s3, carrying out muck point cloud segmentation; and S4, calculating the volume of the muck. According to the method, efficient interaction of point cloud attention is realized by adopting four serialization modes, and the influence of point cloud disorder on calculation is avoided.

The invention relates to the technical field of building structure health monitoring, in particular to an unmanned aerial vehicle laser radar-based building point cloud deformation quantitative extraction method, which comprises the following steps of: based on building corner structure characteristics in point cloud data, carrying out quantitative evaluation on the overall inclination state of a building through point cloud segmentation, straight line fitting and angle calculation; based on an ideal plane hypothesis, performing plane fitting and point-to-plane distance analysis on the building facade point cloud in the point cloud data, identifying a local concave-convex deformation area of the building facade, and performing quantitative evaluation; and roof plane detection and wall surface normal vector analysis are carried out based on the point cloud data, and accurate quantification is carried out on parapet wall inclination based on region growth segmentation and PCA principal direction analysis. Through automatic processing and quantitative analysis of an algorithm, subjective errors and inconsistency possibly occurring in a traditional manual evaluation method are avoided, and objectivity and repeatability of an evaluation result are enhanced.

The invention provides a prefabricated bridge pier column installation quality automatic evaluation method based on a three-dimensional laser point cloud. The prefabricated bridge pier column installation quality automatic evaluation method is used for measuring the perpendicularity of a high pier and the distance between pier columns. The method comprises the following steps: an unmanned aerial vehicle laser scanning system collects pier point cloud data according to an optimized flight path, and pre-processes the pier point cloud data to improve data quality; quickly segmenting the point cloud by using an improved adaptive octree and a machine learning algorithm, and extracting a pier point cloud; and based on the finely segmented point cloud, calculating the included angle between the center axis of the bridge pier and the plane normal of the capping beam and the coordinate of the center point of the top surface of the bridge pier to realize accurate evaluation of the perpendicularity of the bridge pier and the distance between adjacent bridge piers. The optimization of the flight path of the unmanned aerial vehicle is combined with the point cloud data preprocessing, so that the data quality can be effectively improved, and the data volume is reduced. Meanwhile, point cloud segmentation is performed by fusing an improved adaptive octree and a machine learning algorithm, so that piers, capping beams and backgrounds can be accurately distinguished, and geometric features of pier studs are completely extracted.

The invention provides an underwater target three-dimensional reconstruction method and system based on a three-dimensional imaging sonar image, and the method comprises the steps: collecting the three-dimensional imaging sonar data of an underwater target, segmenting the sonar point cloud data through employing an optimized point cloud segmentation model, and extracting a specific target point cloud; and performing sparse reconstruction and dense reconstruction on the target point cloud in sequence, and finally realizing high-precision three-dimensional reconstruction of the target. The system comprises a data acquisition module, a preprocessing module, a reconstruction algorithm module and a visualization module, and is suitable for underwater target surveying, mapping and monitoring. The invention aims to solve the problem of insufficient reconstruction precision and efficiency of a traditional method in a complex underwater environment.

The invention belongs to the field of remote sensing information extraction, and relates to an airborne LiDAR urban point cloud semantic segmentation method and system, and the method comprises the steps: obtaining airborne LiDAR point cloud data of a target region, and carrying out the preprocessing of the point cloud data; a multi-scale attention kernel point convolution network is constructed, the network adopts an encoder-decoder structure, each encoder is configured with a dual-path kernel point convolution block to extract multi-scale features, features between adjacent layers are fused through an adaptive module and are input into a decoder through jump connection, and the multi-scale attention kernel point convolution network is obtained. The decoder adopts a dense connection network and introduces a deep supervision mechanism; and inputting the preprocessed point cloud data into a pre-trained multi-scale attention kernel point convolutional network, and outputting a semantic category label of each point cloud. The airborne LiDAR city point cloud segmentation method and the airborne LiDAR city point cloud segmentation system have the advantages that the performance of the airborne LiDAR city point cloud segmentation method and the airborne LiDAR city point cloud segmentation system are superior to other airborne LiDAR city point cloud segmentation methods, the airborne LiDAR city point cloud segmentation method and the airborne LiDAR city point cloud segmentation method can better obtain and analyze airborne LiDAR city point cloud, and the airborne LiDAR city point cloud segmentation method and the airborne LiDAR city point cloud

The invention provides an interactive point cloud instance segmentation method based on a three-dimensional Gaussian scattering field, and the method comprises the steps: receiving click prompt data of a user, carrying out the calculation of interaction points and weights based on the click prompt data, and obtaining Gaussian features containing interaction prompt information; screening and converting the Gaussian features in the interaction point neighborhood to obtain point cloud batch data; performing foreground and background prediction on the point cloud batch data by using a point cloud segmentation network to obtain a three-dimensional instance label; performing projection mapping on the three-dimensional instance label through a Gaussian grating to obtain a two-dimensional segmentation mask; and performing morphological post-processing on the two-dimensional segmentation mask to obtain a segmentation result. According to the method, the cross-view consistency and the boundary precision of the point cloud segmentation result of the three-dimensional Gaussian scattering field instance are effectively improved, and the segmentation time efficiency is accelerated.

The invention provides a three-dimensional point cloud segmentation method and system based on bidirectional fusion of a point cloud and an aerial view, and belongs to the technical field of three-dimensional scene environment perception, and the method comprises the steps: obtaining to-be-segmented original point cloud data; processing the obtained original point cloud data by using a pre-trained segmentation model to obtain a segmentation result; wherein the segmentation model comprises an encoder module, a backbone network and a fusion segmentation head. According to the method, a bidirectional fusion mechanism of the point cloud and the aerial view is provided, through interactive fusion of the point cloud and the BEV features in multiple stages, the expression ability of the model for local and global features is improved, the problems of fuzzy semantic boundary, difficulty in small target recognition and the like are remarkably improved, and the segmentation precision is obviously superior to that of an existing BEV method. Compared with a voxel method and a multi-representation fusion method, the method has the advantages that the weight of a calculation graph is kept light in structural design, compared with the voxel method and the multi-representation fusion method, the method has remarkable advantages in the aspects of parameter quantity and reasoning speed, precision and real-time performance are better considered, and the method is suitable for scenes with extremely high efficiency requirements such as automatic driving.

The invention discloses a rape population canopy photosynthetic measurement method and device and a storage medium, and relates to the technical field of plant image processing. The method comprises the following steps: constructing a rape group point cloud data set with organ semantic information; training a rape group organ point cloud segmentation model by using the point cloud data set; segmenting the rape group organ point cloud by using the trained point cloud segmentation model; on the basis of the point cloud data of the rape group after organ segmentation in the whole growth period, rape group structure indexes are extracted; and constructing a photosynthetic capacity measurement index based on the rape population structure index, and obtaining photosynthetic capacity estimation of the whole-growth-period rape population. According to the method, high-throughput measurement of the photosynthetic parameters of the rape population can be accurately realized.

The invention relates to an unmanned aerial vehicle autonomous coal inventory method based on a laser radar. The method comprises the following steps: constructing an offline point cloud map of a coal pile environment; controlling the unmanned aerial vehicle to rise to a preset height from a preset range near the original point of the off-line map, collecting an initial point cloud map of the local environment, and registering the initial point cloud map with the off-line map to obtain an optimized initial pose; laser radar point cloud data are continuously collected in real time in the flight process of the unmanned aerial vehicle, and the pose of the unmanned aerial vehicle is estimated based on an offline map so as to update a three-dimensional point cloud map of the environment; the local point cloud density of the three-dimensional point cloud map is monitored in real time, a neighborhood radius parameter of a DBSCAN algorithm is dynamically adjusted, and meanwhile, a point cloud segmentation strategy is optimized in combination with an IMU motion state, so that coal pile point cloud is obtained; incremental mapping of the point cloud of the coal pile is realized through the dynamic point cloud management capability of the ikd-tree, and real-time volume calculation of the coal pile is realized based on the point cloud of the coal pile. Compared with the prior art, the system has the advantages of autonomous coal pile measurement, high measurement accuracy and efficiency and the like.

The invention discloses a training-free 3D zero sample instance segmentation method, system and device and a medium, and relates to the technical field of scene understanding, and the method comprises the steps: obtaining an image and corresponding 3D point cloud data, carrying out the 2D instance segmentation of the image through a pre-training visual model, generating a multi-view instance mask, and carrying out the 3D point cloud segmentation of the image; mapping the point cloud to each visual angle instance mask based on a 3D-2D projection relationship, distributing an initial instance label for the point, adopting a space corresponding relationship adjustment strategy to solve instance label conflicts among multiple visual angles, combining the projection relationship and semantic features, carrying out instance combination on the associated point cloud instances, extracting multi-visual angle semantic features of the combined point cloud instances, and carrying out multi-visual-angle semantic feature extraction on the combined point cloud instances; and carrying out weighted aggregation, optimizing a segmentation result, and outputting 3D instance segmentation. According to the method, the pre-training model and the multi-view geometric information are combined, so that rapid and accurate 3D zero sample instance segmentation without training is realized, and the segmentation efficiency, accuracy, semantic integrity and robustness are remarkably improved.

The invention relates to the field of point cloud segmentation, and discloses a small sample point cloud semantic segmentation method based on self-support, and the method comprises the steps: obtaining a support set point cloud and a query set point cloud, enabling the support set point cloud and the query set point cloud to pass through an embedded network, and obtaining support set features and query set features; enhancing feature representation of the support set features and the query set features through a feature enhancement module to obtain enhanced support set features and query set features; obtaining a support prototype from the enhanced support set features and the corresponding support set masks through an adaptive dynamic multi-prototype generation method; obtaining an initial prediction mask from the enhanced query set feature and the support prototype through a KNN graph construction and label rebroadcasting method; obtaining a final prediction mask from the enhanced query set features and the initial prediction mask through a self-support strategy; according to the method, the problem of low segmentation precision caused by inter-class similarity and inter-class diversity of the existing small sample point cloud semantic segmentation method is solved.

The invention relates to a point cloud segmentation method and system, and relates to the technical field of point cloud segmentation, and the method comprises the steps: obtaining point cloud data, constructing an octree for the point cloud data, carrying out the information enhancement of nodes in the octree, and obtaining a point cloud octree after the information enhancement; generating a point cloud sequence X based on the point cloud octree after information enhancement, and performing Patch coding on the point cloud sequence X; and carrying out point cloud segmentation on the point cloud sequence X after Patch coding. According to the method, the problem of over-segmentation or under-segmentation of point cloud segmentation in the prior art can be effectively solved.

The invention relates to the technical field of point cloud semantic segmentation, and discloses a point cloud segmentation method and system based on point cloud serialization and a Mama network. Specifically, a geometric distance matrix and a semantic distance matrix are calculated for a plurality of representative point units obtained by sampling on an original point cloud, and a path sequence is generated based on a fused comprehensive distance matrix. And traversing the path sequence by adopting a bidirectional scanning strategy to generate a forward sequence and a reverse sequence, extracting features from the forward sequence and the reverse sequence by utilizing a Mama network, cascading or fusing the extracted features, and finally performing classification based on the fused features. According to the method, better long-range dependency and local context modeling effects can be obtained, the comprehensive expression capability of detail features and global context in sparse and irregular scenes is enhanced, and the calculation and memory overhead required for global dependency capture of large-scale point clouds is greatly reduced.

The invention is suitable for the technical field of agricultural information, and provides a fertilizer material volume change measuring method based on multi-sensor information fusion, which comprises the following steps: carrying out physical modeling on a detection area; selecting a depth camera and determining an angle; acquiring and processing point cloud data; and splicing and quantifying the point cloud target areas in the previous and next time. According to the method, a storage space is mapped through physical modeling, multiple sensors are used for data acquisition and reconstruction, and point cloud data of a fertilizer area are accurately extracted through a point cloud segmentation algorithm. The system calculates the change quantity before and after fixed-period data acquisition, and quantifies the accurate change volume through a voxel technology. According to the method, real-time volume change measurement can be provided, the measurement precision can be adjusted according to needs, and the method is suitable for storage spaces of different materials such as fertilizers and grains.

The invention provides a cement conveyor volume measurement method based on deep learning point cloud segmentation. The method comprises the following steps: obtaining 3D point cloud data by using a laser line scanning 3D camera, and determining RGB values of pixels corresponding to the 3D point cloud data to obtain 3D point cloud with color features; inputting the 3D point cloud with the color features into an improved Point-Net + + neural network for 3D point cloud segmentation, and obtaining 3D point cloud data only containing the cement surface in the conveyor after segmentation; constructing a triangulation network based on the cement irregular surface in the segmented 3D point cloud data by adopting a triangulation method, and performing volume calculation according to the constructed triangulation network; wherein the improved Point-Net + + neural network is constructed on the basis of a framework of an original Point-Net + + point cloud segmentation network, and comprises a core point convolution, a context sensing module and a Focal Loss loss function. Therefore, the performance of a point cloud segmentation algorithm is improved, and even under complex conditions, the surface point cloud data of the cement material in the conveyor can still be accurately segmented for volume measurement.

The invention discloses an underwater target volume measurement method, device and equipment based on three-dimensional reconstruction and a medium, and belongs to the technical field of photogrammetry, underwater image processing and point cloud volume calculation cross, and the method comprises the steps: carrying out the video data collection of an underwater target through video collection equipment, and obtaining an original image with image format data; the underwater image enhancement method model based on depth estimation performs image enhancement on the original image to obtain an underwater enhanced image; reconstructing a real scene containing a target based on the underwater enhanced image; and based on the three-dimensional reconstruction point cloud, segmenting to obtain the to-be-measured target, and obtaining the volume parameter of the underwater target. According to the method, a three-dimensional reconstruction technology is utilized, a real target structure is restored, the measurement accuracy of the underwater target defect volume is improved, a reference standard is provided for later repair, the maintenance cost is reduced, and the operation safety of a hydraulic structure is guaranteed.

The invention relates to the field of computer vision, in particular to an intelligent identifying and sorting method and system for traditional Chinese medicinal materials. Based on a multispectral and microscopic vision fusion engine, millisecond-level authenticity identification of traditional Chinese medicinal materials is realized through sub-pixel-level feature extraction and cross-modal knowledge distillation, and similar medicinal material confusion is thoroughly eliminated by combining PointRend point cloud segmentation and pharmacopoeia map confrontation verification; a rotary YOLO-MoE multi-angle defect detection mechanism is innovated, a zero-adulteration quality control closed loop with zero manual intervention is achieved under the assistance of a self-adaptive guide execution unit, and a map database is continuously upgraded synchronously through a dynamic federated learning mechanism. The technical bottleneck that an existing traditional Chinese medicine identification system depends on artificial experience and is weak in authenticity identification capability is broken through, and the key problems of confusion of medicinal materials with similar forms caused by single dimension of semi-automatic pharmacy visual identification, missing detection of defective products caused by no quality control mechanism and the like are thoroughly solved; and the medicinal material identifying and sorting process is improved to a stable, reliable, self-adaptive and cooperative intelligent level.

The invention discloses a point cloud segmentation method, which comprises the following steps that: two-dimensional masks of image frames are extracted frame by frame, the image frames are pictures of an object to be reconstructed shot from different visual angles, and the two-dimensional mask extracted from the previous image frame can be transmitted to the subsequent image frame; the method comprises the following steps: acquiring fringe image sequences of a to-be-reconstructed object at different visual angles, extracting phase information, generating a multi-visual-angle phase coding diagram of the to-be-reconstructed object, performing epipolar correction on the phase coding diagrams at different visual angles to eliminate geometric distortion at different visual angles, and calculating parallax of the same name point at different visual angles to obtain the multi-visual-angle phase coding diagram of the to-be-reconstructed object. Calculating a depth value of an object point corresponding to the homonymy point according to the parallax, and obtaining depth value data of the object to be reconstructed; and obtaining a two-dimensional contour according to the two-dimensional mask of the to-be-reconstructed object, calculating the depth value of the two-dimensional contour of the to-be-reconstructed object pixel by pixel according to the depth value data of the to-be-reconstructed object, mapping the two-dimensional contour information of the to-be-reconstructed object to a three-dimensional space, generating the three-dimensional contour of the to-be-reconstructed object of the current frame, and realizing point cloud segmentation.

The invention discloses a steel structure digital modeling method and system, and the method comprises the steps: obtaining high-precision point cloud data of a steel structure member through a laser scanning technology, carrying out the noise filtering and point cloud segmentation of the point cloud data, automatically recognizing the geometric features of the steel structure member through a geometric feature recognition technology, and distributing a unique identifier, the method comprises the following steps: collecting non-geometric attribute data of a steel structure component from a plurality of heterogeneous information sources, fusing the non-geometric attribute data through priority ranking and a conflict resolution mechanism, performing semantic reasoning completion based on component types, function positioning and engineering specifications, performing strict consistency verification on the completed non-geometric attribute information, and outputting the non-geometric attribute information in an industry general format; according to the method, comprehensive, efficient and accurate digital modeling of the existing steel structure component is realized, the core problems of data missing, information isolation, much manual intervention, low efficiency, error accumulation and the like in the prior art are effectively solved, and a solid and reliable digital foundation is provided for transformation, maintenance and management of steel structure engineering; and the method has remarkable engineering application value and economic benefit.

The invention relates to a slice voxelization and adaptive feature sampling-based foot point cloud segmentation method, which comprises the following steps of: preprocessing an original foot point cloud, including de-noising, down-sampling and normal vector and curvature estimation; slicing and layering the preprocessed point cloud along the height direction, and performing voxelization processing on each layer of slice to obtain structured voxel features; the importance weight of each point is calculated, adaptive feature sampling is carried out according to the weights, and key geometric features are reserved; inputting the sampled point cloud into an improved PointNet + + network for multi-scale feature extraction, and fusing features among different slices through an interlayer attention mechanism; and performing post-processing on a segmentation result output by the network to obtain a final foot point cloud segmentation result. According to the method, multi-level collaborative modeling of the local structure and the overall shape of the foot is achieved, and more accurate and generalized technical support is provided for application of foot three-dimensional medical analysis, shoe type personalized design, gait reconstruction and the like.