A LiDAR Point Clouds Dataset of Ships in a Maritime Environment

For the first time, this article introduces a LiDAR Point Clouds Dataset of Ships composed of both collected and simulated data to address the scarcity of LiDAR data in maritime applications. The collected data are acquired using specialized maritime LiDAR sensors in both inland waterways and wide-open ocean environments. The simulated data is generated by placing a ship in the LiDAR coordinate system and scanning it with a redeveloped Blensor that emulates the operation of a LiDAR sensor equipped with various laser beams. Furthermore,we also render point clouds for foggy and rainy weather conditions. To describe a realistic shipping environment, a dynamic tail wave is modeled by iterating the wave elevation of each point in a time series. Finally, networks serving small objects are migrated to ship applications by feeding our dataset. The positive effect of simulated data is described in object detection experiments, and the negative impact of tail waves as noise is verified in single-object tracking experiments. The Dataset is available at https://github.com/zqy411470859/ship_dataset.

Building Facade Point Clouds Segmentation Based on Optimal Dual-Scale Feature Descriptors

To address the current issues of inaccurate segmentation and the limited applicability of segmentation methods for building facades in point clouds, we propose a facade segmentation algorithm based on optimal dual-scale feature descriptors. First, we select the optimal dual-scale descriptors from a range of feature descriptors. Next, we segment the facade according to the threshold value of the chosen optimal dual-scale descriptors. Finally, we use RANSAC (Random Sample Consensus) to fit the segmented surface and optimize the fitting result. Experimental results show that, compared to commonly used facade segmentation algorithms, the proposed method yields more accurate segmentation results, providing a robust data foundation for subsequent 3D model reconstruction of buildings.

Estimating wood quality attributes from dense airborne LiDAR point clouds

Mapping individual tree quality parameters from high-density LiDAR point clouds is an important step towards improved forest inventories.We present a novel machine learning-based workflow that uses individual tree point clouds from drone laser scanning to predict wood quality indicators in standing trees.Unlike object reconstruction methods,our approach is based on simple metrics computed on vertical slices that summarize information on point distances,angles,and geometric attributes of the space between and around the points.Our models use these slice metrics as predictors and achieve high accuracy for predicting the diameter of the largest branch per log (DLBs) and stem diameter at different heights (DS) from survey-grade drone laser scans.We show that our models are also robust and accurate when tested on suboptimal versions of the data generated by reductions in the number of points or emulations of suboptimal single-tree segmentation scenarios.Our approach provides a simple,clear,and scalable solution that can be adapted to different situations both for research and more operational mapping.

Building 3D CityGML models of mining industrial structures using integrated UAV and TLS point clouds

Mining industrial areas with anthropogenic engineering structures are one of the most distinctive features of the real world.3D models of the real world have been increasingly popular with numerous applications,such as digital twins and smart factory management.In this study,3D models of mining engineering structures were built based on the CityGML standard.For collecting spatial data,the two most popular geospatial technologies,namely UAV-SfM and TLS were employed.The accuracy of the UAV survey was at the centimeter level,and it satisfied the absolute positional accuracy requirement of creat-ing all levels of detail(LoD)according to the CityGML standard.Therefore,the UAV-SfM point cloud dataset was used to build LoD 2 models.In addition,the comparison between the UAV-SfM and TLS sub-clouds of facades and roofs indicates that the UAV-SfM and TLS point clouds of these objects are highly consistent,therefore,point clouds with a higher level of detail and accuracy provided by the integration of UAV-SfM and TLS were used to build LoD 3 models.The resulting 3D CityGML models include 39 buildings at LoD 2,and two mine shafts with hoistrooms,headframes,and sheave wheels at LoD3.

Perceptual Quality Assessment for Point Clouds:A Survey

A point cloud is considered a promising 3D representation that has achieved wide applications in several fields.However,quality degradation inevitably occurs during its acquisition and generation,communication and transmission,and rendering and display.Therefore,how to accurately perceive the visual quality of point clouds is a meaningful topic.In this survey,we first introduce the point cloud to emphasize the importance of point cloud quality assessment(PCQA).A review of subjective PCQA is followed,including common point cloud distortions,subjective experimental setups and subjective databases.Then we review and compare objective PCQA methods in terms of modelbased and projection-based.Finally,we provide evaluation criteria for objective PCQA methods and compare the performances of various methods across multiple databases.This survey provides an overview of classical methods and recent advances in PCQA.

A modified method of discontinuity trace mapping using three-dimensional point clouds of rock mass surfaces

This paper presents an automated method for discontinuity trace mapping using three-dimensional point clouds of rock mass surfaces.Specifically,the method consists of five steps:(1)detection of trace feature points by normal tensor voting theory,(2)co ntraction of trace feature points,(3)connection of trace feature points,(4)linearization of trace segments,and(5)connection of trace segments.A sensitivity analysis was then conducted to identify the optimal parameters of the proposed method.Three field cases,a natural rock mass outcrop and two excavated rock tunnel surfaces,were analyzed using the proposed method to evaluate its validity and efficiency.The results show that the proposed method is more efficient and accurate than the traditional trace mapping method,and the efficiency enhancement is more robust as the number of feature points increases.

Filtering of Airborne Lidar Point Clouds for Complex Cityscapes

A novel filtering algorithm for Lidar point clouds is presented, which can work well for complex cityscapes. Its main features are filtering based on raw Lidar point clouds without previous triangulation or rasterization. 3D topological relations among points are used to search edge points at the top of discontinuities, which are key information to recognize the bare earth points and building points. Experiment results show that the proposed algorithm can preserve discontinuous features in the bare earth and has no impact of size and shape of buildings.

Formula for calculating spatial similarity degrees between point clouds on multi-scale maps taking map scale change as the only independent variable

The degree of spatial similarity plays an important role in map generalization, yet there has been no quantitative research into it. To fill this gap, this study first defines map scale change and spatial similarity degree/relation in multi-scale map spaces and then proposes a model for calculating the degree of spatial similarity between a point cloud at one scale and its gener- alized counterpart at another scale. After validation, the new model features 16 points with map scale change as the x coordinate and the degree of spatial similarity as the y coordinate. Finally, using an application for curve fitting, the model achieves an empirical formula that can calculate the degree of spatial similarity using map scale change as the sole independent variable, and vice versa. This formula can be used to automate algorithms for point feature generalization and to determine when to terminate them during the generalization.

Feature detection on point clouds via Gabriel Triangles creation and l1 normal reconstruction

In this paper, we present a robust subneighborhoods selection technique for feature detection on point clouds scattered over a piecewise smooth surface. The proposed method first identifies all potential features using covariance analysis of the local- neighborhoods. To further extract the accurate features from potential features, Gabriel triangles are created in local neighborhoods of each potential feature vertex. These triangles tightly attach to underlying surface and effectively reflect the local geometry struc- ture. Applying a shared nearest neighbor clustering algorithm on ~ 1 reconstructed normals of created triangle set, we classify the lo- cal neighborhoods of the potential feature vertex into multiple subneighborhoods. Each subneighborhood indicates a piecewise smooth surface. The final feature vertex is identified by checking whether it is locating on the intersection of the multiple surfaces. An advantage of this framework is that it is not only robust to noise, but also insensitive to the size of selected neighborhoods. Ex- perimental results on a variety of models are used to illustrate the effectiveness and robustness of our method.

A voxel-based fine-scale 3D landscape pattern analysis using laser scanner point clouds

The landscape pattern metrics can quantitatively describe the characteristics of landscape pattern and are widely used in various fields of landscape ecology.Due to the lack of vertical information,2D landscape metrics cannot delineate the vertical characteristics of landscape pattern.Based on the point clouds,a high-resolution voxel model and several voxel-based 3D landscape metrics were constructed in this study and 3D metrics calculation results were compared with that of 2D metrics.The results showed that certain quantifying difference exists between 2D and 3D landscape metrics.For landscapes with different components and spatial configurations,significant difference was disclosed between 2D and 3D landscape metrics.3D metrics can better reflect the real spatial structure characteristics of the landscape than 2D metrics.

Automated registration of wide-baseline point clouds in forests using discrete overlap search

Forest is one of the most challenging environments to be recorded in a three-dimensional(3D)digitized geometrical representation,because of the size and the complexity of the environment and the data-acquisition constraints brought by on-site conditions.Previous studies have indicated that the data-acquisition pattern can have more influence on the registration results than other factors.In practice,the ideal short-baseline observations,i.e.,the dense collection mode,is rarely feasible,considering the low accessibility in forest environments and the commonly limited labor and time resources.The wide-baseline observations that cover a forest site using a few folds less observations than short-baseline observations,are therefore more preferable and commonly applied.Nevertheless,the wide-baseline approach is more challenging for data registration since it typically lacks the required sufficient overlaps between datasets.Until now,a robust automated registration solution that is independent of special hardware requirements has still been missing.That is,the registration accuracy is still far from the required level,and the information extractable from the merged point cloud using automated registration could not match that from the merged point cloud using manual registration.This paper proposes a discrete overlap search(DOS)method to find correspondences in the point clouds to solve the low-overlap problem in the wide-baseline point clouds.The proposed automatic method uses potential correspondences from both original data and selected feature points to reconstruct rough observation geometries without external knowledge and to retrieve precise registration parameters at data-level.An extensive experiment was carried out with 24 forest datasets of different conditions categorized in three difficulty levels.The performance of the proposed method was evaluated using various accuracy criteria,as well as based on data acquired from different hardware,platforms,viewing perspectives,and at different points of time.The proposed method achieved a 3D registration accuracy at a 0.50-cm level in all difficulty categories using static terrestrial acquisitions.In the terrestrial-aerial registration,data sets were collected from different sensors and at different points of time with scene changes,and a registration accuracy at the raw data geometric accuracy level was achieved.These results represent the highest automated registration accuracy and the strictest evaluation so far.The proposed method is applicable in multiple scenarios,such as 1)the global positioning of individual under-canopy observations,which is one of the main challenges in applying terrestrial observations lacking a global context,2)the fusion of point clouds acquired from terrestrial and aerial perspectives,which is required in order to achieve a complete forest observation,3)mobile mapping using a new stop-and-go approach,which solves the problems of lacking mobility and slow data collection in static terrestrial measurements as well as the data-quality issue in the continuous mobile approach.Furthermore,this work proposes a new error estimate that units all parameter-level errors into a single quantity and compensates for the downsides of the widely used parameter-and object-level error estimates;it also proposes a new deterministic point sets registration method as an alternative to the popular sampling methods.

Accuracy of common stem volume formulae using terrestrial photogrammetric point clouds:a case study with savanna trees in Benin

Recent applications of digital photogrammetry in forestry have highlighted its utility as a viable mensuration technique.However,in tropical regions little research has been done on the accuracy of this approach for stem volume calculation.In this study,the performance of Structure from Motion photogrammetry for estimating individual tree stem volume in relation to traditional approaches was evaluated.We selected 30 trees from five savanna species growing at the periphery of the W National Park in northern Benin and measured their circumferences at different heights using traditional tape and clinometer.Stem volumes of sample trees were estimated from the measured circumferences using nine volumetric formulae for solids of revolution,including cylinder,cone,paraboloid,neiloid and their respective fustrums.Each tree was photographed and stem volume determined using a taper function derived from tri-dimensional stem models.This reference volume was compared with the results of formulaic estimations.Tree stem profiles were further decomposed into different portions,approximately corresponding to the stump,butt logs and logs,and the suitability of each solid of revolution was assessed for simulating the resulting shapes.Stem volumes calculated using the fustrums of paraboloid and neiloid formulae were the closest to reference volumes with a bias and root mean square error of 8.0%and 24.4%,respectively.Stems closely resembled fustrums of a paraboloid and a neiloid.Individual stem portions assumed different solids as follows:fustrums of paraboloid and neiloid were more prevalent from the stump to breast height,while a paraboloid closely matched stem shapes beyond this point.Therefore,a more accurate stem volumetric estimate was attained when stems were considered as a composite of at least three geometric solids.

3D scene graph prediction from point clouds

Background In this study,we propose a novel 3D scene graph prediction approach for scene understanding from point clouds.Methods It can automatically organize the entities of a scene in a graph,where objects are nodes and their relationships are modeled as edges.More specifically,we employ the DGCNN to capture the features of objects and their relationships in the scene.A Graph Attention Network(GAT)is introduced to exploit latent features obtained from the initial estimation to further refine the object arrangement in the graph structure.A one loss function modified from cross entropy with a variable weight is proposed to solve the multi-category problem in the prediction of object and predicate.Results Experiments reveal that the proposed approach performs favorably against the state-of-the-art methods in terms of predicate classification and relationship prediction and achieves comparable performance on object classification prediction.Conclusions The 3D scene graph prediction approach can form an abstract description of the scene space from point clouds.

An unmanned ground vehicle phenotyping-based method to generate three-dimensional multispectral point clouds for deciphering spatial heterogeneity in plant traits

Fusing three-dimensional(3D)and multispectral(MS)imaging data holds promise for high-throughput and comprehensive plant phenotyping to decipher genome-to-phenome knowledge.Acquiring high-quality 3D MS point clouds(3DMPCs)of plants remains challenging because of poor 3D data quality and limited radiometric calibration methods for plants with a complex canopy structure.Here,we present a novel 3D spatial–spectral data fusion approach to collect high-quality 3DMPCs of plants by integrating the next-best-view planning for adaptive data acquisition and neural reference field(NeREF)for radiometric calibration.This approach was used to acquire 3DMPCs of perilla,tomato,and rapeseed plants with diverse plant architecture and leaf morphological features evaluated by the accuracy of chlorophyll content and equivalent water thickness(EWT)estimation.The results showed that the completeness of plant point clouds collected by this approach was improved by an average of 23.6%compared with the fixed viewpoints alone.The NeREF-based radiometric calibration with the hemispherical reference outperformed the conventional calibration method by reducing the root mean square error(RMSE)of 58.93%for extracted reflectance spectra.The RMSE for chlorophyll content and EWT predictions decreased by 21.25%and 14.13%using partial least squares regression with the generated 3DMPCs.Collectively,our study provides an effective and efficient way to collect high-quality 3DMPCs of plants under natural light conditions,which improves the accuracy and comprehensiveness of phenotyping plant morphological and physiological traits,and thus will facilitate plant biology and genetic studies as well as crop breeding.

3D Distinct Element Back Analysis Based on Rock Structure Modelling of SfM Point Clouds:The Case of the 2019 Pinglu Rockfall of Kaili,China

This paper introduces the use of point cloud processing for extracting 3D rock structure and the 3DEC-related reconstruction of slope failure,based on a case study of the 2019 Pinglu rockfall.The basic processing procedure involves:(1)computing the point normal for HSV-rendering of point cloud;(2)automatically clustering the discontinuity sets;(3)extracting the set-based point clouds;(4)estimating of set-based mean orientation,spacing,and persistence;(5)identifying the block-forming arrays of discontinuity sets for the assessment of stability.The effectiveness of our rock structure processing has been proved by 3D distinct element back analysis.The results show that Sf M modelling and rock structure computing provides enormous cost,time and safety incentives in standard engineering practice.

Dynamic Scene Graph Generation of Point Clouds with Structural Representation Learning

Scene graphs of point clouds help to understand object-level relationships in the 3D space.Most graph generation methods work on 2D structured data,which cannot be used for the 3D unstructured point cloud data.Existing point-cloud-based methods generate the scene graph with an additional graph structure that needs labor-intensive manual annotation.To address these problems,we explore a method to convert the point clouds into structured data and generate graphs without given structures.Specifically,we cluster points with similar augmented features into groups and establish their relationships,resulting in an initial structural representation of the point cloud.Besides,we propose a Dynamic Graph Generation Network(DGGN)to judge the semantic labels of targets of different granularity.It dynamically splits and merges point groups,resulting in a scene graph with high precision.Experiments show that our methods outperform other baseline methods.They output reliable graphs describing the object-level relationships without additional manual labeled data.

COMPUTING HARMONIC MAPS AND CONFORMAL MAPS ON POINT CLOUDS

We use a narrow-band approach to compute harmonic maps and conformal maps for surfaces embedded in the Euclidean 3-space,using point cloud data only.Given a surface,or a point cloud approximation,we simply use the standard cubic lattice to approximate itsϵ-neighborhood.Then the harmonic map of the surface can be approximated by discrete harmonic maps on lattices.The conformal map,or the surface uniformization,is achieved by minimizing the Dirichlet energy of the harmonic map while deforming the target surface of constant curvature.We propose algorithms and numerical examples for closed surfaces and topological disks.To the best of the authors’knowledge,our approach provides the first meshless method for computing harmonic maps and uniformizations of higher genus surfaces.

Nearest Neighbor Sampling of Point Sets Using Rays

We propose a new framework for the sampling,compression,and analysis of distributions of point sets and other geometric objects embedded in Euclidean spaces.Our approach involves constructing a tensor called the RaySense sketch,which captures nearest neighbors from the underlying geometry of points along a set of rays.We explore various operations that can be performed on the RaySense sketch,leading to different properties and potential applications.Statistical information about the data set can be extracted from the sketch,independent of the ray set.Line integrals on point sets can be efficiently computed using the sketch.We also present several examples illustrating applications of the proposed strategy in practical scenarios.

Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://github.com/yahuiliu99/PointC onT.

PuzzleNet:Boundary-Aware Feature Matching for Non-Overlapping 3D Point Clouds Assembly

We address the 3D shape assembly of multiple geometric pieces without overlaps, a scenario often encountered in 3D shape design, field archeology, and robotics. Existing methods depend on strong assumptions on the number of shape pieces and coherent geometry or semantics of shape pieces. Despite raising attention to 3D registration with complex or low overlapping patterns, few methods consider shape assembly with rare overlaps. To address this problem, we present a novel framework inspired by solving puzzles, named PuzzleNet, which conducts multi-task learning by leveraging both 3D alignment and boundary information. Specifically, we design an end-to-end neural network based on a point cloud transformer with two-way branches for estimating rigid transformation and predicting boundaries simultaneously. The framework is then naturally extended to reassemble multiple pieces into a full shape by using an iterative greedy approach based on the distance between each pair of candidate-matched pieces. To train and evaluate PuzzleNet, we construct two datasets, named ModelPuzzle and DublinPuzzle, based on a real-world urban scan dataset (DublinCity) and a synthetic CAD dataset (ModelNet40) respectively. Experiments demonstrate our effectiveness in solving 3D shape assembly for multiple pieces with arbitrary geometry and inconsistent semantics. Our method surpasses state-of-the-art algorithms by more than 10 times in rotation metrics and four times in translation metrics.