Point Cloud Research Articles

Failure analysis of multi-span masonry arch bridges using combination of point cloud data and three-dimensional numerical modeling

Historical structures, including historical bridges, are part of cultural heritage, conveying the traces and characteristic features of past civilizations. To protect historical structures, it is necessary to prepare their 3D photogrammetric documentation, determine detailed geometric and material properties and perform computer-aided structural analysis using appropriate modeling techniques. The aim of this study is to present an effective, reliable and fast multidisciplinary approach for the analysis of historical masonry bridges. The aforementioned approach was illustrated with an example of the historical Halilviran masonry arch bridge and its behavior under possible loadings. Terrestrial laser scanning (TLS) was used to determine the bridge geometry with high accuracy. Point cloud data obtained from TLS was simplified and a three-dimensional CAD-based solid model of the structure was created. The Halilviran Bridge case study summarized in this report was conducted to examine the technical feasibility of using la¬ser scanning technologies for obtaining as-built records for similar historic bridges. A secondary objective was to identify other applications of this technology, notably for other transportation structures, and use numerical methods to assess the seismic behavior and failure model of the bridge. The seismic behavior of the bridge was examined using a finite-element- based macromodeling technique. Nonlinear dynamic analyses were carried out subsequently to identify the most susceptible regions of the bridge. Interpretation of the results, presented in the form of contour plots illustrating tensile damage and maximum displacements, offered a comprehensive depiction of the seismic response across the entire bridge. The methodology employed in this investigation can be viewed as a robust framework for evaluating the seismic response and potential failure of historical structures.

Comprehensive Analysis of Phenotypic Traits in Chinese Cabbage Using 3D Point Cloud Technology

Studies on the phenotypic traits and their associations in Chinese cabbage lack precise and objective digital evaluation metrics. Traditional assessment methods often rely on subjective evaluations and experience, compromising accuracy and reliability. This study develops an innovative, comprehensive trait evaluation method based on 3D point cloud technology, with the aim of enhancing the precision, reliability, and standardization of the comprehensive phenotypic traits of Chinese cabbage. By using multi-view image sequences and structure-from-motion algorithms, 3D point clouds of 50 plants from each of the 17 Chinese cabbage varieties were reconstructed. Color-based region growing and 3D convex hull techniques were employed to measure 30 agronomic traits. Comparisons between 3D point cloud-based measurements of the plant spread, plant height, leaf area, and leaf ball volume and traditional methods yielded R2 values greater than 0.97, with root mean square errors of 1.27 cm, 1.16 cm, 839.77 cm3, and 59.15 cm2, respectively. Based on the plant spread and plant height, a linear regression prediction of Chinese cabbage weights was conducted, yielding an R2 value of 0.76. Integrated optimization algorithms were used to test the parameters, reducing the measurement time from 55 min when using traditional methods to 3.2 min. Furthermore, in-depth analyses including variation, correlation, principal component analysis, and clustering analyses were conducted. Variation analysis revealed significant trait variability, with correlation analysis indicating 21 pairs of traits with highly significant positive correlations and 2 pairs with highly significant negative correlations. The top six principal components accounted for 90% of the total variance. Using the elbow method, k-means clustering determined that the optimal number of clusters was four, thus classifying the 17 cabbage varieties into four distinct groups. This study provides new theoretical and methodological insights for exploring phenotypic trait associations in Chinese cabbage and facilitates the breeding and identification of high-quality varieties. Compared with traditional methods, this system provides significant advantages in terms of accuracy, speed, and comprehensiveness, with its low cost and ease of use making it an ideal replacement for manual methods, being particularly suited for large-scale monitoring and high-throughput phenotyping.

On the hypercomplex numbers and normed division algebras in all dimensions: A unified multiplication.

Mathematics is the foundational discipline for all sciences, engineering, and technology, and the pursuit of normed division algebras in all finite dimensions represents a paramount mathematical objective. In the quest for a real three-dimensional, normed, associative division algebra, Hamilton discovered quaternions, constituting a non-commutative division algebra of quadruples. Subsequent investigations revealed the existence of only four division algebras over reals, each with dimensions 1, 2, 4, and 8. This study transcends such limitations by introducing generalized hypercomplex numbers extending across all dimensions, serving as extensions of traditional complex numbers. The space formed by these numbers constitutes a non-distributive normed division algebra extendable to all finite dimensions. The derivation of these extensions involves the definitions of two new π-periodic functions and a unified multiplication operation, designated as spherical multiplication, that is fully compatible with the existing multiplication structures. Importantly, these new hypercomplex numbers and their associated algebras are compatible with the existing real and complex number systems, ensuring continuity across dimensionalities. Most importantly, like the addition operation, the proposed multiplication in all dimensions forms an Abelian group while simultaneously preserving the norm. In summary, this study presents a comprehensive generalization of complex numbers and the Euler identity in higher dimensions, shedding light on the geometric properties of vectors within these extended spaces. Finally, we elucidate the practical applications of the proposed methodology as a viable alternative for expressing a quantum state through the multiplication of specified quantum states, thereby offering a potential complement to the established superposition paradigm. Additionally, we explore its utility in point cloud image processing.

3D coherent single shot lidar imaging beyond coherence length

Advancements in remote sensing and autonomous vehicle technologies made lidars equally important for unmanned objects alongside cameras. Therefore, precise 3D lidar imaging and point cloud generation have become important subjects. Although existing coherent lidar technologies provide precise imaging results, the spectral linewidth of the laser sources becomes a key limitation over long distances as it defines the maximum detection range. Here, we present long-distance 3D lidar imaging which removes the coherence length limitations and therefore the necessity of high-coherence laser sources. Mainly, we generate optical sidebands, by modulating a continuous wave (CW) laser source with multiple radio-frequency (RF) tones. Then, using our own post-processing and triangulation methods, we use the relative phase changes between the sidebands which are free from laser phase noise to determine the target distance. We prove that the multi-tone coherent Lidar technique can perform precise 3D imaging and point cloud generation of various targets at sub-10pW optical power reception and distances up to ∼12× beyond the coherence length of the CW laser employed in the lidar architecture. Overall, it is demonstrated that coherence length restriction is removed by the suggested method, which makes precise long-distance 3D lidar imaging possible, particularly for applications such as spacecraft and aerial coherent lidars.

A generalized framework for identification and geometrical feature extraction of circular and polygonal shaped prisms

Abstract This paper introduces a versatile framework crucial for robotic applications such as object manipulation, mobile robot navigation, and pole climbing. It addresses the identification of geometric shapes and dimensions of diverse objects found in varied environments. The proposed method utilizes LiDAR scanning to capture objects from different angles, generating point clouds merged through transformations and superimpositions. After filtering and slicing, intersections are isolated and projected onto a chosen datum plane. The framework employs Non-Linear Least Square fitting via Gauss Newton iterative approach, utilizing pseudo-inverse Jacobian of a hypotrochoid to approximate polygons. The algorithm consecutively fits polygon prisms, determining the best fit with the least norm of error. Results indicate an average least square error of less than 9% for radius fitting and a high f-score for shape identification.

A Unified Virtual Model for Real-Time Visualization and Diagnosis in Architectural Heritage Conservation

The aim of this paper is to propose a workflow for the real-time visualization of virtual environments that supports diagnostic tasks in heritage buildings. The approach integrates data from terrestrial laser scanning (3D point clouds and meshes), along with panoramic and thermal images, into a unified virtual model. Additionally, the methodology incorporates several post-processing stages designed to enhance the user experience in visualizing both the building and its associated damage. The methodology was tested on the Medieval Templar Church of Vera Cruz in Segovia, utilizing a combination of visible and infrared data, along with manually prepared damage maps. The project results demonstrate that the use of a hybrid digital model—combining 3D point clouds, polygonal meshes, and panoramic images—is highly effective for real-time rendering, providing detailed visualization while maintaining adaptability for mobile devices with limited computational power.

Underwater point cloud transmission framework: hybrid encoder implementation based on CNN and transformer

Abstract In underwater multi-robot systems, 3D point cloud data generated by sonar and depth sensors facilitates the execution of more complex collaborative tasks among robots, which partly rely on efficient data transmission. In this work, we propose a hybrid encoder framework based on convolutional neural network and Transformer for underwater point cloud transmission, aimed at dealing with large-scale point cloud data. Our encoder allows setting lower compression rate on regions or objects of interest for semantic point clouds, preserving crucial information in the point cloud. For underwater acoustic communication, we employ orthogonal frequency division multiplexing combined with deep joint source-channel coding for transmission to enhance the system’s error-resilience. Compared to state-of-the-art methods in the simulation experiments, our end-to-end framework achieves considerable compression performance while eliminating certain cliff and leveling effects, also demonstrating robustness even with changing channels.

Point-MPP: Point Cloud Self-Supervised Learning From Masked Position Prediction.

Masked autoencoding has gained momentum for improving fine-tuning performance in many downstream tasks. However, it tends to focus on low-level reconstruction details, lacking high-level semantics and resulting in weak transfer capability. This article presents a novel jigsaw puzzle solver inspired by the idea that predicting the positions of disordered point cloud patches provides more semantic information, similar to how children learn by solving jigsaw puzzles. Our method adopts the mask-then-predict paradigm, erasing the positions of selected point patches rather than their contents. We first partition input point clouds into irregular patches and randomly erase the positions of some patches. Then, a Transformer-based model is used to learn high-level semantic features and regress the positions of the masked patches. This approach forces the model to focus on learning transfer-robust semantics while paying less attention to low-level details. To tie the predictions within the encoding space, we further introduce a consistency constraint on their latent representations to encourage the encoded features to contain more semantic cues. We demonstrate that a standard Transformer backbone with our pretraining scheme can capture discriminative point cloud semantic information. Furthermore, extensive experiments indicate that our method outperforms the previous best competitor across six popular downstream vision tasks, achieving new state-of-the-art performance. Codes will be available at https://git.openi.org.cn/OpenPointCloud/Point-MPP.

Point‐AGM : Attention Guided Masked Auto‐Encoder for Joint Self‐supervised Learning on Point Clouds

AbstractMasked point modeling (MPM) has gained considerable attention in self‐supervised learning for 3D point clouds. While existing self‐supervised methods have progressed in learning from point clouds, we aim to address their limitation of capturing high‐level semantics through our novel attention‐guided masking framework, Point‐AGM. Our approach introduces an attention‐guided masking mechanism that selectively masks low‐attended regions, enabling the model to concentrate on reconstructing more critical areas and addressing the limitations of random and block masking strategies. Furthermore, we exploit the inherent advantages of the teacher‐student network to enable cross‐view contrastive learning on augmented dual‐view point clouds, enforcing consistency between complete and partially masked views of the same 3D shape in the feature space. This unified framework leverages the complementary strengths of masked point modeling, attention‐guided masking, and contrastive learning for robust representation learning. Extensive experiments have shown the effectiveness of our approach and its well‐transferable performance across various downstream tasks. Specifically, our model achieves an accuracy of 94.12% on ModelNet40 and 87.16% on the PB‐T50‐RS setting of ScanObjectNN, outperforming other self‐supervised learning methods.

Robust localization of shear connectors in accelerated bridge construction with neural radiance field

Accelerated bridge construction (ABC) demands precise alignment of prefabricated members to prevent assembly failure. Conventional methods struggle to localize shear connectors from point cloud data (PCD) generated by structure-from-motion due to its sparsity. This paper introduces a robust method for shear connector localization using PCD generated by a neural radiance field and a three-step narrowing-down algorithm. The PCD exhibits densely populated points for small connectors, allowing the algorithm to pinpoint their locations accurately. The method successfully identified all 72 shear connectors in a mock-up prefabricated girder, with an average error of 10 mm, demonstrating its potential for assessing constructability in ABC projects. Future research may integrate deep learning-based segmentation techniques to enhance efficiency and adaptability in complex geometries and non-standard bridge designs.

DSGI‐Net: Density‐based Selective Grouping Point Cloud Learning Network for Indoor Scene

AbstractIndoor scene point clouds exhibit diverse distributions and varying levels of sparsity, characterized by more intricate geometry and occlusion compared to outdoor scenes or individual objects. Despite recent advancements in 3D point cloud analysis introducing various network architectures, there remains a lack of frameworks tailored to the unique attributes of indoor scenarios. To address this, we propose DSGI‐Net, a novel indoor scene point cloud learning network that can be integrated into existing models. The key innovation of this work is selectively grouping more informative neighbor points in sparse regions and promoting semantic consistency of the local area where different instances are in proximity but belong to distinct categories. Furthermore, our method encodes both semantic and spatial relationships between points in local regions to reduce the loss of local geometric details. Extensive experiments on the ScanNetv2, SUN RGB‐D, and S3DIS indoor scene benchmarks demonstrate that our method is straightforward yet effective.

PCLC‐Net: Point Cloud Completion in Arbitrary Poses with Learnable Canonical Space

AbstractRecovering the complete structure from partial point clouds in arbitrary poses is challenging. Recently, many efforts have been made to address this problem by developing SO(3)‐equivariant completion networks or aligning the partial point clouds with a predefined canonical space before completion. However, these approaches are limited to random rotations only or demand costly pose annotation for model training. In this paper, we present a novel Network for Point cloud Completion with Learnable Canonical space (PCLC‐Net) to reduce the need for pose annotations and extract SE(3)‐invariant geometry features to improve the completion quality in arbitrary poses. Without pose annotations, our PCLC‐Net utilizes self‐supervised pose estimation to align the input partial point clouds to a canonical space that is learnable for an object category and subsequently performs shape completion in the learned canonical space. Our PCLC‐Net can complete partial point clouds with arbitrary SE(3) poses without requiring pose annotations for supervision. Our PCLC‐Net achieves state‐of‐the‐art results on shape completion with arbitrary SE(3) poses on both synthetic and real scanned data. To the best of our knowledge, our method is the first to achieve shape completion in arbitrary poses without pose annotations during network training.

Quality Evaluation of Sizeable Surveying-Industry-Produced Terrestrial Laser Scanning Point Clouds That Facilitate Building Information Modeling—A Case Study of Seven Point Clouds

Quality Evaluation of Sizeable Surveying-Industry-Produced Terrestrial Laser Scanning Point Clouds That Facilitate Building Information Modeling—A Case Study of Seven Point Clouds

Extracting terrain elevation information in front of the vehicle based on vehicle-mounted LiDAR in dynamic environments

Abstract Point cloud maps constructed using 3D LiDAR, are widely used for robot navigation and localization. Few studies have utilized point cloud maps to extract terrain elevationinformation in front of a vehicle, which can be used as active suspension inputs to reduce vehicle bumps. In addition, the trajectories of dynamic objects in point cloud maps and global navigation satellite system (GNSS) data loss can affect the extraction of elevation information. To solve these problems, this paper proposes a framework for extracting terrain elevation information in front of the vehicle based on vehicle-mounted LiDAR in dynamic environments. The framework consists of two modules: point cloud map construction and vehicle front terrain elevation information extraction. In the point cloud map construction module, a system for simultaneous localization and mapping (SLAM) is proposed, which is capable of building point cloud maps without GNSS. Furthermore, a dynamic descriptor-based dynamic object filtering algorithm is proposed which is applied to SLAM. Therefore, the SLAM system overcomes the influence of dynamic objects on vehicle position and attitude estimation, and there are no trajectories of dynamic objects in the point cloud maps built by the system. In the vehicle front terrain elevation information extraction module, the unscented Kalman filter is utilized to predict the vehicle position at the next moment. Based on the geometric features of the tire-ground contact area, the terrain elevation information of the tire contact area at the predicted position on the point cloud map is extracted. Experiments show that the algorithm in this paper overcomes the effect of dynamic objects and builds a vehicle point cloud map without dynamic objects under GNSS data loss, which improves the accuracy of the extraction of terrain elevation information in front of the vehicle.

Semi-Supervised Online Continual Learning for 3D Object Detection in Mobile Robotics

Continual learning addresses the challenge of acquiring and retaining knowledge over time across multiple tasks and environments. Previous research primarily focuses on offline settings where models learn through increasing tasks from samples paired with ground truth annotations. In this work, we focus on an unsolved, challenging, yet practical scenario, specifically, the semi-supervised online continual learning in autonomous driving and mobile robotics. In our settings, models are tasked with learning new distributions from streaming unlabeled samples and performing 3D object detection as soon as the LiDAR point cloud arrives. Additionally, we conducted experiments on both the KITTI dataset, our newly built IUSL dataset and Canadian Adverse Driving Conditions (CADC) Dataset. The results indicate that our method achieves a balance between rapid adaptation and knowledge retention, showcasing its effectiveness in the dynamic and complex environment of autonomous driving and mobile robotics. The developed ROS packages and IUSL dataset will be publicly available at: https://github.com/npu-ius-lab/OCL3D.

A new technique mapping submerged beachrocks using low-altitude UAV photogrammetry, the Altınova region, northern coast of the Sea of Marmara (NW Türkiye)

High-resolution aerial imagery captured from low altitudes enables the detailed reconstruction of the geomorphological features of submerged beachrocks and the quantification of their topographic complexity. These coastal deposits serve as vital indicators for estimating past sea-level positions and deformation, contributing to our understanding of climate and tectonic processes across various temporal and spatial scales. This study focuses on submerged beachrocks identified in the nearshore coastal area of Tekirdağ city (Altınova), and the existing knowledge regarding such geological formations is limited.Situated in the tectonically active western Marmara region, the coastal zone of The Tekirdağ-Altınova is influenced by the North Anatolian Fault Zone (NAFZ), which has significantly shaped the coastline over time. Utilizing unmanned aerial vehicle (UAV) data, we successfully isolated submerged beachrocks from other coastal deposits, identifying them at depths of 2 m below current sea level and extending approximately 5 km along the coast. This identification was facilitated by integrating high-resolution aerial imagery with morphological analysis techniques, specifically employing structure-from-motion photogrammetry to generate a dense point cloud for bathymetric mapping.The utilization of cost-effective UAV imagery facilitated the efficient monitoring of beachrocks. Geographic information systems (GIS) and the TerraceM application were employed to analyze the high-resolution bathymetry data (with a 5 cm resolution), enabling the precise estimation of shoreline angles and associated errors. These shoreline angles, which correspond to the past sea levels high stand, were mapped using swath profiles oriented perpendicular to the isobaths. Our findings reveal that the majority of submerged beachrocks exhibit shoreline angles between ∼ −0.7 m and −1.1 m. This study presents innovative methodologies for mapping the height and spatial distribution of beachrocks, as well as for reliably estimating reliable uplift rates in the nearshore area of Tekirdağ-Altınova.

PCM-BESO: a reformative multi-constraints topology optimization method using point cloud modeling oriented to additive manufacturing

PCM-BESO: a reformative multi-constraints topology optimization method using point cloud modeling oriented to additive manufacturing

Edge-Cloud Remote Sensing Data-Based Plant Disease Detection Using Deep Neural Networks with Transfer Learning.

The identification and control of plant diseases have become increasingly complex as agricultural lands expand globally. Traditional manual methods of monitoring and diagnosing diseases are not feasible for large-scale farms. The complexity is further heightened by the heterogeneity of data types collected through remote sensing methods, such as images, videos, and sensor readings, which need to be processed in real-time. This paper introduces a novel EdgeCloud Remote Sensing architecture that utilizes Deep Neural Networks (DNNs) with Transfer Learning to enhance the detection of plant diseases using remote sensing data. The proposed system employs a Fuzzy Deep Convolutional Neural Network (FCDCNN) to process multimodal data collected from both edge nodes and satellite point clouds. Transfer learning allows the sharing of model weights between cloud and edge nodes, thus optimizing performance without requiring frequent retraining. Simulations show that the proposed system achieves a 98% detection accuracy and reduces processing time by 25% compared to existing methods. By distributing tasks between edge and cloud resources, the system is able to process large datasets effectively and improve disease detection performance on vast farmlands.

Adversarial Unsupervised Domain Adaptation for 3D Semantic Segmentation with 2D Image Fusion of Dense Depth

AbstractUnsupervised domain adaptation (UDA) is increasingly used for 3D point cloud semantic segmentation tasks due to its ability to address the issue of missing labels for new domains. However, most existing unsupervised domain adaptation methods focus only on uni‐modal data and are rarely applied to multi‐modal data. Therefore, we propose a cross‐modal UDA on multi‐modal datasets that contain 3D point clouds and 2D images for 3D Semantic Segmentation. Specifically, we first propose a Dual discriminator‐based Domain Adaptation (Dd‐bDA) module to enhance the adaptability of different domains. Second, given that the robustness of depth information to domain shifts can provide more details for semantic segmentation, we further employ a Dense depth Feature Fusion (DdFF) module to extract image features with rich depth cues. We evaluate our model in four unsupervised domain adaptation scenarios, i.e., dataset‐to‐dataset (A2D2 → SemanticKITTI), Day‐to‐Night, country‐to‐country (USA → Singapore), and synthetic‐to‐real (VirtualKITTI → SemanticKITTI). In all settings, the experimental results achieve significant improvements and surpass state‐of‐the‐art models.

Massive Point Cloud Processing for Efficient Construction Quality Inspection and Control

The construction of large-scale civil infrastructures requires massive spatiotemporal data to support the management and control of scheduling, quality control, and safety monitoring. Existing artificial-intelligence-based data processing algorithms rely heavily on experienced engineers to adjust the parameters of data processing, which is inefficient and time-consuming when dealing with huge datasets. Limited studies have compared the performance of different algorithms on a unified dataset. This study proposes a framework and evaluation system for comparing different data processing policies for processing huge spatiotemporal data in construction quality control. The proposed method compares the combination of multiple types of algorithms involved in the processing of massive point cloud data. The performance of data processing strategies is evaluated through this framework, and the optimal point cloud processing strategies are explored based on registration accuracy and data fidelity. Results show that a reasonable choice of combinations of point cloud sampling, filtering, and registration algorithms can significantly improve the efficiency of point cloud data processing and satisfy engineering demands for data accuracy and completeness. The proposed method can be applied to the civil engineering problem of processing a large amount of point cloud data and selecting the optimal processing method.