Search

Background Purpose Methods Results Conclusions Retrospective studies indicate that radiation damage to left anterior descending coronary artery (LAD) may be critical for late‐stage radiation‐induced cardiac morbidity. Developing a method that accurately depicts LAD motion and perform dose assessment is crucial.To construct a generalized cardiac surface motion model for LAD dose assessment in left breast cancer radiotherapy.Cine MRI of 25 cases were divided into training and testing sets for model construction, and five external cases were gathered for generalization validation. Motion prediction from average intensity projection images (AIP) surface point cloud to that of each phase was realized by mapping the relationship between datum points and corresponding points with statistical shape modeling (SSM). Root mean square error (RMSE) for predicted corresponding points and Euclidean distance (ED) for predicted surface point cloud were used to assess model's accuracy. LAD dose assessment for 10 left breast cancer radiotherapy cases was perform by model application.The RMSE in testing cases and external cases were 0.209 ± 0.020 mm to 0.841 ± 0.074 mm and 0.895 ± 0.093 mm to 1.912 ± 0.138 mm, respectively; while the ED were 1.399 ± 0.029 mm to 1.658 ± 0.100 mm, 1.571 ± 0.080 mm to 1.779 ± 0.104 mm, respectively, proving the generalized model's high accuracy. The volume of LAD characterizing motion range (WPLAD) (2.392 ± 0.639 cm3) was approximately twice that of LAD from superimposed images (SPLAD) (0.927 ± 0.326 cm3) with p < 0.05, and the former's Dmax (3582.06 ± 575.92 cGy) was significantly larger than latter's (3222.71 ± 665.37 cGy) (p < 0.05). While WPLAD's Dmean (1408.06 ± 413.06 cGy) was slightly smaller than that of SPLAD (1504.15 ± 448.03 cGy), the difference did not reach statistical significance (p > 0.05). WPLAD's V20 (23.42% ± 16.62%) was less than SPLAD's (29.18% ± 21.07%) with p < 0.05, but their comparison in V30 and V40 did not yield statistically significant results. It implies the conventional LAD dose assessment ignores motion impact and may not be justified.The generalized cardiac surface motion model informs LAD dose accurate assessment in left breast cancer radiotherapy. [ABSTRACT FROM AUTHOR]

Point clouds in the real world are often sparse and incomplete. Point cloud completion aims to restore incomplete point clouds into meaningful shapes. In recent years, point cloud completion has attracted the interest of many researchers. In most existing methods, the efficiency of completion is generally ignored in favor of producing meaningful shapes with adequate details. This paper proposes a fast point completion network (FPCN). FPCN is mainly composed of a multi-scale attention encoder (MSAE) and a structural refinement (SR) module. MSAE first obtains multi-scale geometric information by extracting incomplete inputs at different resolutions. After that, MSAE fuses multi-scale geometric information through cross-attention mechanisms. Compared with existing mainstream encoders, MSAE can extract rich geometric information from input point clouds with low complexity. The SR module aims to extract local information from the coarse point clouds to guide the process of extending points. Furthermore, the process of extending points is achieved by a replication strategy. Compared to existing folding-based decoders, the SR module can produce fine point clouds with more local details. Compared to existing transformer-based decoders, the SR module has a lower calculation price by employing a replication strategy to generate high-resolution point clouds. In conclusion, FPCN can restore partial point clouds into meaningful shapes efficiently, and the outcomes of completion contain sufficient details. Extensive experiments on various datasets demonstrate the performance and efficiency of the FPCN in point cloud completion. Source code is available at https://github.com/doldolOuO/FPCN. [ABSTRACT FROM AUTHOR]

The rapid growth on the amount of generated 3D data, particularly in the form of Light Detection And Ranging (LiDAR) point clouds (PCs), poses very significant challenges in terms of data storage, transmission, and processing. Point cloud (PC) representation of 3D visual information has shown to be a very flexible format with many applications ranging from multimedia immersive communication to machine vision tasks in the robotics and autonomous driving domains. In this paper, we investigate the performance of four reference 3D object detection techniques, when the input PCs are compressed with varying levels of degradation. Compression is performed using two MPEG standard coders based on 2D projections and octree decomposition, as well as two coding methods based on Deep Learning (DL). For the DL coding methods, we used a Joint Photographic Experts Group (JPEG) reference PC coder, that we adapted to accept LiDAR PCs in both Cartesian and cylindrical coordinate systems. The detection performance of the four reference 3D object detection methods was evaluated using both pre-trained models and models specifically trained using degraded PCs reconstructed from compressed representations. It is shown that LiDAR PCs can be compressed down to 6 bits per point with no significant degradation on the object detection precision. Furthermore, employing specifically trained detection models improves the detection capabilities even at compression rates as low as 2 bits per point. These results show that LiDAR PCs can be coded to enable efficient storage and transmission, without significant object detection performance loss. [ABSTRACT FROM AUTHOR]

Cloud organization impacts the radiative effects and precipitation patterns of the cloud field. Deviating from randomness, clouds exhibit either clustering or a regular grid structure, characterized by the spacing between clouds and the cloud size distribution. The two measures are coupled but do not fully define each other. Here, we present the deviation from randomness of the cloud‐ and void‐chord length distributions as a measure for both factors. We introduce the LvL representation and an associated 2D score that allow for unambiguously quantifying departure from well‐defined baseline randomness in cloud spacing and sizes. This approach demonstrates sensitivity and robustness in classifying cloud field organization types. Its delicate sensitivity unravels the temporal evolution of a single cloud field, providing novel insights into the underlying governing processes. Plain Language Summary: The spatial arrangement of clouds within a cloud field plays a significant role in influencing the field's radiative effects, cloud properties, and precipitation patterns. Thus, cloud organization, determined by both cloud spacing and sizes, is a critical aspect to consider. Here, we introduce a novel 2D method, termed the LvL space, that assesses cloud field organization by integrating these key factors. This approach utilizes a unified mathematical metric and reference standard to measure both cloud spacing and cloud sizes. Its sensitivity and robustness are evident in accurately classifying different types of cloud field organization and tracking their evolution over time. Such a metric captures intricate dynamic processes and contributes to a deeper understanding of cloud pattern formation and evolution. Through better quantifying cloud organization, the LvL can potentially enhance our understanding of cloud feedback mechanisms. Key Points: Cloud field organization is expressed as a tendency toward regularity or clusteringThe cloud‐chord Length versus void‐chord Length (LvL) space is introduced as a 2D cloud field organization metricThe LvL representation measures organization in terms of spacing between clouds and the cloud size distribution [ABSTRACT FROM AUTHOR]

The recent rise in interest in point clouds as an imaging modality has motivated standardization groups such as JPEG and MPEG to launch activities aiming at developing compression standards for point clouds. Lossy compression usually introduces visual artifacts that negatively impact the perceived quality of media, which can only be reliably measured through subjective visual quality assessment experiments. While MPEG standards have been subjectively evaluated in previous studies on multiple occasions, no work has yet assessed the performance of the recent JPEG Pleno standard in comparison to them. In this study, a comprehensive performance evaluation of JPEG and MPEG standards for point cloud compression is conducted. The impact of different configuration parameters on the performance of the codecs is first analyzed with the help of objective quality metrics. The results from this analysis are used to define three rate allocation strategies for each codec, which are employed to compress a set of point clouds at four target rates. The set of distorted point clouds is then subjectively evaluated following two subjective quality assessment protocols. Finally, the obtained results are used to compare the performance of these compression standards and draw insights about best coding practices. [ABSTRACT FROM AUTHOR]

The recent adoption of deep learning-based models for the processing and coding of multimedia signals has brought noticeable gains in performance, which have established deep learning-based solutions as the uncontested state-of-the-art both for computer vision tasks, targeting machine consumption, as well as, more recently, coding applications, targeting human visualization. Traditionally, applications requiring both coding and computer vision processing require first decoding the bitstream and then applying the computer vision methods to the decompressed multimedia signals. However, the adoption of deep learning-based solutions enables the use of compressed domain computer vision processing, with gains in performance and computational complexity over the decompressed domain approach. For point clouds (PCs), these gains have been demonstrated in the single available compressed domain computer vision processing solution, named Compressed Domain PC Classifier, which processes JPEG Pleno PC coding (PCC) compressed streams using a PC classifier largely compatible with the state-of-the-art spatial domain PointGrid classifier. However, the available Compressed Domain PC Classifier presents strong limitations by imposing a single, specific input size which is associated to specific JPEG Pleno PCC configurations; this limits the compression performance as these configurations are not ideal for all PCs due to their different characteristics, notably density. To overcome these limitations, this paper proposes the first Adaptive Compressed Domain PC Classifier solution which includes a novel adaptive bridge model that allows to process the JPEG Pleno PCC encoded bit streams using different coding configurations, now maximizing the compression efficiency. Experimental results show that the novel Adaptive Compressed Domain PC Classifier allows JPEG PCC to achieve better compression performance by not imposing a single, specific coding configuration for all PCs, regardless of its different characteristics. Moreover, the added adaptability power can achieve slightly better PC classification performance than the previous Compressed Domain PC Classifier and largely better PC classification performance (and lower number of weights) than the PointGrid PC classifier working in the decompressed domain. [ABSTRACT FROM AUTHOR]

AbstractA novel method has been developed for accurately quantifying arsenic species, including As(III), As(V), and total inorganic arsenic, in drinking water. The technique combines ultraviolet-visible spectrophotometry with cloud point extraction (UV/CPE), ensuring high sensitivity and selectivity. The methodology relies on complex formation between As(III) and Pyronin B in the presence of tartaric acid. The resulting complex is efficiently extracted into the surfactant-rich phase consisting of 5.0% (v/v) Triton X-114. Under optimized conditions, a linear calibration relationship from 3 to 500 µg/L is obtained. The method offers low detection and quantification limits of 1.04 and 3.48 µg/L, respectively, with a corresponding relative standard deviation below 5% for 11 replicates. Furthermore, spiked samples demonstrated excellent recovery values from 95.1% to 102.3%. The accuracy was verified by the analysis of the standard reference material SRM 1643e (trace elements in water), revealing no significant differences at the 95% confidence level. The approach was successfully utilized for the quantification of As(III), As(V), and total inorganic arsenic in commercial and domestic drinking water. [ABSTRACT FROM AUTHOR]

With the rapid development of intelligent connected vehicles, there is an increasing demand for hardware facilities and onboard systems of driver assistance systems. Currently, most vehicles are constrained by the hardware resources of onboard systems, which mainly process single-task and single-sensor data. This poses a significant challenge in achieving complex panoramic driving perception technology. While the panoramic driving perception algorithm YOLOP has achieved outstanding performance in multi-task processing, it suffers from poor adaptability of feature map pooling operations and loss of details during downsampling. To address these issues, this paper proposes a panoramic driving perception fusion algorithm based on multi-task learning. The model training involves the introduction of different loss functions and a series of processing steps for lidar point cloud data. Subsequently, the perception information from lidar and vision sensors is fused to achieve synchronized processing of multi-task and multi-sensor data, thereby effectively improving the performance and reliability of the panoramic driving perception system. To evaluate the performance of the proposed algorithm in multi-task processing, the BDD100K dataset is used. The results demonstrate that, compared to the YOLOP model, the multi-task learning network performs better in lane detection, drivable area detection, and vehicle detection tasks. Specifically, the lane detection accuracy improves by 11.6%, the mean Intersection over Union (mIoU) for drivable area detection increases by 2.1%, and the mean Average Precision at 50% IoU (mAP50) for vehicle detection improves by 3.7%. [ABSTRACT FROM AUTHOR]

Recently, multi-modal 3D object detection techniques based on point clouds and images have received increasing attention. However, existing methods for multi-modal feature fusion are often relatively singular, and single point cloud representation methods also have some limitations. For example, voxelization may result in the loss of fine-grained information, while 2D images lack depth information, which can restrict the accuracy of detection. Therefore, in this work, we propose a novel method for multi-modal 3D object detection based on point cloud diversity representation and dual feature fusion, PCDR-DFF, to improve the prediction accuracy of 3D object detection. Firstly, point clouds are projected to the image coordinate system and extract multi-level features of the point cloud corresponding to the image using a 2D backbone network. Then, the point clouds are jointly characterized using graphs and pillars, and the 3D features of the point clouds are extracted using graph neural networks and residual connectivity. Finally, a dual feature fusion method is designed to improve the accuracy of detection with the help of a well-designed multi-point fusion model and multi-feature fusion mechanism embedded with a spare 3D-U Net. Extensive experiments on the KITTI dataset demonstrate the effectiveness and competitiveness of our proposed models in comparison with other methods. [ABSTRACT FROM AUTHOR]

The current mature Simultaneous Localisation And Mapping (SLAM) algorithms, when applied to tunnel scenarios with point cloud degradation and poor lighting conditions, often lead to a sharp increase in the estimated attitude error of the unmanned aerial vehicle (UAV), or even prevent the UAV from moving autonomously due to severe feature degradation. To address the above problems, the authors propose a SLAM algorithm based on factor graph optimisation, Iterative Closest Point and Normal Distributions Transform algorithms. A front‐end point cloud registration module and a back‐end construction algorithm based on filtering and graph optimisation are designed. To verify the effectiveness of the proposed algorithm, experiments are conducted on KITTI dataset and real tunnel scenes, and compared with LiDAR Odometry and Mapping (LOAM) and lightweight and ground optimised (LeGO)‐LOAM algorithms. The results show that the average processing time of the proposed method is about 75 ms, which can meet the real‐time requirements of autonomous aerial vehicles. Compared with LOAM and LeGO‐LOAM in the real tunnel experiment, the proposed method shows the tunnel 3D map construction. [ABSTRACT FROM AUTHOR]

Clamping complex and irregular preformed blanks can be challenging and time-consuming, especially when it comes to precise workpiece locating and allocating machining allowance to curved surfaces. The proposed method aims to improve the efficiency and accuracy of the clamping process. This paper presents a method for complex workpiece locating and machining allowance allocation based on scanned 3D point cloud. An edge detection method is introduced for the workpiece point cloud to preserve its essential features, enabling precise global alignment between the scanned point cloud and CAD models. Additionally, a method is proposed for extracting multiple machining areas from the point cloud, calculating allowances, and optimizing the process coordination to allocate machining allowance effectively. The experimental results show that the machining allowance range is reduced by 77.71 % after compensation, and the average machining allowance of the worst machining area increases by up to 29.69 % compared to the iterative closest point method. • A two-step registration method based on edge point clouds is introduced. • The point cloud of the workpiece in the machining area is extracted. • A machining allowance allocation based on BFGS method is presented. • Our method enhances machining allowances by 22.9 % compared to the iterative closest point method. [ABSTRACT FROM AUTHOR]

3D scanners have great potential to boost the efficiency of geometric inspection if their traceability is established by identifying measurement bias and uncertainty. This article introduces a digital twin for a structured-light 3D scanner that provides these two essential measures in a real-time manner. The error quantification starts from iterated scans taken from a CMM-calibrated ball-plate artifact at eight different configurations. The differences between the erroneous scan readings of the artifact's distance features and the corresponding calibrated values in the CMM set give a spatial distribution of the scanner's error. Then, three polynomial functions map the Cartesian coordinates of the scan set onto their counterparts from the CMM set. In this error model, a least-square approach determines the polynomial coefficients. Evaluating the error model for a given point cloud returns a vector field of volumetric errors, which is then followed by error corrections and then GD&T calculations. The uncertainty propagation is pursued through the three steps of model development, error map evaluation, and GD&T analysis. The Monte-Carlo estimations benchmark and validate the GUM framework for the uncertainty associated with the outputs of each step. Experimental verifications of the proposed methodology suggest that the error correction improves the mean and the standard deviation of measurement bias by 50% and 27%, respectively. The uncertainty map provides the coverage probabilities of 62%, 88%, and 96% for the coverage factors of 1, 2, and 3, while the expected theoretical levels of confidence are 68%, 95%, and 100%. • The digital twin provides error maps for scan data as a field of error vectors. • Corrections reduced the error average from −10 to −5 μm and error dispersion by 27%. • Ellipsoidal uncertainty regions grant coverage probabilities close to expected levels. • GUM framework reliably estimates the uncertainty of digital twin outputs. • Fast uncertainty analysis allows using digital twin in real-time in-process metrology. [ABSTRACT FROM AUTHOR]

The cutting edge radius is a significant parameter of a micromachining tool. When it is not sufficiently sharp, ploughing, which affects the whole machining process and workpiece quality, will occur. It is then essential to be able to estimate the value of the cutting edge radius accurately. In this paper, a three-dimensional strategy that can be used to measure the microturning tool edge radii is presented. The strategy is based on robust cylinder fitting that is applied to a 3D point cloud of the tool. It is implemented in C++ with Open Computer Vision and Point Cloud Library. It was validated using a virtual point cloud, resulting in errors of 0.42% and 1.11% without noise and with noise, respectively. Additionally, uncertainties of 0. 045 μ m and 0. 082 μ m were obtained. It was successfully applied to six microturning inserts: three unused tools and three used tools. The point clouds were obtained with two different 3D surface reconstruction techniques, focus variation with a photon microscope and a multi-view stereo with a scanning electron microscope. The obtained results were more coherent, i.e., they were less dispersed; for example, in non-used tools, the range was [ 3. 11 μ m– 3. 90 μ m] and for the conventional circle fitting the range was [ 2. 62 μ m– 4. 38 μ m]. The traditional method is indirect: the 3D point cloud is sliced into 2D point clouds (profiles) fitted with circles. This 3D-2D process might result in errors. The proposed method is a direct 3D approach with no slicing step. • Importance of tool edge radii in the overall quality of micromachining. • Development of a method for accurate measurement of micro turning tool edge radii from 3D point cloud. • A method based on robust 3D fitting that avoids the 3D-2D process, which is a potential source of errors. • A semi-automatic and practical tool edge radii measurement method. [ABSTRACT FROM AUTHOR]

Three-dimensional point cloud evaluation is used in photogrammetry to validate and assess the accuracy of data acquisition in order to generate various three-dimensional products. This paper determines the optimal accuracy and correctness of a 3D point cloud produced by a low-cost spherical camera in comparison to the 3D point cloud produced by laser scanner. The fisheye images were captured from a chessboard using a spherical camera, which was calibrated using the commercial Agisoft Metashape software (version 2.1). For this purpose, the results of different calibration methods are compared. In order to achieve data acquisition, multiple images were captured from the inside area of our case study structure (an underpass in Wiesbaden, Germany) in different configurations with the aim of optimal network design for camera location and orientation. The relative orientation was generated from multiple images obtained by removing the point cloud noise. For assessment purposes, the same scene was captured with a laser scanner to generate a metric comparison between the correspondence point cloud and the spherical one. The geometric features of both point clouds were analyzed for a complete geometric quality assessment. In conclusion, this study highlights the promising capabilities of low-cost spherical cameras for capturing and generating high-quality 3D point clouds by conducting a thorough analysis of the geometric features and accuracy assessments of the absolute and relative orientations of the generated clouds. This research demonstrated the applicability of spherical camera-based photogrammetry to challenging structures, such as underpasses with limited space for data acquisition, and achieved a 0.34 RMS re-projection error in the relative orientation step and a ground control point accuracy of nearly 1 mm. Compared to the laser scanner point cloud, the spherical point cloud reached an average distance of 0.05 m and acceptable geometric consistency. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel, vision-transformer-based end-to-end pose estimation method, LidPose, for real-time human skeleton estimation in non-repetitive circular scanning (NRCS) lidar point clouds. Building on the ViTPose architecture, we introduce novel adaptations to address the unique properties of NRCS lidars, namely, the sparsity and unusual rosetta-like scanning pattern. The proposed method addresses a common issue of NRCS lidar-based perception, namely, the sparsity of the measurement, which needs balancing between the spatial and temporal resolution of the recorded data for efficient analysis of various phenomena. LidPose utilizes foreground and background segmentation techniques for the NRCS lidar sensor to select a region of interest (RoI), making LidPose a complete end-to-end approach to moving pedestrian detection and skeleton fitting from raw NRCS lidar measurement sequences captured by a static sensor for surveillance scenarios. To evaluate the method, we have created a novel, real-world, multi-modal dataset, containing camera images and lidar point clouds from a Livox Avia sensor, with annotated 2D and 3D human skeleton ground truth. [ABSTRACT FROM AUTHOR]

Pose estimation of metal parts plays a vital role in industrial grasping areas. It is challenging to obtain complete point clouds of metal parts because of their reflective properties. This study introduces an approach for recovering the 6D pose of CAD-known metal parts from images captured by a single RGB camera. The proposed strategy only requires RGB images without depth information. The core idea of the proposed method is to use multiple views to estimate the metal parts' pose. First, the pose of metal parts is estimated in the first view. Second, ray casting is employed to simulate additional views with the corresponding status of the metal parts, enabling the calculation of the camera's next best viewpoint. The camera, mounted on a robotic arm, is then moved to this calculated position. Third, this study integrates the known camera transformations with the poses estimated from different viewpoints to refine the final scene. The results of this work demonstrate that the proposed method effectively estimates the pose of shiny metal parts. [ABSTRACT FROM AUTHOR]

Aircraft engine systems are composed of numerous pipelines. It is crucial to regularly inspect these pipelines to detect any damages or failures that could potentially lead to serious accidents. The inspection process typically involves capturing complete 3D point clouds of the pipelines using 3D scanning techniques from multiple viewpoints. To obtain a complete and accurate representation of the aircraft pipeline system, it is necessary to register and align the individual point clouds acquired from different views. However, the structures of aircraft pipelines often appear similar from different viewpoints, and the scanning process is prone to occlusions, resulting in incomplete point cloud data. The occlusions pose a challenge for existing registration methods, as they can lead to missing or wrong correspondences. To this end, we present a novel registration framework specifically designed for aircraft pipeline scenes. The proposed framework consists of two main steps. First, we extract the point feature structure of the pipeline axis by leveraging the cylindrical characteristics observed between adjacent blocks. Then, we design a new 3D descriptor called PL-PPFs (Point Line–Point Pair Features), which combines information from both the pipeline features and the engine assembly line features within the aircraft pipeline point cloud. By incorporating these relevant features, our descriptor enables accurate identification of the structure of the engine's piping system. Experimental results demonstrate the effectiveness of our approach on aircraft engine pipeline point cloud data. [ABSTRACT FROM AUTHOR]

This study investigates panorama photogrammetry (PPh) as a potential method to collect massive 3D information for long-range deformation monitoring. Particularly, this study focuses on areas with measuring restrictions, i.e., inaccessible objects and distances above 0.6 km. Under these particular conditions, geodetic techniques based on Electromagnetic Distance Meters (EDMs) or Total Stations (TSs) can provide coordinates with a precision better than 1 cm, but only for a limited number of discrete points. For mass capture, Terrestrial Laser Scanning (TLS) is normally the preferred solution, but long-range instruments are expensive, and drawbacks such as weak return signals and non-automatic target recognition appear. As an alternative, PPh is investigated in the well-controlled area of La Muela in Cortes de Pallas, where images are automatically captured from geodetic pillars using a GigaPan device, processed, and then rigorously compared to TLS point clouds. The results obtained after integrating both techniques into a high-accuracy geodetic reference frame show that PPh and TLS provide similar precision to within approximately 4 cm in the range of 0.6–1.0 km. Therefore, considering cost-effectiveness and ease of use, the proposed method can be considered a low-cost alternative to TLS for long-range deformation monitoring. [ABSTRACT FROM AUTHOR]

To enhance the accuracy of detecting objects in front of intelligent vehicles in urban road scenarios, this paper proposes a dual-layer voxel feature fusion augmentation network (DL-VFFA). It aims to address the issue of objects misrecognition caused by local occlusion or limited field of view for targets. The network employs a point cloud voxelization architecture, utilizing the Mahalanobis distance to associate similar point clouds within neighborhood voxel units. It integrates local and global information through weight sharing to extract boundary point information within each voxel unit. The relative position encoding of voxel features is computed using an improved attention Gaussian deviation matrix in point cloud space to focus on the relative positions of different voxel sequences within channels. During the fusion of point cloud and image features, learnable weight parameters are designed to decouple fine-grained regions, enabling two-layer feature fusion from voxel to voxel and from point cloud to image. Extensive experiments on the KITTI dataset demonstrate the significant performance of DL-VFFA. Compared to the baseline network Second, DL-VFFA performs better in medium- and high-difficulty scenarios. Furthermore, compared to the voxel fusion module in MVX-Net, the voxel feature fusion results in this paper are more accurate, effectively capturing fine-grained object features post-voxelization. Through ablative experiments, we conducted in-depth analyses of the three voxel fusion modules in DL-VFFA to enhance the performance of the baseline detector and achieved superior results. [ABSTRACT FROM AUTHOR]

Current point cloud registration methods predominantly focus on extracting geometric information from point clouds. In certain scenarios, i.e., when the target objects to be registered contain a large number of repetitive planar structures, the point-only based methods struggle to extract distinctive features from the similar structures, which greatly limits the accuracy of registration. Moreover, the deep learning-based approaches achieve commendable results on public datasets, but they face challenges in generalizing to unseen few-shot datasets with significant domain differences from the training data, and that is especially common in industrial applications where samples are generally scarce. Moreover, existing registration methods can achieve high accuracy on complete point clouds. However, for partial point cloud registration, many methods are incapable of accurately identifying correspondences, making it challenging to estimate precise rigid transformations. This paper introduces a domain-adaptive multimodal feature fusion method for partial point cloud registration in an unsupervised manner, named DAMF-Net, that significantly addresses registration challenges in scenes dominated by repetitive planar structures, and it can generalize well-trained networks on public datasets to unseen few-shot datasets. Specifically, we first introduce a point-guided two-stage multimodal feature fusion module that utilizes the geometric information contained in point clouds to guide the texture information in images for preliminary and supplementary feature fusion. Secondly, we incorporate a gradient-inverse domain-aware module to construct a domain classifier in a generative adversarial manner, weakening the feature extractor's ability to distinguish between source and target domain samples, thereby achieving generalization across different domains. Experiments on a public dataset and our industrial components dataset demonstrate that our method improves the registration accuracy in specific scenarios with numerous repetitive planar structures and achieves high accuracy on unseen few-shot datasets, compared with the results of state-of-the-art traditional and deep learning-based point cloud registration methods. [ABSTRACT FROM AUTHOR]

Buildings are significant components of digital cities, and their precise extraction is essential for the three-dimensional modeling of cities. However, it is difficult to accurately extract building features effectively in complex scenes, especially where trees and buildings are tightly adhered. This paper proposes a highly accurate building point cloud extraction method based solely on the geometric information of points in two stages. The coarsely extracted building point cloud in the first stage is iteratively refined with the help of mask polygons and the region growing algorithm in the second stage. To enhance accuracy, this paper combines the Alpha Shape algorithm with the neighborhood expansion method to generate mask polygons, which help fill in missing boundary points caused by the region growing algorithm. In addition, this paper performs mask extraction on the original points rather than non-ground points to solve the problem of incorrect identification of facade points near the ground using the cloth simulation filtering algorithm. The proposed method has shown excellent extraction accuracy on the Urban-LiDAR and Vaihingen datasets. Specifically, the proposed method outperforms the PointNet network by 20.73% in precision for roof extraction of the Vaihingen dataset and achieves comparable performance with the state-of-the-art HDL-JME-GGO network. Additionally, the proposed method demonstrated high accuracy in extracting building points, even in scenes where buildings were closely adjacent to trees. [ABSTRACT FROM AUTHOR]

Transformer has recently become widely adopted in point cloud registration. Nevertheless, Transformer is unsuitable for handling dense point clouds due to resource constraints and the sheer volume of data. We propose a method for directly regressing the rigid relative transformation of dense point cloud pairs. Specifically, we divide the dense point clouds into blocks according to the down-sampled superpoints. During training, we randomly select point cloud blocks with varying overlap ratios, and during testing, we introduce the overlap-aware Rotation-Invariant Geometric Transformer Cross-Encoder (RIG-Transformer), which predicts superpoints situated within the common area of the point cloud pairs. The dense points corresponding to the superpoints are inputted into the Transformer Cross-Encoder to estimate their correspondences. Through the fusion of our RIG-Transformer and Transformer Cross-Encoder, we propose Transformer-to-Transformer Regression (TTReg), which leverages dense point clouds from overlapping regions for both training and testing phases, calculating the relative transformation of the dense points by using the predicted correspondences without random sample consensus (RANSAC). We have evaluated our method on challenging benchmark datasets, including 3DMatch, 3DLoMatch, ModelNet, and ModelLoNet, demonstrating up to a 7.2 % improvement in registration recall. The improvements are attributed to our RIG-Transformer module and regression mechanism, which makes the features of superpoints more discriminative. [ABSTRACT FROM AUTHOR]

Existing point cloud feature learning networks often learn high-semantic point features representing the global context by incorporating sampling, neighborhood grouping, neighborhood-wise feature learning, and feature aggregation. However, this process may result in a substantial loss of granular information due to the sampling operation and the widely-used max pooling feature aggregation, which neglects information from non-maximum point features. Consequently, the resulting high-semantic point features could be insufficient to represent the local context, hindering the network's ability to distinguish fine shapes. To address this problem, we propose PointStack, a novel point cloud feature learning network that utilizes multi-resolution feature learning and learnable pooling (LP). PointStack aggregates point features of various resolutions across multiple layers to capture both high-semantic and high-resolution information. The LP function calculates the weighted sum of multi-resolution point features through an attention mechanism with learnable queries, enabling the extraction of all available information. As a result, PointStack can effectively represent both global and local contexts, allowing the network to comprehend both the global structure and local shape details. PointStack outperforms various existing feature learning networks for shape classification and part segmentation on the ScanObjectNN and ShapeNetPart datasets, achieving 87.2% overall accuracy and instance mIoU. [ABSTRACT FROM AUTHOR]

Accompanying climate change and sea level rise, tidal marsh mortality in coastal wetlands has been globally observed that urges the documentation of high-resolution, 3D marsh inventory to assist resilience planning. Drone Lidar has proven useful in extracting the fine-scale bare earth terrain and canopy height. Beyond that, this study performed marsh biomass mapping from drone Lidar point cloud in a S. alterniflora-dominated estuary on the Southeast U.S. coast. Three point classes (ground, low-veg, and high-veg) were classified via point cloud deep learning. Considering only vegetation points in the vertical profile, a profile area-weighted height (HPA) was extracted at a grid size of 50 cm × 50 cm. Vegetation point densities were also extracted at each grid. Adopting the plant-level allometric equations of stem biomass from long-term S. alterniflora surveys, a Lidar biomass index (Lidar_BI) was built to represent the relative quantity of marsh biomass in a range of [0, 1] across the estuary. Compared with the clipped dry biomass samples, it achieved a comparable and slightly better performance (R2 = 0.5) than the commonly applied spectral index approaches (R2 = 0.4) in the same marsh field. This study indicates the feasibility of the drone Lidar point cloud for marsh biomass mapping. More advantageously, the drone Lidar approach yields information on plant community architecture, such as canopy height and plant density distributions, which are key factors in evaluating marsh habitat and its ecological services. [ABSTRACT FROM AUTHOR]

Distribution-to-distribution point cloud registration algorithms are fast and interpretable and perform well in unstructured environments. Unfortunately, existing strategies for predicting the solution error for these methods are overly optimistic, particularly in regions containing large or extended physical objects. In this paper, we introduce the iterative closest ellipsoidal transform (ICET), a novel three-dimensional (3D) lidar scan-matching algorithm that re-envisions the normal distributions transform (NDT) in order to provide robust accuracy prediction from first principles. Like NDT, ICET subdivides a lidar scan into voxels in order to analyze complex scenes by considering many smaller local point distributions; however, ICET assesses the voxel distribution to distinguish random noise from deterministic structure. ICET then uses a weighted least-squares formulation to incorporate this noise/structure distinction while computing a localization solution and predicting the solution-error covariance. To demonstrate the reasonableness of our accuracy predictions, we verify 3D ICET in three lidar tests involving real-world automotive data, high-fidelity simulated trajectories, and simulated corner-case scenes. For each test, ICET consistently performs scan matching with sub-centimeter accuracy. With this level of accuracy, combined with the fact that the algorithm is fully interpretable, this algorithm is well suited for safety-critical transportation applications. Code is available at https://github.com/mcdermatt/ICET. [ABSTRACT FROM AUTHOR]

The fractal dimension of a surface allows its degree of roughness to be characterized quantitatively. However, limited effort is attempted to calculate the fractal dimension of surfaces computed from precisely known atomic coordinates from computational biomolecular and nanomaterial studies. This work proposes methods to estimate the fractal dimension of the surface of any 3D object composed of spheres, by representing the surface as either a voxelized point cloud or a mathematically exact surface, and computing its box‐counting dimension. Sphractal is published as a Python package that provides these functionalities, and its utility is demonstrated on a set of simulated palladium nanoparticle data. [ABSTRACT FROM AUTHOR]

Currently, the digitization of environment objects (vegetation, terrain, architectural structures, etc.) in the form of point clouds is actively being developed. The integration of such digitized objects into virtual environment systems allows the quality of the modeled environment to be improved, but requires efficient methods and algorithms for real-time visualization of large point volumes. In this paper the solution of this task on modern multicore GPUs with support of hardware-accelerated ray tracing is researched. A modified method is proposed where the original unordered point cloud is split up into point groups whose visualization is effectively parallelized on ray tracing cores. The paper describes an algorithm for constructing such groups using swapping arrays of point indices, which works faster than alternative solutions based on linked lists, and also has lower memory overhead. The proposed method and algorithm were implemented in point cloud visualization software complex and approbated on a number of digitized environment objects. The results of the approbation confirmed the efficiency of proposed solutions as well as their applicability for virtual environment systems, video simulators, geoinformation systems, virtual laboratories, etc. [ABSTRACT FROM AUTHOR]

This paper presents an approach to 3D model reconstruction from point cloud data using modern neural network architectures. The method is based on PointNet++ and Transformer. PointNet++ plays a key role, providing efficient feature extraction and encoding of complex geometries in 3D scenes. This is achieved by recursively applying PointNet++ to nested partitions of the input point set in a metric space. Convex decomposition, which is an important step in the proposed approach, transforms complex 3D objects into sets of simpler convex shapes. This facilitates data processing and makes the reconstruction process more manageable. Then, Transformer trains the model on the extracted features, which enables the generation of high-quality reconstructions. It should be noted that Transformer is used only to determine positions of the walls and detect object boundaries. This combination of technologies allows us to achieve high accuracy of 3D model reconstruction. The main idea of the method is to segment the point cloud into small fragments, which are then reconstructed as polygon meshes. To restore missing points in point cloud data, a method based on the L1-median algorithm and local features of the point cloud is used. This approach can adapt to different geometric structures and correct topological connectivity errors. The proposed method is compared with several modern approaches, demonstrating its potential in various fields, including architecture, engineering, digitalization of cultural heritage, as well as augmented and mixed reality systems. This confirms its wide applicability and great perspectives for further development. [ABSTRACT FROM AUTHOR]

Accurate and efficient registration of unmanned aerial vehicle light detection and ranging (UAV‐lidar) and terrestrial lidar (T‐lidar) data is crucial for forest structure parameter extraction. This study proposes a novel method based on a starburst pattern for the automatic registration of UAV‐lidar and T‐lidar data in forest scenes. It employs density‐based spatial clustering of applications with noise (DBSCAN) for individual tree identification, constructs starburst patterns separately from both lidar sources, and utilises polar coordinate rotation and matching to achieve coarse registration. Fine registration is achieved using the iterative closest point (ICP) algorithm. Experimental results demonstrate that the starburst‐pattern‐based method achieves the desired registration accuracy (average coarse registration error of 0.157 m). Further optimisation with ICP yields slight improvements with an average fine registration error of 0.149 m. Remarkably, the proposed method is insensitive to the individual tree detection number when exceeding 10, and the tree position error has minimal impact on registration accuracy. Furthermore, our proposed method outperforms two existing methods in T‐lidar and UAV‐lidar registration over forest environments. [ABSTRACT FROM AUTHOR]

Most existing point cloud segmentation methods ignore directional information when extracting neighbourhood features. Those methods are ineffective in extracting point cloud neighbourhood features because the point cloud data is not uniformly distributed and is restricted by the size of the convolution kernel. Therefore, we take into account both multiple directions and hole sampling (MDHS). First, we execute spherically sparse sampling with directional encoding in the surrounding domain for every point inside the data to increase the local perceptual field. The data input is the basic geometric features. We use the graph convolutional neural network to conduct the maximisation of point cloud characteristics in a local neighbourhood. Then the more representative local point features are automatically weighted and fused by an attention pooling layer. Finally, spatial attention is added to increase the connection between remote points, and then the segmentation accuracy is improved. Experimental results show that the OA and mIoU are 1.3% and 4.0% higher than the method PointWeb and 0.6% and 0.7% higher than the baseline method RandLA‐Net. For the indoor point cloud semantic segmentation, the segmentation effect of the proposed network is superior to other methods. [ABSTRACT FROM AUTHOR]

Diffusion models have been successfully applied to point cloud generation tasks recently. The main notion is using a forward process to progressively add noises into point clouds and then use a reverse process to generate point clouds by denoising these noises. However, since point cloud data is high-dimensional and exhibits complex structures, it is challenging to adequately capture the surface distribution of point clouds. Moreover, point cloud generation methods often resort to sampling methods and local operations to extract features, which inevitably ignores the global structures and overall shapes of point clouds. To address these limitations, we propose a latent diffusion model based on Transformers for point cloud generation. Instead of directly building a diffusion process based on the points, we first propose a latent compressor to convert original point clouds into a set of latent tokens before feeding them into diffusion models. Converting point clouds as latent tokens not only improves expressiveness, but also exhibits better flexibility since they can adapt to various downstream tasks. We carefully design the latent compressor based on an attention-based auto-encoder architecture to capture global structures in point clouds. Then, we propose to use transformers as the backbones of the latent diffusion module to maintain global structures. The powerful feature extraction ability of transformers guarantees the high quality and smoothness of generated point clouds. Experiments show that our method achieves superior performance in both unconditional generation on ShapeNet and multi-modal point cloud completion on ShapeNet-ViPC. Our code and samples are publicly available at https://github.com/Negai-98/LDT. [ABSTRACT FROM AUTHOR]

Hall thrusters are electric propulsion devices that are widely used in modern spaceflight. To obtain the critical corrosion data effectively and accurately during long-life tests of Hall thrusters, this paper proposes an automated corrosion measurement method based on three-dimensional point cloud technology. This method uses binocular structured light scanning method to obtain surface point cloud data. The point cloud topology relationship of these disordered data is also established by KD-tree and radius filtering. The base plane is determined according to the average of the outer circle plane in the discharge chamber, and the original point cloud data is sliced transversely and longitudinally. The point cloud of section data is extracted and the corrosion width data is obtained according to the round hole feature extraction and center of circle calculation. The corrosion angle is calculated according to the angle between the straight line and the normal of the section. The proposed method has been verified and the results show that the overall error accuracy is within 60 μm, which meets the requirements for automatic measurement of Hall thruster corrosion. It is a real and effective method to obtain the critical corrosion data during long-life tests of Hall thrusters. [ABSTRACT FROM AUTHOR]

Simultaneous localization and mapping (SLAM) and 3D reconstruction have numerous applications for indoor ground wheeled robots such as floor sweeping and food delivery. To advance research in leveraging semantic information and multi-sensor data to enhance the performances of SLAM and 3D reconstruction in complex indoor scenes, we propose a novel and complex indoor dataset named CID-SIMS, where semantic annotated RGBD images, inertial measurement unit (IMU) measurements, and wheel odometer data are provided from a ground wheeled robot viewpoint. The dataset consists of 22 challenging sequences captured in nine different scenes including office building and apartment environments. Notably, our dataset achieves two significant breakthroughs. Firstly, semantic information and multi-sensor data are provided meanwhile for the first time. Secondly, GeoSLAM is utilized for the first time to generate ground truth trajectories and 3D point clouds within two-centimeter accuracy. With spatial-temporal synchronous ground truth trajectories and 3D point clouds, our dataset is capable of evaluating SLAM and 3D reconstruction algorithms in a unified global coordinate system. We evaluate state-of-the-art SLAM and 3D reconstruction approaches on our dataset, demonstrating that our benchmark is applicable. The dataset is publicly available on https://cid-sims.github.io. [ABSTRACT FROM AUTHOR]

The registration performance determines the widespread indoor application of 3D models acquired by depth sensors. Many advanced registration methods lack comprehensive feature aggregation and poor generalization capabilities, which improves the mismatching ratio. Here, a dual graph network is proposed by incorporating irregular shape factors to make point cloud features more expressive. At first, we transform point cloud sets into the stellar graph within the local neighbourhood of each point. The deep feature and shape factor of each point are combined in the directional‐connected irregular projection space. Subsequently, the combined features are modelled as the second graph. By the attention mechanism computation, feature information is continuously aggregated with intra‐graph and inter‐graph. Finally, a loss function is utilized to confirm point correspondence and perform the registration through singular value decomposition. Extensive experiments validate that the proposed point cloud registration method achieves state‐of‐the‐art performance. [ABSTRACT FROM AUTHOR]

In recent years, contrastive language‐image pre‐training (CLIP) has gained popularity for processing 2D data. However, the application of cross‐modal transferable learning to 3D data remains a relatively unexplored area. In addition, high‐quality, labelled point cloud data for Mechanical, Electrical, and Plumbing (MEP) scenarios are in short supply. To address this issue, the authors introduce a novel object detection system that employs 3D point clouds and 2D camera images, as well as text descriptions as input, using image‐text matching knowledge to guide dense detection models for 3D point clouds in MEP environments. Specifically, the authors put forth the proposition of a language‐guided point cloud modelling (PCM) module, which leverages the shared image weights inherent in the CLIP backbone. This is done with the aim of generating pertinent category information for the target, thereby augmenting the efficacy of 3D point cloud target detection. After sufficient experiments, the proposed point cloud detection system with the PCM module is proven to have a comparable performance with current state‐of‐the‐art networks. The approach has 5.64% and 2.9% improvement in KITTI and SUN‐RGBD, respectively. In addition, the same good detection results are obtained in their proposed MEP scene dataset. [ABSTRACT FROM AUTHOR]

Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is commonly used in weakly-supervised learning, for its point cloud counterpart with multiple data-specific augmentations, which has not been well studied. We observe that the straightforward way of applying consistency constraints to weakly-supervised point cloud segmentation has two major limitations: noisy pseudo labels due to the conventional confidence-based selection and insufficient consistency constraints due to discarding unreliable pseudo labels. Therefore, we propose a novel Reliability-Adaptive Consistency Network (RAC-Net) to use both prediction confidence and model uncertainty to measure the reliability of pseudo labels and apply consistency training on all unlabeled points while with different consistency constraints for different points based on the reliability of corresponding pseudo labels. Experimental results on the S3DIS and ScanNet-v2 benchmark datasets show that our model achieves superior performance in weakly-supervised point cloud segmentation. The code will be released publicly at https://github.com/wu-zhonghua/RAC-Net. [ABSTRACT FROM AUTHOR]

To tackle the issue of lack of semantic consistency between ground and non-ground points, as well as the damage to the integrity of terrain boundary information during network downsampling, we developed a Semantic Consistency-Convolutional Neural Network (SC-CNN) to improve the precision of point cloud filtering under complex terrain conditions. The novel aspects include: (1) farthest point sampling (FPS) with slope constraints, which enhances terrain contour preservation through adaptive subblock partitioning and slope-based sampling; (2) intra-class feature enhancement via copula correlation and attention mechanisms, improving the network's ability to distinguish between ground and non-ground points by focusing on intra-class feature consistency and inter-class differences; and (3) filter error correction using copula correlation and confidence intervals. refining filtering accuracy by adjusting for negatively correlated point sets. Tested on the ISPRS and 3D Vaihingen datasets, SC-CNN notably outperformed existing methods, reducing the mean total error (MT.E) by 0.17% and 1.93%, respectively, thereby significantly enhancing point-cloud filtering accuracy under complex terrain conditions. [ABSTRACT FROM AUTHOR]

LiDAR-based place recognition is crucial for Simultaneous Localization and Mapping (SLAM) and autonomous driving. However, existing methods face challenges in achieving rotation invariance and are hindered by a large number of parameters and complex data preprocessing steps, such as ground point removal and extensive down-sampling. These limitations hinder their practical implementation in complex real-world scenarios. To address these challenges, we propose LR-Net, a lightweight and rotation-invariant place recognition network designed to handle large-scale raw point clouds. LR-Net tackles rotation invariance by efficiently capturing sparse local neighborhood information and generating rotation-invariant features through the analysis of spatial distribution and positional information within the local region. Furthermore, we enhance the network's feature perception by incorporating residual MLP structures to encode multi-level local region features, and integrating dual-attentional weighting blocks to emphasize important regions and features. Lastly, the Generalized-Mean pooling structure is utilized to aggregate the global descriptor, enabling efficient point cloud retrieval. Meanwhile, we introduce PRmate, an independent sub-network that effectively optimizes retrieval results by analyzing the descriptor similarity and location distribution of the top 25 matching candidates from the place recognition network. We extensively evaluated the proposed methods on four large-scale datasets, including both standardized point cloud scenes (Oxford RobotCar dataset and NUS In-house dataset) and raw point cloud scenes (MulRan dataset and Kitti odometry dataset). The experimental results demonstrate that LR-Net effectively attains rotation-invariance in place recognition and achieves state-of-the-art accuracy with a lightweight model size of 0.4 M parameters. Additionally, LR-Net eliminates the need for data preprocessing, as it can directly process raw point cloud data for stable place recognition and exhibits robustness against variations in point density and noise intensity, enhancing its suitability for challenging scenarios. Moreover, PRmate is compatible with all existing point cloud-based place recognition methods and improves their performance. These advantages make LR-Net and PRmate highly suitable for robotic applications that rely on LiDAR-based place recognition. Our code is publicly available on the project website (https://github.com/zhzhang023/LR-Net). [ABSTRACT FROM AUTHOR]

With the artificial intelligence technology development boom, large language models are demonstrating their potential in comprehension and creativity. Large language models such as GPT-4 and Gemini have been able to powerfully study for various professional-level exams. However, as a language model itself, its powerful comprehension can only be reflected in text sequences. Currently, although videos can be generated through the connection between 3D point clouds and large language models, there is currently no prompt project that directly interacts with one-dimensional through attribute calculation results. The point cloud data is also rich in information that can support various tasks of urban construction. For scene-level point cloud data, there has been a lot of research done on semantic segmentation, target detection, and other tasks. However, it is usually difficult to provide direct help to scene construction from the perception results. This paper presents a method for applying large language models to urban ecological construction by combining the results of 3D point cloud semantic segmentation. The objective is to integrate the prior knowledge and creative capabilities of Large Language Models (LLMs) within urban development with the outcomes derived from point cloud semantic segmentation results. This integration aims to establish an interactive point cloud intelligent analysis system, tailored for aiding decision-making processes in urban ecological civilization construction, thus presenting innovative perspectives for the advancement of smart city development. • Chat3D, a large model for interactive large 3D scene understanding to urban ecological construction based on prompt engineering. • Utilizing thought chains, different levels of prompts input improve the completeness and credibility of report generation. • Experiments show that Chat3D accurately predicts urban environmental indices, assesses urban ecological risks, and benefits sustainable urban development. [ABSTRACT FROM AUTHOR]

To ensure the safety of tunnel construction, it is necessary to accurately and timely measure the deformation of the shotcrete liner during the management of the construction process. The light detection and ranging (LiDAR) technique, known as the reality reproduction technology, provides a new solution for deformation measurement. However, the nonsmooth defects of shotcrete liner and the scattered noise points caused by the nearby dust, as well as a large number of nontunnel structures such as pipes, construction machinery, and vehicles in the obtained tunnel point cloud datasets, hinder the application of point clouds in deformation measurement of shotcrete liner. In this paper, a ring simulation sampling (RSS) method for automatic sampling and deformation measurement of shotcrete liner using the multiepoch LiDAR point clouds is proposed. This method constructs the virtual ring according to shape of the tunnel cross section and emits the rays from the ring to the center of each tunnel cross section. The length difference of the rays arriving at the outer wall of the multiepoch tunnel point clouds is calculated to achieve the analysis of overall and local deformations of the shotcrete liner. The shotcrete liner point clouds generated by the manual modeling and terrestrial laser scanning are tested to validate the effectiveness of the method in extracting the deformation of shotcrete liner. Compared with the conventional total station monitoring, the mean absolute deviation and root mean square error are 1.39 and 1.93 mm, respectively, which indicates that the RSS method could be effectively applied to the deformation measurement of tunnel shotcrete liner. Deformation measurement of tunnel shotcrete liner is crucial to safety of tunnel construction and implementation of dynamic parameter design. This study recommends the light detection and ranging (LiDAR) technique. The main work of this paper is to determine whether the tunnel shotcrete lining has been deformed as a whole or locally by comparing the obtained multiepoch high-precision 3D point clouds. Furthermore, the authors propose a method for automatic sampling and deformation measurement of shotcrete liner using the multiepoch LiDAR point clouds. Compared with conventional deformation measurement methods (i.e., the total station and fiber optics) that capture deformation information from a limited number of monitoring points, LiDAR technology enables the high-precision, omnidirectional, and noncontact acquisition of spatial data within tunnels. This serves as a complementary and enhanced tool to tunnel safety monitoring techniques and methodologies. In addition, the adoption of the method proposed in this paper facilitates the quality check of shotcrete liner, including thickness assessment and smoothness detection. [ABSTRACT FROM AUTHOR]

Autonomous robot-based orchard operations will become an alternative solution in the field of precision agriculture. One of the keys to robotic work is to achieve autonomous navigation that is as accurate as possible to ensure the most accurate working effect. In this work, we propose an orchard path fitting and navigation method based on the fusion of improved A-Star algorithm and Support Vector Machine Regression (SVR) to meet the requirements of autonomous navigation crawler platform for autonomous navigation in orchard environment and ensure accuracy. In this study, the actual speed and turning radius of the left and right tracks of the crawler platform were collected under 5 different slopes and 400 sets of different theoretical speed combinations of left and right tracks through the design nesting test, and the motion model of the crawler platform was constructed based on SVR. Orchard point cloud data were obtained by 3D solid-state LiDAR, and the improved A-star algorithm was used to fit the navigation path and calculate the turning curvature radius. Taking this curvature radius as the optimal navigation target value, the motion model predicts the optimal theoretical speed of left and right tracks, which is used as a reference for autonomous navigation. The comparison experiment of autonomous navigation was carried out in two modes: traditional and improved A-Star algorithm. The results show that the average values of the maximum lateral and longitudinal deviation of the improved automatic navigation method between orchards row are 6.90 cm and 9.88 cm, respectively. Compared with the method combined with the traditional A-Star algorithm and SVR, the values were 8.94 cm and 10.88 cm and were optimized by 29.57% and 10.12%, respectively. The autonomous navigation method proposed in this paper can meet the needs of orchards rows autonomous navigation, and can be widely applied to different orchard site environments (slope, ground obstacles, bad surface conditions), which can provide reference for the production practices of unmanned orchards. [ABSTRACT FROM AUTHOR]

Varimax factor rotations, while popular among practitioners in psychology and statistics since being introduced by Kaiser (1958) , have historically been viewed with skepticism and suspicion by some theoreticians and mathematical statisticians. Now, work by Rohe & Zeng (2023) provides new, fundamental insight: varimax rotations provably perform statistical estimation in certain classes of latent variable models when paired with spectral-based matrix truncations for dimensionality reduction. We build on this new-found understanding of varimax rotations by developing further connections to network analysis and spectral methods rooted in entrywise matrix perturbation analysis. Concretely, this paper establishes the asymptotic multivariate normality of vectors in varimax-transformed Euclidean point clouds that represent low-dimensional node embeddings in certain latent space random graph models. We address related concepts including network sparsity, data denoising and the role of matrix rank in latent variable parameterizations. Collectively, these findings, at the confluence of classical and contemporary multivariate analysis, reinforce methodology and inference procedures grounded in matrix factorization-based techniques. Numerical examples illustrate our findings and supplement our discussion. [ABSTRACT FROM AUTHOR]

In modern manufacturing processes, ensuring the precision of 3D profiles of products is crucial. Nonetheless, achieving this accuracy is challenging due to the complex interactions between process inputs and the data structure of the 3D profile data. Our solution, a 3D profile-based control framework, addresses this challenge by actively adapting and controlling the manufacturing process to enhance 3D shape accuracy. 3D profile scans represent the ultimate measure of desired part quality. Therefore, utilizing them as the system responses for control purposes yields the most direct and effective feedback. We leverage recent advancements from Koopman operator theory to create an effective model-based control strategy. Initially, we estimate the process model by exploring the relationship between 3D profiles and heterogeneous process inputs. Then, we formulate an online model predictive control law. Challenges include dealing with unstructured, high-dimensional 3D point cloud data, capturing spatial and temporal structures, and integrating heterogeneous, high-dimensional process input data into the control model. To overcome these challenges, we introduce RETROFIT, a solution designed for the real-time control of time-dependent 3D point cloud profiles. Unlike traditional models, RETROFIT is not bound by linear assumptions and can handle unstructured 3D point cloud data directly. We demonstrate its effectiveness through a wire arc additive manufacturing case study, highlighting its potential to enhance 3D profile accuracy in manufacturing processes. [ABSTRACT FROM AUTHOR]

Analytical atomic spectrometry is a well-established and widely-used analytical technique for the sensitive detection of inorganic elements in diverse samples. Sample pretreatment methods are still a critical part of elemental analysis, which are usually used to remove interfering matrix components and preconcentrate the targets of interest before analysis. Significant advances in the development of sample separation and preconcentration techniques for elemental analysis have been made in recent years. This review focuses on the applications of sample separation and preconcentration techniques for analytical atomic spectrometry, including liquid phase (micro)extraction, cloud point extraction, solid phase (micro)extraction, microwave-assisted extraction, ultrasonic-assisted extraction, chemical vapor generation as well as hyphenated techniques. This review presents several applications of the above sample pretreatment methods in recent years, whose advantages and drawbacks were also discussed. [ABSTRACT FROM AUTHOR]

The integrity of road markings has a significant impact on driving safety, especially in the emerging automated driving scenario. Road markings are susceptible to wearing damage; it is therefore important for road agencies to examine and maintain markings periodically. This study presents a novel method for detection of road marking defect via an unmanned aerial vehicle (UAV)–laser radar (LiDAR) platform. The key idea is to evaluate the damage rate of road markings by point reflectivity. The method consists of three major steps: point cloud registration, marking segmentation, and defective marking detection. A high-intensity prioritized raster method is proposed to extract whole marking regions within defect area, and the damage rate of markings is defined to evaluate damage severity. Field test results show that the precision and recall of marking extraction are over 90%, and the precision of marking defect detection is over 93%. The failed detections were attributed to subjectivity of ground truth and neglect of small defects. [ABSTRACT FROM AUTHOR]

Traditionally, 3D segmentation tasks have operated in silos, focusing separately on semantic and instance segmentation. However, this disjointed approach lacks interoperability and fails to fully unleash the potential of a more integrated, multitask solution. To overcome this limitation, we introduce TUS-Net, an innovative transformer-based architecture meticulously crafted for both semantic and instance segmentation of point clouds. Our model introduces two pivotal advancements: First, it employs a superpoint-based pre-processing step that minimizes computational overhead without compromising on precision. Second, we leverage a dual-branch design within the transformer architecture, allowing it to adapt to the nuances of both segmentation tasks dynamically. Through extensive experimentation on the ScanNet dataset, our findings demonstrate that TUS-Net surpasses prevailing specialized models by a substantial margin and maintains remarkable computational efficiency. Notably, we achieve a 5.7% enhancement in mean Average Precision (mAP), for instance, segmentation, while striking an optimal balance between accuracy and runtime for semantic segmentation. These outcomes underscore the versatility, efficiency and high-performance attributes of TUS-Net, positioning it as an indispensable framework for robust 3D point cloud segmentation. [ABSTRACT FROM AUTHOR]

The measurement of contaminant elements, especially cadmium and lead, in biological samples typically requires time-consuming sample preparation methods that consume organic solvents that are harmful to humans and the environment. Therefore, a fast, easy, low-cost, and green method is necessary for their determination. In this work, for the first time, the cloud point extraction method has been transferred into a simple plastic syringe, resulting in the in-syringe cloud point extraction (IS-CPE) method. The effective parameters on IS-CPE were optimized using an experimental design approach, and the optimized method was used to measure cadmium and lead in human hair samples using inductively coupled plasma-optical emission spectroscopy (ICP OES). The IS-CPE method is based on forming a hydrophobic complex of lead and cadmium ions with 8-hydroxy-quinoline (8-HQ), followed by extraction into the micellar environment of the cationic surfactant cetyltrimethylammonium bromide (CTAB), and then injection of the extractive phase of the ethanol solvent into the instrument. Using factorial design in the parameter screening stage showed that the three parameters of ligand concentration, potassium iodide (KI) salt as a clouding agent, and pH are effective at the 95% confidence level. Then, the central composite design was used in the optimization stage to obtain the response level and identify the critical values. Under optimal conditions (pH = 4.5, 8-HQ = 0.002 mol L−1, and KI = 0.2 mol L−1), a linear range of 10.0–1500.0 and 200.0–15 000.0 μg L−1 was obtained for cadmium and lead, respectively. The detection limit of 3.0 and 62.0 μg L−1 was obtained for cadmium and lead, respectively. A relative standard deviation of 3.1–4.1% at concentration 0.3–0.7 mg L−1 and 5.0–5.8% at concentration 3.0–7.0 mg L−1, respectively, for cadmium and lead was obtained. The proposed IS-CPE method was successfully used to measure lead and cadmium ions in human hair samples. [ABSTRACT FROM AUTHOR]

The rocker arm plays a crucial role in an internal combustion engine's valve train system. Issues often arise when there are errors in the production of the rocker arm, such as the following: (1) misalignment of the rocker arm spindle hole and thread hole; and (2) bevel errors in the rocker arm spindle hole. This paper focuses on the development of a rocker arm chamfering and coaxial defect inspection system, which utilizes the RANSAC algorithm. The algorithm consists of five steps: (i) representing a 2D point cloud as a matrix with X and Y coordinates; (ii) detecting the number of circles present in the input point cloud; (iii) setting a tolerance threshold for the distance between the selected circle and other points, crucial for achieving high accuracy; (iv) specifying the maximum number of iterations to find the best model from the input points; (v) defining the maximum number of points that can belong to the same circle, considering point density and the anticipated circle's surface. The real-time inspection system is designed with a camera mounted on top of the box, and two LED arrays positioned around the box at suitable distances. Test results using a collected data set demonstrate the effectiveness and accuracy of the proposed method in detecting each type of error. In the experiments, the proposed method successfully detected all coaxial defect samples and achieved a detection rate of 95.1% for chamfer defect samples. [ABSTRACT FROM AUTHOR]

Heritage buildings represent history and act as vessels of human civilisation. The significance of these architectural phenomena increases as society increases, which renders their preservation and ethical use increasingly crucial. Hence, preserving heritage buildings is necessary for societal benefit. The accuracy of three-dimensional (3D) point cloud models of heritage buildings is important to their digital conservation. Traditional mapping methods typically require more time and human resources. Furthermore, the outcome is subject to measurement omissions, errors, and other issues, which are contrary to the protection of the object measured. The complex elements of ancient Chinese architecture render it challenging for traditional measuring techniques to accurately capture spatial structural information. The 3D laser scanning technology is a novel technology to obtain 3D data rapidly. In this paper, the Great Achievement Palace of the Confucian Temple in Yuci District, Jinzhong City, Shanxi Province, was used as an example to examine the application of 3D laser scanning technology to acquire point cloud models of heritage buildings. Field data collection for architectural heritage using 3D laser scanning technology requires measuring station setting analysis to ensure effect accuracy while considering the elements of target location and quantity. For the 3D point cloud model of the Great Achievement Palace, error analysis and accuracy assessment were conducted on the quality elements of alignment accuracy between scanning stations, point cloud model reliability, point cloud data noise condition, and whether the point cloud data were stratified. The findings demonstrated that the improved method quickly and accurately acquired 3D point cloud model data and obtained realistic spatial data models of the heritage building. [ABSTRACT FROM AUTHOR]