Local Point Cloud Research Articles

Boosting point cloud understanding through graph convolutional network with scale measurement and high-frequency enhancement

Graph-based methods have exhibited exceptional performance in point cloud understanding by capturing local geometric relationships. However, existing approaches often struggle to characterize the overall spatial scale of local graphs. In addition, they fail to capture the differences between nodes effectively, which is crucial for distinguishing different classes. This study introduces SM-HFEGCN, a novel graph convolutional network that addresses these limitations through two key innovations: scale measurement and high-frequency enhancement. First, we introduce a spatial scale feature derived from the diagonal vectors of the neighborhood, which serves as a unique graph-specific property related to the geometry and density of the local point cloud. This feature can characterize the overall spatial scale of the local point cloud. Second, we enhance the high-frequency information to capture node variations and integrate it with smoothed information to represent the differences and similarities between nodes simultaneously. Extensive experiments demonstrate the effectiveness of SM-HFEGCN in point cloud classification and segmentation tasks.

A Local Information Entropy-Based Point Cloud Simplification Algorithm for Hazardous Chemical Warehouses

A Local Information Entropy-Based Point Cloud Simplification Algorithm for Hazardous Chemical Warehouses

Localization in MR-based Indoor Navigation System using point cloud registration

Abstract. This paper addresses the pervasive challenge of localization within indoor navigation systems. Many existing systems grapple with this issue, relying on marker-based methods, Bluetooth beacon localization, and image processing. However, these solutions often necessitate the placement of predetermined markers within the environment, presenting limitations such as marker deterioration over time, spatial constraints, and associated costs. In response, we propose a novel point cloud registration-based approach. This method involves the creation of a comprehensive global point cloud representing the entire indoor environment, effectively serving as a three-dimensional virtual map. Concurrently, a mixed-reality device is utilized to generate a local point cloud specific to the device’s current location within the building. By aligning and registering the local cloud with the global counterpart, the device’s precise location within the virtual map can be determined. This approach enables seamless navigation within indoor environments without the reliance on physical markers, offering a versatile and cost-effective solution to the challenge of localization in indoor navigation systems. Finally, an error analysis was also done to test localization accuracy for different illumination conditions, demonstrating the effectiveness of this method.

PillarVTP: vehicle trajectory prediction method based on local point cloud aggregation and receptive field expansion

PillarVTP: vehicle trajectory prediction method based on local point cloud aggregation and receptive field expansion

Vibration Position Detection of Robot Arm Based on Feature Extraction of 3D Lidar.

In the process of construction, pouring and vibrating concrete on existing reinforced structures is a necessary process. This paper presents an automatic vibration position detecting method based on the feature extraction of 3D lidar point clouds. Compared with the image-based method, this method has better anti-interference performance to light with reduced computational consumption. First, lidar scans are used to capture multiple frames of local steel bar point clouds. Then, the clouds are stitched by Normal Distribution Transform (NDT) for preliminary matching and Iterative Closest Point (ICP) for fine-matching. The Graph-Based Optimization (g2o) method further refines the precision of the 3D registration. Afterwards, the 3D point clouds are projected into a 2D image. Finally, the locations of concrete vibration points and concrete casting points are discerned through point cloud and image processing technologies. Experiments demonstrate that the proposed automatic method outperforms ICP and NDT algorithms, reducing the mean square error (MSE) by 11.5% and 11.37%, respectively. The maximum discrepancies in identifying concrete vibration points and concrete casting points are 0.059 ± 0.031 m and 0.089 ± 0.0493 m, respectively, fulfilling the requirement for concrete vibration detection.

Automated body measurement of beef cattle based on keypoint detection and local point cloud clustering

Abstract Body size parameters of beef cattle are crucial for assessing growth status and breeding value. In actual farming environments, the various postures of beef cattle and complex backgrounds can affect the accuracy and stability of non-contact body measurement methods. Therefore, this paper proposes a novel method called the cattle body measurement method (CBMM), which combines keypoint detection with local point cloud clustering. First, a keypoint detection model based on YOLOv8-SimBiFPN is constructed. This model enhances the feature extraction and fusion capabilities of YOLOv8-pose by introducing SimAM and BiFPN into the backbone and neck networks, respectively, and realizes 2D keypoint detection for beef cattle in various postures. Second, a 3D keypoint-locating algorithm based on Density-based spatial clustering of applications with noise (DBSCAN) is proposed. This algorithm utilizes 2D keypoints, depth maps and camera parameters to generate local point clouds, which are then clustered using DBSCAN to segment cattle body point clouds, thereby relocating the 3D keypoints based on their positional features. Finally, body size parameters are calculated based on the 3D keypoints and distance formulae. In our experiment, the mean average precision (mAP@0.5) of YOLOv8-SimBiFPN reached 99.1% on an Angus beef cattle keypoint detection dataset. The mean absolute percentage errors for measuring beef cattle withers height, hip height, body depth, body length, and oblique body length using the CBMM were 4.37%, 4.96%, 6.47%, 4.84%, and 4.14%, respectively. In summary, our method can achieve non-contact body measurement for beef cattle in a free-moving state with high accuracy and stability.

Calibration Methods for Large-Scale and High-Precision Globalization of Local Point Cloud Data Based on iGPS.

The point cloud is one of the measurement results of local measurement and is widely used because of its high measurement accuracy, high data density, and low environmental impact. However, since point cloud data from a single measurement are generally small in spatial extent, it is necessary to accurately globalize the local point cloud to measure large components. In this paper, the method of using an iGPS (indoor Global Positioning System) as an external measurement device to realize high-accuracy globalization of local point cloud data is proposed. Two calibration models are also discussed for different application scenarios. Verification experiments prove that the average calibration errors of these two calibration models are 0.12 mm and 0.17 mm, respectively. The proposed method can maintain calibration precision in a large spatial range (about 10 m × 10 m × 5 m), which is of high value for engineering applications.

Collaborative Obstacle Detection for Dual USVs Using MGNN-DANet with Movable Virtual Nodes and Double Attention

To reduce missed detections in LiDAR-based obstacle detection, this paper proposes a dual unmanned surface vessels (USVs) obstacle detection method using the MGNN-DANet template matching framework. Firstly, point cloud templates for each USV are created, and a clustering algorithm extracts suspected targets from the point clouds captured by a single USV. Secondly, a graph neural network model based on the movable virtual nodes is designed, introducing a neighborhood distribution uniformity metric. This model enhances the local point cloud distribution features of the templates and suspected targets through a local sampling strategy. Furthermore, a feature matching model based on double attention is developed, employing self-attention to aggregate the features of the templates and cross-attention to evaluate the similarity between suspected targets and aggregated templates, thereby identifying and locating another USV within the targets detected by each USV. Finally, the deviation between the measured and true positions of one USV is used to correct the point clouds obtained by the other USV, and obstacle positions are annotated through dual-view point cloud clustering. Experimental results show that, compared to single USV detection methods, the proposed method reduces the missed detection rate of maritime obstacles by 7.88% to 14.69%.

LSGRNet: Local Spatial Latent Geometric Relation Learning Network for 3D point cloud semantic segmentation

In recent years, remarkable ability has been demonstrated by the Transformer model in capturing remote dependencies and improving point cloud segmentation performance. However, localized regions separated from conventional sampling architectures have resulted in the destruction of structural information of instances and a lack of exploration of potential geometric relationships between localized regions. To address this issue, a Local Spatial Latent Geometric Relation Learning Network (LSGRNet) is proposed in this paper, with the geometric properties of point clouds serving as a reference. Specifically, spatial transformation and gradient computation are performed on the local point cloud to uncover potential geometric relationships within the local neighborhood. Furthermore, a local relationship aggregator based on semantic and geometric relationships is constructed to enable the interaction of spatial geometric structure and information within the local neighborhood. Simultaneously, boundary interaction feature learning module is employed to learn the boundary information of the point cloud, aiming to better describe the local structure. The experimental results indicate that excellent segmentation performance is exhibited by the proposed LSGRNet in benchmark tests on the indoor datasets S3DIS and ScanNetV2, as well as the outdoor datasets SemanticKITTI and Semantic3D.

Target reconstruction and process parameter decision-making for bolt intelligent assembly based on robot and multi-camera

Bolt assembly is widely used in modern manufacturing. And with the development of industrial automation, there is a growing demand for automatic assembly. To form a fully automatic and highly intelligent system for bolt assembly, a novel strategy based robot and multi-camera is proposed. In this strategy, a high assurance components reconstruction scheme is designed, wherein the Mask R-CNN is used for the identification and segmentation of the workpiece, then the shape, size and pose of the workpiece are determined by the local point cloud data and its envelope using basic geometries. The results show that the accuracy of workpiece recognition exceeds 96 %, the maximum positioning accuracy of the hole is 0.334 mm based on multi-camera system. Based on the historical fastening process data, an improved artificial jellyfish search optimizer (AJSO) BP neural network is proposed to automatically determine the optimal values for the bolt fastening speed and torque. The BP neural network optimized by AJSO reduces the maximum prediction error of process parameters from 0.117 mm/s to 0.051 mm/s for speed and from 0.052 N·m to 0.027 N·m for torque. Finally, the feasibility of the proposed strategy is demonstrated by an experimental case, which used a dual robot unit for the bearing seat assembly.

Underwater Mapping and Optimization Based on Multibeam Echo Sounders

Multibeam echo sounders (MBESs) enable extensive underwater environment exploration. However, due to weak correlation between adjacent multibeam sonar data and difficulties in inter-frame feature matching, the resulting underwater mapping accuracy frequently falls short of the desired level. To address this issue, this study presents the development of a multibeam data processing system, which includes functionalities for sonar parameter configuration, data storage, and point cloud conversion. Subsequently, an Iterative Extended Kalman Filter (iEKF) algorithm is employed for odometry estimation, facilitating the initial construction of the point cloud map. To further enhance mapping accuracy, we utilize the Generalized Iterative Closest Point (GICP) algorithm for point cloud registration, effectively merging point cloud data collected at different times from the same location. Finally, real-world lake experiments demonstrate that our method achieves an Absolute Trajectory Error (ATE) of 15.10 m and an average local point cloud registration error of 0.97 m. Furthermore, we conduct measurements on various types of artificial targets. The experimental results indicate that the average location error of the targets calculated by our method is 4.62 m, which meets the accuracy requirements for underwater target exploration.

A Hybrid Improved SAC-IA with a KD-ICP Algorithm for Local Point Cloud Alignment Optimization

To overcome incomplete point cloud data obtained from laser scanners scanning complex surfaces, multi-viewpoint cloud data needs to be aligned for use. A hybrid improved SAC-IA with a KD-ICP algorithm is proposed for local point cloud alignment optimization. The scanned point cloud data is preprocessed with statistical filtering, as well as uniform down-sampling. The sampling consistency initial alignment (SAC-IA) algorithm is improved by introducing a dissimilarity vector for point cloud initial alignment. In addition, the iterative closest point (ICP) algorithm is improved by incorporating bidirectional KD-tree to form the KD-ICP algorithm for fine point cloud alignment. Finally, the algorithms are compared in terms of runtime and alignment accuracy. The implementation of the algorithms is based on the Visual Studio 2013 software configurating point cloud library environment for testing experiments and practical experiments. The overall alignment method can be 40%~50% faster in terms of running speed. The improved SAC-IA algorithm provides better transformed poses, combined with the KD-ICP algorithm to select the corresponding nearest neighbor pairs, which improves the accuracy, as well as the applicability of the alignment.

TriClsNet: Surface Reconstruction via Graph-based Triangle Classification

In this paper, we introduce TriClsNet, a novel learning-based network that reconstructs surfaces by reframing the triangle classification problem as a graph node classification problem. An improved graph-based triangle classification module is employed to aggregate information from neighboring triangles, effectively leveraging local neighborhood information and enhancing triangle classification accuracy. Additionally, a self-supervised learning branch is incorporated to predict point cloud normals, aiding our network in better learning local point cloud features. Furthermore, a new loss function is designed to guide our network in effective multi-task learning, encompassing both graph node classification and normal prediction. Comparative experimental results on ShapeNet demonstrate that our method can efficiently perform surface reconstruction, outperforming existing methods in the aspects of preserving surface details, reducing holes, and generalization.

Enhanced Path Planning and Obstacle Avoidance Based on High-Precision Mapping and Positioning.

High-precision positioning and multi-target detection have been proposed as key technologies for robotic path planning and obstacle avoidance. First, the Cartographer algorithm was used to generate high-quality maps. Then, the iterative nearest point (ICP) and the occupation probability algorithms were combined to scan and match the local point cloud, and the positions and attitudes of the robot were obtained. Furthermore, Sparse Matrix Pose Optimization was carried out to improve the positioning accuracy. The positioning accuracy of the robot in x and y directions was kept within 5 cm, the angle error was controlled within 2°, and the positioning time was reduced by 40%. An improved timing elastic band (TEB) algorithm was proposed to guide the robot to move safely and smoothly. A critical factor was introduced to adjust the distance between the waypoints and the obstacle, generating a safer trajectory, and increasing the constraint of acceleration and end speed; thus, smooth navigation of the robot to the target point was achieved. The experimental results showed that, in the case of multiple obstacles being present, the robot could choose the path with fewer obstacles, and the robot moved smoothly when facing turns and approaching the target point by reducing its overshoot. The proposed mapping, positioning, and improved TEB algorithms were effective for high-precision positioning and efficient multi-target detection.

Granular3D: Delving into multi-granularity 3D scene graph prediction

This paper addresses the significant challenges in 3D Semantic Scene Graph (3DSSG) prediction, essential for understanding complex 3D environments. Traditional approaches, primarily using PointNet and Graph Convolutional Networks, struggle with effectively extracting multi-grained features from intricate 3D scenes, largely due to a focus on global scene processing and single-scale feature extraction. To overcome these limitations, we introduce Granular3D, a novel approach that shifts the focus towards multi-granularity analysis by predicting relation triplets from specific sub-scenes. One key is the Adaptive Instance Enveloping Method (AIEM), which establishes an approximate envelope structure around irregular instances, providing shape-adaptive local point cloud sampling, thereby comprehensively covering the contextual environments of instances. Moreover, Granular3D incorporates a Hierarchical Dual-Stage Network (HDSN), which differentiates and processes features of instances and their pairs at varying scales, leading to a targeted prediction of instance categories and their relationships. To advance the perception of sub-scene in HDSN, we design a Gather Point Transformer structure (GaPT) that enables the combinatorial interaction of local information from multiple point cloud sets, achieving a more comprehensive local contextual feature extraction. Extensive evaluations on the challenging 3DSSG benchmark demonstrate that our methods provide substantial improvements, establishing a new state-of-the-art in 3DSSG prediction, boosting the top-50 triplet accuracy by ＋2.8%.

A novel model-based welding trajectory planning method for identical structural workpieces

Welding robots have been widely used with the development of manufacturing industry. At present, welding trajectory planning and programming of welding robots are performed separately for similar (structural) workpieces with different dimensions or deformations. Besides, the welding torch pose planning using conventional robot programming methods is time-consuming for workpieces with complex welding trajectories. To realize automatic planning of the welding torch pose for similar workpieces and improve the programming efficiency of welding robots, we propose a novel model-based welding trajectory planning method for welding robots. We create a basic model (point set) containing information on welding seam trajectory planning for similar workpieces. The welding seam trajectory extraction of similar workpieces is achieved by the non-rigid point set registration of the feature point cloud of similar workpieces with the basic model. Then, the welding torch pose planning is implemented by the geometric projection method of the local point cloud of the welding seam trajectory. Finally, the results of offline experiments and online experiments demonstrate the effectiveness of the proposed method.

A Novel Local-Global Graph Convolutional Method for Point Cloud Semantic Segmentation.

Although convolutional neural networks (CNNs) have shown good performance on grid data, they are limited in the semantic segmentation of irregular point clouds. This article proposes a novel and effective graph CNN framework, referred to as the local-global graph convolutional method (LGGCM), which can achieve short- and long-range dependencies on point clouds. The key to this framework is the design of local spatial attention convolution (LSA-Conv). The design includes two parts: generating a weighted adjacency matrix of the local graph composed of neighborhood points, and updating and aggregating the features of nodes to obtain the spatial geometric features of the local point cloud. In addition, a smooth module for central points is incorporated into the process of LSA-Conv to enhance the robustness of the convolution against noise interference by adjusting the position coordinates of the points adaptively. The learned robust LSA-Conv features are then fed into a global spatial attention module with the gated unit to extract long-range contextual information and dynamically adjust the weights of features from different stages. The proposed framework, consisting of both encoding and decoding branches, is an end-to-end trainable network for semantic segmentation of 3-D point clouds. The theoretical analysis of the approximation capabilities of LSA-Conv is discussed to determine whether the features of the point cloud can be accurately represented. Experimental results on challenging benchmarks of the 3-D point cloud demonstrate that the proposed framework achieves excellent performance.

MDU‐sampling: Multi‐domain uniform sampling method for large‐scale outdoor LiDAR point cloud registration

AbstractSampling is a crucial concern for outdoor light detection and ranging (LiDAR) point cloud registration due to the large amounts of point cloud. Numerous algorithms have been devised to tackle this issue by selecting key points. However, these approaches often necessitate extensive computations, giving rise to challenges related to computational time and complexity. This letter proposes a multi‐domain uniform sampling method (MDU‐sampling) for large‐scale outdoor LiDAR point cloud registration. The feature extraction based on deep learning aggregates information from the neighbourhood, so there is redundancy between adjacent features. The sampling method in this paper is carried out in the spatial and feature domains. First, uniform sampling is executed in the spatial domain, maintaining local point cloud uniformity. This is believed to preserve more potential point correspondences and is beneficial for subsequent neighbourhood information aggregation and feature sampling. Subsequently, a secondary sampling in the feature domain is performed to reduce redundancy among the features of neighbouring points. Notably, only points on the same ring in LiDAR data are considered as neighbouring points, eliminating the need for additional neighbouring point search and thereby speeding up processing rates. Experimental results demonstrate that the approach enhances accuracy and robustness compared with benchmarks.

High-Precision Map Construction in Degraded Long Tunnel Environments of Urban Subways

In response to the demand for high-precision point cloud mapping of subway trains in long tunnel degradation scenarios in major urban cities, we propose a map construction method based on LiDAR and inertial measurement sensors. This method comprises a tightly coupled frontend odometry system based on error Kalman filters and backend optimization using factor graphs. In the frontend odometry, inertial calculation results serve as predictions for the filter, and residuals between LiDAR points and local map plane point clouds are used for filter updates. The global pose graph is constructed based on inter-frame odometry and other constraint factors, followed by a smoothing optimization for map building. Multiple experiments in subway tunnel scenarios demonstrate that the proposed method achieves robust trajectory estimation in long tunnel scenes, where classical multi-sensor fusion methods fail due to sensor degradation. The proposed method achieves a trajectory consistency of 0.1 m in tunnel scenes, meeting the accuracy requirements for train arrival, parking, and interval operations. Additionally, in an industrial park scenario, the method is compared with ground truth provided by inertial navigation, showing an accumulated error of less than 0.2%, indicating high precision.

Evaluating global vegetation products for application in heterogeneous forest-savanna landscapes

ABSTRACT While satellite-derived global vegetation structure products are powerful and easy to use, their utility for studying spatial patterns within heterogeneous landscapes such as forest-savanna mosaics has not been extensively evaluated. We explored the application of global vegetation structure products in heterogeneous landscapes by comparing them with Airborne Laser Scanning. Specifically, we assessed the accuracy and bias of two fractional cover products, MODIS Vegetation Continuous Fields (VCF) and Hansen Global Forest Change (GFC), and one global canopy height model, Global Forest Canopy Height Model (CHM), in comparison with the same variables derived from local ALS point clouds. We found that there were limitations to all three products. MODIS VCF was less accurate than its reported accuracy by at least 3%, and GFC was 10% less accurate than MODIS VCF. While Global CHM had a similar magnitude of error to its reported product accuracy, product agreement was much lower (R2 0.19 vs. R2 0.61). We also found that the context of the analysis is important when choosing whether to use one fractional product over the other. Global products should be applied with caution in heterogeneous landscapes. Increased training and validation from these landscapes could improve the performance of these products and their utility for landscape-scale ecological research.