Search Results (648)

LiDAR point clouds of reflective targets often contain significant noise, which severely impacts the feature extraction accuracy and performance of object detection algorithms. These challenges present substantial obstacles to point cloud processing and its applications. In this paper, we propose a Unified Denoising Framework (UDF) aimed at removing noise and restoring the geometry of reflective targets. The proposed method consists of three steps: veiling effect denoising using an improved pass-through filter, range anomalies correction through M-estimator Sample Consensus (MSAC) plane fitting and ray projection, and blooming effect denoising based on an adaptive error ellipse. The parameters of the error ellipse are automatically determined using the divergence angle of the laser beam, blooming factors, and the normal vector along the boundary of the point cloud. The proposed method was validated on a self-constructed traffic sign point cloud dataset. The experimental results showed that the method achieved a mean square error (MSE) of 0.15 cm², a mean city-block distance (MCD) of 0.05 cm, and relative height and width errors of 1.92% and 1.91%, respectively. Compared to five representative algorithms, the proposed method demonstrated superior performance in both denoising accuracy and the restoration of target geometric features. Full article

UAV LiDAR and digital aerial photogrammetry (DAP) have shown great performance in forest inventory due to their advantage in three-dimensional information extraction. Many studies have compared their performance in individual tree segmentation and structural parameters extraction (e.g. tree height). However, few studies have compared their performance in tree species classification. Therefore, we have compared the performance of UAV LiDAR and DAP-based point clouds in individual tree species classification with the following steps: (1) Point cloud data processing: Denoising, smoothing, and normalization were conducted on LiDAR and DAP-based point cloud data separately. (2) Feature extraction: Spectral, structural, and texture features were extracted from the pre-processed LiDAR and DAP-based point cloud data. (3) Individual tree segmentation: The marked watershed algorithm was used to segment individual trees on canopy height models (CHM) derived from LiDAR and DAP data, respectively. (4) Pixel-based tree species classification: The random forest classifier (RF) was used to classify urban tree species with features derived from LiDAR and DAP data separately. (5) Individual tree species classification: Based on the segmented individual tree boundaries and pixel-based classification results, the majority filtering method was implemented to obtain the final individual tree species classification results. (6) Fused with hyperspectral data: LiDAR-hyperspectral and DAP-hyperspectral fused data were used to conduct individual tree species classification. (7) Accuracy assessment and comparison: The accuracy of the above results were assessed and compared. The results indicate that LiDAR outperformed DAP in individual tree segmentation (F-score 0.83 vs. 0.79), while DAP achieved higher pixel-level classification accuracy (73.83% vs. 57.32%) due to spectral-textural features. Fusion with hyperspectral data narrowed the gap, with LiDAR reaching 95.98% accuracy in individual tree classification. Our findings suggest that DAP offers a cost-effective alternative for urban forest management, balancing accuracy and operational costs. Full article

Intercropping is a key cultivation strategy for safeguarding national food and oil security. Accurate early-stage yield prediction of intercropped soybeans is essential for the rapid screening and breeding of high-yield soybean varieties. As a widely used technique for crop yield estimation, the accuracy of 3D reconstruction models directly affects the reliability of yield predictions. This study focuses on optimizing the 3D reconstruction process for intercropped soybeans to efficiently extract canopy structural parameters throughout the entire growth cycle, thereby enhancing the accuracy of early yield prediction. To achieve this, we optimized image acquisition protocols by testing four imaging angles (15°, 30°, 45°, and 60°), four plant rotation speeds (0.8 rpm, 1.0 rpm, 1.2 rpm, and 1.4 rpm), and four image acquisition counts (24, 36, 48, and 72 images). Point cloud preprocessing was refined through the application of secondary transformation matrices, color thresholding, statistical filtering, and scaling. Key algorithms—including the convex hull algorithm, voxel method, and 3D α-shape algorithm—were optimized using MATLAB, enabling the extraction of multi-dimensional canopy parameters. Subsequently, a stepwise regression model was developed to achieve precise early-stage yield prediction for soybeans. The study identified optimal image acquisition settings: a 30° imaging angle, a plant rotation speed of 1.2 rpm, and the collection of 36 images during the vegetative stage and 48 images during the reproductive stage. With these improvements, a high-precision 3D canopy point-cloud model of soybeans covering the entire growth period was successfully constructed. The optimized pipeline enabled batch extraction of 23 canopy structural parameters, achieving high accuracy, with linear fitting R² values of 0.990 for plant height and 0.950 for plant width. Furthermore, the voxel volume-based prediction approach yielded a maximum yield prediction accuracy of R² = 0.788. This study presents an integrated 3D reconstruction framework, spanning image acquisition, point cloud generation, and structural parameter extraction, effectively enabling early and precise yield prediction for intercropped soybeans. The proposed method offers an efficient and reliable technical reference for acquiring 3D structural information of soybeans in strip intercropping systems and contributes to the accurate identification of soybean germplasm resources, providing substantial theoretical and practical value. Full article

In this study, we analyzed regional spatial features and optimized tourism routes based on point cloud data provided by unmanned aerial vehicles (UAVs) with the goal of developing the Xiaosongyuan Red Tourism Scenic Area in Kunming, Yunnan Province, China. We first proposed a novel method for UAV point cloud data coverage based on an irregular regional segmentation technique along with an optimized search path designed to minimize travel time within the specified area. Three DJI Phantom drones were employed to collect data over the designated region, and an improved progressive triangular irregular network densification filtering algorithm was used to extract ground points from the UAV-acquired point cloud data. DJI Terra software was used for image stitching to generate a comprehensive map of spatial features in the target area. Using this three-dimensional map of spatial features, we explored tourist routes in complex environments and applied an improved particle swarm optimization algorithm to identify optimal tourist routes characterized by safety, smoothness, and feasibility. The findings provide valuable technical support for enhancing tourism planning and management in scenic areas while maintaining a balance with conservation efforts. Full article

Accurate forest monitoring and resource assessment are crucial for sustainable forest management, with tree diameter at breast height (DBH) serving as a key metric for tree growth assessment and carbon storage estimation. In this study, we developed a comprehensive mobile-LiDAR-based point cloud processing pipeline to segment individual trees and estimate the DBH of trees. We first conducted terrain extraction using a resolution-passing method combined with a cloth simulation filter. Then, by leveraging the vertical structural characteristics of trees and changes in point cloud density, we achieved high-performance tree trunk segmentation. On this basis, we deployed the Randomized Hough Transform algorithm to estimate the DBH of the trees. Finally, a large-scale experiment was conducted in a forest (Olympic Forest Park, Beijing, China) and we provided experimental results comparing our trunk segmentation and DBH estimation to ground-truth measurements recorded manually. Eventually, our results showed that 97.4% of the trees were accurately segmented, and the DBH estimation error was reduced to 3.2 cm, which shows that the proposed pipeline is able to achieve high-accuracy trunk segmentation and high-precision DBH estimation. Further, this research demonstrates that integrating MLS with SLAM technology can enhance the efficiency and accuracy of forest surveys, providing a valuable tool for future forest management strategies. Full article

The safe operation of power transmission lines is critical for ensuring the stability of the power supply, especially given the increasing frequency of extreme weather events and the risks posed by tree growth. This study proposes a novel method for detecting and predicting the tree barrier risks on transmission lines using Unmanned Aerial Vehicle–Light Detection and Ranging (UAV-LiDAR) technology. The method employs point cloud classification to effectively separate ground, conductor, tower, and vegetation points, followed by 3D reconstruction of the power lines using the catenary equation. Tree growth models are integrated with measured data to predict future tree barrier risks. The experimental results demonstrate that the point-cloud-based method detects 31 tree barriers, with an RMSE of 0.08 m, while the 3D-reconstruction-based method detects 32 tree barriers, with an RMSE of 0.04 m, indicating its higher accuracy. The Cloth Simulation Filter (CSF) ground point classification method achieved the lowest roughness (1.5%), mean error (0.147 m), and RMSE (0.174 m), proving its effectiveness for flat terrain. Additionally, the assisted seed point individual tree segmentation method extracted tree height with high accuracy (R² = 0.84, RMSE = 1.01 m). This study predicts an average tree growth rate of 0.248 m/year over the next five years, identifying a new tree barrier at the coordinates 30°15′16.64″ N, 119°43′16.01″ E. This method enhances the efficiency and accuracy of transmission line inspections, supporting both power line safety and sustainable forest management. Its findings provide a robust technical approach to improving power line operations and forest resource utilization. Full article

With advancement in Unmanned Aerial Vehicle (UAV) photogrammetry, productivity in construction management can now be achieved with accuracy and is less labour-intensive. In the basement construction of buildings, prudent earthwork activities are often necessary, setting the basis of the building footprint. As such, monitoring earthwork volume estimation becomes important to avoid over- or under-cutting the earth. Conventional methods by means of land surveying are time-consuming, labour-intensive, and susceptible to varying degrees of accuracy. Moreover, earthwork sites often have multiple activities ongoing that increase the complexity of volume estimation through land surveying. This study explores the use of UAV photogrammetry to estimate earthwork excavation volume in a complex urban earthwork site in Singapore over time and discusses the feasibility, challenges and productivity enhancements of integrating the technology into the construction process. In this study, the earthwork site and controlled trials show that the models reconstructed with UAV photogrammetry data can produce volume measurements that fulfil the stakeholder’s accuracy tolerance of 5% between the estimated and actual volume. The filtering of unwanted objects in the model, such as columns, cranes and trucks, was successful but was insufficient for objects that occluded large areas of the soil surface. The integration of UAV photogrammetry with a highly automated acquisition and processing workflow for earthwork monitoring brings about productivity enhancements in time and labour efforts and improves the efficiency and consistency of models. Furthermore, the digitalisation of earthwork sites into point clouds and three-dimensional (3D) models increases data visualisation and accessibility, facilitates project team collaboration, and enables cross-platform compatibility into Building Information Modelling (BIM), which can significantly aid in reporting and decision-making processes. Full article

In order to detect the abrasion of rails, a new point cloud alignment method combining 4-points congruent sets (4PCS) coarse alignment based on internal shape signature (ISS) and K-dimensional iterative closest points (KD-ICP) fine alignment is proposed, and for the first time, the combined algorithm is applied to the detection of rail wear. Due to the large amount of 3D rail point cloud data collected by the 3D line laser sensor, the original data are first downsampled by voxel filtering. Then, ISS feature points are extracted from the processed point cloud data for 4PCS coarse alignment, and the feature points are quantitatively analyzed, which in turn provides good alignment conditions for fine alignment. Then, the K-dimensional tree structure is used for the near-neighbor search to improve the alignment efficiency of the ICP algorithm. Finally, the total rail wear is calculated by combining the fine alignment results with the wear calculation formula. The experimental results show that when the number of ISS feature points extracted is 4496, the 4PCS coarse alignment algorithm based on ISS feature points is higher than the original 4PCS algorithm as well as the other algorithms in terms of alignment accuracy; the ICP fine alignment algorithm based on the kd-tree is less than the original ICP algorithm as well as the other algorithms in terms of the time consumed. Further, the proposed new ISS-4PCS + KD-ICP two-stage point cloud alignment method is superior to the original 4PCS + ICP algorithm both in terms of alignment accuracy and runtime. The combined algorithm is applied to the detection of rail wear for the first time, which provides a reference for the non-contact rail wear detection method. The high accuracy and low time consumption of the proposed algorithm lays a good foundation for the calculation of rail wear in the next step. Full article

This article examines the combined use of UAV (Unmanned Aerial Vehicle) photogrammetry and TLS (Terrestrial Laser Scanning) to detect changes in coastal cliffs in the Strunjan Nature Reserve. Coastal cliffs present unique surveying challenges, including limited access, unstable reference points due to erosion, GNSS (Global Navigation Satellite System) signal obstruction, dense vegetation, private property restrictions and weak mobile data. To overcome these limitations, UAV and TLS techniques are used with the help of GNSS and TPS (Total Positioning Station) surveying to establish a network of GCPs (Ground Control Points) for georeferencing. The methodology includes several epochs of data collection between 2019 and 2024, using a DJI Phantom 4 RTK for UAV surveys and a Riegl VZ-400 scanner for TLS. The data processing includes point cloud filtering, mesh comparison and a DoD (DEM of difference) analysis to quantify cliff surface changes. This study addresses the effects of vegetation by focusing on vegetation-free regions of interest distributed across the cliff face. The results aim to demonstrate the effectiveness and limitations of both methods for detecting and monitoring cliff erosion and provide valuable insights for coastal management and risk assessment. Full article

This paper proposes a pose estimation algorithm using INS and LiDAR for precise cooperative relative navigation between target and chaser spacecraft in a close docking mission scenario. Previous cooperative algorithms have proposed estimating position and pose transformations using typical matching methods or to pre-extract and utilize features from point cloud data. However, in the case of general proximity rendezvous docking, a straight-line approach scenario with very few changes in attitude is usually assumed, and, in this case, pose estimation using simple matching techniques or feature point extraction leads to inaccurate results. To solve this problem, this paper performed a principal component analysis (PCA) based on ICP to align the initial transformation matrix. To keep the distribution of point cloud data constant, the point cloud at the time of docking was applied to ICP to minimize the change in the distribution of point clouds over time. Finally, we designed an EKF filter that estimates the relative position, velocity, and attitude using the INS model and combines it with the relative pose estimated from the point cloud; the proposed method showed the results of estimating the relative pose more effectively than the previous method. The simulation and experiment showed more accurate estimation results than the ICP method in position and attitude, respectively. In particular, in the case of position, both the simulation and experiment showed 0.46 m and 0.32 m better estimation results in the z-axis. Also, attitude estimation showed 0.11° and 2.66° better results in roll and 0.01° and 0.34° better results in pitch. This shows that the proposed algorithm provided better pose estimation results in the docking scenario in a straight line. Full article

Plant phenotyping is crucial for advancing precision agriculture and modern breeding, with 3D point cloud segmentation of plant organs being essential for phenotypic parameter extraction. Nevertheless, although existing approaches maintain segmentation precision, they struggle to efficiently process complex geometric configurations and large-scale point cloud datasets, significantly increasing computational costs. Furthermore, their heavy reliance on high-quality annotated data restricts their use in high-throughput settings. To address these limitations, we propose a novel multi-stage region-growing algorithm based on an octree structure for efficient stem-leaf segmentation in maize point cloud data. The method first extracts key geometric features through octree voxelization, significantly improving segmentation efficiency. In the region-growing phase, a preliminary structural segmentation strategy using fitted cylinder parameters is applied. A refinement strategy is then applied to improve segmentation accuracy in complex regions. Finally, stem segmentation consistency is enhanced through central axis fitting and distance-based filtering. In this study, we utilize the Pheno4D dataset, which comprises three-dimensional point cloud data of maize plants at different growth stages, collected from greenhouse environments. Experimental results show that the proposed algorithm achieves an average precision of 98.15% and an IoU of 84.81% on the Pheno4D dataset, demonstrating strong robustness across various growth stages. Segmentation time per instance is reduced to 4.8 s, offering over a fourfold improvement compared to PointNet while maintaining high accuracy and efficiency. Additionally, validation experiments on tomato point cloud data confirm the proposed method’s strong generalization capability. In this paper, we present an algorithm that addresses the shortcomings of traditional methods in complex agricultural environments. Specifically, our approach improves efficiency and accuracy while reducing dependency on high-quality annotated data. This solution not only delivers high precision and faster computational performance but also lays a strong technical foundation for high-throughput crop management and precision breeding. Full article

In low-illumination environments, traditional traffic accident survey methods struggle to obtain high-quality data. This paper proposes a traffic accident reconstruction method utilizing an unmanned aerial vehicle (UAV) and auxiliary equipment. Firstly, a methodological framework for investigating traffic accidents under low-illumination conditions is developed. Accidents are classified based on the presence of obstructions, and corresponding investigation strategies are formulated. As for the unobstructed scene, a UAV-mounted LiDAR scans the accident site to generate a comprehensive point cloud model. In the partially obstructed scene, a ground-based mobile laser scanner complements the areas that are obscured or inaccessible to the UAV-mounted LiDAR. Subsequently, the collected point cloud data are processed with a multiscale voxel iteration method for down-sampling to determine optimal parameters. Then, the improved normal distributions transform (NDT) algorithm and different filtering algorithms are adopted to register the ground and air point clouds, and the optimal combination of algorithms is selected, thus, to reconstruct a high-precision 3D point cloud model of the accident scene. Finally, two nighttime traffic accident scenarios are conducted. DJI Zenmuse L1 UAV LiDAR system and EinScan Pro 2X mobile scanner are selected for survey reconstruction. In both experiments, the proposed method achieved RMSE values of 0.0427 m and 0.0451 m, outperforming traditional aerial photogrammetry-based modeling with RMSE values of 0.0466 m and 0.0581 m. The results demonstrate that this method can efficiently and accurately investigate low-illumination traffic accident scenes without being affected by obstructions, providing valuable technical support for refined traffic management and accident analysis. Moreover, the challenges and future research directions are discussed. Full article

The Ice, Cloud, and Land Elevation 2 (ICESat-2) mission uses a micropulse photon-counting lidar system for mapping, which provides technical support for capturing forest parameters and carbon stocks over large areas. However, the current algorithm is greatly affected by the slope, and the extraction of the forest canopy height in the area with steep terrain is poor. In this paper, an improved algorithm was provided to reduce the influence of topography on canopy height estimation and obtain higher accuracy of forest canopy height. First, the improved clustering algorithm based on ordering points to identify the clustering structure (OPTICS) algorithm was developed and used to remove the noisy photons, and then the photon points were divided into canopy photons and ground photons based on mean filtering and smooth filtering, and the pseudo-signal photons were removed according to the distance between the two photons. Finally, the photon points were classified and interpolated again to obtain the canopy height. The results show that the improved algorithm was more effective in estimating ground elevation and canopy height, and the result was better in areas with less noise. The root mean square error (RMSE) values of the ground elevation estimates are within the range of 1.15 m for daytime data and 0.67 m for nighttime data. The estimated RMSE values for vegetation height ranged from 3.83 m to 2.29 m. The improved algorithm can provide a good basis for forest height estimation, and its DEM and CHM accuracy improved by 36.48% and 55.93%, respectively. Full article

At the microscale, the three-dimensional morphological features of contact surfaces have a significant impact on the performance of electrical contacts. This paper aims to reconstruct the microscopic contact state of contact groups and to deeply study the effect of contact morphological features on electrical contact performance. To fully obtain multimodal data such as the three-dimensional micro-morphological features and chemical composition distribution of contact surfaces, this paper proposes a contact surface feature-matching method based on entropy rate superpixel seed point adaptive morphological reconstruction. This method can adaptively retain meaningful seed points while filtering out invalid seed points, effectively solving the problem of over-segmentation in traditional superpixel segmentation method. Experimental results show that the proposed method achieves a segmentation accuracy of 92% and reduces over-segmentation by 30% compared to traditional methods. Subsequently, on the basis of the moving and static contact group difference plane model and the W-M model, this paper constructs a three-dimensional surface fractal contact model with an irregular base. This model has the ability to layer simulate multi-parameter elastic and plastic and to extract fractal parameter point cloud height, which can more accurately reflect the actual contact state of the contact group. The model demonstrates a 15% improvement in contact area prediction accuracy and a 20% reduction in contact resistance estimation error compared to existing models. Finally, this paper compares and verifies the theoretical feasibility of the model, providing a new theoretical contact model for the study of the impact of three-dimensional micro-morphology on the electrical contact reliability. Full article

Three-dimensional (3D) virtual trees play a vital role in modern forestry research, enabling the visualization of forest structures and supporting diverse simulations, including radiation transfer, climate change impacts, and dynamic forest management. Current virtual tree modeling primarily relies on 3D point cloud reconstruction from field survey data, and this approach faces significant challenges in scalability and structural diversity representation, limiting its broader applications in ecological modeling of forests. To address these limitations, we propose Diff-Tree, a novel diffusion model-based framework for generating diverse and realistic tree point cloud with reduced dependence on real-world data. The framework incorporates an innovative tree realism-aware filtering mechanism to ensure the authenticity of generated data while maintaining structural diversity. We validated Diff-Tree using two distinct datasets: one comprising five tree species from different families and genera, and another containing five Eucalyptus species from the same genus, demonstrating the method’s versatility across varying taxonomic levels. Quantitative evaluation shows that Diff-Tree successfully generates realistic tree point cloud while effectively enhancing structural diversity, achieving average ${MMD}_{CD}$ and ${COV}_{CD}$ values of (0.41, 65.78) and (0.56, 47.09) for the two datasets, respectively. The proposed method not only significantly reduces data acquisition costs but also provides a flexible, data-driven approach for virtual forest generation that adapts to diverse research requirements, offering a more efficient and practical solution for forestry research and ecological modeling. Full article