A novel and efficient method for wood–leaf separation from terrestrial laser scanning point clouds at the forest plot level

The fully automatic registration of 3D terrestrial laser scanning (TLS) point clouds, which is the first step in the usage of point clouds, is a highly challenging task in Light Detection and Ranging (LiDAR) remote sensing applications. Here, an automatic algorithm for pairwise coarse registration of TLS point clouds using 3D line features is proposed. First, the 3D line sets were extracted from the original pair of point clouds respectively, and two arbitrary lines from a point cloud were used to construct a 2-line base; Then, a pair of conjugate 2-line bases were identified from the source and target 3D line sets at a time, based on which a 3D rotation matrix together with its corresponding overlap between the pairwise 3D line sets was calculated; Third, a series of 3D rotation matrixes together with their overlaps were obtained using the traversing strategy to identify conjugate 2-line base pairs, and the 3D rotation matrix with the highest overlap was outputted as the final 3D rotation matrix, which was further used to compute the corresponding lines set from the pairwise 3D line sets; Next, based on the set of common perpendicular midpoints between the line correspondences, the 3D translation vector was computed; Finally, the 3D transformation matrix between pairwise point clouds was obtained by combining the 3D rotation matrix and the 3D translation vector. The proposed method was tested on three different TLS datasets, with experimental results demonstrating that the proposed algorithm could perform well on registering pairwise TLS point clouds. The rotation and translation errors of aligning the nine experimental pairwise point clouds were all less than 0.50° and 0.55m, respectively. This registration framework was also shown to be superior to state-of-the-art methods in terms of registration accuracy.

Large-scale terrestrial laser scanning (TLS) point clouds are increasingly used for applications such as digital twins and cultural heritage documentation; however, removing unwanted human points captured during acquisition remains a largely manual and time-consuming process. This study proposes a geometry-aware framework for automatically removing human noise from TLS point clouds by projecting 2D instance segmentation masks (obtained using You Only Look Once (YOLO) v8 with an instance segmentation head) into 3D space and validating candidates through multi-stage geometric filtering. To suppress false positives induced by reprojection misalignment and planar background structures (e.g., walls and ground), we introduce projection-followed geometric validation (or "geometric gating") using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and principal component analysis (PCA)-based planarity analysis, followed by cluster-level plausibility checks. Experiments were conducted on two real-world outdoor TLS datasets-(i) Osaka Metropolitan University Sugimoto Campus (OMU) (82 scenes) and (ii) Jinaimachi historic district in Tondabayashi (JM) (68 scenes). The results demonstrate that the proposed method achieves high noise removal accuracy, obtaining precision/recall/intersection over union (IoU) of 0.9502/0.9014/0.8607 on OMU and 0.8912/0.9028/0.8132 on JM. Additional experiments on mobile mapping system (MMS) data from the Waymo Open Dataset demonstrate stable performance without parameter recalibration. Furthermore, quantitative and qualitative comparisons with representative time-series geometric dynamic object removal methods, including DUFOMap and BeautyMap, show that the proposed approach maintains competitive recall under a human-only ground-truth definition while reducing over-removal of static structures in TLS scenes, particularly when humans are observed in only one or a few scans due to limited revisit frequency. The end-to-end processing time with YOLOv8 was 935.62 s for 82 scenes (11.4 s/scene) on OMU and 571.58 s for 68 scenes (8.4 s/scene) on JM, supporting practical efficiency on high-resolution TLS imagery. Ablation studies further clarify the role of each stage and indicate stable performance under the observed reprojection errors. The annotated human point cloud dataset used in this study has been publicly released to facilitate reproducibility and further research on human noise removal in large-scale TLS scenes.

In forestry research, for forest inventories or other applications which require accurate 3D information on the forest structure, a Terrestrial Laser Scanner (TLS) is an efficient tool for vegetation structure estimation. Light Detection and Ranging (LiDAR) can even provide high-resolution information in tree canopies due to its high penetration capability. Depending on the forest plot size, tree density, and structure, multiple TLS scans are acquired to cover the forest plot in all directions to avoid any voids in the dataset that are generated. However, while increasing the number of scans, we often tend to increase the data redundancy as we keep acquiring data for the same region from multiple scan positions. In this research, an extensive qualitative analysis was carried out to examine the capability and efficiency of TLS to generate canopy top points in six different scanning combinations. A total of nine scans were acquired for each forest plot, and from these nine scans, we made six different combinations to evaluate the 3D vegetation structure derived from each scan combination, such as Center Scans (CS), Four Corners Scans (FCS), Four Corners with Center Scans (FCwCS), Four Sides Center Scans (FSCS), Four Sides Center with Center Scans (FSCwCS), and All Nine Scans (ANS). We considered eight forest plots with dimensions of 25 m × 25 m, of which four plots were of medium tree density, and the other four had a high tree density. The forest plots are located in central Slovakia; European beech was the dominant tree species with a mixture of European oak, Silver fir, Norway spruce, and European hornbeam. Altogether, 487 trees were considered for this research. The quantification of tree canopy top points obtained from a TLS point cloud is very crucial as the point cloud is used to derive the Digital Surface Model (DSM) and Canopy Height Model (CHM). We also performed a statistical evaluation by calculating the differences in the canopy top points between ANS and the five other combinations and found that the most significantly different combination was FSCwCS respective to ANS. The Root Mean Squared Error (RMSE) of the deviations in tree canopy top points obtained for plots TLS_Plot1 and TLS_Plot2 ranged from 0.89 m to 14.98 m and 0.61 m to 7.78 m, respectively. The relative Root Mean Squared Error (rRMSE) obtained for plots TLS_Plot1 and TLS_Plot2 ranged from 0.15% to 2.48% and 0.096% to 1.22%, respectively.

The effective extraction of shape features is an important requirement for the accurate and efficient classification of terrestrial laser scanning (TLS) point clouds. However, the challenge of how to obtain robust and discriminative features from noisy and varying density TLS point clouds remains. This paper introduces a novel multiscale and hierarchical framework, which describes the classification of TLS point clouds of cluttered urban scenes. In this framework, we propose multiscale and hierarchical point clusters (MHPCs). In MHPCs, point clouds are first resampled into different scales. Then, the resampled data set of each scale is aggregated into several hierarchical point clusters, where the point cloud of all scales in each level is termed a point-cluster set. This representation not only accounts for the multiscale properties of point clouds but also well captures their hierarchical structures. Based on the MHPCs, novel features of point clusters are constructed by employing the latent Dirichlet allocation (LDA). An LDA model is trained according to a training set. The LDA model then extracts a set of latent topics, i.e., a feature of topics, for a point cluster. Finally, to apply the introduced features for point-cluster classification, we train an AdaBoost classifier in each point-cluster set and obtain the corresponding classifiers to separate the TLS point clouds with varying point density and data missing into semantic regions. Compared with other methods, our features achieve the best classification results for buildings, trees, people, and cars from TLS point clouds, particularly for small and moving objects, such as people and cars.

For more than a decade, Terrestrial Laser Scanning (TLS) has been a primary remote sensing technique for disciplines related to archaeology, architecture, built heritage, earth science, metrology, and land survey. The increasing precision, range, and survey speed of TLS make this technology even more viable for large-scale data capturing in the Age of Sensing. This chapter reviews the state of the art of Terrestrial Laser Scanning in 2015 with the aim to assess its applications in a context of lower data capturing costs for alternative technologies, such as new commodity sensors, Image-based 3D Modeling, Unmanned Aerial Systems (UAS), optical 3D scanning, and Airborne Laser Scanning. More specifically, TLS still maintains a fundamental role in the documentation and interpretation of archaeological contexts at intrasite scale: (i) Terrestrial Laser Scanning delivers high-fidelity data of surfaces and structures of buildings as well as ultra-precise measurements of the morphology of stratigraphic layers; (ii) research in remote sensing proved that TLS point clouds can be successfully interpolated with data recorded with other instruments and techniques, such as magnetometry, Ground Penetrating Radar, Unmanned Aerial Vehicles, Image-Based Modeling, in order to generate hybrid documentation and new knowledge on natural and cultural heritage sites. Inevitably, the current advancements in TLS bring new questions. For example, how can micro-differences only visible in the point clouds change the analysis and interpretation of layers and buildings? How to improve the monitoring and conservation of a site via automated analysis of TLS data? How to enhance the mapping process of built-heritage using data segmentation or semi-automatic feature extraction of TLS point clouds? This chapter proposes a new approach to TLS based on multi-modal capture workflows, semi-automated post processing, online archiving, and online visualization and management of point clouds with the aim to open new horizons for digital archaeology, architectural survey, and heritage conservation .

The objective of this study was to identify and quantify surface depressions on grass-covered land surfaces using a high-resolution terrestrial laser scanning (TLS) point cloud, and a triangulated irregular network (TIN). The entire grassy land surface in the study area was divided into five subwatersheds of different topographic attributes (i.e., depression depth and surface slope). Surface depressions were identified and quantified using a TIN generated from a high-resolution TLS point cloud. The results indicated that microtopography of the grassy land surface was well-characterized within each subwatershed in comparison with field observations. With the terrestrial light detection and ranging (LIDAR) point cloud of 15-mm point spacing and the TIN method, surface depression storage depths of the five subwatersheds ranged from 1.73 to 14.28 mm in the study area. The surface depression storage depth, as expected, increased with the maximum depth of surface depression. It was also found to increase when the land surface slope became milder. A sensitivity analysis indicated that a point cloud with a point spacing of 30 mm was sufficient to obtain an accurate representation of the terrain surface in the study area. This study also indicated the TIN method can represent the ground surface and the surface depression more realistically than the commonly used digital elevation model (DEM) method due to the TIN method’s higher capability of identifying and filtering out surface obstructions such as blades of grass. Moreover, by using the high-resolution TLS technology and the TIN method, our study provides an important and broad range of reference data on the surface depression storage depth commonly needed in application of the Storm Water Management Model (SWMM) and other watershed models.

In recent years, the use of terrestrial laser scanning (TLS) technology in the mining industry has grown in popularity because of its many benefits, including non-contact measurement, high precision, rapid data acquisition, and large-scale coverage. This study provides a thorough overview of the application of the TLS method in underground, open-pit, and closed mines, using data from 56 publications over the past fourteen years, from 2010 to May 2024. The reviewed literature shows that the TLS approach can be applied in five main operations in mining areas, particularly for monitoring deformation, displacement, subsidence, and landslides, as well as generating maps, 3D models, and point clouds. The findings reveal that TLS is an excellent technology for multitasking in any type of mine. In addition, future development trends for the mining industry based on the integration of TLS with machine learning and AI technologies are also discussed in this study. The results of this study may suggest directions for creating the specifications required for TLS deployment on mine sites.

The use of 3D point cloud-based technology for quantifying standing wood and stand parameters can play a key role in forestry ecological benefit assessment and standing tree cultivation and utilization. With the advance of 3D information acquisition techniques, such as light detection and ranging (LiDAR) scanning, the stand information of trees in large areas and complex terrain can be obtained more efficiently. However, due to the diversity of the forest floor, the morphological diversity of the trees, and the fact that forestry is often planted as large-scale plantations, efficiently segmenting the point cloud of artificially planted forests and extracting standing wood feature parameters remains a considerable challenge. An effective method based on energy segmentation and PointCNN is proposed in this work to address this issue. The network is enhanced for learning point cloud features by geometric feature balance model (GFBM), enabling the efficient segmentation of tree point clouds from forestry point cloud data collected by terrestrial laser scanning (TLS) in outdoor environments. The 3D Forest software is then used to obtain single wood point cloud after semantic segmentation, and the extracted single wood point cloud is finally employed to extract standing wood feature parameters using TreeQSM. The point cloud semantic segmentation method is the most important part of our research. According to our findings, this method can segment datasets of two different artificially planted woodland point clouds with an overall accuracy of 0.95 and a tree segmentation accuracy of 0.93. When compared with the manual measurements, the root-mean-square error (RMSE) for tree height in the two datasets are 0.30272 and 0.21015 m, and the RMSEs for the diameter at breast height are 0.01436 and 0.01222 m, respectively. Our method is a robust framework based on deep learning that is applicable to forestry for extracting the feature parameters of artificially planted trees. It solves the problem of segmenting tree point clouds in artificially planted trees and provides a reliable data processing method for tree information extraction, trunk shape analysis, etc.

Benchmarking tree instance segmentation of terrestrial laser scanning point clouds

Automatic pairwise registration for unordered terrestrial laser scanner (TLS) point clouds is the pre-requisite for many applications, including 3D model reconstruction, cultural heritage management and landslide monitoring. However, most of the existing registration methods are still suffering from several limitations: (1) difficult to find the correct corresponding point pairs from the source and target point cloud, (2) low accuracy of pairwise registration and (3) the iterative process of registration is time-consuming. To overcome these challenges, based on the covariance matrix, this paper presents a robust and descriptive feature descriptor vector (FDV) to locally describe a point, by which the corresponding point pairs are obtained and the registration matrix is calculated. First, the FDVs of the original point cloud’s keypoints are calculated. Second, the corresponding point pairs are found via their FDVs. Third, the coarse transformation matrix is calculated by the corresponding point pairs using the singular value decomposition (SVD) algorithm, and which is further refined by the iterative closest point (ICP) algorithm to get a better result. Finally, the experiments are conducted on the Autonomous Systems Lab (ASL) and ISPRS datasets; our results show that the proposed algorithm can obtain good registration performance, and outperforms the compared methods.

Several methods to conduct single-tree inventories using airborne laser scanning (ALS) have been proposed, and even terrestrial laser scanning (TLS) has recently emerged as a possible tool for the collection of forest inventory data. In the present study, a novel methodological framework for a combined use of ALS and TLS in an inventory was tested and compared to a method without the use of TLS. Single-tree Norway spruce crown biomass was predicted using an ALS-model with training data obtained by TLS. ALS and TLS data were collected for sets of sample trees, including 68 trees with both ALS and TLS data. In total, 29 destructively sampled trees were used to fit a TLS crown biomass model, which then was used to predict crown biomass in a separate set of 68 trees. This dataset was subsequently used to fit an ALS crown biomass model. When validating the model, using a separate dataset with accurately measured crown biomass obtained through destructive sampling, the mean error was 32% of the observed mean biomass. Corresponding crown biomass predictions derived with ALS-predicted diameters and the use of conventional and existing allometric models resulted in a mean error of 35%. Thus, in the present study, a slight improvement, in terms of prediction accuracy, was found when using training data with ground reference values obtained by TLS.

Registration of large-scale terrestrial laser scanner point clouds: A review and benchmark

The ability to classify urban objects in large urban scenes from point clouds efficiently and accurately still remains a challenging task today. A new methodology for the effective and accurate classification of terrestrial laser scanning (TLS) point clouds is presented in this paper. First, in order to efficiently obtain the complementary characteristics of each 3-D point, a set of point-based descriptors for recognizing urban point clouds is constructed. This includes the 3-D geometry captured using the spin-image descriptor computed on three different scales, the mean RGB colors of the point in the camera images, the LAB values of that mean RGB, and the normal at each 3-D point. The initial 3-D labeling of the categories in urban environments is generated by utilizing a linear support vector machine classifier on the descriptors. These initial classification results are then first globally optimized by the multilabel graph-cut approach. These results are further refined automatically by a local optimization approach based upon the object-oriented decision tree that uses weak priors among urban categories which significantly improves the final classification accuracy. The proposed method has been validated on three urban TLS point clouds, and the experimental results demonstrate that it outperforms the state-of-the-art method in classification accuracy for buildings, trees, pedestrians, and cars.

The registration of long-strip, terrestrial laser scanning (TLS) point clouds is a prerequisite for various engineering tasks, including tunnels, bridges, and roads. An artificial target-based registration method is proposed in this paper to automatically calculate registration parameters (i.e., rotation, translation) of scanned pairs without initial estimations. The approach is based on the well-known Random Sample Consensus (RANSAC) method and effectively searches the point cloud for corresponding returns from a system of artificial targets. In addition, Closed Constraint Adjustment (CCA) is integrated into the registration method to significantly reduce the accumulative error. Experimental results demonstrate the robustness and feasibility of the proposed approach. It is a promising approach to register automatically long strips with limited external control points with satisfactory precision.

Annotated datasets are essential for training and evaluating machine learning models in forest ecology. This dataset provides high-resolution, annotated LiDAR point clouds of 674 individual trees from 12 forest plots in the Shivalik Range of northern Haryana, India, representing 24 species. Data were acquired using Terrestrial Laser Scanning (TLS) and Airborne Laser Scanning (ALS), include field-measured attributes such as species identity and Diameter at Breast Height (DBH), and terrestrial and aerial RGB imagery. TLS point clouds were georeferenced and co-registered with centimetre-level accuracy, enabling precise integration with ALS data. The dataset includes segmented individual trees and wood–leaf classifications, suitable for applications such as tree morphology analysis, biomass estimation, and species classification. To support benchmarking, outputs from established classification algorithms (LeWoS, TLSeparation, CANUPO, and Random Forest) are included. As one of the first open-access LiDAR datasets from Indian tropical forests, it provides critical reference data for developing and validating forest structure models. It can also aid biomass mapping efforts in support of large-scale missions such as NASA-ISRO’s NISAR and ESA’s BIOMASS.