Individual Tree Segmentation from Side-View LiDAR Point Clouds of Street Trees Using Shadow-Cut

As one of the most important components of urban space, an outdated inventory of road-side trees may misguide managers in the assessment and upgrade of urban environments, potentially affecting urban road quality. Therefore, automatic and accurate instance segmentation of road-side trees from urban point clouds is an important task in urban ecology research. However, previous works show under- or over-segmentation effects for road-side trees due to overlapping, irregular shapes and incompleteness. In this paper, a deep learning framework that combines semantic and instance segmentation is proposed to extract single road-side trees from vehicle-mounted mobile laser scanning (MLS) point clouds. In the semantic segmentation stage, the ground points are filtered to reduce the processing time. Subsequently, a graph-based semantic segmentation network is developed to segment road-side tree points from the raw MLS point clouds. For the individual tree segmentation stage, a novel joint instance and semantic segmentation network is adopted to detect instance-level roadside trees. Two complex Chinese urban point cloud scenes are used to evaluate the individual urban tree segmentation performance of the proposed method. The proposed method accurately extract approximately 90% of the road-side trees and achieve better segmentation results than existing published methods in both two urban MLS point clouds. Living Vegetation Volume (LVV) calculation can benefit from individual tree segmentation. The proposed method provides a promising solution for ecological construction based on the LVV calculation of urban roads.

Over an extended period, remote-sensing-based individual tree analysis has played a critical role in modern forest inventory and management research. The segmentation of individual trees from aerial point clouds usually depends on the characteristics of peak-like uplift on the crown surface; however, the performance inevitably decreases with increasing visibility of such features in point clouds, especially for high-density forests. Herein, we developed a novel hierarchical region-merging algorithm that first over-segmented the entire forest scene based on local density and then merged the over-segmented partitions into pairs through a stepwise optimal process to produce the final segmentation. In the region-merging method, a global merging cost was introduced to shift from local detection of crown features to use the overall compactness of forest point clouds. The experiments were conducted using unmanned aerial vehicle light detection and ranging (UAV-LiDAR) point clouds from three coniferous stands with different densities and a high-density coniferous and broad-leaved mixed stand. A total of 5510 field-measured trees in 36 plots were used to assess the accuracy of the proposed method. Our method achieved F-scores of 0.91, 0.88, 0.84, and 0.80 for low- (~700 stems/ha), medium- (~1000 stems/ha), and high-density (~2000 stems/ha) conifer stands and coniferous and broad-leaved mixed forests (~1800 stems/ha), respectively. Compared with the classical individual tree segmentation methods (marker-controlled watershed segmentation and point cloud region-growing algorithm), our method obtained comparable performance in low-density conifer stands and superior performance in the other stands. Furthermore, the region-merging algorithm could detect 10% more suppressed trees on average, which led to an apparent improvement in detection accuracy. The proposed algorithm provides a flexible segmentation framework that could be further improved by a different design that merges costs or applies multiscale segmentation with different stopping criteria.

Individual tree (IT) segmentation is crucial for forest management, supporting forest inventory, biomass monitoring or tree competition analysis. Light detection and ranging (LiDAR) is a prominent technology in this context, outperforming competing technologies. Aerial laser scanning (ALS) is frequently used for forest documentation, showing good point densities at the tree-top surface. Even though under-canopy data collection is possible with multi-echo ALS, the number of points for regions near the ground in leafy forests drops drastically, and, as a result, terrestrial laser scanners (TLS) may be required to obtain reliable information about tree trunks or under-growth features. In this work, an IT extraction method for terrestrial backpack LiDAR data is presented. The method is based on DBSCAN clustering and cylinder voxelization of the volume, showing a high detection rate (∼90%) for tree locations obtained from point clouds, and low commission and submission errors (accuracy over ). The method includes a sensibility assessment to calculate the optimal input parameters and adapt the workflow to real-world data. This approach shows that forest management can benefit from IT segmentation, using a handheld TLS to improve data collection productivity.

Individual tree segmentation (ITS) from terrestrial laser scanning (TLS) point clouds is foundational for deriving detailed forest structural parameters, crucial for precision forestry, biomass calculation, and carbon accounting. Conventional ITS algorithms often struggle in complex forest stands due to reliance on heuristic rules and manual feature engineering. Deep learning methodologies proffer more efficacious and automated solutions, but their segmentation accuracy is restricted by imprecise center offset predictions, particularly in intricate forest environments. To address this issue, we proposed a deep learning method, SPA-Net, for achieving tree instance segmentation of forest point clouds. Unlike methods heavily reliant on potentially error-prone global offset vector predictions, SPA-Net employs a novel sampling-shifting-grouping paradigm within its sparse geometric proposal (SGP) module to directly generate initial proposal candidates from raw point data, aiming to reduce dependence on the offset branch. Subsequently, an affinity aggregation (AA) module robustly refines these proposals by assessing inter-proposal relationships and merging fragmented segments, effectively mitigating oversegmentation of large or complex trees; integrating with SGP eliminates the postprocessing step of scoring/NMS. SPA-Net was rigorously validated on two different forest datasets. On both BaiMa and Hong-Tes Lake datasets, the approach demonstrated superior performance compared to several contemporary segmentation approaches evaluated under the same conditions. It achieved 95.8% precision, 96.3% recall, and 92.9% coverage on BaiMa dataset, and achieved 92.6% precision, 94.8% recall, and 88.8% coverage on the Hong-Tes Lake dataset. This study provides a robust tool for individual tree analysis, advancing the accuracy of individual tree segmentation in challenging forest environments.

As fundamental units of forest ecosystems, individual trees provide essential structural characteristics for forest resource assessment. However, existing LiDAR-based individual tree segmentation methods are often limited by a trade-off between information preservation and computational efficiency. This study proposes a novel framework for individual tree segmentation from LiDAR data based on canopy surface points (CSP), aiming to balance this trade-off. The framework introduces a Snow-Covered Filter (SCF) that simulates snow deposition to extract surface points from the point cloud. After removing ground points from these surface points, the resulting CSP retains the core 3D structure of the canopy while significantly reducing data volume. We validate the proposed framework on four multi-platform datasets using four algorithms that represent the evolution of individual tree segmentation methods: Dalponte2016, K-means, Li2012, and SegmentAnyTree. The results demonstrate that: (a) the SCF effectively extracts surface points, with an average F1-score of 0.703; (b) segmentation using CSP achieves accuracy comparable to that obtained using all points or raster data (mean ΔF = 0.027), with the primary gap observed for SegmentAnyTree (maximum F-score reduction of 0.259); (c) the framework offers substantial efficiency gains: >40% point reduction, ~38.4% average runtime reduction (maximum saving ~4660 s), and lower memory consumption. By providing a lightweight yet structurally rich data representation, this work presents an innovative and efficient approach to individual tree segmentation, with promising potential for large-scale forest resource management.

Mountain treelines are among the most climate-sensitive ecosystems on Earth, yet their fine-scale structural and species level dynamics remain poorly resolved in the Himalayas. In particular, the absence of three-dimensional, crown level measurements have hindered the detection of structural thresholds and species turnover that often precede treeline shifts. To bridge this gap, we introduce UAV LiDAR—applied for the first time in the Hindu Kush Himalayas—to quantify canopy structure and tree species distributions across a steep treeline ecotone in the Manang Valley of central Nepal. High-density UAV-LiDAR data acquired over elevations of 3504–4119 m was used to quantify elevation-dependent changes in canopy stature and cover from a canopy height model derived from the 3D point cloud, while individual tree segmentation and species classification were performed directly on the 3D, height-normalized point cloud at the crown level. Individual trees were delineated using a watershed-based segmentation algorithm while tree species were classified using a random forest model trained on LiDAR-derived structural and intensity metrics, supported by field-validated reference data. Results reveal a sharply defined treeline characterized by an abrupt collapse in canopy height and cover within a narrow ~60–80 m vertical interval. Treeline “threshold” was quantified as a breakpoint elevation from a piecewise model of tree cover versus elevation, and the elevation span over which modeled cover and height distributions rapidly declined from forest values to near-zero. Segmented regression identified a distinct structural breakpoint near 3995 m elevation. Crown-level species predictions aggregated by elevation quantified an ordered turnover in dominance, with Pinus wallichiana most frequent at lower elevations, Abies spectabilis peaking mid-slope, and Betula utilis concentrated near the upper treeline. Species classification achieved high overall accuracy (>85%), although performance varied among taxa, with broadleaf Betula more difficult to discriminate than conifers. These findings underscore UAV LiDAR’s value for resolving sharp ecological thresholds, identifying elevation-driven simplification in forest structure, and bridging observation gaps in remote, rugged mountain ecosystems.

Individual tree detection from airborne laser scanning data based on supervoxels and local convexity

Forests are the main part of the terrestrial ecosystem. Airborne LiDAR is fast, comprehensive, penetrating, and contactless and can depict 3D canopy information with a high efficiency and accuracy. Therefore, it plays an important role in forest ecological protection, tree species recognition, carbon sink calculation, etc. Accurate recognition of individual trees in forests is a key step to various application. In real practice, however, the accuracy of individual tree segmentation (ITS) is often compromised by under-segmentation due to the diverse species, obstruction and understory trees typical of a high-density multistoried mixed forest area. Therefore, this paper proposes an ITS optimization method based on Gaussian mixture model for airborne LiDAR data. First, the mean shift (MS) algorithm is used for the initial ITS of the pre-processed airborne LiDAR data. Next, under-segmented samples are extracted by integrated learning, normally segmented samples are classified by morphological approximation, and the approximate distribution uncertainty of the normal samples is described with a covariance matrix. Finally, the class composition among the under-segmented samples is determined, and the under-segmented samples are re-segmented using Gaussian mixture model (GMM) clustering, in light of the optimal covariance matrix of the corresponding categories. Experiments with two datasets, Trento and Qingdao, resulted in ITS recall of 94% and 96%, accuracy of 82% and 91%, and F-scores of 0.87 and 0.93. Compared with the MS algorithm, our method is more accurate and less likely to under-segment individual trees in many cases. It can provide data support for the management and conservation of high-density multistoried mixed forest areas.

In recent years, due to the significant advancements in hardware sensors and software technologies, 3D environmental point cloud modeling has gradually been applied in the automation industry, autonomous vehicles, and construction engineering. With the high-precision measurements of 3D LiDAR, its point clouds can clearly reflect the geometric structure and features of the environment, thus enabling the creation of high-density 3D environmental point cloud models. However, due to the enormous quantity of high-density 3D point clouds, storing and processing these 3D data requires a considerable amount of memory and computing time. In light of this, this paper proposes a real-time 3D point cloud environmental contour modeling technique. The study uses the point cloud distribution from the 3D LiDAR body frame point cloud to establish structured edge features, thereby creating a 3D environmental contour point cloud map. Additionally, unstable objects such as vehicles will appear during the mapping process; these specific objects will be regarded as not part of the stable environmental model in this study. To address this issue, the study will further remove these objects from the 3D point cloud through image recognition and LiDAR heterogeneous matching, resulting in a higher quality 3D environmental contour point cloud map. This 3D environmental contour point cloud not only retains the recognizability of the environmental structure but also solves the problems of massive data storage and processing. Moreover, the method proposed in this study can achieve real-time realization without requiring the 3D point cloud to be organized in a structured order, making it applicable to unorganized 3D point cloud LiDAR sensors. Finally, the feasibility of the proposed method in practical applications is also verified through actual experimental data.

The long-lasting outbreak of the pine shoot beetle (PSB, Tomicus spp.) threatens forest ecological security. Effective monitoring is urgently needed for the Integrated Pest Management (IPM) of this pest. UAV-based hyperspectral remote sensing (HRS) offers opportunities for the early and accurate detection of PSB attacks. However, the insufficient exploration of spectral and structural information from early-attacked crowns and the lack of suitable detection models limit UAV applications. This study developed a UAV-based framework for detecting early-stage PSB attacks by integrating hyperspectral images (HSIs), LiDAR point clouds, and structure from motion (SfM) photogrammetry data. Individual tree segmentation algorithms were utilized to extract both spectral and structural variables of damaged tree crowns. Random forest (RF) was employed to determine the optimal detection model as well as to clarify the contributions of the candidate variables. The results are as follows: (1) Point cloud segmentation using the Canopy Height Model (CHM) yielded the highest crown segmentation accuracy (F-score: 87.80%). (2) Near-infrared reflectance exhibited the greatest decrease for early-attacked crowns, while the structural variable intensity percentile (int_P50-int_P95) showed significant differences (p < 0.05). (3) In the RF model, spectral variables were predominant, with LiDAR structural variables serving as a supplement. The anthocyanin reflectance index and int_kurtosis were identified as the best indicators for early detection. (4) Combining HSI with LiDAR data obtained the best RF model accuracy (classification accuracy: 87.31%; Kappa: 0.8275; SDR estimation accuracy: R2 = 0.8485; RMSEcv = 3.728%). RF integrating HSI and SfM data exhibited similar performance. In conclusion, this study identified optimal spectral and structural variables for UAV monitoring and improved HRS model accuracy and thereby provided technical support for the IPM of PSB outbreaks.

Benchmarking tree instance segmentation of terrestrial laser scanning point clouds

ABSTRACTThis letter aims to propose an automatic method for the segmentation of street trees from LiDAR point clouds. The first step is to extract tree points to reduce the scale of data to be processed. The second step is to formulate supervoxels for grouping homogeneous points. The third step is to optimize the segmentation of individual trees based on the minimum distance rule. Each supervoxel will be assigned the same tree index as its spatially closest treetop supervoxel, therefore, points from the homogeneous region sharing the same tree index. Experiments show that we achieve the completeness of 78.5%, correctness of 94.5% and -score of 0.85 in the airborne LiDAR data. For mobile LiDAR data our accuracy is 100, 93.8% and 0.96 in terms of the recall, precision and -score, respectively.

Structural complexity refers to the three-dimensional arrangement and variability of both biotic and abiotic components of an ecosystem. Metrics that characterize structural complexity are often used to manage various aspects of ecosystem function, such as light transmittance, wildlife habitat, and biological diversity. Additionally, these metrics aid in evaluating resilience to disturbance events, including hurricanes, bark-beetle outbreaks, and wildfire. Recent advances in wildland fire modelling have facilitated the integration of forest structural complexity metrics into the QUIC-Fire model, enabling real-time prediction of fire spread and behaviour by simulating interactions between fire, weather, topography, and forest structure. While QUIC-Fire is designed to be highly adaptable, model performance depends on the availability and accuracy of local data inputs. Expanding the model's usability across different regions can be facilitated by the availability of more comprehensive and high-quality data. Thus, the primary goal behind the data products we developed was to establish a basis for collaborative research across various disciplines, particularly within the focal areas of the Southern Research Station, such as forestry, wildland fire, hydrology, soil science, and cultural resources at Bent Creek, Coweeta, Escambia, and Hitchiti Experimental Forests (EFs).Airborne laser scanning (ALS) was used to collect point-cloud data for each EF during the leaf-off season to minimize interference from foliage. Subsequent processing of the raw lidar data involved outlier detection and filtering, ground and non-ground classification, and the computation of a variety of metrics representing various aspects of topography and forest structure at both the pixel-level and the tree-level. Pixel-level topographic data products include: digital elevation model (DEM), slope, aspect, topographic position index (TPI), topographic roughness index (TRI), roughness, and flow direction. Forest structural-complexity metrics include canopy height, foliar height diversity (FHD), vertical distribution ratio (VDR), canopy rugosity, crown relief ratio (CRR), understory complexity index (UCI), vertical complexity index (VCI), canopy cover, mean vegetation height, and the standard deviation of vegetation height. Tree-level data products were computed from the point cloud using multiple algorithms to perform individual tree detection (ITD) and individual tree segmentation (ITS). The datasets have been harmonized and are openly accessible through the USDA Forest Service Research Data Archive.

The spectral clustering method has notable advantages in segmentation. But the high computational complexity and time consuming limit its application in large-scale and dense airborne Light Detection and Ranging (LiDAR) point cloud data. We proposed the Nyström-based spectral clustering (NSC) algorithm to decrease the computational burden. This novel NSC method showed accurate and rapid in individual tree segmentation using point cloud data. The K-nearest neighbour-based sampling (KNNS) was proposed for the Nyström approximation of voxels to improve the efficiency. The NSC algorithm showed good performance for 32 plots in China and Europe. The overall matching rate and extraction rate of proposed algorithm reached 69% and 103%. For all trees located by Global Navigation Satellite System (GNSS) calibrated tape-measures, the tree height regression of the matching results showed an value of 0.88 and a relative root mean square error (RMSE) of 5.97%. For all trees located by GNSS calibrated total-station measures, the values were 0.89 and 4.49%. The method also showed good performance in a benchmark dataset with an improvement of 7% for the average matching rate. The results demonstrate that the proposed NSC algorithm provides an accurate individual tree segmentation and parameter estimation using airborne LiDAR point cloud data.

This paper provides a practical procedure for fusing LiDAR and photogrammetric point clouds for the extraction of tree metrics. Aerial photogrammetric point clouds are first generated using the structure-from-motion and dense-matching methods. Registration of the LiDAR and photogrammetric point clouds is then performed using an onboard global positioning system and inertial measurement unit. However, due to systematic deviations, it is impossible to directly merge the two types of point cloud. Therefore, an urban street network obtained from the OpenStreetMap digital mapping system is utilized for point cloud segmentation. After segmentation, each chunk is finely registered and merged based on the iterative closest point algorithm, allowing the two types of data to be accurately co-registered and a fused point cloud obtained. Finally, we conducted experiments to extract stand and individual tree metrics from fused point clouds created for two study plots. The height distributions of the fused point clouds were highly consistent with LiDAR data, with the 5%, 10%, 25%, 50%, 75%, 90%, and 95% height percentiles showing acceptable similarities. The height distribution of individual trees was also consistent with that of field measurements. Furthermore, the fused point clouds contain a high point density and RGB color information, which allow shape delineation and estimation of tree health status. This comprehensive analysis demonstrates that this procedure provides a practical way to inventory tree stands and individuals in urban areas.