Extract Individual Tree Research Articles

CDP-MVS: Forest Multi-View Reconstruction with Enhanced Confidence-Guided Dynamic Domain Propagation

Using multi-view images of forest plots to reconstruct dense point clouds and extract individual tree parameters enables rapid, high-precision, and cost-effective forest plot surveys. However, images captured at close range face challenges in forest reconstruction, such as unclear canopy reconstruction, prolonged reconstruction times, insufficient accuracy, and issues with tree duplication. To address these challenges, this paper introduces a new image dataset creation process that enhances both the efficiency and quality of image acquisition. Additionally, a block-matching-based multi-view reconstruction algorithm, Forest Multi-View Reconstruction with Enhanced Confidence-Guided Dynamic Domain Propagation (CDP-MVS), is proposed. The CDP-MVS algorithm addresses the issue of canopy and sky mixing in reconstructed point clouds by segmenting the sky in the depth maps and setting its depth value to zero. Furthermore, the algorithm introduces a confidence calculation method that comprehensively evaluates multiple aspects. Moreover, CDP-MVS employs a decentralized dynamic domain propagation sampling strategy, guiding the propagation of the dynamic domain through newly defined confidence measures. Finally, this paper compares the reconstruction results and individual tree parameters of the CDP-MVS, ACMMP, and PatchMatchNet algorithms using self-collected data. Visualization results show that, compared to the other two algorithms, CDP-MVS produces the least sky noise in tree reconstructions, with the clearest and most detailed canopy branches and trunk sections. In terms of parameter metrics, CDP-MVS achieved 100% accuracy in reconstructing tree quantities across the four plots, effectively avoiding tree duplication. The accuracy of breast diameter extraction values of point clouds reconstructed by CDPMVS reached 96.27%, 90%, 90.64%, and 93.62%, respectively, in the four sample plots. The positional deviation of reconstructed trees, compared to ACMMP, was reduced by 0.37 m, 0.07 m, 0.18 m and 0.33 m, with the average distance deviation across the four plots converging within 0.25 m. In terms of reconstruction efficiency, CDP-MVS completed the reconstruction of the four plots in 1.8 to 3.1 h, reducing the average reconstruction time per plot by six minutes compared to ACMMP and by two to three times compared to PatchMatchNet. Finally, the differences in tree height accuracy among the point clouds reconstructed by the different algorithms were minimal. The experimental results demonstrate that CDP-MVS, as a multi-view reconstruction algorithm tailored for forest reconstruction, shows promising application potential and can provide valuable support for forestry surveys.

Estimating the Aboveground Biomass of Robinia pseudoacacia Based on UAV LiDAR Data

Robinia pseudoacacia is widely planted in the Loess Plateau as a major soil and water conservation tree species because of its dense canopy, complex structure, and strong soil and water conservation ability. The precise measurement of small-scale locust forest biomass is crucial to monitoring and evaluating the carbon sequestration functions of soil and water conservation vegetation. This study focuses on an artificial locust forest planted in the early 1990s in Caijiachuan Basin, Jixian County, Shanxi Province. A drone equipped with LiDAR was used to obtain point cloud data and generate a canopy height model. A watershed segmentation algorithm was used to identify tree vertices and extract individual trees. A relationship model between tree height, diameter at breast height, and biomass, combined with sample survey data, was established to explore the spatial distribution of biomass in the artificial locust forest at the level of the entire basin. The results show the following: (1) the structural parameters of locust extracted using UAV point cloud data have a good degree of fit and accuracy, and the recall rate is 72.7%; (2) the average error rate of the extracted maximum tree height value of locust is 7%, that of the minimum tree height value is 14%, and that of the average tree height value is 18%; (3) the average error rate of the extracted maximum diameter at breast height of locust is 15%, that of the minimum diameter at breast height is 37%, and that of the average diameter at breast height is 36%; and (4) the average error rate of the biomass estimation of locust calculated using point cloud data is 16.0%.

INDIVIDUAL TREE SEGMENTATION FROM BLS DATA BASED ON GRAPH AUTOENCODER

Abstract. In the last two decades, Light detection and ranging (LiDAR) has been widely employed in forestry applications. Individual tree segmentation is essential to forest management because it is a prerequisite to tree reconstruction and biomass estimation. This paper introduces a general framework to extract individual trees from the LiDAR point cloud based on a graph link prediction problem. First, an undirected graph is generated from the point cloud based on K-nearest neighbors (KNN). Then, this graph is used to train a convolutional autoencoder that extracts the node embeddings to reconstruct the graph. Finally, the individual trees are defined by the separate sets of connected nodes of the reconstructed graph. A key advantage of the proposed method is that no further knowledge about tree or forest structure is required. Seven sample plots from a plantation forest with poplar and dawn redwood species have been employed in the experiments. Though the precision of the experimental results is up to 95 % for poplar species and 92 % for dawn redwood trees, the method still requires more investigations on natural forest types with mixed tree species.

Soft Segmentation and Reconstruction of Tree Crown from Laser Scanning Data

Point cloud data obtained by laser scanning can be used for object shape modeling and analysis, including forest inventory. One of the inventory tasks is individual tree extraction and measurement. However, individual tree segmentation, especially tree crown segmentation, is challenging. In this paper, we present a novel soft segmentation algorithm to segment tree crowns in point clouds automatically and reconstruct the tree crown surface from the segmented crown point cloud. The soft segmentation algorithm mainly processes the overlapping region of the tree crown. The experimental results showed that the segmented crown was accurate, and the reconstructed crown looked natural. The reconstruction algorithm was highly efficient in calculating the time and memory cost aspects since the number of the extracted boundary points was small. With the reconstructed crown geometry, the crown attributes, including the width, height, superficial area, projecting ground area, and volume, could be estimated. The algorithm presented here is effective for tree crown segmentation.

An Individual Tree Segmentation Method That Combines LiDAR Data and Spectral Imagery

The dynamic monitoring of forest resources is an integral component of forest resource management and forest eco-system stability maintenance. In recent years, LiDAR (Light Detection and Ranging) has been increasingly utilized in precision forest surveys due to its great penetrating ability and capacity to detect forest vertical structure information. However, the present airborne LiDAR data individual tree segmentation algorithms are not highly adaptable to forest types, particularly in mixed coniferous and broad-leaved forest zones, where the accuracy of individual tree extraction is low, and trees are incorrectly recognized and missed. In order to address these issues, in this study, spectral images and LiDAR data of a red pine conifer–broadleaf mixed forest in the Changbai Mountain Nature Reserve in Jilin Province were chosen, and the normalized point cloud was segmented iteratively using the distance-threshold-based individual tree segmentation method to obtain the initial segmented individual tree vertices. For individual trees with deviations in the initial vertex identification position, and unidentified individual trees, identification anchor points of real tree vertices are added within the canopy of the trees. These identification anchor points have strong position directivity in LiDAR data, which can mark the individual trees whose vertices were misidentified or missed during the initial individual tree segmentation process and identify these two tuples. The tree vertices may be inserted precisely based on the 3D shape of the individual tree point cloud, and the seed-point-based individual tree segmentation method is used to segment the normalized point cloud and finish the extraction of individual trees in red pine mixed conifer forests. The results indicate that, compared to the previous individual tree segmentation approach based on the relative spacing between individual trees, this study enhances the accuracy of individual tree segmentation from 83% to 96%. The extremely high segmentation accuracy indicates that the proposed method can accurately identify individual trees based on remote sensing techniques to segment forest individual trees, can provide a data basis for subsequent individual tree information extraction, and has great potential in practical applications.

An object-based image analysis approach for comparing tree detection from satellite imagery at different scales; A case study in Sukumba Mali

This paper combines an object-based image analysis (OBIA) approach, with markov-random field based-super resolution mapping (MRF-SRM) technique to extract individual tree objects from satellite imagery. Extraction of individual trees in urban and developing cities using satellite imageries has been quite challenging and a subject of active research with many approaches to it. The study area is a part of Sukumba village located in Koutiala district, Mali. The aim is to evaluate the performance comparison of the combined MRF-SRM approach, which was demonstrated for each combination of scale factor and class separability. Due to varying contrast sensitivity, there exist a general limitation in the spatial distribution of land cover data sets derived from most coarse and fine resolution satellite imageries. A 10 m spatial resolution Sentinel-2 and 2 m spatial resolution Worldview-3 satellite images were used for the study. First, the pixel based MRF-SRM classification technique of Tolpekin and Stein, 2009 was applied on both images. Subsequently, the classified SRM thematic results were partitioned into objects (segments) using region growing segmentation algorithm as post a classification procedure. Finally, validation and comparison of the resulting tree objects was done using an object based image analysis approach to determine existential (TP), extensional (FP) and positional (PA) accuracy. For Sentinel-2 image and out of 1787 reference objects, 1214 (TP) was detected and 573 (FP) was undetected. The PA is 6.504 m out of 10 m, total detection error is 0.467 m and the final detection accuracy is 68%. Similarly, for Worldview-3 image and out of 1787 reference objects, 1772 (TP) was detected and 15 (FP) was undetected. The PA is 1.714 m out of 2 m, total detection error is 0.318 m and the final detection accuracy is 99%. The successful approach used in this study will support the capacity of monitoring agricultural change in data sparse regions and developing countries.

Forest Structure Measurement in Tropical Rainforest using Laser Scanning Technology

Numerous measurements can be made to extract the forest structure. Forest structure is one of the main aspects of forest management. The precise estimation of forest structure is vital for some forestry applications. Thus, this study presents a novel non-destructive approach for the measurement of forest structure using laser scanning technologies of airborne LiDAR and Terrestrial Laser Scanning (TLS). The study area was located at the forest campus of the Forest Research Institute of Malaysia (FRIM), Kepong, Selangor. The elements of forest structure that were measured: were canopy height; plant density and basal area. The field survey was conducted over 3 plots of 25 m radius circular shape with a total of 60 trees with diameter at breast height (DBH) of 10 cm and above. The tree canopy height was estimated based on canopy height model (CHM) of LiDAR data. For plant density, it was estimated based on crown delineation created from CHM. While, for TLS data, the extraction of individual trees was done using Cyclone algorithm. The forest structure measurement obtained from laser scanning technologies is proven to be reliable with the root mean square error (RMSE) of 5.415, t-test of 3.011, and p-value of 0.004 for canopy height. For basal area, the mean of RMSE, t-test and p-value was 0.22589, 0.620 and 0.324 for the overall 3 plots, respectively. The result obtained for plant density was one tree per meter². The final outputs were presented as the map of CHM, plant density and basal area map. In conclusion, laser scanning measurement improves and provides a precise technique for forest structure measurement.

Trunk-Constrained and Tree Structure Analysis Method for Individual Tree Extraction from Scanned Outdoor Scenes

The automatic extraction of individual tree from mobile laser scanning (MLS) scenes has important applications in tree growth monitoring, tree parameter calculation and tree modeling. However, trees often grow in rows and tree crowns overlap with varying shapes, and there is also incompleteness caused by occlusion, which makes individual tree extraction a challenging problem. In this paper, we propose a trunk-constrained and tree structure analysis method to extract trees from scanned urban scenes. Firstly, multi-feature enhancement is performed via PointNet to segment the tree points from raw urban scene point clouds. Next, the candidate local tree trunk clusters are obtained by clustering based on the intercepted local tree trunk layer, and the real local tree trunk is obtained by removing noise data. Then, the trunk is located and extracted by combining circle fitting and region growing, so as to obtain the center of the tree crown. Further, the points near the tree’s crown (core points) are segmented through distance difference, and the tree crown boundary (boundary points) is distinguished by analyzing the density and centroid deflection angle. Therefore, the core and boundary points are deleted to obtain the remaining points (intermediate points). Finally, the core, intermediate and boundary points, as well as the tree trunks, are combined to extract individual tree. The performance of the proposed method was evaluated on the Pairs-Lille-3D dataset, which is a benchmark for point cloud classification, and data were produced using a mobile laser system (MLS) applied to two different cities in France (Paris and Lille). Overall, the precision, recall, and F1-score of instance segmentation were 90.00%, 98.22%, and 99.08%, respectively. The experimental results demonstrate that our method can effectively extract trees with multiple rows of occlusion and improve the accuracy of tree extraction.

Tree Species Classification Using Ground-Based LiDAR Data by Various Point Cloud Deep Learning Methods

Tree species information is an important factor in forest resource surveys, and light detection and ranging (LiDAR), as a new technical tool for forest resource surveys, can quickly obtain the 3D structural information of trees. In particular, the rapid and accurate classification and identification of tree species information from individual tree point clouds using deep learning methods is a new development direction for LiDAR technology in forest applications. In this study, mobile laser scanning (MLS) data collected in the field are first pre-processed to extract individual tree point clouds. Two downsampling methods, non-uniform grid and farthest point sampling, are combined to process the point cloud data, and the obtained sample data are more conducive to the deep learning model for extracting classification features. Finally, four different types of point cloud deep learning models, including pointwise multi-layer perceptron (MLP) (PointNet, PointNet++, PointMLP), convolution-based (PointConv), graph-based (DGCNN), and attention-based (PCT) models, are used to classify and identify the individual tree point clouds of eight tree species. The results show that the classification accuracy of all models (except for PointNet) exceeded 0.90, where the PointConv model achieved the highest classification accuracy for tree species classification. The streamlined PointMLP model can still achieve high classification accuracy, while the PCT model did not achieve good accuracy in the tree species classification experiment, likely due to the small sample size. We compare the training process and final classification accuracy of the different types of point cloud deep learning models in tree species classification experiments, further demonstrating the advantages of deep learning techniques in tree species recognition and providing experimental reference for related research and technological development.

Semantic Segmentation Guided Coarse-to-Fine Detection of Individual Trees from MLS Point Clouds Based on Treetop Points Extraction and Radius Expansion

Urban trees are vital elements of outdoor scenes via mobile laser scanning (MLS), accurate individual trees detection from disordered, discrete, and high-density MLS is an important basis for the subsequent analysis of city management and planning. However, trees cannot be easily extracted because of the occlusion with other objects in urban scenes. In this work, we propose a coarse-to-fine individual trees detection method from MLS point cloud data (PCD) based on treetop points extraction and radius expansion. Firstly, an improved semantic segmentation deep network based on PointNet is applied to segment tree points from the scanned urban scene, which combining spatial features and dimensional features. Next, through calculating the local maximum, the candidate treetop points are located. In addition, the optimized treetop points are extracted after the tree point projection plane was filtered to locate the candidate treetop points, and a distance rule is used to eliminate the pseudo treetop points then the optimized treetop points are obtained. Finally, after the initial clustering of treetop points and vertical layering of tree points, a top-down layer-by-layer segmentation based on radius expansion to realize the complete individual extraction of trees. The effectiveness of the proposed method is tested and evaluated on five street scenes in point clouds from Oakland outdoor MLS dataset. Furthermore, the proposed method is compared with two existing individual trees segmentation methods. Overall, the precision, recall, and F-score of instance segmentation are 98.33%, 98.33%, and 98.33%, respectively. The results indicate that our method can extract individual trees effectively and robustly in different complex environments.

Reliably mapping low-intensity forest disturbance using satellite radar data

In the last decades tropical forests have experienced increased fragmentation due to a global growing demand for agricultural and forest commodities. Satellite remote sensing offers a valuable tool for monitoring forest loss, thanks to the global coverage and the temporal consistency of the acquisitions. In tropical regions, C-band Synthetic Aperture Radar (SAR) data from the Sentinel-1 mission provides cloud-free and open imagery on a 6- or 12-day repeat cycle, offering the unique opportunity to monitor forest disturbances in a timely and continuous manner. Despite recent advances, mapping subtle forest losses, such as those due to small-scale and irregular selective logging, remains problematic. A Cumulative Sum (CuSum) approach has been recently proposed for forest monitoring applications, with preliminary studies showing promising results. Unfortunately, the lack of accurate in-situ measurements of tropical forest loss has prevented a full validation of this approach, especially in the case of low-intensity logging. In this study, we used high-quality field measurements from the tropical Forest Degradation Experiment (FODEX), combining unoccupied aerial vehicle (UAV) LiDAR, Terrestrial Laser Scanning (TLS), and field-inventoried data of forest structural change collected in two logging concessions in Gabon and Peru. The CuSum algorithm was applied to VV-polarized Sentinel-1 ground range detected (GRD) time series to monitor a range of canopy loss events, from individual tree extraction to forest clear cuts. We developed a single change metric using the maximum of the CuSum distribution, retrieving location, time, and magnitude of the disturbance events. A comparison of the CuSum algorithm with the LiDAR reference map resulted in a 78% success rate for the test site in Gabon and 65% success rate for the test site in Peru, for disturbances as small as 0.01 ha in size and for canopy height losses as fine as 10 m. A correlation between the change metric and above ground biomass (AGB) change was found with R2 = 0.95, and R2 = 0.83 for canopy height loss. From the regression model we directly estimated local AGB loss maps for the year 2020, at 1 ha scale and in percentages of AGB loss. Comparison with the Global Forest Watch (GFW) Tree Cover Loss (TCL) product showed a 61% overlap between the two maps when considering only deforested pixels, with 504 ha of deforestation detected by CuSum vs. 348 ha detected by GFW. Low intensity disturbances captured by the CuSum method were largely undetected by GFW and by the SAR-based Radar for Detecting Deforestation (RADD) Alert System. The results of this study confirm this approach as a simple and reproducible change detection method for monitoring and quantifying fine-scale to high intensity forest disturbances, even in the case of multi-storied and high biomass forests.

A novel algorithm of individual tree crowns segmentation considering three-dimensional canopy attributes using UAV oblique photos

Extracting the individual tree crowns (ITCs) information is significant to fine forest resource investigation and carbon storage estimation. UAV oblique photogrammetry (UOP) can obtain point cloud data with high density due to higher presence of overlap, which has potential for tree crown information extraction. Many ITCs segmentation methods have been proposed to extract individual tree information. However, accurate ITCs segmentation using UOP data remains a challenge due to the uncertainties in environments with high heterogeneity of forest canopy vertical structure. Here, we proposed a novel approach, adaptive-kernel bandwidth mean-shift algorithm (AMS) considering three-dimensional canopy attributes, to segment ITCs using UOP data in complex forest environment. First, we developed a kernel bandwidth model with automatic adaptive parameter assignment using tree height derived from UOP data and applied it to the mean-shift algorithm. We demonstrated the generality of our algorithm in different tree species plots of a subtropical forest in China with overall precision f ≥ 0.72 and crown width rRMSE ≤ 0.13. Compared with the fixed-kernel bandwidth mean-shift algorithm (FMS) and seed region growth algorithm (SRG), the average f and rRMSE of the AMS algorithm were improved by 0.04 and 0.12, 0.16 and 0.11 respectively. Then, we evaluated the segmentation effect of AMS algorithm with point cloud densities of 25%, 50%, 75% and 100% respectively. We found that the segmentation accuracy decreases with decreasing point cloud density, but 75% of the point cloud density can satisfy most ITCs segmentation needs. In addition, we used LiDAR data (∼45 pts/m2) obtained by UAV to validate generalization ability of our approach, and the average r, p and f reached 0.97, 0.73 and 0.83. These results showed that the AMS algorithm can solve the ITCs segmentation problem in forests with complex structures using UOP and LiDAR point cloud data, which can support the accurate survey and scientific management of forest resources and provide basic data for the accurate estimation of forest carbon sinks.

Individual tree point clouds and tree measurements from multi-platform laser scanning in German forests

Abstract. Laser scanning from different acquisition platforms enables the collection of 3D point clouds from different perspectives and with varying resolutions. These point clouds allow us to retrieve detailed information on the individual tree and forest structure. We conducted airborne laser scanning (ALS), uncrewed aerial vehicle (UAV)-borne laser scanning (ULS) and terrestrial laser scanning (TLS) in two German mixed forests with species typical of central Europe. We provide the spatially overlapping, georeferenced point clouds for 12 forest plots. As a result of individual tree extraction, we furthermore present a comprehensive database of tree point clouds and corresponding tree metrics. Tree metrics were derived from the point clouds and, for half of the plots, also measured in the field. Our dataset may be used for the creation of 3D tree models for radiative transfer modeling or lidar simulation studies or to fit allometric equations between point cloud metrics and forest inventory variables. It can further serve as a benchmark dataset for different algorithms and machine learning tasks, in particular automated individual tree segmentation, tree species classification or forest inventory metric prediction. The dataset and supplementary metadata are available for download, hosted by the PANGAEA data publisher at https://doi.org/10.1594/PANGAEA.942856 (Weiser et al., 2022a).

Extraction of individual trees based on Canopy Height Model to monitor the state of the forest

Active remotely sensed data can be used to perform a variety of forestry tasks including stand characterization, inventory, and management of forest and fire behavior modeling. The present work investigates the potential of Airborne Laser Scanning (ALS) derived methods applied in the deciduous forest by processing an individual tree detection (ITD) based on canopy Height model (CHM) and tree segmentation of larger-area point clouds. Different algorithms are tested and their performances are evaluated to show which of them can provide the most adequate number of trees compared with the ground truth. Tree scale information is used in order to determine stand age. The forest height, structure, and density are specified by applying individual tree Detection (ITD) to calculate some forest attributes such as stem volume, forest uniformity, and biomass estimation. The major aim of this post is to examine the state of the forest to monitor it in real-time. We assume that utilizing the LM algorithm, which was originally built for ITD from LiDAR data, trees should be automatically distinguished from the ALS-derived CHM with reasonable accuracy. As a result, the present research work studies the fixed treetop window size (FWS), fixed smoothing window size (SWS), and variable window (VW) effect on ITD performance (RMSE=3.4% and R=0.88). It is obvious, from the obtained results that smaller window sizes result in more trees. In fact, the smallest trees obscured by the largest trees containing the highest points in the neighborhood are often ignored by large windows. Crown delineation is also explored to extract the height of the trees, radius crown and, 3D coordinates and to compare them to those detected by a Low Bluetooth sensor “iBeacon.”.

Estimating aboveground biomass of urban forest trees with dual-source UAV acquired point clouds

Urban forest is a crucial part of urban ecological environment. The accurate estimation of its tree aboveground biomass (AGB) is of significant value to evaluate urban ecological functions and estimate urban forest carbon storage. It has a high accuracy to estimate the forest AGB with field measured canopy structure parameters, but unsuitable for large-scale operations. Limited by low spatial resolution or spectral saturation, the estimated forest AGBs based on various satellite remotely sensed data have relatively low accuracies. In contrast, Unmanned Aerial Vehicle (UAV) remote sensing provides a promising way to accurately estimate the tree AGB of fragmented urban forest. In this study, taking an artificial urban forest in Ma'anxi Wetland Park in Chongqing City, China as an example, we used UAVs equipped with a digital camera and a LiDAR to acquire two point cloud data. One was produced from overlapping images using Structure from Motion (SfM) photogrammetry, and the other was resolved from laser scanned raw data. The dual point clouds were combined to extract individual tree height (H) and canopy radius (Rc), which were then input to the newly established allometric equation with tree H and Rc as predictor variables to obtain the AGBs of all dawn redwood trees in study area. In accuracy assessment, the coefficient of determination (R2) and Root Mean Square Error (RMSE) of extracted H were 0.9341 and 0.59 m; the R2 and RMSE of extracted Rc were 0.9006 and 0.28 m; the R2 and RMSE of estimated AGB were 0.9452 and 17.59 kg. These results proved the feasibility and effectiveness of applying dual-source UAV point cloud data and the new allometric equation on H and Rc to accurate AGB estimation of urban forest trees.

Allometric Vegetation Modeling and SAR Image Simulation for Polarimetry and Interferometry

This paper establishes a low degrees-of-freedom allometric vegetation model based on the Biomass and allometry database (BAAD). It consists of a 5-bit species encoding scheme and a 5-parameter relationship derived from the BAAD data records. Combined with opensource fractal tree generation engine, it can produce realistic tree samples of a large variety of species. A coherent electromagnetic scattering calculation method is developed for the vegetation model where the generalized Rayleigh-Gans (GRG) approximation and the infinite cylinder approximation are used to calculate the scattering matrix of leaves and branches/trunk. Four-path multiple scattering mechanisms between vegetation and the ground are considered and attenuations through vegetation canopy are also considered. The scattering model is validated against numerical methods. In addition, an end-to-end simulation tool is developed. Optical image is used to extract individual trees with center positions and crown diameters. The rest parameters are generated using the derived allometry model. Virtual 3D scene with vegetation on digital elevation map (DEM) can be generated and SAR images can be simulated. Several case studies are carried out for both polarimetric synthetic aperture radar (SAR) interferometry (PolInSAR) and multi-temporal interferometric SAR (InSAR). One case of the Mount Fuji area is simulated and validated against ALOS-2 data and demonstrates an average scattering coefficient error of less than 3dB. Additional cases of Southwest China, Hainan Island and the Great Khingan Mountain demonstrate the feasibility of the proposed simulation scheme for various application scenarios.

Individual Tree Structural Parameter Extraction and Volume Table Creation Based on Near-Field LiDAR Data: A Case Study in a Subtropical Planted Forest.

Individual tree structural parameters are vital for precision silviculture in planted forests. This study used near-field LiDAR (light detection and ranging) data (i.e., unmanned aerial vehicle laser scanning (ULS) and ground backpack laser scanning (BLS)) to extract individual tree structural parameters and fit volume models in subtropical planted forests in southeastern China. To do this, firstly, the tree height was acquired from ULS data and the diameter at breast height (DBH) was acquired from BLS data by using individual tree segmentation algorithms. Secondly, point clouds of the complete forest canopy were obtained through the combination of ULS and BLS data. Finally, five tree taper models were fitted using the LiDAR-extracted structural parameters of each tree, and then the optimal taper model was selected. Moreover, standard volume models were used to calculate the stand volume; then, standing timber volume tables were created for dawn redwood and poplar. The extraction of individual tree structural parameters exhibited good performance. The volume model had a good performance in calculating the standing volume for dawn redwood and poplar. Our results demonstrate that near-field LiDAR has a strong capability of extracting tree structural parameters and creating volume tables for subtropical planted forests.

Testing Forestry Digital Twinning Workflow Based on Mobile LiDAR Scanner and AI Platform

Climate-smart forestry is a sustainable forest management approach for increasing positive climate impacts on society. As climate-smart forestry is focusing on more sustainable solutions that are resource-efficient and circular, digitalization plays an important role in its implementation. The article aimed to validate an automatic workflow of processing 3D pointclouds to produce digital twins for every tree on large 1-ha sample plots using a GeoSLAM mobile LiDAR scanner and VirtSilv AI platform. Specific objectives were to test the efficiency of segmentation technique developed in the platform for individual trees from an initial cloud of 3D points observed in the field and to quantify the efficiency of digital twinning by comparing the automatically generated results of (DBH, H, and Volume) with traditional measurements. A number of 1399 trees were scanned with LiDAR to create digital twins and, for validation, were measured with traditional tools such as forest tape and vertex. The segmentation algorithm developed in the platform to extract individual 3D trees recorded an accuracy varying between 95 and 98%. This result was higher in accuracy than reported by other solutions. When compared to traditional measurements the bias for diameter at breast height (DBH) and height was not significant. Digital twinning offers a blockchain solution for digitalization, and AI platforms are able to provide technological advantage in preserving and restoring biodiversity with sustainable forest management.

A branch-trunk-constrained hierarchical clustering method for street trees individual extraction from mobile laser scanning point clouds

The three-dimensional individual expression of street trees in the point cloud of urban road environments has important applications in many aspects. We propose a branch-trunk-constrained hierarchical clustering method to individually extract street trees from mobile laser scanning (MLS) point clouds. Firstly, potential tree crowns and trunks are selected through data preprocessing and regions of interest selection. Next, a branch-to-trunk matching method is proposed to locate the street tree positions. Then, tree crowns are segmented individually by a new hierarchical clustering method based on the identified tree positions. Finally, the tree trunk corresponding to each crown is selected from the potential ones to realize the complete individual extraction of street trees. The proposed method was tested and evaluated by three different MLS datasets. The results indicate that it can effectively extract individual street trees in different complex environments. Overall, the precision, recall and F-score of street tree positions locating have all reached 99.3%, and the precision, recall and F-score of street tree instance segmentation are 98.2%, 98.1% and 98.1%, respectively.

Drone-Image-Based Method of Estimating Forest-Fire Fuel Loads

A method of estimating forest-fire fuel loads was developed using drones to collect information about the height and diameter-at-breast-height (DBH) of individual trees. It was conducted for forest fire prevention monitoring (Control, 20% thinned, and 40% thinned area) located in Goseong-gun, Gangwon-do. Object-based images and 3D-model red/green/blue band characteristics were superimposed to select and extract individual trees. A digital crown height model was developed based on the difference between the heights of digital surface and terrain models. In addition, the DBH was estimated based on the crown area. The 40%-thinned area exhibited the highest accuracy (95%) for extracting individual trees, and the difference between the field-survey and drone-image heights was in the range of 0.64-2.02 m. The goodness-of-fit of the DBH-crown area model was 0.61. The difference between the imageand field-survey-based forest-fire fuel loads ranged from -1.20 to 0.40 ton/ha.