3D Tree Models Research Articles

VRTree: Example‐Based 3D Interactive Tree Modeling in Virtual Reality

AbstractWe present VRTree, an example‐based interactive virtual reality (VR) system designed to efficiently create diverse 3D tree models while faithfully preserving botanical characteristics of real‐world references. Our method employs a novel representation called Hierarchical Branch Lobe (HBL), which captures the hierarchical features of trees and serves as a versatile intermediary for intuitive VR interaction. The HBL representation decomposes a 3D tree into a series of concise examples, each consisting of a small set of main branches, secondary branches, and lobe‐bounded twigs. The core of our system involves two key components: (1) We design an automatic algorithm to extract an initial library of HBL examples from real tree point clouds. These HBL examples can be optionally refined according to user intentions through an interactive editing process. (2) Users can interact with the extracted HBL examples to assemble new tree structures, ensuring the local features align with the target tree species. A shape‐guided procedural growth algorithm then transforms these assembled HBL structures into highly realistic, finegrained 3D tree models. Extensive experiments and user studies demonstrate that VRTree outperforms current state‐of‐the‐art approaches, offering a highly effective and easy‐to‐use VR tool for tree modeling.

Comparing the accuracy of 3D urban olive tree models detected by smartphone using LiDAR sensor, photogrammetry and NeRF: a case study of ’Ascolana Tenera’ in Italy

Abstract. Rapid urban growth makes green space management crucial to improve citizens’ well-being. Urban olive trees characterize the Italian landscapes and their culture. This study explores different methodologies for urban tree assessment in this context, using an iPhone 14 Pro Max. These included: 1) its integrated Light Detection and Ranging (LiDAR) sensor using the Recon3D app, 2) its camera with Structure from Motion (SfM) techniques, and 3) its camera for generating 3D models using Neural Radiance Fields (NeRF). Additionally, a professional Mobile Laser Scanner (MLS), was used for comparison. Total height (H), canopy base height (CBH) and canopy volume (CV) measurements were extracted using both CloudCompare and allometric formulas. The main aim of this paper is to compare the 3D models of olive trees obtained from low-cost sensors with those generated from the MLS, which is a more accurate device but comes with significantly higher costs. The results, in terms of RMSE (iPhone LiDAR - H: 0.46 m, CBH: 0.12 m, CV: 15.66 m3; iPhone-SfM - H: 0.95 m, CBH: 0.19 m, CV: 25.85 m3; iPhone-NeRF - H: 1.26 m, CBH: 0.31 m, CV: 33.79 m3), bias and volume differences, reveal that the smartphone, in all the methodologies, tends to underestimate measurements as the size of the trees increases. This is due to the higher MLS range of acquisition. Despite these limitations, low-cost solutions like smartphone-based methods can be a viable alternative given their economic accessibility.

Conceptual Model of Graph-based Individual Tree and Its Utilization in Digital Twin and Metaverse of Urban Forest

Abstract. 3D city models are an important cornerstone in the development of digital twin cities, allowing for various analyses and simulations. CityGML, as an open standard for 3D city models, emphasizes five main aspects: scale or level of detail (LoD), semantics, geometry, topology, and appearance. One of the important elements in CityGML 3D city models is representation of vegetation. Vegetation in CityGML, especially individual trees, is still limited in terms of detail and resolution, reducing its effectiveness for specific applications. This paper proposes a graph-based conceptual model for individual trees that conforms to the CityGML v2.0 specification. The model refers to the morphological structure of a tree consisting of roots, trunk, and crown (including branches, twigs, and leaves), and considers the five main aspects of CityGML. By enhancing semantic information and geometric details, the model aims to provide an information-rich and realistic representation of individual trees in a 3D city environment. The 3D tree model created based on this conceptual model may be applicable in the development of digital twin urban forests and virtual forest simulations that utilize immersive technologies such as the metaverse. This research opens up new opportunities in the development of solitary vegetation objects through CityGML ADE by including more detailed semantic and topological information.

L1-Tree: A novel algorithm for constructing 3D tree models and estimating branch architectural traits using terrestrial laser scanning data

Branch architecture provides crucial information for the understanding of plant trait variability and the adaptive strategies employed by trees in response to their environment. High-fidelity terrestrial laser scanning (TLS) data provide an accurate, efficient, and non-destructive means for constructing three-dimensional (3D) tree models and estimating architectural traits. However, the complex canopy structure of trees in natural forests and the presence of occlusion in TLS data pose significant challenges to achieving this goal. In this study, we present a novel algorithm, L1-Tree, for the construction of 3D tree models and the estimation of architectural traits from TLS data. This algorithm is grounded in the L1-Median algorithm and integrates a tree skeleton optimization procedure that considers the structural characteristics of tree branches. By comparing modeling results and manually derived branch traits for 24 trees of 24 species, we found that the L1-Tree algorithm achieved precision, recall, and F-score values of 0.94 for branch identification, coefficient of determination, root-mean-squared error, and normalized root-mean-squared error of 0.998, 0.068 m, and 0.3 % for branch length estimation, and a respective value of 0.958, 0.257 cm and 0.9 % for branch radius estimation. Additionally, the branch identification accuracy and accuracy in branch architectural trait estimation remained satisfactory across branch orders. Compared to established 3D tree model construction algorithms (e.g., TreeQSM), our L1-Tree algorithm demonstrated a superior capability in handling noisy environments and data gaps, making it a robust tool for TLS data-based tree architecture studies. Leaf-wood separation emerged as a crucial step influencing the performance of the L1-Tree algorithm. We observed significant drop in branch identification accuracy when using an automatic leaf-wood separation algorithm as input, highlighting the urgent need to develop effective leaf-wood separation algorithms to generate high-quality wood point clouds for tree architecture studies.

Structured Generation Method of 3D Synthetic Tree Models for Precision Assessment

Abstract. The technology for 3D reconstruction of tree models based on point clouds has been extensively researched, necessitating effective datasets for the study of branch and leaf separation, skeleton point extraction, and tree parameter extraction methods. However, existing datasets for 3D tree models face several challenges, including insufficient data volume for deep learning network training, low accuracy of model ground truth impeding effective method precision evaluation, and a lack of dataset richness to satisfy the needs of multi-type method assessments. In response to these challenges, This paper introduces, for the first time, a fully automated method for generating structured three-dimensional synthetic tree models, and constructs a large-scale 3D synthetic tree dataset enriched with comprehensive structural information. This method facilitates automated computation across several processes, including the mass generation of simulated trees, separation of branches and leaves, noise generation, extraction of skeleton points, and volume calculation. To validate the usability of this dataset across various applications, this paper employs state-of-the-art (SoTA) algorithms to verify the accuracy of methods in 3D tree model reconstruction and carbon stock calculation, thereby thoroughly demonstrating the dataset’s effectiveness.

Non-Destructive Estimation of Deciduous Forest Metrics: Comparisons between UAV-LiDAR, UAV-DAP, and Terrestrial LiDAR Leaf-Off Point Clouds Using Two QSMs

Timely acquisition of forest structure is crucial for understanding the dynamics of ecosystem functions. Despite the fact that the combination of different quantitative structure models (QSMs) and point cloud sources (ALS and DAP) has shown great potential to characterize tree structure, few studies have addressed their pros and cons in alpine temperate deciduous forests. In this study, different point clouds from UAV-mounted LiDAR and DAP under leaf-off conditions were first processed into individual tree point clouds, and then explicit 3D tree models of the forest were reconstructed using the TreeQSM and AdQSM methods. Structural metrics obtained from the two QSMs were evaluated based on terrestrial LiDAR (TLS)-based surveys. The results showed that ALS-based predictions of forest structure outperformed DAP-based predictions at both plot and tree levels. TreeQSM performed with comparable accuracy to AdQSM for estimating tree height, regardless of ALS (plot level: 0.93 vs. 0.94; tree level: 0.92 vs. 0.92) and DAP (plot level: 0.86 vs. 0.86; tree level: 0.89 vs. 0.90) point clouds. These results provide a robust and efficient workflow that takes advantage of UAV monitoring for estimating forest structural metrics and suggest the effectiveness of LiDAR in temperate deciduous forests.

Three Dimensional Tree Modeling Based on the Skeleton Path Optimization and Geometrical Shapes

Nowadays, the 3D individual tree reconstruction has played a significant role in the phenotypic study of trees. This paper proposes a new automatic method for extracting skeletons of individual trees and reconstructing 3D models. Firstly, the Euclidean clustering is performed to obtain center points of candidate branch regions. Then, the initial skeletons of LiDAR point clouds are obtained by slicing clusters in three dimensions. Secondly, skeleton points are completed by the proposed branch tracking. Then, the radius of the branches is accurately estimated from the branches. Thirdly, optimal points are interpolated in appropriate directions to refine skeletons of individual trees. Then, the Laplacian algorithm is conducted for smoothing branches. After that, optimal geometric shapes are formulated to reconstruct the final 3D tree models. Experimental results show that the average accuracy of our individual tree models is up to 97.49%, which shows a promising algorithm in 3D tree reconstructions.

Usage of Airborne LiDAR Data and High-Resolution Remote Sensing Images in Implementing the Smart City Concept

The cities of the future should not only be smart, but also smart green, for the well-being of their inhabitants, the biodiversity of their ecosystems and for greater resilience to climate change. In a smart green city, the location of urban green spaces should be based on an analysis of the ecosystem services they provide. Therefore, it is necessary to develop appropriate information technology tools that process data from different sources to support the decision-making process by analysing ecosystem services. This article presents the methodology used to develop an urban green space planning tool, including its main challenges and solutions. Based on the integration of data from ALS, CLMS, topographic data, and orthoimagery, an urban green cover model and a 3D tree model were generated to complement a smart-city model with comprehensive statistics. The applied computational algorithms allow for reports on canopy volume, CO2 reduction, air pollutants, the effect of greenery on average temperature, interception, precipitation absorption, and changes in biomass. Furthermore, the tool can be used to analyse potential opportunities to modify the location of urban green spaces and their impact on ecosystem services. It can also assist urban planners in their decision-making process.

FILLING GAPS BETWEEN MESHES OF TREE CROWN AND TREE TRUNK BASED ON BOUNDARY CONSTRAINTS AND COORDINATE PROJECTION FOR 3D TREE MODELLING

Abstract. In order to reconstruct high-quality 3D tree models, trunks and crowns could be reconstructed using appropriate methods separately and merged together. During this process, gaps will appear after tree models are spliced, which will affect the models' topological connectivity and visual effects. In this paper, a gap-repair algorithm for tree mesh models based on boundary restriction and coordinates projection is proposed. The algorithm first extracts all the holes in the tree trunk meshes and crown meshes and matched them according to their relative positions. Then, the gaps in the tree meshes are identified. After that, based on the projection of the hole vertices from 3D space to 2D space, the relative positions of the hole vertices were determined, and vertex connection and surface addition were carried out to generate a 2-manifold patch. Finally, the patch was refined to keep its density of vertices similar to the surrounding meshes. Real 3D Tree meshes of different species were used to conduct experiments, and the quality of the repaired tree models are evaluated qualitatively and quantitatively. Experimental results revealed that the proposed algorithm could fill gaps in tree meshes quickly and effectively, so as to achieve the topology connection and smooth transition between the trunk and crown meshes.

Modeling of the 3D Tree Skeleton using Real-World Data: A Survey.

Tree modeling has been extensively studied in computer graphics. Recent advances in the development of high-resolution sensors and data processing techniques are extremely useful for collecting 3D datasets of real-world trees and generating increasingly plausible branching structures. The rapid development of versatile acquisition platforms allows us to capture multi-view images and scanned data that can be used for guided 3D tree modeling. In this paper, we carry out a comprehensive review of the state-of-the-art methods for the 3D modeling of botanical tree geometry by taking input data from real scenarios. A wide range of studies has been proposed following different approaches. To summarize the most relevant contributions, these have been classified into three categories: (1) procedural reconstruction, (2) geometry-based extraction, which is also divided into three groups (thinning, clustering and spanning tree refinement), and (3) image-based modeling. In addition, we describe other approaches aimed at improving the reconstruction process by adding additional features to achieve a realistic appearance of the tree models. Thus, we provide an overview of the most effective procedures to assist researchers in the photorealistic modeling of trees in geometry and appearance. The article concludes with remarks and trends for promising research opportunities in 3D tree modeling using real-world data.

Classification of tree forms in aerial LiDAR point clouds using CNN for 3D tree modelling

ABSTRACT Three-dimensional models of trees that correspond to the real-world forms of the trees on the ground are used in urban planning, solar power estimation, and other disciplines. Previous studies have focused on generating 3D tree models from high-density point cloud data such as Terrestrial Laser Scanning (TLS) data, which is expensive and limited to small spatial extents. However, there has been limited exploration of inexpensive solutions to model trees over large spatial extents. The goal of this study is to use widely available discrete return Airborne Laser Scanning (ALS) data along with field-captured tree photographs and Google Street View (GSV) images to develop 3D equivalents of trees over larger spatial extents. To this end, we designed a process to assign representative 3D models for individual trees in discrete return ALS point clouds. This study demonstrates the use of a Convolutional Neural Network (CNN) model and 3D models generated with Structure from Motion (SfM) for the realistic modelling of deciduous non-overlapping trees from discrete return ALS data. We classified and labelled the crown shapes of deciduous trees in a study area into four classes based on GSV images of trees. We delineated and segmented non-overlapping deciduous trees from ALS data and reduced them to 2D images using voxel point counts. Next, we trained a CNN architecture to match the 2D images to the corresponding classes observed from GSV images. For each class, we created a representative 3D tree model using field-captured circumnavigational photos of trees and SfM. To demonstrate 3D visualization using the 3D tree models, we created a 3D visualization of the trees surrounding a parking lot. The trained CNN model from this study can be used to classify non-overlapping deciduous trees from discrete return ALS data and subsequently visualize near-realistic 3D tree models of trees.

Branching the limits: Robust 3D tree reconstruction from incomplete laser point clouds

Accurate individual tree reconstruction based on laser point clouds is vital for precise biomass estimation, virtual geographic environment modeling, and simulation. However, mobile laser 3D scanning systems often capture tree point clouds obscured by leaves, resulting in missing or incomplete branch data, posing significant challenges to detailed tree reconstruction. In this paper, a novel method for fine-grained 3D tree model reconstruction from incomplete point clouds is proposed. This approach addresses the structural reconstruction of trees, tackling two main problems: reconstructing the main trunk and branches based on data completeness. Initially, a 3D morphological algorithm is employed to separate the main trunk and branches in the point cloud. Next, branch point clouds are node-aggregated using clustering, and the trunk’s skeleton point is computed using a multi-scale curve fitting method. To account for incomplete branch point clouds, the Alpha shape is calculated and used as a constraint for the growth model of the L-system, enabling the automatic generation of branch structures. Finally, a morphologically constrained multi-level trunk fusion method is utilized to achieve complete tree model reconstruction. To validate the effectiveness of this method, five trees with varying structures and levels of complexity were selected for structural reconstruction and compared with state-of-the-art (SOTA) methods. Experimental results evince that the method delineated in this study exhibits an aptitude for adeptly approximating tree nodes, even in scenarios characterized by incomplete point cloud data. This approach transcends the reconstruction accuracy manifested by SOTA algorithms specific to three-dimensional tree modeling, simultaneously demonstrating a pronounced resilience to noise and enhanced robustness.

Latent L-systems: Transformer-based Tree Generator

We show how a Transformer can encode hierarchical tree-like string structures by introducing a new deep learning-based framework for generating 3D biological tree models represented as Lindenmayer system (L-system) strings. L-systems are string-rewriting procedural systems that encode tree topology and geometry. L-systems are efficient, but creating the production rules is one of the most critical problems precluding their usage in practice. We substitute the procedural rules creation with a deep neural model. Instead of writing the rules, we train a deep neural model that produces the output strings. We train our model on 155k tree geometries that are encoded as L-strings, de-parameterized, and converted to a hierarchy of linear sequences corresponding to branches. An end-to-end deep learning model with an attention mechanism then learns the distributions of geometric operations and branches from the input, effectively replacing the L-system rewriting rule generation. The trained deep model generates new L-strings representing 3D tree models in the same way L-systems do by providing the starting string. Our model allows for the generation of a wide variety of new trees, and the deep model agrees with the input by 93.7% in branching angles, 97.2% in branch lengths, and 92.3% in an extracted list of geometric features. We also validate the generated trees using perceptual metrics showing 97% agreement with input geometric models.

Tree Architecture & Blockchain Integration: An off-the-shelf Experimental Approach

Temporally sensitive tree modeling and urban park spatially explicit simulation offer advantages to large-scale landscape planning and design, especially in the context of smart applications for virtual parks and forests, while Blockchain technology provides collaborative engineering, data integrity, and information confidence. A proof-of-concept 2.5D tree architecture and Blockchain integration technique (distributed Internet-of-Trees images, “IoTr-images”) was presented as a low-cost metaverse case study that affects the forest monitoring and digital landscape architecture design infrastructures. At the core of the proposed feature-based parametric modeling methodology is a 2.5D tree CAD model composed of two perpendicular 2D tree frames on which recorded tree texture has been assigned. A “Batch command-line programming” technique has been implemented, as a user-defined routine at the top of a commercial CAD platform, to describe the proposed off-the-self method and to create tangible tree-image NFT tokens (Internet-of-Trees-images Blockchain). As important findings were recorded, the add-in planning intelligence, the superior data integrity, and confidence, the offline relaxed error-free CAD design, and the superiority in terms of time and cost compared to traditional 3D tree modeling methods (laser scanning, close-range photogrammetry, etc.); as well as the satisfactory tree modeling accuracy for smart forest monitoring and landscape architecture applications. The proposed 2.5D parametric tree model added new value to the CAD-Blockchain integration industry because a plain “Blockchain/Merkle hash tree” tracks tree geometry growth and texture change temporarily with simple parametric transactions (i.e. controlled hash tree magnification/scaling). So, metaverse functionality (decentralized, autonomous, coordinated, and parallel design; same-data sharing; data validation), modification and redesign ability, and planning intelligence are effectively supported by the proposed technique. Main contributions are regarded as the ability for smart forest distributed surveillance and collaborative parallel landscape architecture design, open-source Web-based educational simulations, as well as the potential for off-the-shelf contractual collaborative frameworks (smart contracts between designers and clients). Stratification based on forest types improved above-ground biomass (AGB) estimation, especially when AGB was greater than 500 Mg/ha, using the proposed “IoTr-images” technique. So, this research provides new insight into AGB modeling and monitoring. Finally, the proposed method’s robustness has been validated by performance evaluation testing.

Path Planning and Navigation of Miniature Serpentine Robot for Bronchoscopy Application.

The miniature serpentine robot can be applied to NOTES (Natural Orifice Transluminal Endoscopic Surgery). In this paper, a bronchoscopy application is addressed. This paper describes the basic mechanical design and control scheme of this miniature serpentine robotic bronchoscopy. In addition, off-line backward path planning and real-time and in situ forward navigation in this miniature serpentine robot are discussed. The proposed backward-path-planning algorithm utilizes the 3D model of a bronchial tree constructed from the synthetization of medical images such as images from CT (Computed Tomography), MRI (Magnetic Resonance Imaging), or X-ray, to define a series of nodes/events backward from the destination, for example, the lesion, to the original starting point, for example, the oral cavity. Accordingly, forward navigation is designed to make sure this series of nodes/events shall be passed/occur from the origin to the destination. This combination of backward-path planning and forward navigation does not require accurate positioning information of the tip of the miniature serpentine robot, which is where the CMOS bronchoscope is located. Collaboratively, a virtual force is introduced to maintain the tip of the miniature serpentine robot at the center of the bronchi. Results show that this method of path planning and navigation of the miniature serpentine robot for bronchoscopy applications works.

Geomatic Data Fusion for 3D Tree Modeling: The Case Study of Monumental Chestnut Trees

In recent years, advancements in remote and proximal sensing technology have driven innovation in environmental and land surveys. The integration of various geomatics devices, such as reflex and UAVs equipped with RGB cameras and mobile laser scanners (MLS), allows detailed and precise surveys of monumental trees. With these data fusion method, we reconstructed three monumental 3D tree models, allowing the computation of tree metric variables such as diameter at breast height (DBH), total height (TH), crown basal area (CBA), crown volume (CV) and wood volume (WV), even providing information on the tree shape and its overall conditions. We processed the point clouds in software such as CloudCompare, 3D Forest, R and MATLAB, whereas the photogrammetric processing was conducted with Agisoft Metashape. Three-dimensional tree models enhance accessibility to the data and allow for a wide range of potential applications, including the development of a tree information model (TIM), providing detailed data for monitoring tree health, growth, biomass and carbon sequestration. The encouraging results provide a basis for extending the virtualization of these monumental trees to a larger scale for conservation and monitoring.

A Novel 3D Tree-Modeling Method of Incorporating Small-Scale Spatial Structure Parameters in a Heterogeneous Forest Environment

Currently, 3D tree modeling in a highly heterogeneous forest environment remains a significant challenge for the modeler. Previous research has only focused on morphological characteristics and parameters, overlooking the impact of micro-environmental factors (e.g., spatial-structural diversification and habitat heterogeneity) and providing less structural information about the individual tree and decreasing the applicability and authenticity of 3D tree models in a virtual forest. In this paper, we chose a mixed-forest conversion of Chinese fir (Cunninghamia lanceolata) plantations in a subtropical region of China as our study subject and proposed a novel 3D tree-modeling method based on a structural unit (TMSU). Our approach modified traditional rule-based tree modeling (RTM) by introducing a nonlinear mixed-effect model (NLME) to study the coupling response between the spatial structures and morphological characteristics (e.g., tree height (H), height-to-crown base (HCB), and crown width (CW)) of three dominant trees (e.g., Cunninghamia lanceolata (SM), Machilus pauhoi (BHN), and Schima superba (MH)) and develop a prediction model of the morphological characteristic by incorporating forest-based structural parameters. The results showed that: (1) The NLME model in TMSU was found to better fit the data and predict the morphological characteristics than the OLS model in RTM. As compared to the RTM morphological model, the prediction accuracy of the TMSU model of morphological features was improved by 10.4%, 3.02%, and 17.8%, for SM’s H, HCB, and CW, respectively; 6.5%, 7.6%, and 8.9% for BHN’s H, HCB, and CW, respectively; and 13.3%, 15.7%, and 13.4% for MH’s H, HCB, and CW, respectively. (2) The spatial-structural parameters of crowding (Ci), mingling (Mi), and dominance (Ui) had a significant impact on the morphological characteristics of SM, BHN, and MH in TMSU. The degree of crowding, for example, had a positive relationship with tree height, height-to-crown base, and crown width in SM, BHN, and MH; under the same crowding conditions, mingling was positively correlated with tree crown width in SM, and dominance was positively correlated with tree height but negatively correlated with height-to-crown base in BHN; under the same crowding and mingling, dominance was positively correlated with height-to-crown base in MH. (3) Using 25 scenes based on the value class of Ci,Mi for SM, 25 scenes based on the value class of Ci,Ui for BHN, and 125 scenes based on the value class of Ci,Mi,Ui for MH, we generated the model libraries for the three dominating species based on TMSU. As a result, our TSMU method outperformed the traditional 3D tree-modeling method RTM in a complex and highly heterogeneous spatial structure of a forest stand, and it provided more information concerning the spatial structure based on the neighborhood relationships than the simple morphological characteristics; a higher morphological prediction accuracy with fewer parameters; and the relationship between the spatial-structural parameters and the morphological characteristics of a reference tree.

Estimation of Aboveground Biomass of Individual Trees by Backpack LiDAR Based on Parameter-Optimized Quantitative Structural Models (AdQSM)

Forest aboveground biomass (AGB) plays a key role in assessing forest productivity. In this study, we extracted individual tree structural parameters using backpack LiDAR, assessed their accuracy using terrestrial laser scanning (TLS) data and field measurements as reference values, and reconstructed 3D models of trees based on parameter-optimized quantitative structural models (AdQSM). The individual tree AGB was estimated based on individual tree volumes obtained from the tree model reconstruction, combined with the basic wood density values of specific tree species. In addition, the AGB calculated using the allometric biomass models was validated to explore the feasibility of nondestructive estimation of individual tree AGB by backpack LiDAR. We found that (1) the backpack LiDAR point cloud extracted individual tree diameter at breast height (DBH) with high accuracy. In contrast, the accuracy of the tree height extraction was low; (2) the optimal parameter values of the AdQSM reconstruction models for Larix gmelinii and Betula platyphylla were HS = 0.4 m and HS = 0.6 m, respectively; (3) the individual tree AGB estimated based on the backpack LiDAR and AdQSM fit well with the reference values. Our study confirms that backpack LiDAR can nondestructively estimate individual tree AGB, which can provide a reliable basis for further forest resource management and carbon stock estimation.

POINTNET++ TRANSFER LEARNING FOR TREE EXTRACTION FROM MOBILE LIDAR POINT CLOUDS

Abstract. Trees are an essential part of the natural and urban environment due to providing crucial benefits such as increasing air quality and wildlife habitats. Therefore, various remote sensing and photogrammetry technologies, including Mobile Laser Scanner (MLS), have been recently introduced for precise 3D tree mapping and modeling. The MLS provides densely 3D LiDAR point clouds from the surrounding, which results in measuring applicable information of trees like stem diameter or elevation. In this paper, a transfer learning procedure on the PointNet++ has been proposed for tree extraction. Initially, two steps of converting the MLS point clouds into same-length smaller sections and eliminating ground points have been conducted to overcome the massive volume of MLS data. The algorithm was tested on four LiDAR datasets ranging from challengeable urban environments containing multiple objects like tall buildings to railway surroundings. F1-Score accuracy was gained at around 93% and 98%, which showed the feasibility and efficiency of the proposed algorithm. Noticeably, the algorithms also measured geometrical information of extracted trees such as 2D coordinate space, height, stem diameter, and 3D boundary tree locations.

3D modeling of laser-scanned trees based on skeleton refined extraction

Laser point cloud provides a high-precision data source for the 3D model reconstruction of existing trees. However, due to the complexity of tree structure and the data missing of point cloud, it is difficult to reconstruct complete, detailed and accurate 3D tree models from discrete points, especially the points are incomplete due to single-view scanning. To this end, a new point cloud driven method based on skeleton refined extraction is proposed in this paper. First, as the focus of refined modeling, the main (thick) branches are separated from the raw tree points. Then, the main branch points are over-segmented into some whorl-segments, and the corresponding raw points on the branch surfaces of each whorl-segment are shrunk to generate smooth, continuous and local detail preserved potential skeleton nodes of the main branches. Next, a new shortest path metric meeting the natural growth characteristics of trees is adopted to extract the complete, detailed and correctly connected tree skeleton from both of the shrunk main branch points and the non-main-branch points. After that, to ensure the skeleton centralization, especially that extracted from single-view scanned data, the extracted skeleton is translated by a combination of cylinder fitting and allometric theory. Finally, the complete, detailed and accurate 3D tree model is expressed by a series of cylinders based on the extracted refined skeleton. The proposed method is tested with 7 different tree point clouds, some of which are obtained by single-view scanning and suffer from serious data missing. Both qualitative and quantitative evaluations prove the effectiveness of this method for the refined reconstruction of trees from point clouds. Overall, the average modeling accuracy and its standard deviation of the used different trees are 2.58 cm and 3.20 cm respectively.