Tree Segmentation Research Articles

Detection of tree destruction induced by heavy rainfall in the afforested loess catchment of China

Rainstorm events are becoming increasingly frequent due to the impacts of global warming, which results in widespread erosion disasters and related tree destruction. However, previous corresponding studies of forest damage have focused on typhoons or wildfires, ignoring the increasing risk of rainstorm erosion-induced tree destruction. It is unclear what scale of tree destruction can be caused by heavy rainfall. In this study, we used a tree segmentation method based on airborne light detection and ranging (LiDAR) technology to accurately quantify the tree destruction during heavy rainfall in a representative afforested catchment on the Chinese Loess Plateau. Additionally, topographic changes were calculated using pre- and post-heavy rainfall LiDAR datasets, and tree destruction was assessed by combining terrain information and tree structural parameters. The results showed that 3253 trees in the catchment (0.9 km2) were destroyed due to rainstorm erosion, among which 2845 trees were located on gully slope landform, accounting for 87.4 % of all destroyed trees. Tree destruction on steep gully slope (slope: 45.5°-50.5°) was mainly induced by rainstorm erosion, while that on both sides of the gully bed (altitude: 1137 m-1147 m) was mainly induced by sediment deposition. In the catchment, the deposition area that resulted in tree destruction (21265 m2) was greater than the erosion area (20020 m2). However, the damage caused by erosion was more destructive than that caused by deposition. There was a significant linear relationship between tree structural parameters and terrain in the forestland catchment. Our study provides a reference methodology for studies of forest damage due to extreme weather events worldwide, and has significant implications for ecosystem management and reforestation in the context of global change.

Computed tomography morphological assessments of central airways in interstitial lung abnormalities and idiopathic pulmonary fibrosis

BackgroundLittle is known about whether central airway morphological changes beyond traction bronchiectasis develop and affect clinical outcomes in patients with idiopathic pulmonary fibrosis (IPF). This study aimed to compare central airway structure comprehensively between patients with IPF, subjects with interstitial lung abnormality (ILA), and those without ILA (control) using computed tomography (CT). We further examined the prognostic impact of IPF-specific CT airway parameters in patients with IPF.MethodsThis retrospective study included male patients with IPF, and male health checkup subjects divided into those with ILA and control based on lung cancer screening CT. Using an artificial intelligence-based segmentation technique, the extent of fibrotic regions in the lung was quantified. After airway tree segmentation, CT parameters for central airway morphology, including the lumen area of the extrapulmonary airways (LAextra), wall and lumen area of the segmental/subsegmental intrapulmonary airways (WAintra and LAintra), tracheal distortion (tortuosity and curvature) and bifurcation angle of the main carina, were calculated.ResultsThere were 106 patients with IPF, 53 subjects with ILA, and 1295 controls. Multivariable models adjusted for age, height and smoking history revealed that LAintra and WAintra were larger in both ILA and IPF, and that tracheal tortuosity and curvature were higher in IPF, but not in ILA, than in the control, whereas the bifurcation angle did not differ between the 3 groups. According to multivariable Cox proportional hazards models including only patients with IPF, increased WAintra was significantly associated with greater mortality (standardized hazard ratio [95% confidence interval] = 1.58 [1.17, 2.14]), independent of the volume of fibrotic regions, normal-appearing regions, or the whole airway tree in the lung.ConclusionIncreased lumen area and wall thickening of the central airways may be involved in the pathogenesis of ILA and IPF, and wall thickening may affect the prognosis of patients with IPF.

Nonlinear relationships between canopy structure and cooling effects in urban forests: Insights from 3D structural diversity at the single tree and community scales

Three-dimensional structural diversity (3SD) directly influences the distribution and flow of heat within the canopy. However, the nonlinear effects of 3SD of different species on the cooling effects remain unclear. Here, we proposed an analytical framework to explore this relationship at the single tree and community scales. Results indicated that: (1) A benchmark dataset for individual tree segmentation was established, with the best-performing algorithm achieving an accuracy of 77.36% (F-score=0.75), the UAV-based LiDAR, multispectral and thermal infrared imagery using a data fusion approach achieved a better species classification accuracy of 80.41% (kappa=0.78); (2) At the single tree scale, the cooling effects are controlled by vertical structure, heterogeneity, and leaf density (15.36%<rel.inf<26.84%). Entropy, VAI, and Hmax exhibited the largest seasonal relative importance change rates (7%<|Δrel.inf|<11%); (3) At the community scale (10m × 10m), VAI contributed the most to coniferous cooling in summer, while Hmax had the greatest impact on broadleaf cooling in winter. Species’ spatial connectivity had a significantly greater impact on the cooling effects in broadleaf in summer and coniferous in winter compared to structural diversity. This study supports optimizing urban forestry by demonstrating UAV-based data fusion for species classification and highlighting structural diversity's role in regulating temperature across scales and seasons.

Location-specific prognostic significance of plaque burden, stenosis, and plaque morphology in coronary artery disease

Abstract Background The prognostic significance of coronary plaque localization, percentage atheroma volume (PAV), stenosis, and plaque morphology has been underexplored. Purpose To investigate the prognostic significance of plaque localization beyond plaque burden, presence of stenosis and plaque morphology. Methods Patients with no cardiac history who underwent coronary CTA were included. PAV, maximum diameter stenosis, and plaque morphology were assessed and classified into proximal, mid, or distal segments of the coronary tree. Major adverse cardiac events (MACE) were defined as death or non-fatal myocardial infarction. Results Among 2819 patients 267 events (9.5%) occurred during a median follow-up of 6.9 years. PAV of the proximal segments was strongly correlated to PAV localized at of the mid (R= 0.76) and distal segments (R = 0.74, p &amp;lt; 0.01 for both). When adjusted for traditional risk factors and presence of plaque on other locations, only proximal PAV was independently associated with MACE (3rd quartile HR 2.08, 95% 1.17–3.71, p=0.01 and 4th quartile HR 2.29, 95% CI 1.21–4.34, p=0.01). Similar results were seen for presence of stenosis. Proximal, mid, and distal PAV as a solitary metric (unadjusted) had similar predictive value for MACE with an AUC of 0.73 (95% CI 0.69-0.76) for proximal PAV and 0.72 (95% CI 0.68-0.76) for both mid and distal localized plaque). Similar results were obtained using diameter stenosis instead of PAV. The presence of low-attenuation plaque (LAP) in the proximal segments had additional prognostic value. Calcified or noncalcified PAV did not provide additional value beyond total location-specific PAV and presence of low-attenuation plaque. Conclusions Proximal located PAV is an independent predictor of death and non-fatal MI, while there was no incremental prognostic value of plaque localized at the mid or distal coronary segments. The presence of LAP in the proximal segments provided additional prognostic value for prediction of MACE.

Benchmarking of Individual Tree Segmentation Methods in Mediterranean Forest Based on Point Clouds from Unmanned Aerial Vehicle Imagery and Low-Density Airborne Laser Scanning

Three raster-based (RB) and one point cloud-based (PCB) algorithms were tested to segment individual Aleppo pine trees and extract their tree height (H) and crown diameter (CD) using two types of point clouds generated from two different techniques: (1) Low-Density (≈1.5 points/m2) Airborne Laser Scanning (LD-ALS) and (2) photogrammetry based on high-resolution unmanned aerial vehicle (UAV) images. Through intensive experiments, it was concluded that the tested RB algorithms performed best in the case of UAV point clouds (F1-score &gt; 80.57%, H Pearson’s r &gt; 0.97, and CD Pearson´s r &gt; 0.73), while the PCB algorithm yielded the best results when working with LD-ALS point clouds (F1-score = 89.51%, H Pearson´s r = 0.94, and CD Pearson´s r = 0.57). The best set of algorithm parameters was applied to all plots, i.e., it was not optimized for each plot, in order to develop an automatic pipeline for mapping large areas of Mediterranean forests. In this case, tree detection and height estimation showed good results for both UAV and LD-ALS (F1-score &gt; 85% and &gt;76%, and H Pearson´s r &gt; 0.96 and &gt;0.93, respectively). However, very poor results were found when estimating crown diameter (CD Pearson´s r around 0.20 for both approaches).

Automated tree crown labeling with 3D radiative transfer modelling achieves human comparable performances for tree segmentation in semi-arid landscapes

Mapping tree crowns in arid or semi-arid areas, which cover around one-third of the Earth’s land surface, is a key methodology towards sustainable management of trees. Recent advances in deep learning have shown promising results for tree crown segmentation. However, a large amount of manually labeled data is still required. We here propose a novel method to delineate tree crowns from high resolution satellite imagery using deep learning trained with automatically generated labels from 3D radiative transfer modeling, intending to reduce human annotation significantly. The methodological steps consist of 1) simulating images with a 3D radiative transfer model, 2) image style transfer learning based on generative adversarial network (GAN) and 3) tree crown segmentation using U-net segmentation model. The delineation performances of the proposed method have been evaluated on a manually annotated dataset consisting of more than 40,000 tree crowns. Our approach, which relies solely on synthetic images, demonstrates high segmentation accuracy, with an F1 score exceeding 0.77 and an Intersection over Union (IoU) above 0.64. Particularly, it achieves impressive accuracy in extracting crown areas (r2 greater than 0.87) and crown densities (r2 greater than 0.72), comparable to that of a trained dataset with human annotations only. In this study, we demonstrated that the integration of a 3D radiative transfer model and GANs for automatically generating training labels can achieve performances comparable to human labeling, and can significantly reduce the time needed for manual labeling in remote sensing segmentation applications.

Enhanced Neonatal Brain Tissue Analysis via Minimum Spanning Tree Segmentation and the Brier Score Coupled Classifier

Automatic assessment of brain regions in an MR image has emerged as a pivotal tool in advancing diagnosis and continual monitoring of neurological disorders through different phases of life. Nevertheless, current solutions often exhibit specificity to particular age groups, thereby constraining their utility in observing brain development from infancy to late adulthood. In our research, we introduce a novel approach for segmenting and classifying neonatal brain images. Our methodology capitalizes on minimum spanning tree (MST) segmentation employing the Manhattan distance, complemented by a shrunken centroid classifier empowered by the Brier score. This fusion enhances the accuracy of tissue classification, effectively addressing the complexities inherent in age-specific segmentation. Moreover, we propose a novel threshold estimation method utilizing the Brier score, further refining the classification process. The proposed approach yields a competitive Dice similarity index of 0.88 and a Jaccard index of 0.95. This approach marks a significant step toward neonatal brain tissue segmentation, showcasing the efficacy of our proposed methodology in comparison to the latest cutting-edge methods.

AeroPath: An airway segmentation benchmark dataset with challenging pathology and baseline method.

To improve the prognosis of patients suffering from pulmonary diseases, such as lung cancer, early diagnosis and treatment are crucial. The analysis of CT images is invaluable for diagnosis, whereas high quality segmentation of the airway tree are required for intervention planning and live guidance during bronchoscopy. Recently, the Multi-domain Airway Tree Modeling (ATM'22) challenge released a large dataset, both enabling training of deep-learning based models and bringing substantial improvement of the state-of-the-art for the airway segmentation task. The ATM'22 dataset includes a large group of COVID'19 patients and a range of other lung diseases, however, relatively few patients with severe pathologies affecting the airway tree anatomy was found. In this study, we introduce a new public benchmark dataset (AeroPath), consisting of 27 CT images from patients with pathologies ranging from emphysema to large tumors, with corresponding trachea and bronchi annotations. Second, we present a multiscale fusion design for automatic airway segmentation. Models were trained on the ATM'22 dataset, tested on the AeroPath dataset, and further evaluated against competitive open-source methods. The same performance metrics as used in the ATM'22 challenge were used to benchmark the different considered approaches. Lastly, an open web application is developed, to easily test the proposed model on new data. The results demonstrated that our proposed architecture predicted topologically correct segmentations for all the patients included in the AeroPath dataset. The proposed method is robust and able to handle various anomalies, down to at least the fifth airway generation. In addition, the AeroPath dataset, featuring patients with challenging pathologies, will contribute to development of new state-of-the-art methods. The AeroPath dataset and the web application are made openly available.

TreeSeg—A Toolbox for Fully Automated Tree Crown Segmentation Based on High-Resolution Multispectral UAV Data

Single-tree segmentation on multispectral UAV images shows significant potential for effective forest management such as automating forest inventories or detecting damage and diseases when using an additional classifier. We propose an automated workflow for segmentation on high-resolution data and provide our trained models in a Toolbox for ArcGIS Pro on our GitHub repository for other researchers. The database used for this study consists of multispectral UAV data (RGB, NIR and red edge bands) of a forest area in Germany consisting of a mix of tree species consisting of five deciduous trees and three conifer tree species in the matured closed canopy stage at approximately 90 years. Information of NIR and Red Edge bands are evaluated for tree segmentation using different vegetation indices (VIs) in comparison to only using RGB information. We trained Faster R-CNN, Mask R-CNN, TensorMask and SAM in several experiments and evaluated model performance on different data combinations. All models with the exception of SAM show good performance on our test data with the Faster R-CNN model trained on the red and green bands and the Normalized Difference Red Edge Index (NDRE) achieving best results with an F1-Score of 83.5% and an Intersection over Union of 65.3% on highly detailed labels. All models are provided in our TreeSeg toolbox and allow the user to apply the pre-trained models on new data.

Mapping percent canopy cover using individual tree- and area-based procedures that are based on airborne LiDAR data: Case study from an oak-hickory-pine forest in the USA

Canopy cover (CC) is the proportion of a forest floor covered by the vertical projection of tree crowns. Recently, it has become common to utilize LiDAR (light detection and ranging) canopy metrics to estimate CC over large areas. However, these metrics are primarily related to canopy density rather than the specific definition of CC. Here, two processes that employed individual tree segmentation (ITS) and area-based procedures based on LiDAR data are presented to estimate CC across the Talladega Division of the Talladega National Forest (93,694 ha) at the plot, stand, and landscape levels. The two analytical procedures were assessed using the results of a plot/grid method as a reference dataset, which focused on CC estimates within 255 field measurement fixed-area sample plots. The accuracy of a third process, employing an imagery-based visual CC assessment, was also compared against the two procedures and the reference dataset. The LiDAR-based analytical procedures were able to provide estimates of CC with an RMSE of approximately 15 %, which is acceptable for landscape-level assessments. Based on the results of this study, we conclude that CC maps, when created using LiDAR data, may be suitable for various operational tasks such as assessing the impact of forest disturbances and helping to determine the habitat suitability for certain wildlife species.

A novel BH3DNet method for identifying pine wilt disease in Masson pine fusing UAS hyperspectral imagery and LiDAR data

Pine Wilt Disease (PWD) is a forest infectious disease that inflicts substantial economic losses to China’s forestry. Its rapid spread and the significant challenges associated with its control make early detection of infected trees crucial for disaster prevention. Unmanned aerial systems (UASs) hyperspectral imaging (HSI) and light detection and ranging (LiDAR) technologies provide high-resolution spectral diagnostic information coupled with intricate three-dimensional structural data, which has potential for fine grained monitoring of PWD. However, how to fuse HSI and LiDAR data to identify the early infected individual trees is still a challenge. This study presents a novel instance segmentation network, BH3DNet, to identify individual trees at different PWD-infected stages by extracting high-level abstract features based on the fusion of drone HSI and LiDAR data. BH3DNet introduces the PointNet++ model as the base network, and incorporates a shared encoder and twin parallel decoders to align semantic category prediction and instance segmentation of individual trees in an end-to-end approach. By applying an enhanced point cloud dataset that fuses drone HSI and LiDAR point cloud data, this model facilitates the identification of PWD infection stages at the individual tree scale. We evaluated the proposed model in a Masson pine forest stand sparsely mixed with broadleaf trees in a variety of infection states ranging from healthy to severely infected by PWD, and compared the performance of the model using the RGB bands, full HSI bands and screened bands as inputs, respectively. BH3DNet achieves an overall accuracy of 89.65 % with a Kappa × 100 of 87.29 for identifying individual trees using screened HSI bands and LiDAR point cloud, significantly outperforming the Mask R-CNN using only HSI data (overall accuracy: 70.81 %, Kappa × 100: 64.16). Moreover, BH3DNet’s accuracy at the early infection stage reaches 83.75 %. It proves that fusing HSI and point cloud data reflects the information of individual trees distribution and infection status, and the BH3DNet is suitable for high-precision monitoring of PWD.

Three-Dimensional Reconstruction of Forest Scenes with Tree–Shrub–Grass Structure Using Airborne LiDAR Point Cloud

Fine three-dimensional (3D) reconstruction of real forest scenes can provide a reference for forestry digitization and forestry resource management applications. Airborne LiDAR technology can provide valuable data for large-area forest scene reconstruction. This paper proposes a 3D reconstruction method for complex forest scenes with trees, shrubs, and grass, based on airborne LiDAR point clouds. First, forest vertical distribution characteristics are used to segment tree, shrub, and ground–grass points from an airborne LiDAR point cloud. For ground–grass points, a ground–grass grid model is constructed. For tree points, a method based on hierarchical canopy point fitting is proposed to construct a trunk model, and a crown model is constructed with the 3D α-shape algorithm. For shrub points, a shrub model is directly constructed based on the 3D α-shape algorithm. Finally, tree, shrub, and ground–grass models are spatially combined to achieve the reconstruction of real forest scenes. Taking six forest plots located in Hebei, Yunnan, and Guangxi provinces in China and Baden-Württemberg in Germany as study areas, experimental results show that the accuracy of individual tree segmentation reaches 87.32%, the accuracy of shrub segmentation reaches 60.00%, the height accuracy of the grass model is evaluated with an RMSE &lt; 0.15 m, the volume accuracy of shrub and tree models is assessed with R2 &gt; 0.848 and R2 &gt; 0.904, respectively. Furthermore, we compared the model constructed in this study with simplified point cloud and voxel models. The results demonstrate that the proposed modeling approach can meet the demand for the high-accuracy and lightweight modeling of large-area forest scenes.

YOLO-SegNet: A Method for Individual Street Tree Segmentation Based on the Improved YOLOv8 and the SegFormer Network

In urban forest management, individual street tree segmentation is a fundamental method to obtain tree phenotypes, which is especially critical. Most existing tree image segmentation models have been evaluated on smaller datasets and lack experimental verification on larger, publicly available datasets. Therefore, this paper, based on a large, publicly available urban street tree dataset, proposes YOLO-SegNet for individual street tree segmentation. In the first stage of the street tree object detection task, the BiFormer attention mechanism was introduced into the YOLOv8 network to increase the contextual information extraction and improve the ability of the network to detect multiscale and multishaped targets. In the second-stage street tree segmentation task, the SegFormer network was proposed to obtain street tree edge information more efficiently. The experimental results indicate that our proposed YOLO-SegNet method, which combines YOLOv8+BiFormer and SegFormer, achieved a 92.0% mean intersection over union (mIoU), 95.9% mean pixel accuracy (mPA), and 97.4% accuracy on a large, publicly available urban street tree dataset. Compared with those of the fully convolutional neural network (FCN), lite-reduced atrous spatial pyramid pooling (LR-ASPP), pyramid scene parsing network (PSPNet), UNet, DeepLabv3+, and HRNet, the mIoUs of our YOLO-SegNet increased by 10.5, 9.7, 5.0, 6.8, 4.5, and 2.7 percentage points, respectively. The proposed method can effectively support smart agroforestry development.

Temporal Exploration of COPD Phenotypes: Insights from the COPDGene and SPIROMICS Cohorts.

Chronic obstructive pulmonary disease (COPD) exhibits considerable progression heterogeneity. We hypothesized that elastic principal graph analysis (EPGA) would identify distinct clinical phenotypes and their longitudinal relationships. Cross-sectional data from 8,972 tobacco-exposed COPDGene participants, with and without COPD, were used to train a model with EPGA, using thirty clinical, physiologic and CT features. Principal component analysis (PCA) was used to reduce data dimensionality to six principal components. An elastic principal tree was fitted to the reduced space. 4,585 participants from COPDGene Phase 2 were used to test longitudinal trajectories. 2,652 participants from SPIROMICS tested external reproducibility. Our analysis used cross-sectional data to create an elastic principal tree, where the concept of time is represented by distance on the tree. Six clinically distinct tree segments were identified that differed by lung function, symptoms, and CT features: 1) Subclinical (SC); 2) Parenchymal Abnormality (PA); 3) Chronic Bronchitis (CB); 4) Emphysema Male (EM); 5) Emphysema Female (EF); and 6) Severe Airways (SA) disease. Cross-sectional SPIROMICS data confirmed similar groupings. 5-year data from COPDGene mapped longitudinal changes onto the tree. 29% of patients changed segment during follow-up; longitudinal trajectories confirmed a net flow of patients along the tree, from SC towards Emphysema, although alternative trajectories were noted, through airway disease predominant phenotypes, CB and SA. This novel analytic methodology provides an approach to defining longitudinal phenotypic trajectories using cross sectional data. These insights are clinically relevant and could facilitate precision therapy and future trials to modify disease progression.

Global Distribution of Mammalian Cradles and Museums is Driven by Past Climate Dynamics and Present Water–Energy Balance

ABSTRACTAimTo describe worldwide distribution of mammalian cradles and museums using the rates of phylogenetic lineage turnover as a surrogate. Additionally, we investigated the influences of current water–energy dynamics, climate instability, past climate changes and elevational ranges on the distribution of these evolutionary zones.LocationGlobal.Time PeriodCurrent.Major Taxa StudiedTerrestrial mammals.MethodsWe developed a new methodology that consists of calculating the spatial phylogenetic turnover for non‐overlapping temporal segments of phylogenetic trees. By calculating the relative turnover in each tree segment, we quantified the rate of accumulation of phylogenetic turnover through time. We depicted cold and hotspots of rates of lineage turnover using bivariate maps and examined the effects of environmental factors using a path model.ResultsThe distributions of cradles and museums of biodiversity are primarily driven by water–energy dynamics. Environments with higher water availability than energetic demand predominantly act as cradles, as seen in tropical rainforests, while xeric‐like environments predominantly serve as museums. Conversely, regions undergoing higher historical climate changes become cradles, such as in higher northern latitudes, while climatically stable areas function as museums. Mountains play a dual role, acting as both cradles and museums by generating new lineages along their elevation bands while simultaneously providing climate refuges for ancient mammal lineages.Main ConclusionsOur findings demonstrate that cradles and museums are not merely a dichotomy but exist along an evolutionary continuum. Furthermore, they reveal how spatial patterns of mammalian cradles and museums are intricately shaped by biogeographical processes governed by environmental forces. Uncovering these hidden effects provides insights into the ecological mechanisms by which ongoing climate changes continually shape evolutionary assemblages over time.

A new understanding of coronary curvature and haemodynamic impact on the course of plaque onset and progression

The strong link between atherosclerosis and luminal biomechanical stresses is well established. Yet, this understanding has not translated into preventative coronary diagnostic imaging, particularly due to the under-explored role of coronary anatomy and haemodynamics in plaque onset, which we aim to address with this work. The left coronary trees of 20 non-stenosed (%diameter stenosis [%DS] = 0), 12 moderately (0 &lt; %DS &lt; 70) and 7 severely (%DS ≥ 70) stenosed cases were dissected into bifurcating and non-bifurcating segments for whole-tree and segment-specific comparisons, correlating nine three-dimensional coronary anatomical features, topological shear variation index (TSVI) and luminal areas subject to low time-average endothelial shear stress (%LowTAESS), high oscillatory shear index (%HighOSI) and high relative residence time (%HighRRT). We found that TSVI is the only metric consistently differing between non-stenosed and stenosed cases across the whole tree, bifurcating and non-bifurcating segments ( p &lt; 0.002, AUC = 0.876), whereas average curvature and %HighOSI differed only for the whole trees ( p &lt; 0.024) and non-bifurcating segments ( p &lt; 0.027), with AUC &gt; 0.711. Coronary trees with moderate or severe stenoses differed only in %LowTAESS ( p = 0.009) and %HighRRT ( p = 0.012). This suggests TSVI, curvature and %HighOSI are potential factors driving plaque onset, with greater predictive performance than the previously recognized %LowTAESS and %HighRRT, which appears to play a role in plaque progression.

Improvement of horizontal streak on disparity map thru parameter optimization for stereo vision algorithm

In this paper, an improved local based stereo vision disparity map (SVDM) algorithm is proposed. The proposed local based SVDM algorithm include four stages and they are matching cost computation, cost aggregation disparity optimization and disparity refinement. The matching cost computation started by combining pixel to pixel matching techniques, which are absolute difference (AD) and gradient matching (GM) in producing the initial disparity map. Next, the cost aggregation uses minimum spanning tree (MST) segmentation, which equipped with edge preserving properties and noise filtering. Then, disparity optimization uses local approach with winner-take-all (WTA) technique. At the final stage, disparity refinement uses bilateral filter (BF) with weighted median (WM), which can improve the disparity map through noise removing and edges preserving. Then, the research continues to optimize the proposed local based SVDM algorithm through parameters optimization in obtaining the final disparity map. Here, multiple parameters from the proposed SVDM algorithm are manipulated and they are constant values for GM and several constant parameters in BF. By selecting the optimum parameter values, the performance of the proposed SVDM algorithm increased, especially robustness towards the horizontal streaks.

Research on hybrid segmentation technologies for postprocessing the lung and trachea CT images

This paper introduces a systematic method for segmenting the main trachea and bronchioles in lung computed tomography scans. It begins with a stack-based three-dimensional region growth algorithm to outline the main trachea, which is then refined using morphological techniques to improve accuracy. The segmentation of bronchioles is achieved through domain labeling, lung tissue segmentation, adaptive binarization, and inner product analysis. The main trachea and bronchioles are integrated using an operating room (OR) operation and a novel splicing algorithm to form a complete tracheal tree. The method’s accuracy is validated against manual labeling, showing a Dice coefficient of about 0.99, on average, in lung parenchyma segmentation and a segmentation overlap with expert results ranging from 79.89% to 93.31% in lung trachea tree segmentation. This robust methodology is thoroughly tested and validated.

Towards automatic urban tree inventory: Enhancing tree instance segmentation via moving object removal and a chord length-based DBH estimation approach

To enhance urban forestry efficacy in Hong Kong, implementing a paradigm shift towards an automated urban tree inventory that utilizes advanced sensing technologies and artificial intelligence is essential for streamlined data collection and analysis. This study advances this objective by creating a comprehensive framework for estimating diameter at breast height (DBH) and extracting tree images. This framework encompasses five key stages: (1) data acquisition utilizing StructXray, a mobile mapping system equipped with a 360° camera and a multi-beam flash LiDAR sensor; (2) vegetation point clouds extraction using deep learning techniques; (3) individual tree segmentation through machine learning algorithms; (4) DBH estimation; and (5) tree image extraction. Six datasets were collected, yielding tree detection precision, recall and F1 score of 0.88, 0.95 and 0.91 respectively. The presence of moving objects within the 3D point cloud map, exhibiting diverse geometric structures, hinders precise vegetation point cloud segmentation by the pointwise neural network. To tackle this challenge, SalsaNext was employed to rectify the predictions of a pointwise neural network, specifically RandLA-Net in this study, eliminating 91 % of misclassified moving object point clouds and completely removing them from 47 % of affected individual tree point clouds. Additionally, a chord length-based method was proposed to enhance DBH estimation accuracy by dividing the point cloud slice into sectors and summing the chord lengths to estimate the tree trunk perimeter. Compared to the ellipse least squares fitting method, this approach reduced the root-mean-square error of the estimated DBH by 1.31 cm.

In vitro propagation of triploid Toxicodendron vernicifluum (Stokes) F. A. Barkl

AbstractTriploid lacquer trees have a higher yield of raw lacquer and greater stress resistance; however, it is challenging to develop efficient and rapid seedling culture techniques because of the influence of metabolites with raw lacquer. In this study, the stem segments of a triploid lacquer tree were used to investigate the effects of explant sterilization treatment, different combinations of exogenous hormone concentrations on the induction of axillary buds, seedling development, and rooting, as well as transplanting substrate ratios. The results showed that the optimal combination of disinfection treatment for triploid Toxicodendron vernicifluum (Stokes) F. A. Barkl explants involves 75% alcohol immersion for 10 s, followed by 2.0% benzalkonium chloride treatment for 1 min and 0.1% HgCl2 treatment for 4 min. The suitable medium for axillary bud induction was Murashige and Skoog (MS) containing 0.1 mg•L−1 zeatin (ZT) and 0.1 mg•L−1 6-benzylaminopurine (6-BA), resulting in a high induction rate of 95.0%. Use of 1/2 MS supplemented with 0.5 mg•L−1 6-BA and 0.3 mg•L−1 2,4-dichlorophenoxyacetic acid (2,4-D) was the most effective for axillary bud proliferation. The combination of 1/2 MS containing 0.1 mg•L−1 6-BA, 0.5 mg•L−1 2,4-D, 0.5 mg•L−1 indole-3-butyric acid (IBA), and 0.2% activated carbon (AC) was an optimum for hardening-off. With woody plant medium (WPM) supplemented with 0.5 mg•L−1 naphthaleneacetic acid (NAA) and 0.5 mg•L−1 2,4-D and 0.5 g•L−1 AC as a rooting medium, the rooting rate was 67.8%. Also, the appropriate transplanting substrate ratio for triploid Toxicodendron vernicifluum (Stokes) F. A. Barkl was grass charcoal:laterite:humus = 1:1:1. Collectively, the results provided the technical assurance for seedling scale multiplication and propagation, facilitating its application in production.