Tree Segmentation Research Articles

Quantification of the ilio-femoral arteries tortuosity and data cluster modelling for preoperative examination

Detecting spatial tortuosity and atherosclerotic changes of the ilio-femoral arteries are crucial for planning endovascular access. The aim of this study was to find a reliable quantification procedure of arterial lumen and tortuosity to qualify patients for a suitable endovascular procedure. We conducted computed tomographic angiography in 76 patients. All ilio-femoral segments of the arterial tree were visualized using Osirix Dicom Viewer software to help qualify the patients to one of two groups: with possible or non-recommended vascular access. The same tomograms were then analyzed with image processing algorithms to perform ilio-femoral artery segmentation and quantification. We chose a set of arterial tortuosity and lumen measuring methods, such as the modified Gustafson-Kessel clustering algorithm and Support Vector Machine classifier, to automatically classify arterial-tree regions. The two 2D feature spaces were selected with the modified Gustafson-Kessel clusterization to create a combined model to assign around 2/3 cases to the access groups with high specificity (more than 88%) whereas the remaining patients were selected for re-evaluation. We concluded that the novel modification of the Gustafson-Kessel clustering algorithm is more suitable to the highly inseparable data than commonly used approaches. To identify ilio-femoral access limitations, we recommend more complex decision model. This study confirmed high usability of our chosen methodology in the quantitative examination of arteries for endovascular access planning.

Prediction of emotional competence in future education teachers through a multiple logistic regression model and classification trees

In order to know the level of emotional competence of future education teachers and evaluate the incidence that different personal and academic factors, we have used binary logistic regression and classification trees. Non-experimental design was carried out, with a sample of 359 students from the Faculties of Education of the University of Malaga and Almería. The results show that variables such as university access scores, the average mark of the first four-month period of the first year of the degree, the effort before the study, being a repeater, the choice of the degree as the first option and having siblings are significant predictors in the logistic model, where the last variable has the greatest determination capacity. Furthermore, in the segmentation tree it has been obtained that those students who do have siblings have a higher level of development of emotional competence, with a probability of 69.2% and if they have also chosen the degree as the first option, this percentage is increased to 75.9%. It can be concluded that it is essential to institutionally establish sufficient conditions so that teachers can detect the predictor variables and establish training strategies that allow increasing the level of development of the competence emotional.

Identification of tree species based on the fusion of UAV hyperspectral image and LiDAR data in a coniferous and broad-leaved mixed forest in Northeast China.

Rapid and accurate identification of tree species via remote sensing technology has become one of the important means for forest inventory. This paper is to develop an accurate tree species identification framework that integrates unmanned airborne vehicle (UAV)-based hyperspectral image and light detection and ranging (LiDAR) data under the complex condition of natural coniferous and broad-leaved mixed forests. First, the UAV-based hyperspectral image and LiDAR data were obtained from a natural coniferous and broad-leaved mixed forest in the Maoer Mountain area of Northeast China. The preprocessed LiDAR data was segmented using a distance-based point cloud clustering algorithm to obtain the point cloud of individual trees; the hyperspectral image was segmented using the projection outlines of individual tree point clouds to obtain the hyperspectral data of individual trees. Then, different hyperspectral and LiDAR features were extracted, respectively, and the importance of the features was analyzed by a random forest (RF) algorithm in order to select appropriate features for the single-source and multi-source data. Finally, tree species identification in the study area were conducted by using a support vector machine (SVM) algorithm together with hyperspectral features, LiDAR features and fused features, respectively. Results showed that the total accuracy for individual tree segmentation was 84.62%, and the fused features achieved the best accuracy for identification of the tree species (total accuracy = 89.20%), followed by the hyperspectral features (total accuracy = 86.08%) and LiDAR features (total accuracy = 76.42%). The optimal features for tree species identification based on fusion of the hyperspectral and LiDAR data included the vegetation indices that were sensitive to the chlorophyll, anthocyanin and carotene contents in the leaves, the partial components of the transformed independent component analysis (ICA), minimum noise fraction (MNF) and principal component analysis (PCA), and the intensity features of the LiDAR echo, respectively. It was concluded that the framework developed in this study was effective in tree species identification under the complex conditions of natural coniferous and broad-leaved mixed forest and the fusion of UAV-based hyperspectral image and LiDAR data can achieve enhanced accuracy compared the single-source UAV-based remote sensing data.

Correction of Terrain Effects on Forest Canopy Height Estimation Using ICESat-2 and High Spatial Resolution Images

The Ice, Cloud, and Land Elevation Satellite–2 (ICESat–2) carries the Advanced Topographic Laser Altimeter System (ATLAS), enabling global canopy height measurements from forest canopy height models (CHMs). Topographic slope is a crucial factor affecting the accuracy of canopy height estimates from ICESat–2 CHMs, but it has not been sufficiently studied. This paper aims to eliminate the influence of slope on canopy height estimates from ICESat–2 data and establishes a method for correcting forest canopy heights based on high spatial resolution digital orthophoto maps (DOM). The cross-track photons are corrected horizontally to eliminate the estimation error. Multi-resolution segmentation is used to segment tree crowns in the DOM, and the distance and relative position between the top of canopy (TOC) photons and the center point of the crown are calculated. TOC photon correction rules are established for different terrains, and the vertical error of the TOC photons is corrected. The results indicate that the vertical error increases exponentially with the slope. The cross-track photon correction and the TOC photon correction method eliminate the effect of slope on canopy height estimates. The cross-track photon correction method reduces the mean absolute error (MAE) and root mean square error (RMSE) of the canopy height estimates by 35.71% and 35.98%, respectively. The TOC photon correction approach further reduces the MAE and RMSE by 23% and 19.23%, respectively. The proposed method has significantly higher accuracy for forest canopy height estimation using ICESat–2 data than the traditional method.

Automatic Segmentation of Standing Trees from Forest Images Based on Deep Learning.

Semantic segmentation of standing trees is important to obtain factors of standing trees from images automatically and effectively. Aiming at the accurate segmentation of multiple standing trees in complex backgrounds, some traditional methods have shortcomings such as low segmentation accuracy and manual intervention. To achieve accurate segmentation of standing tree images effectively, SEMD, a lightweight network segmentation model based on deep learning, is proposed in this article. DeepLabV3+ is chosen as the base framework to perform multi-scale fusion of the convolutional features of the standing trees in images, so as to reduce the loss of image edge details during the standing tree segmentation and reduce the loss of feature information. MobileNet, a lightweight network, is integrated into the backbone network to reduce the computational complexity. Furthermore, SENet, an attention mechanism, is added to obtain the feature information efficiently and suppress the generation of useless feature information. The extensive experimental results show that using the SEMD model the MIoU of the semantic segmentation of standing tree images of different varieties and categories under simple and complex backgrounds reaches 91.78% and 86.90%, respectively. The lightweight network segmentation model SEMD based on deep learning proposed in this paper can solve the problem of multiple standing trees segmentation with high accuracy.

A Double Random Matrix Design Model for Fractal Art Patterns Based on Visual Characteristics

This paper adopts the method of visual characteristics of the double random matrix to conduct in-depth research and analysis on the design of fractal art patterns. For the practical application needs in fractal graphic design, a method is proposed to automatically extract the core base pattern based on fractal graphic content and generate a four-sided continuous pattern. The method first uses the Canny operator for edge detection to analyze the area of the main pattern. Then, it uses a grayscale cogeneration matrix to extract and analyze the graphic texture features, based on which the best splicing method is selected to splice the extracted pattern, and then, it achieves two splicing methods of flat row and staggered four-sided continuous pattern. The method has good practicality with low complexity and high versatility under the premise of ensuring the beauty of the generated four-sided continuous pattern. It can assist designers to design patterns, improve efficiency, and save design costs. In this paper, we improve the existing image segmentation methods, adopt two segmentation methods, namely quadratic tree segmentation and HV segmentation, propose a new local codebook selection strategy, and study the degree of self-adaptation of different methods to images in terms of segmentation methods and local codebook selection strategies. It makes the network unable to train efficiently on long text prediction problems. Finally, the improved algorithm of this paper is tested on the standard and living image libraries, and the experimental results show that the use of local codebooks makes the image coding speed significantly improved compared with the fixed fractal. In the face of the image to be retrieved, it is only necessary to perform the coding operation to obtain the fractal code to perform similarity matching, which can meet the requirement of real-time retrieval. Applying the improved distance formula, the search accuracy obtained on the test gallery is significantly better than that of the grayscale histogram algorithm.

An Unsupervised Canopy-to-Root Pathing (UCRP) Tree Segmentation Algorithm for Automatic Forest Mapping

Terrestrial laser scanners, unmanned aerial LiDAR, and unmanned aerial photogrammetry are increasingly becoming the go-to methods for forest analysis and mapping. The three-dimensionality of the point clouds generated by these technologies is ideal for capturing the structural features of trees such as trunk diameter, canopy volume, and biomass. A prerequisite for extracting these features from point clouds is tree segmentation. This paper introduces an unsupervised method for segmenting individual trees from point clouds. Our novel, canopy-to-root, least-cost routing method segments trees in a single routine, accomplishing stem location and tree segmentation simultaneously without needing prior knowledge of tree stem locations. Testing on benchmark terrestrial-laser-scanned datasets shows that we achieve state-of-the-art performances in individual tree segmentation and stem-mapping accuracy on boreal and temperate hardwood forests regardless of forest complexity. To support mapping at scale, we test on unmanned aerial photogrammetric and LiDAR point clouds and achieve similar results. The proposed algorithm’s independence from a specific data modality, along with its robust performance in simple and complex forest environments and accurate segmentation results, make it a promising step towards achieving reliable stem-mapping capabilities and, ultimately, towards building automatic forest inventory procedures.

Towards real-time forest inventory using handheld LiDAR

While mobile LiDAR sensors are increasingly used to scan in ecology and forestry applications, reconstruction and characterization are typically carried out offline. Motivated by this, we present an online LiDAR system which is capable of running on a handheld device. Our system is capable of creating 3D point cloud reconstructions of large forest areas, segment and track individual trees, and create an inventory for the detected trees. Segments relating to each tree are accumulated over time, and tree models are completed as more scans are captured from different perspectives. The LiDAR scans are processed in an online fashion, and feedback can be provided to the operator via a screen mounted on the device. This allows the operator to ensure the desired area is mapped satisfactorily without any gaps or missing sections. We employ a pose-graph based SLAM system with loop closures to correct for drift errors allowing us to map large areas accurately. Our mapping system also provides multi-session capability where data captured during different runs can be automatically merged in a post-processing step. In this work, we estimate the Diameter at Breast Height (DBH) of individual trees as an example parameter for the forest inventory. The DBH is estimated online by fitting a cylinder to each tree trunk through a least-squares optimization within a RANSAC loop. We demonstrate our mapping approach operating in two different forests (both ecological and commercial) with the total travel distance spanning several kilometres. Further, we also provide experimental results comparing our DBH estimation to ground-truth measurements recorded manually in an ecological forest (Wytham Woods, Oxford). We demonstrate that our DBH estimates are within ∼7 cm accuracy for 90% of individual trees detected in the dataset.

TreeKnit: Inferring ancestral reassortment graphs of influenza viruses.

When two influenza viruses co-infect the same cell, they can exchange genome segments in a process known as reassortment. Reassortment is an important source of genetic diversity and is known to have been involved in the emergence of most pandemic influenza strains. However, because of the difficulty in identifying reassortment events from viral sequence data, little is known about their role in the evolution of the seasonal influenza viruses. Here we introduce TreeKnit, a method that infers ancestral reassortment graphs (ARG) from two segment trees. It is based on topological differences between trees, and proceeds in a greedy fashion by finding regions that are compatible in the two trees. Using simulated genealogies with reassortments, we show that TreeKnit performs well in a wide range of settings and that it is as accurate as a more principled bayesian method, while being orders of magnitude faster. Finally, we show that it is possible to use the inferred ARG to better resolve segment trees and to construct more informative visualizations of reassortments.

Assessing vascular complexity of PAOD patients by deep learning-based segmentation and fractal dimension

The assessment of vascular complexity in the lower limbs provides relevant information about peripheral artery occlusive diseases (PAOD), thus fostering improvements both in therapeutic decisions and prognostic estimation. The current clinical practice consists of visually inspecting and evaluating cine-angiograms of the interested region, which is largely operator-dependent. We present here an automatic method for segmenting the vessel tree and compute a quantitative measure, in terms of fractal dimension (FD), of the vascular complexity. The proposed workflow consists of three main steps: (i) conversion of the cine-angiographies to single static images with a broader field of view, (ii) automatic segmentation of the vascular trees, and (iii) calculation and assessment of FD as complexity index. In particular, this work defines (1) a method to reduce the inter-observer variability in judging vascular complexity in cine-angiography images from patients affected by peripheral artery occlusive disease (PAOD), and (2) the use of Fractal Dimension as a metric of shape complexity of vascular tree. The inter-class correlation coefficient (ICC) is computed as inter-observer agreement metric and to account for possible systematic error, that depends on the experience of the raters. The automatic segmentation of vascular tree achieved an Area Under the Curve mean value of 0.77~pm ~0.07, with a min-max range of 0.57-0.87. Absolute operator agreement was higher over the segmented image (ICC=0.96) compared to the video (ICC=0.76) and the a broader field of view image (ICC=0.92). Fractal Dimension computed on both manual segmented images (ground truths) and automatically showed a good correlation with the clinical score (0.85 and 0.75, respectively). Experimental analyses suggest that extracting the vascular tree from cine-angiography can substantially improve the reliability of visual assessment of vascular complexity in PAOD. Results also reveal the effectiveness of FD in evaluating complex vascular tree structures.

Pembelajaran Struktur Data Berbasis Visualisasi dengan Menggunakan Visualgo.Net

Abstract: Purpose: The purpose of the activity include preparing Prambanan Sleman High School students who will take part in the National Science Competition, especially in the field of Informatics. One of the preparations made is assistance on data structure material. Data structure is an important material in learning programming. Method: The activity method is provided by providing assistance in the process of providing data structure material that is adjusted to the syllabus including primitive data types, arrays, strings, stacks, queues, binary heaps, disjoint sets and segment trees. The material is packed with visualization-based explanations. Visualization learning is given using the visualgo.net application. Result: By using visualization, students who take part in the mentoring have experience of the process and logic in creating and understanding data structures. The results of the implementation, students get data structure material based on visualgo.net and explained how the data structure algorithm process is related to visualization-based. Conclusion: Data structure learning is given by using the visualgo.net application. Visualgo.net can help students in the process of studying data structure material. Visualization-based learning in studying data structure material is very helpful in the process of learning programming material. In this activity, students get an explanation of the algorithm used in the data structure, both with theory and with visualization-based explanations. Keywords: 1. Competition 2. computer 3. data structure 4. visualization 5. students

A Deep Learning-Based Method for Extracting Standing Wood Feature Parameters from Terrestrial Laser Scanning Point Clouds of Artificially Planted Forest

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

Street Tree Extraction and Segmentation from Mobile LiDAR Point Clouds Based on Spatial Geometric Features of Object Primitives

Extracting street trees from mobile Light Detection and Ranging (LiDAR) point clouds is still encountering challenges, such as low extraction accuracy and poor robustness in complex urban environment, and difficulty in the segmentation of overlapping trees. To solve these problems, this paper proposed a street tree extraction and segmentation method based on spatial geometric features of object primitives. In this paper, mobile LiDAR point clouds were first segmented into object primitives based on the proposed graph segmentation method, which can release the computation burden effectively. According to the spatial geometric features of the segmented object primitives, stem points were extracted. In doing so, the robustness and accuracy for stem detecting can be improved. Furthermore, voxel connectivity analysis and individual tree optimization were combined successively. In doing so, the neighboring trees could be separated successfully. Four datasets located in Henan Polytechnic University, China, were used for validating the performance of the proposed method. The four mobile LiDAR point clouds contained 106, 45, 76, and 46 trees, respectively. The experimental results showed that the proposed method can achieve the performance of individual tree separation in all the four testing plots. Compared to the other three methods, the proposed method can make a good balance between the commission and omission errors and achieved the highest average F1 scores.

Comparative Evaluation of a Newly Developed Trunk-Based Tree Detection/Localization Strategy on Leaf-Off LiDAR Point Clouds with Varying Characteristics

LiDAR data acquired by various platforms provide unprecedented data for forest inventory and management. Among its applications, individual tree detection and segmentation are critical and prerequisite steps for deriving forest structural metrics, especially at the stand level. Although there are various tree detection and localization approaches, a comparative analysis of their performance on LiDAR data with different characteristics remains to be explored. In this study, a new trunk-based tree detection and localization approach (namely, height-difference-based) is proposed and compared to two state-of-the-art strategies—DBSCAN-based and height/density-based approaches. Leaf-off LiDAR data from two unmanned aerial vehicles (UAVs) and Geiger mode system with different point densities, geometric accuracies, and environmental complexities were used to evaluate the performance of these approaches in a forest plantation. The results from the UAV datasets suggest that DBSCAN-based and height/density-based approaches perform well in tree detection (F1 score > 0.99) and localization (with an accuracy of 0.1 m for point clouds with high geometric accuracy) after fine-tuning the model thresholds; however, the processing time of the latter is much shorter. Even though our new height-difference-based approach introduces more false positives, it obtains a high tree detection rate from UAV datasets without fine-tuning model thresholds. However, due to the limitations of the algorithm, the tree localization accuracy is worse than that of the other two approaches. On the other hand, the results from the Geiger mode dataset with low point density show that the performance of all approaches dramatically deteriorates. Among them, the proposed height-difference-based approach results in the greatest number of true positives and highest F1 score, making it the most suitable approach for low-density point clouds without the need for parameter/threshold fine-tuning.

Biomass and Carbon Stock Quantification in Cork Oak Forest of Maamora Using a New Approach Based on the Combination of Aerial Laser Scanning Carried by Unmanned Aerial Vehicle and Terrestrial Laser Scanning Data

The Mediterranean forests, particularly Cork oak (Quercus suber L., 1927), make a major contribution to the fight against climate change through Carbon sequestration. Hence, there is a great interest in the accurate quantification of biomass and carbon stock. In this context, this study aims at assessing the performance of a new approach, based on the combination of Unmanned aerial vehicle airborne Aerial laser scanning (ALS-UAV) and Terrestrial laser scanning (TLS) data, in the determination of dendrometric parameters (Circumference at 1.30 m and Tree Height), and consequently the estimation of biomass and carbon stock, considering field data as reference. This study takes the Maamora forest in Morocco as an example of a Mediterranean Cork oak forest. The methodology consists of collecting data at three levels: the entire area level for an ALS-UAV scan, the plot and tree levels for TLS surveys, as well as field data collection. Afterwards, dendrometric parameters (Circumference at 1.30 m and the Tree height) were estimated using individual tree segmentation and biomass; the carbon stock (aboveground, belowground, and total) was estimated using allometric equations. The comparison of the estimated dendrometric parameters with those measured in the field shows a strong relationship, with a Pearson coefficient of 0.86 and 0.83, a correlation coefficient (R2) of 0.81 and 0.71, and a Root mean square error (RMSE) of 1.84 cm and 0.47 m, respectively. Concerning the biomass and carbon stock estimation, the proposed approach gives a satisfactory accuracy, with a Pearson coefficient of 0.77, an R2 of 0.83, and an RMSE of 36.40 kg for biomass and 20.24 kg for carbon stock.

Plot-level reconstruction of 3D tree models for aboveground biomass estimation

Complexity of forest structure is an important factor contributing to uncertainty in aboveground biomass estimates. In this study, we present a new method for reducing uncertainty in forest aboveground biomass (AGB) estimation based on plot-level terrestrial laser scanner (TLS) point clouds reconstruction. The method estimates the total AGB of plots with complex structures after automatically performing the steps of ground point filtering, single tree segmentation, and three-dimensional (3D) structure reconstruction. We used plot data from temperate and tropical forest ecosystems to verify the effectiveness of the method, reconstructing a 1300 m2 temperate plantation plot and a 5000 m2 mingled forest plot, respectively. The total biomass of 153 trees in the plantation plot was overestimated by 17.12 %, and the total biomass of 61 trees in the mingled forest plot was underestimated by 10.88 %. We found that the uncertainty of aboveground biomass estimation in tropical forests with more complex structures is not necessarily greater than in plantations. Therefore, in large-scale remote sensing observations of forest biomass, the number or area of plots can be increased to reduce the uncertainty of the results caused by the complex structure. The focus of this study is to explore TLS point clouds modeling methods to reduce the uncertainty in AGB estimation caused by the complexity of forest structures, and to provide reference cases for plot-level point clouds reconstruction methods. Forest ecologists can use this method to regularly observe forest growth and obtain indicators related to forest ecology without destroying trees.

Measuring the Tree Height of Picea crassifolia in Alpine Mountain Forests in Northwest China Based on UAV-LiDAR

Forests in alpine mountainous regions are sensitive to global climate change. Accurate measurement of tree height is essential for forest aboveground biomass estimation. Unmanned aerial vehicle light detection and ranging (UAV-LiDAR) in tree height estimation has been extensively used in forestry inventories. This study investigated the influence of varying flight heights and point cloud densities on the extraction of tree height, and four flight heights (i.e., 85, 115, 145, and 175 m) were set in three Picea crassifolia plots in the Qilian Mountains. After point cloud data were classified, tree height was extracted from a canopy height model (CHM) on the basis of the individual tree segmentation. Through comparison with ground measurements, the tree height estimations of different flight heights and point cloud densities were analyzed. The results indicated that (1) with a flight height of 85 m, the tree height estimation achieved the highest accuracy (R2 = 0.75, RMSE = 2.65), and the lowest accuracy occurred at a height of 175 m (R2 = 0.65, RMSE = 3.00). (2) The accuracy of the tree height estimation decreased as the point cloud density decreased. The accuracies of tree height estimation from low-point cloud density (R2 = 0.70, RMSE = 2.75) and medium density (R2 = 0.69, RMSE = 2.80) were comparable. (3) Tree height was slightly underestimated in most cases when CHM-based segmentation methods were used. Consequently, a flight height of 145 m was more applicable for maintaining tree height estimation accuracy and assuring the safety of UAVs flying in alpine mountain regions. A point cloud density of 125–185 pts/m2 can guarantee tree height estimation accuracy. The results of this study could potentially improve tree height estimation and provide available UAV-LiDAR flight parameters in alpine mountainous regions in Northwest China.

Peripheral artery disease affects the function of the legs of claudicating patients in a diffuse manner irrespective of the segment of the arterial tree primarily involved.

Different levels of arterial occlusive disease (aortoiliac, femoropopliteal, multi-level disease) can produce claudication symptoms in different leg muscle groups (buttocks, thighs, calves) in patients with peripheral artery disease (PAD). We tested the hypothesis that different locations of occlusive disease uniquely affect the muscles of PAD legs and produce distinctive patterns in the way claudicating patients walk. Ninety-seven PAD patients and 35 healthy controls were recruited. PAD patients were categorized to aortoiliac, femoropopliteal and multi-level disease groups using computerized tomographic angiography. Subjects performed walking trials both pain-free and during claudication pain and joint kinematics, kinetics, and spatiotemporal parameters were calculated to evaluate the net contribution of the calf, thigh and buttock muscles. PAD patients with occlusive disease affecting different segments of the arterial tree (aortoiliac, femoropopliteal, multi-level disease) presented with symptoms affecting different muscle groups of the lower extremity (calves, thighs and buttocks alone or in combination). However, no significant biomechanical differences were found between PAD groups during the pain-free conditions with minimal differences between PAD groups in the claudicating state. All statistical differences in the pain-free condition occurred between healthy controls and one or more PAD groups. A discriminant analysis function was able to adequately predict if a subject was a control with over 70% accuracy, but the function was unable to differentiate between PAD groups. In-depth gait analyses of claudicating PAD patients indicate that different locations of arterial disease produce claudication symptoms that affect different muscle groups across the lower extremity but impact the function of the leg muscles in a diffuse manner generating similar walking impairments.

The RETA Benchmark for Retinal Vascular Tree Analysis

Topological and geometrical analysis of retinal blood vessels could be a cost-effective way to detect various common diseases. Automated vessel segmentation and vascular tree analysis models require powerful generalization capability in clinical applications. In this work, we constructed a novel benchmark RETA with 81 labelled vessel masks aiming to facilitate retinal vessel analysis. A semi-automated coarse-to-fine workflow was proposed for vessel annotation task. During database construction, we strived to control inter-annotator and intra-annotator variability by means of multi-stage annotation and label disambiguation on self-developed dedicated software. In addition to binary vessel masks, we obtained other types of annotations including artery/vein masks, vascular skeletons, bifurcations, trees and abnormalities. Subjective and objective quality validations of the annotated vessel masks demonstrated significantly improved quality over the existing open datasets. Our annotation software is also made publicly available serving the purpose of pixel-level vessel visualization. Researchers could develop vessel segmentation algorithms and evaluate segmentation performance using RETA. Moreover, it might promote the study of cross-modality tubular structure segmentation and analysis.

Individual tree segmentation and tree species classification in subtropical broadleaf forests using UAV-based LiDAR, hyperspectral, and ultrahigh-resolution RGB data

Accurate classification of individual tree species is essential for inventorying, managing, and protecting forest resources. Individual tree species classification in subtropical forests remains challenging as existing individual tree segmentation algorithms typically result in over-segmentation in subtropical broadleaf forests, in which tree crowns often have multiple peaks. In this study, we proposed a watershed-spectral-texture-controlled normalized cut (WST-Ncut) algorithm, and applied it to delineate individual trees in a subtropical broadleaf forest situated in Shenzhen City of southern China (114°23′28″E, 22°43′50″N). Using this algorithm, we first obtained accurate crown boundary of individual broadleaf trees. We then extracted different suites of vertical structural, spectral, and textural features from UAV-based LiDAR, hyperspectral, and ultrahigh-resolution RGB data, and used these features as inputs to a random forest classifier to classify 18 tree species. The results showed that the proposed WST-Ncut algorithm could reduce the over-segmentation of the watershed segmentation algorithm, and thereby was effective for delineating individual trees in subtropical broadleaf forests (Recall = 0.95, Precision = 0.86, and F-score = 0.91). Combining the structural, spectral, and textural features of individual trees provided the best tree species classification results, with overall accuracy reaching 91.8%, which was 10.2%, 13.6%, and 19.0% higher than that of using spectral, structural, and textural features alone, respectively. In addition, results showed that better individual tree segmentation would lead to higher accuracy of tree species classification, but the increase of the number of tree species would result in the decline of classification accuracy.