Marker-controlled Watershed Segmentation Research Articles

Marker-controlled watershed algorithm and fuzzy C-means clustering machine learning: automated segmentation of glioblastoma from MRI images in a case series.

Automated segmentation of glioblastoma multiforme (GBM) from MRI images is crucial for accurate diagnosis and treatment planning. This paper presents a new and innovative approach for automating the segmentation of GBM from MRI images using the marker-controlled watershed segmentation (MCWS) algorithm. The technique involves several image processing techniques, including adaptive thresholding, morphological filtering, gradient magnitude calculation, and regional maxima identification. The MCWS algorithm efficiently segments images based on local intensity structures using the watershed transform, and fuzzy c-means (FCM) clustering improves segmentation accuracy. The presented approach achieved improved segmentation accuracy in detecting and segmenting GBM tumours from axial T2-weighted (T2-w) MRI images, as demonstrated by the mean characteristics performance metrics for GBM segmentation (sensitivity: 0.9905, specificity: 0.9483, accuracy: 0.9508, precision: 0.5481, F_measure: 0.7052, and jaccard: 0.9340). The results of this study underline the importance of reliable and accurate image segmentation for effective diagnosis and treatment planning of GBM tumours. The MCWS technique provides an effective and efficient approach for the segmentation of challenging medical images.

Segmentation of Individual Tree Points by Combining Marker-Controlled Watershed Segmentation and Spectral Clustering Optimization

Accurate identification and segmentation of individual tree points are crucial for assessing forest spatial distribution, understanding tree growth and structure, and managing forest resources. Traditional methods based on Canopy Height Models (CHM) are simple yet prone to over- and/or under-segmentation. To deal with this problem, this paper introduces a novel approach that combines marker-controlled watershed segmentation with a spectral clustering algorithm. Initially, we determined the local maxima within a series of variable windows according to the lower bound of the prediction interval of the regression equation between tree crown radius and tree height to preliminarily segment individual trees. Subsequently, using this geometric shape analysis method, the under-segmented trees were identified. For these trees, vertical tree crown profile analysis was performed in multiple directions to detect potential treetops which were then considered as inputs for spectral clustering optimization. Our experiments across six plots showed that our method markedly surpasses traditional approaches, achieving an average Recall of 0.854, a Precision of 0.937, and an F1-score of 0.892.

Automated segmentation of meningioma from contrast-enhanced T1-weighted MRI images in a case series using a marker-controlled watershed segmentation and fuzzy C-means clustering machine learning algorithm

Introduction and importanceAccurate segmentation of meningiomas from contrast-enhanced T1-weighted (CE T1-w) magnetic resonance imaging (MRI) is crucial for diagnosis and treatment planning. Manual segmentation is time-consuming and prone to variability. To evaluate an automated segmentation approach for meningiomas using marker-controlled watershed segmentation (MCWS) and fuzzy c-means (FCM) algorithms. Case presentation and methodsCE T1-w MRI of 3 female patients (aged 59, 44, 67 years) with right frontal meningiomas were analyzed. Images were converted to grayscale and preprocessed with Otsu's thresholding and FCM clustering. MCWS segmentation was performed. Segmentation accuracy was assessed by comparing automated segmentations to manual delineations. Clinical discussionThe approach successfully segmented meningiomas in all cases. Mean sensitivity was 0.8822, indicating accurate identification of tumors. Mean Dice similarity coefficient between Otsu's and FCM1 was 0.6599, suggesting good overlap between segmentation methods. ConclusionThe MCWS and FCM approach enables accurate automated segmentation of meningiomas from CE T1-w MRI. With further validation on larger datasets, this could provide an efficient tool to assist in delineating meningioma boundaries for clinical management.

Remote Sensing Parameter Extraction of Artificial Young Forests under the Interference of Undergrowth

Due to the lower canopy height at the maximum crown width at the bottom of young Picea crassifolia trees, they are mixed with undergrowth. This makes it challenging to accurately determine crown size using CHM data or point cloud data. UAV imagery, on the other hand, incorporates rich color information and, after processing, can effectively distinguish between spruce trees and ground vegetation. In this study, the experimental site was an artificial young forest of Picea crassifolia in Shangshan Village, Qinghai Province, China. UAV images were used to obtain normalized saturation data for the sample plots. A marker-controlled watershed segmentation algorithm was employed to extract tree parameters, and the results were compared with those obtained via point cloud clustering segmentation and the marker-controlled watershed segmentation algorithm based on Canopy Height Model (CHM) images. The research results showed that the single tree recognition capabilities of the three types of data were similar, with F-measures of 0.96, 0.95, and 0.987 for the CHM image, UAV imagery, and point cloud data, respectively. The mean square errors of crown width information extracted from the UAV imagery using the marker-controlled watershed segmentation algorithm were 0.043, 0.125, and 0.046 for the three sample plots, which were better than the values of 0.103, 0.182, and 0.074 obtained from CHM data, as well as the values of 0.36, 0.461, and 0.4 obtained from the point cloud data. The point cloud data exhibited better fitting results for tree height extraction compared to the CHM images. This result indicates that UAV-acquired optical imagery has applicability in extracting individual tree feature parameters and can compensate for the deficiencies of CHM and point cloud data.

Calibration of wall effects in mesostructure modelling of concrete using marker-controlled watershed segmentation

This paper proposes formulae for refined models that account for wall effects when modelling the geometric mesostructure of concrete. The wall effect should be taken into account in the mesostructure modelling of concrete since it affects the spatial distribution and packing of aggregates within concrete elements. However, scarce research has focused on the calibration of the wall effect in geometric modelling. Measurements on sections of real specimens using the marker-controlled watershed segmentation (MCWS) method are used to accurately identify aggregate particles from digital images and these data are used to calibrate and validate the proposed formulae. The distance and diameters of aggregates relevant to wall effect were obtained and a distribution factor γ that can control the minimum gaps surrounding the particles was calibrated. A demonstrative application of the refined wall effect model shows that the mesostructure modelled agrees well with the experimental data.

Monitoring Individual Tree Phenology in a Multi-Species Forest Using High Resolution UAV Images

Monitoring tree phenology is important for understanding ecosystem functioning and for assessing ecosystem responses to climate change. Satellite imagery offers open-access global coverage but is restricted to forest-level analyses, due to its coarse spatial resolution. Unmanned aerial vehicle (UAV) imagery can monitor phenology at the individual tree level by utilizing a centimeter-scale resolution. Two research objectives were identified for this study: (1) to derive phenological metrics at the individual tree level, using various vegetation indices (VIs); and (2) to assess the accuracy of automatic crown delineation in a diverse ecosystem. To achieve this, fourteen multi-spectral UAV flights were performed, and the ability of the normalized difference vegetation index (NDVI), enhanced vegetation index 2 (EVI2), optimized soil-adjusted vegetation index (OSAVI), and chlorophyll index red-edge (CIre) to model seasonal phenology was assessed. A double logistic model was fitted on the VI observations for each individual tree, to derive the start of season (SOS) and end of season (EOS). Individual tree crowns were delineated automatically using marker-controlled watershed segmentation (MCWS), and the treetops were identified using a local maximum filter (LMF). Overall, the automatic segmentation performed well (F-score: 0.79, IoU: 0.58), with higher accuracies in single-species areas, while it underperformed in complex mixed forest structures. All VIs captured a strong seasonal signal for the deciduous trees and derived SOS and EOS estimates consistent with literature and ground observations. General phenological patterns included an early silver birch SOS, a quick beech budburst, and large within-species phenology variations for oak trees. Seasonal VI variation for coniferous evergreen trees was limited, and the resulting phenology estimates proved unreliable. In conclusion, these findings emphasize the capabilities of UAV imagery for individual tree crown phenology monitoring. However, they also show the difficulty of monitoring evergreen phenology with the commonly-used VIs and stress the need for further investigations.

A New Approach to Estimate Fuel Budget and Wildfire Hazard Assessment in Commercial Plantations Using Drone-Based Photogrammetry and Image Analysis

Increased demand for sustainable timber products has resulted in large investments in agroforestry in Australia, with plantations growing various Pinus species, selected to suit a plantation’s environment. Juvenile Pinus species have a low fire tolerance. With Australia’s history of wildfires and the likelihood of climate change exacerbating that risk, the potential for a total loss of invested capital is high unless cost-effective targeted risk minimisation is part of forest management plans. Based on the belief that the understory profiles within the juvenile plantations are a major factor determining fuel hazard risks, an accurate assessment of these profiles is required to effectively mitigate those risks. At present, assessment protocols are largely reliant on ground-based observations, which are labour-intensive, time consuming, and expensive. This research project investigates the effectiveness of using geospatial analysis of drone-derived photographic data collected in the commercial pine plantations of south-eastern Queensland as a cost-saving alternative to current fuel hazard risk assessment practices. Understory composition was determined using the supervised classification of orthomosaic images together with derivations of canopy height models (CHMs). The CHMs were subjected to marker-controlled watershed segmentation (MCWS) analysis, isolating and removing the plantation pine trees, enabling the quantification of understory fuel profiles. The method used proved highly applicable to immature forest environments with minimal canopy closure, but became less reliable for close canopied older plantations.

Coastal Aquaculture Extraction Using GF-3 Fully Polarimetric SAR Imagery: A Framework Integrating UNet++ with Marker-Controlled Watershed Segmentation

Coastal aquaculture monitoring is vital for sustainable offshore aquaculture management. However, the dense distribution and various sizes of aquacultures make it challenging to accurately extract the boundaries of aquaculture ponds. In this study, we develop a novel combined framework that integrates UNet++ with a marker-controlled watershed segmentation strategy to facilitate aquaculture boundary extraction from fully polarimetric GaoFen-3 SAR imagery. First, four polarimetric decomposition algorithms were applied to extract 13 polarimetric scattering features. Together with the nine other polarisation and texture features, a total of 22 polarimetric features were then extracted, among which four were optimised according to the separability index. Subsequently, to reduce the “adhesion” phenomenon and separate adjacent and even adhering ponds into individual aquaculture units, two UNet++ subnetworks were utilised to construct the marker and foreground functions, the results of which were then used in the marker-controlled watershed algorithm to obtain refined aquaculture results. A multiclass segmentation strategy that divides the intermediate markers into three categories (aquaculture, background and dikes) was applied to the marker function. In addition, a boundary patch refinement postprocessing strategy was applied to the two subnetworks to extract and repair the complex/error-prone boundaries of the aquaculture ponds, followed by a morphological operation that was conducted for label augmentation. An experimental investigation performed to extract individual aquacultures in the Yancheng Coastal Wetlands indicated that the crucial features for aquacultures are Shannon entropy (SE), the intensity component of SE (SE_I) and the corresponding mean texture features (Mean_SE and Mean_SE_I). When the optimal features were introduced, our proposed method performed better than standard UNet++ in aquaculture extraction, achieving improvements of 1.8%, 3.2%, 21.7% and 12.1% in F1, IoU, MR and insF1, respectively. The experimental results indicate that the proposed method can handle the adhesion of both adjacent objects and unclear boundaries effectively and capture clear and refined aquaculture boundaries.

Assessing the detectability of European spruce bark beetle green attack in multispectral drone images with high spatial- and temporal resolutions

Detecting disease- or insect-infested forests as early as possible is a classic application of remote sensing. Under conditions of climate change and global warming, outbreaks of the European spruce bark beetle (Ips typographus, L.) are threatening spruce forests and the related timber industry across Europe, and early detection of infestations is important for damage control. Infested trees without visible discoloration (green attack) have been identified using multispectral images, but how early green attacks can be detected is still unknown. This study aimed to determine when infested trees start to show an abnormal spectral response compared with healthy trees, and to quantify the detectability of infested trees during the infestation process. Pheromone bags were used to attract bark beetles in a controlled experiment, and subsequent infestations were assessed in the field on a weekly basis. In total, 977 trees were monitored, including 208 attacked trees. Multispectral drone images were obtained before and during the insect attacks, representing different periods of infestation. Individual tree crowns (ITC) were delineated by marker-controlled watershed segmentation, and the average reflectance of ITCs was analyzed based on the duration of infestation. The detectability of green attacks and driving factors were examined. We propose new Multiple Ratio Disease–Water Stress Indices (MR-DSWIs) as vegetation indices (VI) for detecting infestations. We defined a VI range of 5–95% as a healthy tree, and a VI value outside that range as an infested tree. Detection rates using multispectral images were always higher than discoloration rates observed in the field, and the newly proposed MR-DSWIs detected more infested trees than the established VIs. Infestations were detectable at 5 and 10 weeks after an attack at a rate of 15% and 90%, respectively, from the multispectral drone images. Weeks 5–10 of infestation therefore represent a suitable period for using the proposed methodology to map infestation at an early stage.

Automated Pneumonia Based Lung Diseases Classification with Robust Technique Based on a Customized Deep Learning Approach.

Many people have been affected by infectious lung diseases (ILD). With the outbreak of the COVID-19 disease in the last few years, many people have waited for weeks to recover in the intensive care wards of hospitals. Therefore, early diagnosis of ILD is of great importance to reduce the occupancy rates of health institutions and the treatment time of patients. Many artificial intelligence-based studies have been carried out in detecting and classifying diseases from medical images using imaging applications. The most important goal of these studies was to increase classification performance and model reliability. In this approach, a powerful algorithm based on a new customized deep learning model (ACL model), which trained synchronously with the attention and LSTM model with CNN models, was proposed to classify healthy, COVID-19 and Pneumonia. The important stains and traces in the chest X-ray (CX-R) image were emphasized with the marker-controlled watershed (MCW) segmentation algorithm. The ACL model was trained for different training-test ratios (90-10%, 80-20%, and 70-30%). For 90-10%, 80-20%, and 70-30% training-test ratios, accuracy scores were 100%, 96%, and 96%, respectively. The best performance results were obtained compared to the existing methods. In addition, the contribution of the strategies utilized in the proposed model to classification performance was analyzed in detail. Deep learning-based applications can be used as a useful decision support tool for physicians in the early diagnosis of ILD diseases. However, for the reliability of these applications, it is necessary to undertake verification with many datasets.

Mapping the urban forest in detail: From LiDAR point clouds to 3D tree models

Trees are an integral component of the urban environment and important for human well-being, adaption measures to climate change and sustainable urban transformation. Understanding the small-scale impacts of urban trees and strategically managing the ecosystem services they provide requires high-resolution information on urban forest structure, which is still scarce. In contrast, there is an abundance of data portraying urban areas and an associated trend towards smart cities and digital twins as analysis platforms. A GIS workflow is presented in this paper that may close this data gap by classifying the urban forest from LiDAR point clouds, detecting and reconstructing individual crowns, and enabling a tree representation within semantic 3D city models. The workflow is designed to provide robust results for point clouds with a density of at least 4 pts/m2 that are widely available. Evaluation was conducted by mapping the urban forest of Dresden (Germany) using a point cloud with 4 pts/m². An object-based data fusion approach is implemented for the classification of the urban forest. A classification accuracy of 95 % for different urban settings is achieved by combining LiDAR with multispectral imagery and a 3D building model. Individual trees are detected by local maxima filtering and crowns are segmented using marker-controlled watershed segmentation. Evaluation highlights the influences of both urban and forest structure on individual tree detection. Substantial differences in detection accuracies are evident between trees along streets (72 %) and structurally more complex tree stands in green areas (31 %), as well as dependencies on tree height and crown diameter. Furthermore, an approach for parameterized reconstruction of tree crowns is presented, which enables efficient and realistic city-wide modeling. The suitability of LiDAR to measure individual tree metrics is illustrated as well as a framework for modeling individual tree crowns via geometric primitives.

Efficient automatic 3D segmentation of cell nuclei for high-content screening

BackgroundHigh-content screening (HCS) is a pre-clinical approach for the assessment of drug efficacy. On modern platforms, it involves fluorescent image capture using three-dimensional (3D) scanning microscopy. Segmentation of cell nuclei in 3D images is an essential prerequisite to quantify captured fluorescence in cells for screening. However, this segmentation is challenging due to variabilities in cell confluency, drug-induced alterations in cell morphology, and gradual degradation of fluorescence with the depth of scanning. Despite advances in algorithms for segmenting nuclei for HCS, robust 3D methods that are insensitive to these conditions are still lacking.ResultsWe have developed an algorithm which first generates a 3D nuclear mask in the original images. Next, an iterative 3D marker-controlled watershed segmentation is applied to downsized images to segment adjacent nuclei under the mask. In the last step, borders of segmented nuclei are adjusted in the original images based on local nucleus and background intensities. The method was developed using a set of 10 3D images. Extensive tests on a separate set of 27 3D images containing 2,367 nuclei demonstrated that our method, in comparison with 6 reference methods, achieved the highest precision (PR = 0.97), recall (RE = 0.88) and F1-score (F1 = 0.93) of nuclei detection. The Jaccard index (JI = 0.83), which reflects the accuracy of nuclei delineation, was similar to that yielded by all reference approaches. Our method was on average more than twice as fast as the reference method that produced the best results. Additional tests carried out on three stacked 3D images comprising heterogenous nuclei yielded average PR = 0.96, RE = 0.84, F1 = 0.89, and JI = 0.80.ConclusionsThe high-performance metrics yielded by the proposed approach suggest that it can be used to reliably delineate nuclei in 3D images of monolayered and stacked cells exposed to cytotoxic drugs.

Deep learning-based individual tree crown delineation in mangrove forests using very-high-resolution satellite imagery

Mangrove forests are vulnerable ecosystems that require broad-scale monitoring. Various solutions based on satellite imagery have emerged for this purpose but still suffer from the lack of methods to accurately delineate individual tree crowns (ITCs). Within-stand variability in crown size and shape, crown clumping and fragmentation, and understory vegetation hamper the delineation in these ecosystems. To cope with these factors, the proposed method combines a deep learning-based enhancement of ITCs with a marker-controlled watershed segmentation algorithm. The MT-EDv3 neural network is employed to compute the normalized Euclidean distance of crown pixels to treetops and a Laplacian of Gaussian filter is applied to the resulting image to enhance crown borders before segmentation. The method was applied to WorldView imagery over four mangrove sites worldwide and compared to previously published methods using standardized metrics. Accurate detection (Overall Accuracy ≥ 0.93 and Kappa ≥ 0.87) and area estimation (R2 ≥ 0.66, NRMSE ≤ 12%) of crowns was achieved for all sites using either the panchromatic band or a combination of the pan-sharpened visible-near-infrared bands. Based on Precision, Recall, and F1-score, the proposed method outperformed previous watershed segmentation and software-based algorithms of crown delineation, as well as the Mask R-CNN segmentation framework. The viewing geometry of images and the forest heterogeneity were identified as important contributors to the delineation accuracy. This study is the first to achieve accurate delineation of ITCs in mangrove forests across sites, opening perspectives of applications to satellite-based monitoring. The method shows promising transferability to other very-high-resolution satellite sensors as well as to aerial and unmanned aerial vehicle imagery and could be improved by including more spectral information and LiDAR-derived canopy height models.

Detection of Lung Cancer Stages on Computed Tomography Image Using Laplacian Filter and Marker Controlled Watershed Segmentation Technique

Lung cancer is a form of malignant tumor distinguished by aggressive multiplication of abnormal cells in lung tissues. If we can assure the detection of lung cancer in the early stage, then we have a chance to increase the survival rate by five years as effective treatment is still available at this stage. Many researchers in the field of image processing sector have built various systems to detect cancer by using image processing techniques. Internationally TNM (Tumor, Nodule, Metastases respectively) method is followed by a physician and radiologist to describe the stage of lung cancer. Our proposed system uses image processing techniques to detect and classify the tumor according to the TNM staging method. First, a series of image processing techniques are performed in a Computed tomography (CT) image. Then, features are extracted to identify the region of interest (ROI). In our proposed system, the classification approach is different from the reviewed existing systems, and the detection rate is comparatively high.

Deep Learning-Based Phenotypic Assessment of Red Cell Storage Lesions for Safe Transfusions.

This study presents a novel approach to automatically perform instant phenotypic assessment of red blood cell (RBC) storage lesion in phase images obtained by digital holographic microscopy. The proposed model combines a generative adversarial network (GAN) with marker-controlled watershed segmentation scheme. The GAN model performed RBC segmentations and classifications to develop ageing markers, and the watershed segmentation was used to completely separate overlapping RBCs. Our approach achieved good segmentation and classification accuracy with a Dice's coefficient of 0.94 at a high throughput rate of about 152 cells per second. These results were compared with other deep neural network architectures. Moreover, our image-based deep learning models recognized the morphological changes that occur in RBCs during storage. Our deep learning-based classification results were in good agreement with previous findings on the changes in RBC markers (dominant shapes) affected by storage duration. We believe that our image-based deep learning models can be useful for automated assessment of RBC quality, storage lesions for safe transfusions, and diagnosis of RBC-related diseases.

A novel fully convolutional network based on marker-controlled watershed segmentation algorithm for industrial soot robot target segmentation

A novel fully convolutional network based on marker-controlled watershed segmentation algorithm for industrial soot robot target segmentation

Development and Application of Automatized Routines for Optical Analysis of Synaptic Activity Evoked by Chemical and Electrical Stimulation.

The recent development of cellular imaging techniques and the application of genetically encoded sensors of neuronal activity led to significant methodological progress in neurobiological studies. These methods often result in complex and large data sets consisting of image stacks or sets of multichannel fluorescent images. The detection of synapses, visualized by fluorescence labeling, is one major challenge in the analysis of these datasets, due to variations in synapse shape, size, and fluorescence intensity across the images. For their detection, most labs use manual or semi-manual techniques that are time-consuming and error-prone. We developed SynEdgeWs, a MATLAB-based segmentation algorithm that combines the application of an edge filter, morphological operators, and marker-controlled watershed segmentation. SynEdgeWs does not need training data and works with low user intervention. It was superior to methods based on cutoff thresholds and local maximum guided approaches in a realistic set of data. We implemented SynEdgeWs in two automatized routines that allow accurate, direct, and unbiased identification of fluorescently labeled synaptic puncta and their consecutive analysis. SynEval routine enables the analysis of three-channel images, and ImgSegRout routine processes image stacks. We tested the feasibility of ImgSegRout on a realistic live-cell imaging data set from experiments designed to monitor neurotransmitter release using synaptic phluorins. Finally, we applied SynEval to compare synaptic vesicle recycling evoked by electrical field stimulation and chemical depolarization in dissociated cortical cultures. Our data indicate that while the proportion of active synapses does not differ between stimulation modes, significantly more vesicles are mobilized upon chemical depolarization.

Phenotypic Traits Extraction and Genetic Characteristics Assessment of Eucalyptus Trials Based on UAV-Borne LiDAR and RGB Images

Phenotype describes the physical, physiological and biochemical characteristics of organisms that are determined or influenced by genes and environment. Accurate extraction of phenotypic data is a prerequisite for comprehensive forest phenotyping in order to improve the growth and development of forest plantations. Combined with the assessments of genetic characteristics, forest phenotyping will help to accelerate the breeding process, improve stress resistance and enhance the quality of the planted forest. In this study, we disposed our study in Eucalyptus trials within the Gaofeng forest farm (a typical Eucalyptus plantation site in southern China) for a high-throughput phenotypic traits extraction and genetic characteristics analysis based on high-density point clouds (acquired by a UAV-borne LiDAR sensor) and high-resolution RGB images (acquired by a UAV-borne camera), aiming at developing a high-resolution and high-throughput UAV-based phenotyping approach for tree breeding. First, we compared the effect of CHM-based Marker-Controlled Watershed Segmentation (MWS) and Point Cloud-based Cluster Segmentation (PCS) for extracting individual trees; Then, the phenotypic traits (i.e., tree height, diameter at breast height, crown width), the structural metrics (n = 19) and spectral indices (n = 9) of individual trees were extracted and assessed; Finally, a genetic characteristics analysis was carried out based on the above results, and we compared the differences between high-throughput phenotyping by UAV-based data and on manual measurements. Results showed that: in the relatively low stem density site of the trial (760 n/ha), the overall accuracy of MWS and PCS was similar, while in the higher stem density sites (982 n/ha, 1239 n/ha), the overall accuracy of MWS (F(2) = 0.93, F(3) = 0.86) was higher than PCS (F(2) = 0.84, F(3) = 0.74); With the increase of stem density, the difference between the overall accuracy of MWS and PCS gradually expanded. Both UAV–LiDAR extracted phenotypic traits and manual measurements were significantly different across the Eucalyptus clones (P < 0.05), as were most of the structural metrics (47/57) and spectral indices (26/27), revealing the genetic divergence between the clones. The rank of clones demonstrated that the pure clones (of E. urophylla), the hybrid clones (of E. urophylla as the female parent) and the hybrid clones (of E. wetarensis and E. grandis) have a higher fineness of growth. This study proved that UAV-based fine-resolution remote sensing could be an efficient, accurate and precise technology in phenotyping (used in genetic analysis) for tree breeding.

Comparison of Classical Methods and Mask R-CNN for Automatic Tree Detection and Mapping Using UAV Imagery

Detecting and mapping individual trees accurately and automatically from remote sensing images is of great significance for precision forest management. Many algorithms, including classical methods and deep learning techniques, have been developed and applied for tree crown detection from remote sensing images. However, few studies have evaluated the accuracy of different individual tree detection (ITD) algorithms and their data and processing requirements. This study explored the accuracy of ITD using local maxima (LM) algorithm, marker-controlled watershed segmentation (MCWS), and Mask Region-based Convolutional Neural Networks (Mask R-CNN) in a young plantation forest with different test images. Manually delineated tree crowns from UAV imagery were used for accuracy assessment of the three methods, followed by an evaluation of the data processing and application requirements for three methods to detect individual trees. Overall, Mask R-CNN can best use the information in multi-band input images for detecting individual trees. The results showed that the Mask R-CNN model with the multi-band combination produced higher accuracy than the model with a single-band image, and the RGB band combination achieved the highest accuracy for ITD (F1 score = 94.68%). Moreover, the Mask R-CNN models with multi-band images are capable of providing higher accuracies for ITD than the LM and MCWS algorithms. The LM algorithm and MCWS algorithm also achieved promising accuracies for ITD when the canopy height model (CHM) was used as the test image (F1 score = 87.86% for LM algorithm, F1 score = 85.92% for MCWS algorithm). The LM and MCWS algorithms are easy to use and lower computer computational requirements, but they are unable to identify tree species and are limited by algorithm parameters, which need to be adjusted for each classification. It is highlighted that the application of deep learning with its end-to-end-learning approach is very efficient and capable of deriving the information from multi-layer images, but an additional training set is needed for model training, robust computer resources are required, and a large number of accurate training samples are necessary. This study provides valuable information for forestry practitioners to select an optimal approach for detecting individual trees.

A Hierarchical Region-Merging Algorithm for 3-D Segmentation of Individual Trees Using UAV-LiDAR Point Clouds

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