Individual Tree Crowns Research Articles

Individual Tree Crown Segmentation and Crown Width Extraction From a Heightmap Derived From Aerial Laser Scanning Data Using a Deep Learning Framework.

Deriving individual tree crown (ITC) information from light detection and ranging (LiDAR) data is of great significance to forest resource assessment and smart management. After proof-of-concept studies, advanced deep learning methods have been shown to have high efficiency and accuracy in remote sensing data analysis and geoscience problem solving. This study proposes a novel concept for synergetic use of the YOLO-v4 deep learning network based on heightmaps directly generated from airborne LiDAR data for ITC segmentation and a computer graphics algorithm for refinement of the segmentation results involving overlapping tree crowns. This concept overcomes the limitations experienced by existing ITC segmentation methods that use aerial photographs to obtain texture and crown appearance information and commonly encounter interference due to heterogeneous solar illumination intensities or interlacing branches and leaves. Three generative adversarial networks (WGAN, CycleGAN, and SinGAN) were employed to generate synthetic images. These images were coupled with manually labeled training samples to train the network. Three forest plots, namely, a tree nursery, forest landscape and mixed tree plantation, were used to verify the effectiveness of our approach. The results showed that the overall recall of our method for detecting ITCs in the three forest plot types reached 83.6%, with an overall precision of 81.4%. Compared with reference field measurement data, the coefficient of determination R2 was ≥ 79.93% for tree crown width estimation, and the accuracy of our deep learning method was not influenced by the values of key parameters, yielding 3.9% greater accuracy than the traditional watershed method. The results demonstrate an enhancement of tree crown segmentation in the form of a heightmap for different forest plot types using the concept of deep learning, and our method bypasses the visual complications arising from aerial images featuring diverse textures and unordered scanned points with irregular geometrical properties.

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.

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.

Assessing vegetation traits estimates accuracies from the future SBG and biodiversity hyperspectral missions over two Mediterranean Forests

ABSTRACT The estimation and mapping of vegetation traits from satellite hyperspectral imagery is entering a new era, as multiple missions have recently started and more are currently in preparatory phase. With expected ground sampling distances (GSD) ranging from 8 to 30 m, these missions could complement each other, especially over spatially heterogeneous environments where the canopy cover (CC) is low. This study focused on the retrieval of five vegetation traits (gap fraction, leaf chlorophylls (C) and carotenoids (Car) contents, equivalent water thickness, and leaf mass per area) of two Mediterranean-climate forests from AVIRIS-Classic (AVIRIS-C), synthetic Biodiversity, and synthetic Surface Biology and Geology (SBG) missions with 18 m, 8 m, and 30 m GSD, respectively, using a hybrid method. The synthetic SBG images were provided by NASA, while the Biodiversity images were generated from airborne AVIRIS-Next Generation hyperspectral imagery. Partial least-square regressors were trained over the outputs of the DART model to estimates vegetation traits. Estimated accuracies were assessed, when possible, by comparison with in situ measurements. We showed that estimated accuracy of gap fraction was similar between AVIRIS-C and SBG (RMSE of 0.09, R of 0.8 and RMSE of 0.07, R of 0.59, respectively). Leaf traits estimated accuracies were also similar between these two sensors, but only acceptable for C and Car ( 7.5 μg.cm RMSE for C, 1.65 μg.cm RMSE for Car), especially over the densest parts of the canopy. When comparing estimates obtained from Biodiversity and SBG imagery, it appeared that the denser the canopy, the more estimates from both sensors were in agreement for all leaf traits (for instance, C, R was 0.2 for 30% CC 50% and 0.48 for CC 80%). The results show that (i) SBG imagery should lead to estimated accuracies similar to AVIRIS-C, with acceptable performances over dense canopies, and that (ii) Biodiversity imagery has a high potential to map vegetation traits over any canopy no matter its sparsity, as individual tree crowns are mostly resolved at an 8 m GSD.

Spectral invariants in ultra-high spatial resolution hyperspectral images

Current operational optical satellite-based Earth observation methods targeting at vegetation are optimised for the high- and medium-resolution satellites with pixels sizes starting at ten meters. This resolution is coarser than the typical size of a vegetation structural element, such as a tree crown, and much coarser that of scattering elements, such as leaves. For this reason, vegetation can be treated as a continuous medium and the variation in the local illumination conditions on individual leaves or tree crowns can be ignored. This does not hold anymore for very and ultra-high resolution imagery, obtained from new satellite systems or unmanned aerial vehicles, where individual tree crowns or even leaves can be discerned. We tested the applicability of the spectral invariant theory to this type of imagery for characterising the local illumination conditions on plant leaves using Monte Carlo ray tracing simulations. The simulations corroborated the direct link between the spectral invariant parameter ρ and the sunlit fraction of visible leaves, earlier alleged for hyperspectral remote sensing data based on mathematical considerations. The approach allowed us to separate the direct beam and multiple scattering irradiance components and provided intuitive interpretations of the recollision probability and canopy scattering coefficient computed for each image pixel.

Predicting Tree Mortality Using Spectral Indices Derived from Multispectral UAV Imagery

Past research has shown that remotely sensed spectral information can be used to predict tree health and vitality. Recent developments in unmanned aerial vehicles (UAVs) have now made it possible to derive such information at the tree and stand scale from high-resolution imagery. We used visible and multispectral bands from UAV imagery to calculate a set of spectral indices for 52,845 individual tree crowns within 38 forest stands in western Canada. We then used those indices to predict the mortality of these canopy trees over the following year. We evaluated whether including multispectral indices leads to more accurate predictions than indices derived from visible wavelengths alone and how the performance varies among three different tree species (Picea glauca, Pinus contorta, Populus tremuloides). Our results show that spectral information can be effectively used to predict tree mortality, with a random forest model producing a mean area under the receiver operating characteristic curve (AUC) of 89.8% and a balanced accuracy of 83.3%. The exclusion of multispectral indices worsened the model performance, but only slightly (AUC = 87.9%, balanced accuracy = 81.8%). We found variation in model performance among species, with higher accuracy for the broadleaf species (balanced accuracy = 85.2%) than the two conifer species (balanced accuracy = 73.3% and 77.8%). However, all models overpredicted tree mortality by a major degree, which limits the use for tree mortality predictions on an individual level. Further improvements such as long-term monitoring, the use of hyperspectral data and cost-sensitive learning algorithms, and training the model with a larger and more balanced data set are necessary. Nevertheless, our results demonstrate that imagery from UAVs has strong potential for predicting annual mortality for individual canopy trees.

Detection of heartwood rot in Norway spruce trees with lidar and multi-temporal satellite data

Norway spruce pathogenic fungi causing root, butt and stem rot represent a substantial problem for the forest sector in many countries. Early detection of rot presence is important for efficient management of the forest resources but due to its nature, which does not generate evident exterior signs, it is very difficult to detect without invasive measurements. Remote sensing has been widely used to monitor forest health status in relation to many pathogens and infestations. In particular, multi-temporal remotely sensed data have shown to be useful in detecting degenerative diseases. In this study, we explored the possibility of using multi-temporal and multi-spectral satellite data to detect rot presence in Norway spruce trees in Norway. Images with four bands were acquired by the Dove satellite constellation with a spatial resolution of 3 m, ranging over three years from June 2017 to September 2019. Field data were collected in 2019–2020 by a harvester during the logging: 16163 trees were recorded, classified in terms of species and presence of rot at the stump and automatically geo-located. The analysis was carried out at individual tree crown (ITC) level, and ITCs were delineated using lidar data. ITCs were classified as healthy, infested and other species using a weighted Support Vector Machine. The results showed an underestimation of the rot presence (balanced accuracy of 56.3%, producer’s accuracies of 64.3 and 48.4% and user’s accuracies of 81.0% and 32.7% respectively for healthy and rot ITCs). The method can be used to provide a tentative map of the rot presence to guide more detailed assessments in field and harvesting activities.

Combining Spectral, Spatial-Contextual, and Structural Information in Multispectral UAV Data for Spruce Crown Delineation

Precise delineation of individual tree crowns is critical for accurate forest biophysical parameter estimation, species classification, and ecosystem modelling. Multispectral optical remote sensors mounted on low-flying unmanned aerial vehicles (UAVs) can rapidly collect very-high-resolution (VHR) photogrammetric optical data that contain the spectral, spatial, and structural information of trees. State-of-the-art tree crown delineation approaches rely mostly on spectral information and underexploit the spatial-contextual and structural information in VHR photogrammetric multispectral data, resulting in crown delineation errors. Here, we propose the spectral, spatial-contextual, and structural information-based individual tree crown delineation (S3-ITD) method, which accurately delineates individual spruce crowns by minimizing the undesirable effects due to intracrown spectral variance and nonuniform illumination/shadowing in VHR multispectral data. We evaluate the performance of the S3-ITD crown delineation method over a white spruce forest in Quebec, Canada. The highest mean intersection over union (IoU) index of 0.83, and the lowest mean crown-area difference (CAD) of 0.14 m2, proves the superior crown delineation performance of the S3-ITD method over state-of-the-art methods. The reduction in error by 2.4 cm and 1.0 cm for the allometrically derived diameter at breast height (DBH) estimates compared with those from the WS-ITD and the BF-ITD approaches, respectively, demonstrates the effectiveness of the S3-ITD method to accurately estimate biophysical parameters.

Riparian ecosystems mapping at fine scale: a density approach based on multi‐temporal UAV photogrammetric point clouds

AbstractIn recent years, numerous directives worldwide have addressed the conservation and restoration of riparian corridors, activities that rely on continuous vegetation mapping to understand its volumetric features and health status. Mapping riparian corridors requires not only fine‐scale resolution but also the coverage of relatively large areas. The use of Unmanned Aerial Vehicles (UAV) allows for meeting both conditions, although the cost‐effectiveness of their use is highly influenced by the type of sensor mounted on them. Few works have so far investigated the use of photogrammetric sensors for individual tree crown detection, despite being cheaper than the most common Light Detection and Ranging (LiDAR) ones. This work aims to improve the individual crown detection from UAV‐photogrammetric datasets in a twofold way. Firstly, the effectiveness of a new approach that has already achieved interesting results in LiDAR applications was tested for photogrammetric point clouds. The test was carried out by comparing the accuracy achieved by the new approach, which is based on the point density features of the analysed dataset, with those related to the more common local maxima and textural methods. The results indicated the potentiality of the density‐based method, which achieved accuracy values (0.76 F‐score) consistent with the traditional methods (0.49–0.80 F‐score range) but was less affected by under‐ and over‐fitting. Secondly, the potential improvement of working on intra‐annual multi‐temporal datasets was assessed by applying the density‐based approach to seven different scenarios, three of which were constituted by single‐epoch datasets and the remaining given by the joining of the others. The F‐score increased from 0.67 to 0.76 when passing from single‐ to multi‐epoch datasets, aligning with the accuracy achieved by the new method when applied to LiDAR data. The results demonstrate the potential of multi‐temporal acquisitions when performing individual crown detection from photogrammetric data.

Wood Decay Detection in Norway Spruce Forests Based on Airborne Hyperspectral and ALS Data

Wood decay caused by pathogenic fungi in Norway spruce forests causes severe economic losses in the forestry sector, and currently no efficient methods exist to detect infected trees. The detection of wood decay could potentially lead to improvements in forest management and could help in reducing economic losses. In this study, airborne hyperspectral data were used to detect the presence of wood decay in the trees in two forest areas located in Etnedal (dataset I) and Gran (dataset II) municipalities, in southern Norway. The hyperspectral data used consisted of images acquired by two sensors operating in the VNIR and SWIR parts of the spectrum. Corresponding ground reference data were collected in Etnedal using a cut-to-length harvester while in Gran, field measurements were collected manually. Airborne laser scanning (ALS) data were used to detect the individual tree crowns (ITCs) in both sites. Different approaches to deal with pixels inside each ITC were considered: in particular, pixels were either aggregated to a unique value per ITC (i.e., mean, weighted mean, median, centermost pixel) or analyzed in an unaggregated way. Multiple classification methods were explored to predict rot presence: logistic regression, feed forward neural networks, and convolutional neural networks. The results showed that wood decay could be detected, even if with accuracy varying among the two datasets. The best results on the Etnedal dataset were obtained using a convolution neural network with the first five components of a principal component analysis as input (OA = 65.5%), while on the Gran dataset, the best result was obtained using LASSO with logistic regression and data aggregated using the weighted mean (OA = 61.4%). In general, the differences among aggregated and unaggregated data were small.

Evaluation of UAS LiDAR data for tree segmentation and diameter estimation in boreal forests using trunk- and crown-based methods

Very high point density laser scanning data from unmanned aerial systems (UAS) can be used to segment the trunks of individual trees. Such segmentation (e.g., individual trunk segmentation (ITS)) is useful, for example, in the estimation of diameter at breast height (DBH), which in turn is needed for the estimation of other tree and stand attributes, such as stem volume and diameter of the basal area median tree (DGM). In this paper, we assess the estimation of DBH directly from UAS LiDAR data in open and closed canopy conditions that represent the range of operational conditions encountered in boreal forests in Finland. We also compare trunk-based DBH estimates to corresponding estimates from individual tree crown segmentation (ITC) and fuse the results from the trunk- and crown-based estimates. The results showed that trunk segmentation performed slightly better than ITC in open canopy areas, whereas ITC performed better in closed canopy areas. The DBH prediction error was smaller for ITS (3.0 cm) than ITC (3.9 cm) when considering the trees that were recognized by both methods. We also conclude that a hybrid method, where both segmented tree trunks and tree crowns are fused, considerably increases the number of correctly segmented trees but does not decrease the prediction error associated with DGM compared to using either ITC or ITS individually.

Vision based crown loss estimation for individual trees with remote aerial robots

With the capability of capturing high-resolution imagery data and the ease of accessing remote areas, aerial robots are becoming increasingly popular for forest health monitoring applications. For example, forestry tasks such as field surveys and foliar sampling which are generally manual and labour intensive can be automated with remotely controlled aerial robots. In this study, we propose two new online frameworks to quantify and rank the severity of individual tree crown loss. The real-time crown loss estimation (RTCLE) model localises and classifies individual trees into their respective crown loss percentage bins. Experiments are conducted to investigate if synthetically generated tree images can be used to train the RTCLE model as real images with diverse viewpoints are generally expensive to collect. Results have shown that synthetic data training helps to achieve a satisfactory baseline mean average precision (mAP) which can be further improved with just some additional real imagery data. We showed that the mAP can be increased approximately from 60% to 78% by mixing the real dataset with the generated synthetic data. For individual tree crown loss ranking, a two-step crown loss ranking (TSCLR) framework is developed to handle the inconsistently labelled crown loss data. The TSCLR framework detects individual trees before ranking them based on some relative crown loss severity measures. The tree detection model is trained with the combined dataset used in the RTCLE model training where we achieved an mAP of approximately 95% suggesting that the model generalises well to unseen datasets. The relative crown loss severity of each tree is estimated, with deep representation learning, by a probabilistic encoder from a fully trained variational autoencoder (VAE) model. The VAE is trained end-to-end to reconstruct tree images in a background agnostic way. Based on a conservative evaluation, the estimated crown loss severity from the probabilistic encoder generally showed moderate agreement with the expert’s estimation across all species of trees present in the dataset. All the software pipelines, the dataset, and the synthetic dataset generation can be found in the GitHub link.

Upscaling aboveground biomass of larch (Larix olgensis Henry) plantations from field to satellite measurements: a comparison of individual tree-based and area-based approaches

ABSTRACT Currently, aboveground biomass (AGB) estimation primarily relies on an area-based approach (ABA), particularly at a large scale. With the advancement of individual tree detection techniques and the availability of multi-platform remotely sensed data, the individual tree-based approach (ITA) provides the potential of accurate and nondestructive fine AGB mapping. However, the performances of the two approaches on upscaling AGB from individual tree to stand level have not been thoroughly investigated. This study conducted the nondestructive AGB estimation using both ITA and ABA and compared the AGB estimates and their spatial uncertainties from an individual tree- to stand-level based on multi-platform LiDAR and Landsat 8 OLI imagery, taking Larix olgensis that is one of the most notable afforestation tree species in northeastern China as an example. Results showed that the point cloud segmentation (PCS) outperformed CHM-based individual tree crown delineation algorithms and obtained the highest accuracy of individual tree AGB estimate (R2 = 0.97, RMSE = 28.58 kg, rRMSE = 21.13%) for the dense larch plantations (about 1265 trees/ha). The plot-level AGB estimate aggregated by all detected trees and its uncertainty based on Monte Carlo simulation were 158.16 and 3.64 Mg·ha−1, respectively. The average pixel-level AGB of larch plantations in Maorshan Forest Farm estimated by ITA and ABA were similar (129.66 v.s 144.38 Mg·ha−1). ITA outperformed ABA in terms of pixel-level AGB accuracy and spatial uncertainty of pixel-level and stand-level AGB estimates. The overestimation of low AGB values, typical in ABA, was effectively eliminated by the ITA. The upscaling frameworks proposed in this study for AGB estimation and spatial uncertainty quantification based on ITA and ABA could be extended to other plantations or uncomplex forests. This study contributes to the accurate quantification of AGB and understanding of the uncertainties in the carbon stock of forest ecosystems at multi-scales.

Dominant Tree Species Classification using Remote Sensing Data and Object -Based Image Analysis

Abstract Over the last few decades, forests have been the victims of over logging and deforestation. Uncontrolled of this activity gave an impact to the tree species to be endangered. A detailed inventory of tree species is needed to manage and plan the forest on a sustainable basis. Many techniques had been done to identify the tree species, but in the recent three decades, remote sensing technique was widely used to study the distribution of tree species. In this study, an object-based image analysis (OBIA) with a combination of high-resolution multispectral satellite imagery (WV-2) and airborne laser scanning (LiDAR) data was tested for classification of individual tree crowns of tropical tree species at Forest Research Institute Malaysia (FRIM) forest, Selangor. LiDAR data was taken using fixed-wing aircraft with Gemini Airborne Laser Terrain Mapper (ALTM) laser with 0.15m and 0.25 resolution for horizontal and vertical. WV-2 was captured with a 0.5m spatial resolution. In this study, hyperspectral data captured using Bayspec sensor mount at UAV with height 220m from the ground and have 0.3 resolution was used to extract the spectral reflectance of tree species. Segmentation of the image was performed using multi-resolution segmentation in eCognition software. Accuracy assessment for segmentation was done by measure the ‘goodness fit’ (D value) between training object and output segmentation. The overall accuracy of the segmentation was 86%. For species classification, the accuracy assessment was performed using the error matrix confusion technique to 7 classes of tree species. The result had shown the overall accuracy classification was 64%.

The Use of Machine Learning Algorithms in Urban Tree Species Classification

Trees are the key components of urban vegetation in cities. The timely and accurate identification of existing urban tree species with their location is the most important task for improving air, water, and land quality; reducing carbon accumulation; mitigating urban heat island effects; and protecting soil and water balance. Light detection and ranging (LiDAR) is frequently used for extracting high-resolution structural information regarding tree objects. LiDAR systems are a cost-effective alternative to the traditional ways of identifying tree species, such as field surveys and aerial photograph interpretation. The aim of this work was to assess the usage of machine learning algorithms for classifying the deciduous (broadleaf) and coniferous tree species from 3D raw LiDAR data on the Davutpasa Campus of Yildiz Technical University, Istanbul, Turkey. First, ground, building, and low, medium, and high vegetation classes were acquired from raw LiDAR data using a hierarchical-rule-based classification method. Next, individual tree crowns were segmented using a mean shift clustering algorithm from high vegetation points. A total of 25 spatial- and intensity-based features were utilized for support vector machine (SVM), random forest (RF), and multi-layer perceptron (MLP) classifiers to discriminate deciduous and coniferous tree species in the urban area. The machine learning-based classification’s overall accuracies were 80%, 83.75%, and 73.75% for the SVM, RF, and MLP classifiers, respectively, in split 70/30 (training/testing). The SVM and RF algorithms generally gave better classification results than the MLP algorithm for identifying the urban tree species.

Linking Drone and Ground-Based Liana Measurements in a Congolese Forest

Lianas are abundant and diverse in tropical forests and impact forest dynamics. They occupy part of the canopy, forming a layer of leaves overtopping tree crowns. Yet, their interaction with trees has been mainly studied from the ground. With the emergence of drone-based sensing, very high-resolution data may be obtained on liana distribution above canopies. Here, we assessed the relationship between common liana ground measurements and drone-determined liana leaf coverage over tree crowns, tested if this relationship is mediated by liana functional composition, and compared the signature of liana patches and tree crowns in our drone images. Using drone platforms, we acquired very high resolution RGB and multispectral images and LiDAR data over two 9-ha permanent plots located in northern Republic of Congo and delineated liana leaf coverage and individual tree crowns from these data. During a concomitant ground survey, we focused on 275 trees infested or not by lianas, for which we measured all lianas ≥ 1 cm in diameter climbing on them (n= 615) and estimated their crown occupancy index (COI). We additionally measured or recorded the wood density and climbing mechanisms of most liana taxa. Contrary to recent findings, we found significant relationships between most ground-derived metrics and the top-of-view liana leaf coverage over tree crowns. Tree crown infestation by lianas was primarily explained by the load of liana climbing on them, and negatively impacted by tree height. Liana leaf coverage over individual tree crowns was best predicted by liana basal area and negatively mediated by liana wood density, with a higher leaf area to diameter ratio for light-wooded lianas. COI scores were concordant with drone assessments, but two thirds differed from those obtained from drone measurements. Finally, liana patches had a higher light reflectance and variance of spectral responses than tree crowns in all studied spectra. However, the large overlap between them challenges the autodetection of liana patches in canopies. Overall, we illustrate that the joint use of ground and drone-based data deepen our understanding of liana-infestation pathways and of their functional and spectral diversity. We expect drone data to soon transform the field of liana ecology.

Individual Tree Crown Delineation Method Based on Multi-Criteria Graph Using Geometric and Spectral Information: Application to Several Temperate Forest Sites

Individual tree crown (ITC) delineation in temperate forests is challenging owing to the presence of broadleaved species with overlapping crowns. Mixed coniferous/deciduous forests with characteristics that differ with the type of tree thus require a flexible method of delineation. The ITC delineation method based on the multi-criteria graph (MCG-Tree) addresses this problem in temperate monospecific or mixed forests by combining geometric and spectral information. The method was used to segment trees in three temperate forest sites with different characteristics (tree types, species distribution, planted or natural forest). Compared with a state-of-the-art watershed segmentation approach, our method increased delineation performance by up to 25%. Our results showed that the main geometric criterion to improve delineation quality is related to the crown radius (performance improvement around 8%). Coniferous/deciduous classification automatically adapts the MCG-Tree criteria to the type of tree. Promising results are then obtained to improve delineation performance for mixed forests.

Multi-Species Individual Tree Segmentation and Identification Based on Improved Mask R-CNN and UAV Imagery in Mixed Forests

High-resolution UAV imagery paired with a convolutional neural network approach offers significant advantages in accurately measuring forestry ecosystems. Despite numerous studies existing for individual tree crown delineation, species classification, and quantity detection, the comprehensive situation in performing the above tasks simultaneously has rarely been explored, especially in mixed forests. In this study, we propose a new method for individual tree segmentation and identification based on the improved Mask R-CNN. For the optimized network, the fusion type in the feature pyramid network is modified from down-top to top-down to shorten the feature acquisition path among the different levels. Meanwhile, a boundary-weighted loss module is introduced to the cross-entropy loss function Lmask to refine the target loss. All geometric parameters (contour, the center of gravity and area) associated with canopies ultimately are extracted from the mask by a boundary segmentation algorithm. The results showed that F1-score and mAP for coniferous species were higher than 90%, and that of broadleaf species were located between 75–85.44%. The producer’s accuracy of coniferous forests was distributed between 0.8–0.95 and that of broadleaf ranged in 0.87–0.93; user’s accuracy of coniferous was distributed between 0.81–0.84 and that of broadleaf ranged in 0.71–0.76. The total number of trees predicted was 50,041 for the entire study area, with an overall error of 5.11%. The method under study is compared with other networks including U-net and YOLOv3. Results in this study show that the improved Mask R-CNN has more advantages in broadleaf canopy segmentation and number detection.

Effect of varied unmanned aerial vehicle laser scanning pulse density on accurately quantifying forest structure

ABSTRACT Airborne laser scanning (ALS) is increasingly used to estimate various forest characteristics. Technological improvements in unmanned aerial vehicles (UAVs) and drone laser scanning (DLS) sensors have permitted the acquisition of high pulse density datasets. There is an assumption that higher pulse densities yield greater accuracies in estimating forest characteristics. In this study, we investigated the effect of pulse density (.25, .5, 1, 5, 10, 50, 100 and 300 pulses m−2) on the ability to delineate individual tree crowns (ITCs) and estimate ITC height and crown horizontal diameter, in addition to plot-level leaf area index (LAI). The current study took place in an experimentally varied Pinus taeda L. forest, which included three stem densities: (i) 618; (ii) 1236; and (iii) 1853 trees per hectare (TPH). ITCs were classified directly from the DLS point cloud for each of the pulse densities. The correct delineation of ITCs relative to field tree-coordinates was relatively consistent (±5%) for pulse densities of 5 to 300 pulses m−2. ITC delineation accuracy decreased with lower pulse densities. Planting stem density did impact ITC delineation accuracy. Higher pulse densities, plots with 618 TPH correctly classified ~88% of ITCs, and plots with the 1853 TPH correctly classified ~50% of ITCs. Estimates of tree height were largely unaffected by changes in tree density. Root mean square error (RMSE) for tree height varied from .5 to 2.5 m at pulse densities of 300 to .25 pulses m−2, respectively. Estimates of crown horizontal diameter varied with regard to both pulse and stem density from 1.2 (300 ppm−2 and 1853 TPH) to 4.2 m (.25 ppm−2 and 618 TPH). RMSE varied among stem densities from .6 to 1.2 m as pulse density decreased. There was significant difference in ITC delineation accuracy, particularly when considering stem density, and the estimates of tree height and crown horizontal diameter among the DLS pulse densities used. The accuracy of predicted LAI was largely unaffected by changes in pulse density, when pulse density was above .5 pulses m−2. There was little or no difference in estimates of LAI at these pulse densities. Our results suggest that low-density DLS data may be capable of estimating plot-level forest metrics reliably in some situations, however once the analysis scale is reduced to the individual-tree-level, the influence of pulse density is more substantial. The results here provide guidance to forest managers who must balance metric estimation accuracy and price when planning new ALS or DLS acquisitions.

Towards low vegetation identification: A new method for tree crown segmentation from LiDAR data based on a symmetrical structure detection algorithm (SSD)

Obtaining low vegetation data is important in order to quantify the structural characteristics of a forest. Dense three-dimensional (3D) laser scanning data can provide information on the vertical profile of a forest. However, most studies have focused on the dominant and subdominant layers of the forest, while few studies have tried to delineate the low vegetation. To address this issue, we propose a framework for individual tree crown (ITC) segmentation from laser data that focuses on both overstory and understory trees. The framework includes 1) a new algorithm (SSD) for 3D ITC segmentation of dominant trees, by detecting the symmetrical structure of the trees, and 2) removing points of dominant trees and mean shift clustering of the low vegetation. The framework was tested on a boreal forest in Sweden and the performance was compared 1) between plots with different stem density levels, vertical complexities, and tree species composition, and 2) using airborne laser scanning (ALS) data, terrestrial laser scanning (TLS) data, and merged ALS and TLS data (ALS + TLS data). The proposed framework achieved detection rates of 0.87 (ALS + TLS), 0.86 (TLS), and 0.76 (ALS) when validated with field-inventory data (of trees with a diameter at breast height ≥ 4 cm). When validating the estimated number of understory trees by visual interpretation, the framework achieved 19%, 21%, and 39% root-mean-square error values with ALS + TLS, TLS, and ALS data, respectively. These results show that the SSD algorithm can successfully separate laser points of overstory and understory trees, ensuring the detection and segmentation of low vegetation in forest. The proposed framework can be used with both ALS and TLS data, and achieve ITC segmentation for forests with various structural attributes. The results also illustrate the potential of using ALS data to delineate low vegetation.