Individual Tree Segmentation and Tree Height Estimation Using Leaf-Off and Leaf-On UAV-LiDAR Data in Dense Deciduous Forests

Abstract

Accurate individual tree segmentation (ITS) is fundamental to forest management and to the studies of forest ecosystem. Unmanned Aerial Vehicle Light Detection and Ranging (UAV-LiDAR) shows advantages for ITS and tree height estimation at stand and landscape scale. However, dense deciduous forests with tightly interlocked tree crowns challenge the performance for ITS. Available LiDAR points through tree crown and appropriate algorithm are expected to attack the problem. In this study, a new UAV-LiDAR dataset that fused leaf-off and leaf-on point cloud (FULD) was introduced to assess the synergetic benefits for ITS and tree height estimation by comparing different types of segmentation algorithms (i.e., watershed segmentation, point cloud segmentation and layer stacking segmentation) in the dense deciduous forests of Northeast China. Field validation was conducted in the four typical stands, including mixed broadleaved forest (MBF), Mongolian oak forest (MOF), mixed broadleaf-conifer forest (MBCF) and larch plantation forest (LPF). The results showed that the combination of FULD and the layer stacking segmentation (LSS) algorithm produced the highest accuracies across all forest types (F-score: 0.70 to 0.85). The FULD also showed a better performance on tree height estimation, with a root mean square error (RMSE) of 1.54 m at individual level. Compared with using the leaf-on dataset solely, the RMSE of tree height estimation was reduced by 0.22 to 0.27 m, and 12.3% more trees were correctly segmented by the FULD, which are mainly contributed by improved detection rate at nearly all DBH levels and by improved detection accuracy at low DBH levels. The improvements are attributed to abundant points from the bole to the treetop of FULD, as well as each layer point being included for segmentation by LSS algorithm. These findings provide useful insights to guide the application of FULD when more multi-temporal LiDAR data are available in future.

Will “Tall Oaks from Little Acorns Grow”? White Oak (Quercus alba) Biology in the Anthropocene

“…The capabilities of these sensors and accompanying analyses characterize many aspects of tree physiology and above-ground anatomy. Individual tree segmentation and species identification are possible from both drone-based imagery and drone-based Light Detection and Ranging (LiDAR) [317][318][319]. Near-infrared (NIR), wide-infrared, and RGB sensors can be used to effectively measure tree water stress via various indices, such as the Normalized Difference Vegetation Index (NDVI) [320,321].…”

Experience of using the DeepForest neural network to detect trees in a broad-leaved forest

“…Portnov A.M. 1 , Ivanova N.V. 1,2 , Shashkov M.P. Полученные результаты также сравнивали с результатами для широколиственных лесов в Провинции Ляонин (Китай) [1].…”

“…Portnov A.M. 1 , Ivanova N.V. 1,2 , Shashkov M.P. Полученные результаты также сравнивали с результатами для широколиственных лесов в Провинции Ляонин (Китай) [1]. Эта работа выполнена на основе анализа разносезонных плотных облаков точек LiDAR и цифровых моделей высот древесного полога.…”

“…Эта работа выполнена на основе анализа разносезонных плотных облаков точек LiDAR и цифровых моделей высот древесного полога. Мы можем заключить, что в нашем исследовании на летнем ортофотоплане DeepForest показал точностью большую, чем использованные в [1] алгоритмы Watershed и PCS, которые показали F 0.66 ± 0.01 для всех наборов данных (лиственного, безлистного, смешанного). В то же время, результаты анализа композитного набора данных, составленного из разновременных съемок при помощи алгоритма LSS (сегментации стекирования слоёв) показал F 0.74 ± 0.01, что значительно превосходит результат DeepForest.…”

Tree Stem Detection and Crown Delineation in a Structurally Diverse Deciduous Forest Combining Leaf-On and Leaf-Off UAV-SfM Data

“…Nonetheless, the use of MLS is impractical for large areas, and its cost-intensive equipment makes it inaccessible to many users. Although LiDAR tools mounted on unoccupied aerial vehicles (UAV) can overcome some of the spatial limitations of MLS and generate high-density forest point clouds [8,9], their accessibility within the forestry sector is still limited due to cost constraints.…”