Estimating Individual Tree Above-Ground Biomass of Chinese Fir Plantation: Exploring the Combination of Multi-Dimensional Features from UAV Oblique Photos

Abstract

Chinese fir (Cunninghamia lanceolata (Lamb.) Hook) is one of the important tree species in plantation in southern China. Rapid and accurate acquisition of individual tree above-ground biomass (IT-AGB) information is of vital importance for precise monitoring and scientific management of Chinese fir forest resources. Unmanned Aerial Vehicle (UAV) oblique photogrammetry technology can simultaneously obtain high-density point cloud data and high spatial resolution spectral information, which has been a main remote sensing source for obtaining forest fine three-dimensional structure information and provided possibility for estimating IT-AGB. In this study, we proposed a novel approach to estimate IT-AGB by introducing the color space intensity information into a regression-based model that incorporates three-dimensional point cloud and two-dimensional spectrum feature variables, and the accuracy was evaluated using a leave-one-out cross-validation approach. The results demonstrated that the intensity variables derived from the color space were strongly correlated with the IT-AGB and obviously improved the estimation accuracy. The model constructed by the combination of point cloud variables, vegetation index and RGB spatial intensity variables had high accuracy (R2 = 0.79; RMSECV = 44.77 kg; and rRMSECV = 0.25). Comparing the performance of estimating IT-AGB models with different spatial resolution images (0.05, 0.1, 0.2, 0.5 and 1 m), the model was the best at the spatial resolution of 0.2 m, which was significantly better than that of the other four. Moreover, we also divided the individual tree canopy into four directions (East, West, South and North) to develop estimation models respectively. The result showed that the IT-AGB estimation capacity varied significantly in different directions, and the West-model had better performance, with the estimation accuracy of 67%. This study indicates the potential of using oblique photogrammetry technology to estimate AGB at an individual tree scale, which can support carbon stock estimation as well as precision forestry application.

ACE R-CNN: An Attention Complementary and Edge Detection-Based Instance Segmentation Algorithm for Individual Tree Species Identification Using UAV RGB Images and LiDAR Data

“…R is the individual tree identification rate, which is the rati ber of correctly identified trees and the number of ground-truth trees. The F1 accuracy of identified trees, which combines P and R. These indicators range larger values indicating higher accuracy, and are calculated based on true po itives (FP), and false negatives (FN) using Equations ( 11)- (13). Ideally, we wo have higher P and R; however, this relationship is usually negative in reality.…”

“…Unlike multispectral and hyperspectral, LiDAR sensors acquire three-dimensional point cloud information and vertical structure information of the forest by emitting highfrequency pulses from laser transmitters [13]. Researches on forestry applications of LiDAR data have focused on individual tree segmentation [14][15][16] and forest structure parameter extraction such as stand height, crown width, and biomass [17][18][19].…”

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

“…The second category for ITC segmentation comprises deep learning-based models for processing unmanned aerial vehicle (UAV) images and forest point clouds. Trees are identified by feeding input UAV images ( Lei et al, 2022 ) and point clouds into multiple conceptual layers using deep learning convolutional neural networks ( Zhang et al, 2020a ) and tuning the training hyperparameters through a gradient descent strategy, leading to the choices of parameters falling within a reasonable range. These optimization objectives have driven numerous synergetic studies using UAV images and deep learning techniques in forest applications, such as the utilization of U-net ( Cao and Zhang, 2020 ) to map forest types in the Atlantic Forest ( Wagner et al, 2019 ), the employment of DeepLab and an attention domain adaptation network for detecting Amazonian and Southeast Asia palms ( Ferreira et al, 2020 ; Zheng et al, 2020 ), the adoption of Faster-RCNN for tree seedling mapping ( Pearse et al, 2020 ) and the construction of multitask end-to-end optimized deep neural networks (MEON) for oak and pine detection ( Weinstein et al, 2020 ).…”

Using a Vegetation Index to Monitor the Death Process of Chinese Fir Based on Hyperspectral Data

“…Chinese fir is a principal timber forest species in the subtropical region of China, with advantages such as being fast-growing and productive [1,2]. To meet the increasing demand for timber, the afforestation area of Chinese fir plantations has continued to increase, and its forest stock volume now ranks first in the country [3,4].…”