Automated tree-crown and height detection in a young forest plantation using mask region-based convolutional neural network (Mask R-CNN)

• Published in: ISPRS journal of photogrammetry and remote sensing Vol. 178; pp. 112 - 123
• Main Authors: Hao, Zhenbang, Lin, Lili, Post, Christopher J., Mikhailova, Elena A., Li, Minghui, Chen, Yan, Yu, Kunyong, Liu, Jian
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.08.2021
• Subjects: automation; China; Cunninghamia lanceolata; Deep learning; forest inventory; forest plantations; Instance segmentation; neural networks; photogrammetry; Plantation forest; tree crown; Tree height; Tree-crown delineation; trees; UAV imagery; China; Deep learning; Instance segmentation; UAV imagery; Plantation forest; Tree height; Tree-crown delineation

Tree-crown and height are primary tree measurements in forest inventory. Convolutional neural networks (CNNs) are a class of neural networks, which can be used in forest inventory; however, no prior studies have developed a CNN model to detect tree crown and height simultaneously. This study is the...