Tree Crown Delineation Algorithm Based on a Convolutional Neural Network

Remote Sensing

HaroldoF.de Campos Velho¹  MatheusP. Ferreira²  ElcioH. Shiguemori³  Yuliya Tarabalka⁴  Vinícius Peripato⁵  Ricardo Dalagnol⁵  JoséR. G. Braga⁵  LuizE. O. C. Aragão⁵  FabienH. Wagner⁵ 

[1] Associated Laboratory for Computing and Applied Mathematics, National Institute for Space Research—INPE, Av. dos Astronautas 1758, São José dos Campos 12227-010, Brazil;Cartographic Engineering Section, Military Institute of Engineering—IME, Praça Gen.Tibúrcio 80, Rio de Janeiro 22290-270, Brazil;Department of Aerospace Science and Technology, Institute for Advanced Studies—IEAv, Trevo Coronel Aviador José Alberto Albano do Amarante 01, São José dos Campos 12228-001, Brazil;Inria Sophia Antipolis, Cedex Sophia Antipolis, 06902 Valbonne, France;Remote Sensing Division, National Institute for Space Research—INPE, Av. dos Astronautas 1758, São José dos Campos 12227-010, Brazil;

关键词: tree crown delineation;    tropical forests;    optical satellite images;    deep learning;   

DOI  :  10.3390/rs12081288

来源: DOAJ

【 摘 要 】

Tropical forests concentrate the largest diversity of species on the planet and play a key role in maintaining environmental processes. Due to the importance of those forests, there is growing interest in mapping their components and getting information at an individual tree level to conduct reliable satellite-based forest inventory for biomass and species distribution qualification. Individual tree crown information could be manually gathered from high resolution satellite images; however, to achieve this task at large-scale, an algorithm to identify and delineate each tree crown individually, with high accuracy, is a prerequisite. In this study, we propose the application of a convolutional neural network—Mask R-CNN algorithm—to perform the tree crown detection and delineation. The algorithm uses very high-resolution satellite images from tropical forests. The results obtained are promising—the $Recall$ , $Precision$ , and $F_1$ score values obtained were were $0.81$ , $0.91$ , and $0.86$ , respectively. In the study site, the total of tree crowns delineated was $59,062$ . These results suggest that this algorithm can be used to assist the planning and conduction of forest inventories. As the algorithm is based on a Deep Learning approach, it can be systematically trained and used for other regions.

【 授权许可】

Unknown