ExtSpecR: An R Package and Tool for Extracting Tree Spectra from UAV-Based Remote Sensing

Zhuo Liu; Mahmoud Al-Sarayreh; Cong Xu; Federico Tomasetto; Yanjie Li

doi:10.34133/plantphenomics.0103

ExtSpecR: An R Package and Tool for Extracting Tree Spectra from UAV-Based Remote Sensing

Plant Phenomics. 2023 Oct 16:5:0103. doi: 10.34133/plantphenomics.0103. eCollection 2023.

Authors

Zhuo Liu^{1

2}, Mahmoud Al-Sarayreh³, Cong Xu⁴, Federico Tomasetto⁵, Yanjie Li^{1

2

2}

Affiliations

¹ State Key Laboratory of Tree Genetics and Breeding, Research Institute of Subtropical Forestry, Chinese Academy of Forestry, Hangzhou, Zhejiang 311400, China.
² Key Laboratory of Tree Breeding of Zhejiang Province, Research Institute of Subtropical Forestry, Chinese Academy of Forestry, Hangzhou, Zhejiang 311400, China.
³ Department of Computer Engineering, German Jordanian University, Amman 11180, Jordan.
⁴ School of Forestry, University of Canterbury, Private Bag 4800, Christchurch 8140, New Zealand.
⁵ AgResearch Ltd., Christchurch 8140, New Zealand.

Abstract

The development of unmanned aerial vehicle (UAV) remote sensing has been increasingly applied in forestry for high-throughput and rapid acquisition of tree phenomics traits for various research areas. However, the detection of individual trees and the extraction of their spectral data remain a challenge, often requiring manual annotation. Although several software-based solutions have been developed, they are far from being widely adopted. This paper presents ExtSpecR, an open-source tool for spectral extraction of a single tree in forestry with an easy-to-use interactive web application. ExtSpecR reduces the time required for single tree detection and annotation and simplifies the entire process of spectral and spatial feature extraction from UAV-based imagery. In addition, ExtSpecR provides several functionalities with interactive dashboards that allow users to maximize the quality of information extracted from UAV data. ExtSpecR can promote the practical use of UAV remote sensing data among forest ecology and tree breeding researchers and help them to further understand the relationships between tree growth and its physiological traits.