Article Highlight | 15-Jan-2024

Transforming forestry: The role of ExtSpecR in streamlining UAV-based tree phenomics and spectral analysis

Plant Phenomics

Unmanned aerial vehicles (UAVs) have revolutionized forestry by enabling high-throughput data collection of tree phenotypic traits. Despite advances in remote sensing and object detection technologies, accurate detection and spectral data extraction of individual trees remain significant challenges, often  requiring laborious manual annotation. Current research focuses on  improving segmentation algorithms and convolutional neural networks for better tree detection, but widespread adoption is hindered by the need for accurate manual labeling. This highlights the  urgent need for developing a more efficient, high-throughput method to autonomously extract individual tree spectral information.

In October 2023, Plant Phenomics published a database/software article entitled  “ExtSpecR: An R Package and Tool for Extracting Tree Spectra from UAV-Based Remote Sensing".

This paper  presents ExtSpecR, an open source tool for single tree spectral extraction in forestry using UAV-based imagery, which provides an easy-to-use interactive web application. It streamlines the detection and annotation for individual trees, reducing the time and simplifying the process of extracting spectral and spatial features. ExtSpecR’s user interface allows  the upload of TIFF-formatted spectral images, enabling users to calculate vegetation indices and view outputs as false-color and VI-specific images. Its core phenotyping capabilities are facilitated by an interactive dashboard, where users upload point cloud data and multispectral images, then define the region of interest (ROI) for tree identification and segmentation. This process uses functions such as “locate_trees” from the lidR package and provides 3D visualizations of the segmented trees. ExtSpecR's performance has been evaluated against ground truth in tree plantations with varying canopy densities, demonstrating accuracies between 91% and 97% in detecting individual trees.

The functionality of ExtSpecR is compared to other tools, highlighting its unique strategy of integrating existing algorithms for an optimized user experience, and providing comprehensive tree analysis by combining point cloud data with multispectral imagery. While it faces challenges with large input data sizes and complex environments with overlapping canopies, recommendations include segmenting point cloud data and defining specific target areas to improve results. The paper suggests that future enhancements should aim to improve cloud quality and evaluate efficiency with LiDAR point clouds and hyperspectral imagery. Overall, ExtSpecR proves to be a powerful, user-friendly tool for accelerating and simplifying plant phenomics extraction processes in forestry research.




Zhuo  Liu1,2, Mahmoud  Al-Sarayreh3, Cong  Xu4, Federico  Tomasetto5, and Yanjie  Li1,2,*


1State Key Laboratory of Tree Genetics and Breeding, Research Institute of Subtropical Forestry, Chinese Academy  of  Forestry,  Hangzhou,  Zhejiang  311400,  China.  

2Key  Laboratory  of  Tree  Breeding  of  Zhejiang  Province, Research Institute of Subtropical Forestry, Chinese Academy of Forestry, Hangzhou, Zhejiang 311400, China.

3Department of Computer Engineering, German Jordanian University, Amman 11180, Jordan.

4School of Forestry, University of Canterbury, Private Bag 4800, Christchurch 8140, New Zealand.

5AgResearch Ltd., Christchurch 8140, New Zealand.

About Yanjie  Li

He is currently an associate professor at the State Key Laboratory of Tree Genetics and Breeding, Research Institute of Subtropical Forestry, Chinese Academy of Forestry. His research interests include genetic breeding and germplasm resource evaluation, mainly focusing on the rapid estimation and evaluation of high-throughput forest germplasm resource phenotypes in important timber species in subtropical areas such as Pinus wetland, Pinus torch pine and Sassafras.

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.