For example, proposed a pixel-based algorithm for 50 cm pan-sharpened satellite RGB data from a tropical forest in Brazil evaluated against field-collected tree stem locations, and proposed a vector-based algorithm for 10 cm fixed-winged aircraft RGB data from oak forests in California evaluated against image-annotated crowns. While there are dozens of proposed algorithms, they are often designed and evaluated using a range of different data inputs, sensor resolutions, forest structures, evaluation protocols, and output formats. A central task in remote sensing of forests is converting raw sensor data into information on individual trees. Compared to traditional field surveys, airborne remote sensing allows forest monitoring at broad scales. Quantifying individual trees is a central task for ecology and management of forested landscapes. This is a PLOS Computational Biology Benchmarking paper. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.Ĭompeting interests: The authors have declared that no competing interests exist. White and by the National Science Foundation (1926542) to EPW, SB, AZ, DW, and AS and by the USDA National Institute of Food and Agriculture McIntire Stennis project 1007080 to SB. įunding: This research was supported by the Gordon and Betty Moore Foundation’s Data-Driven Discovery Initiative (GBMF4563) to EPW. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.ĭata Availability: The data are available on Zenodo: And as part of the github repo. Received: OctoAccepted: JPublished: July 2, 2021Ĭopyright: © 2021 Weinstein et al. PLoS Comput Biol 17(7):Įditor: Jacopo Grilli, Abdus Salam International Centre for Theoretical Physics, ITALY (2021) A benchmark dataset for canopy crown detection and delineation in co-registered airborne RGB, LiDAR and hyperspectral imagery from the National Ecological Observation Network. We provide an example submission and score for an open-source algorithm that can serve as a baseline for future methods.Ĭitation: Weinstein BG, Graves SJ, Marconi S, Singh A, Zare A, Stewart D, et al. We discuss the different evaluation data sources and assess the accuracy of the image-annotated crowns by comparing annotations among multiple annotators as well as overlapping field-annotated crowns. In addition, we include over 10,000 training crowns for optional use. The benchmark dataset contains over 6,000 image-annotated crowns, 400 field-annotated crowns, and 3,000 canopy stem points from a wide range of forest types. This benchmark dataset includes an R package to standardize evaluation metrics and simplify comparisons between methods. Combining RGB, LiDAR and hyperspectral sensor data from the USA National Ecological Observatory Network’s Airborne Observation Platform with multiple types of evaluation data, we created a benchmark dataset to assess crown detection and delineation methods for canopy trees covering dominant forest types in the United States. There is a need for a benchmark dataset to minimize differences in reported results as well as support evaluation of algorithms across a broad range of forest types. While dozens of crown detection algorithms have been proposed, their performance is typically not compared based on standard data or evaluation metrics. A crucial step in this process is to associate sensor data into individual crowns.
Broad scale remote sensing promises to build forest inventories at unprecedented scales.
0 kommentar(er)
