Please use this identifier to cite or link to this item:
Appears in Collections:Computing Science and Mathematics Journal Articles
Peer Review Status: Refereed
Title: Benchmarking Anchor-Based and Anchor-Free State-of-the-Art Deep Learning Methods for Individual Tree Detection in RGB High-Resolution Images
Author(s): Zamboni, Pedro
Marcato Junior, José
de Andrade Silva, Jonathan
Miyoshi, Gabriela Takahashi
Matsubara, Edson Takashi
Nogueira, Keiller
Gonçalves, Wesley Nunes
Keywords: object detection
convolutional neural network
remote sensing
Issue Date: Jul-2021
Date Deposited: 29-Jul-2021
Citation: Zamboni P, Marcato Junior J, de Andrade Silva J, Miyoshi GT, Matsubara ET, Nogueira K & Gonçalves WN (2021) Benchmarking Anchor-Based and Anchor-Free State-of-the-Art Deep Learning Methods for Individual Tree Detection in RGB High-Resolution Images. Remote Sensing, 13 (13), Art. No.: 2482.
Abstract: rban forests contribute to maintaining livability and increase the resilience of cities in the face of population growth and climate change. Information about the geographical distribution of individual trees is essential for the proper management of these systems. RGB high-resolution aerial images have emerged as a cheap and efficient source of data, although detecting and mapping single trees in an urban environment is a challenging task. Thus, we propose the evaluation of novel methods for single tree crown detection, as most of these methods have not been investigated in remote sensing applications. A total of 21 methods were investigated, including anchor-based (one and two-stage) and anchor-free state-of-the-art deep-learning methods. We used two orthoimages divided into 220 non-overlapping patches of 512 × 512 pixels with a ground sample distance (GSD) of 10 cm. The orthoimages were manually annotated, and 3382 single tree crowns were identified as the ground-truth. Our findings show that the anchor-free detectors achieved the best average performance with an AP50 of 0.686. We observed that the two-stage anchor-based and anchor-free methods showed better performance for this task, emphasizing the FSAF, Double Heads, CARAFE, ATSS, and FoveaBox models. RetinaNet, which is currently commonly applied in remote sensing, did not show satisfactory performance, and Faster R-CNN had lower results than the best methods but with no statistically significant difference. Our findings contribute to a better understanding of the performance of novel deep-learning methods in remote sensing applications and could be used as an indicator of the most suitable methods in such applications.
DOI Link: 10.3390/rs13132482
Rights: © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (
Licence URL(s):

Files in This Item:
File Description SizeFormat 
remotesensing-13-02482.pdfFulltext - Published Version36.08 MBAdobe PDFView/Open

This item is protected by original copyright

A file in this item is licensed under a Creative Commons License Creative Commons

Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved

If you believe that any material held in STORRE infringes copyright, please contact providing details and we will remove the Work from public display in STORRE and investigate your claim.