PAPER SENDING SUBSCRIPTION

  • googleplus
  • facebook
  • twitter
  • linkedin
  • linkedin

DYNA JOURNAL ENGINEERING DYNA JOURNAL ENGINEERING

  • Skip to the menu
  • Skip to the content
  • DYNA Publishing
    • DYNA
    • DYNA Energy & Sustainability
    • DYNA Management
    • DYNA New Technologies
  • Journal
    • The Journal and its organs
      • Editors Board
      • Scientific Board
    • History
    • Mission - Vision and Values
    • Annual survey result
    • Frequent asked questions
    • Dissemination and Indexing
    • It is said about DYNA...
    • Collaborate with DYNA
    • Links of interest for engineering
      • FRIENDLY organizations
      • Contributing organizations
      • Engineering Associations
      • Others engineering journals
      • Other interesting links
  • Authors and Referees
    • Guidelines, rules and forms
    • Dissemination and indexing
    • How researchers can collaborate
  • Papers
    • Search
    • Volumes and issues
    • Most downloaded last year
    • Submission of papers
    • Next issue contents
    • Monographic reports
  • News
    • News & Topic Collections
    • Newsletters
    • Book Review
    • Software review
  • Blogs and Community
    • Forums
    • How collaborate
  • Subscribing
    • Sign up
  • Advertising
    • Target audience & ad formats
    • Advertising prices
    • Contents for next issue
    • Newsletter
  • Contact
    • How to contact
  • Search
    • In this Journal

Return to the menu

  • Homepage
  • Papers
  • Search

Search

×

 |    : /

Vote:

Results: 

0 points

 0  Votes

AUTOMATED DETECTION AND GEOLOCATION OF TEAK TREES BASED ON DEEP LEARNING FROM VERY-HIGH-RESOLUTION RGB UAV IMAGERY

 |    : /

JANUARY 2026   -  Volume: 101 -  Pages: 81-86

DOI:

https://doi.org/10.52152/D11497

Authors:

FERNANDO J. AGUILAR
- ALFREDO ALCAYDE GARCIA - MARCO EMILIO VALVERDE ALONSO - ABDERRAHIM NEMMAOUI -
MANUEL A. AGUILAR

Disciplines:

  • Computer technology (ORDENADORES DIGITALES )

Downloads:   22

How to cite this paper:  
Download pdf

Download pdf

Received Date :   18 July 2025

Reviewing Date :   23 July 2025

Accepted Date :   5 November 2025


Key words:
UAV Images, YOLOX, Tree Detection, Teak Plantations, Deep Learning, teak tree counting, individual tree detection, UAV remote sensing, Ecuador plantations, carbon stock estimation, RGB drone imagery, precision forestry, convolutional neural networks, object detection model, tropical forestry, plantation inventory
Article type:
ARTICULO DE INVESTIGACION / RESEARCH ARTICLE
Section:
RESEARCH ARTICLES

The control, supervision and monitoring of trees, both in terms of their location and height, is of vital importance in teak plantations (Tectona grandis L.f.). This allows planning silvicultural work related to thinning, replanting, irrigation and phytosanitary treatments, estimating production and harvesting. Knowing the number of plants, their spatial location, and estimating their height is crucial for managing large tree plantations and determining their carbon sequestration capacity to contribute to climate change mitigation. In this work, three different size versions of the anchor-free and single-stage detector YOLOX deep learning network, pre-trained on the COCO dataset, were specifically trained for automatic localization of teak trees in large and dense plantations from UAV imagery. This study used two teak plantations located in Ecuador. "La Marina" plantation (456 ha) served as the training and validation area, while "La Selena" (195 ha), was reserved for testing and accuracy evaluation, constituting a true holdout dataset to assess the generalization capabilities of the developed model. Very high-resolution RGB images were taken in both plantations using a Phantom 4 drone at a flight altitud of 120 m above ground. Regarding the results obtained, they showed that the "small" version of the YOLOX deep learning network performed significantly better than the other two versions tested ("medium" and "large" size YOLOX), presenting notably good average metrics of Precision (94.74%), Recall (82.40%) and F1-score (87.91%). In this sense, the trained model proved to be a suitable solution to address complex visual recognition challenges in very high-resolution UAV images.

Keywords: UAV Images, YOLOX, Tree Detection, Teak Plantations, Deep Learning

Share:  

  • Twittear
  • facebook
  • google+
  • linkedin
  • delicious
  • yahoo
  • myspace
  • meneame
  

Search

banner crosscheck

  •  
  • Twitter
  • Twitter
  •  
  • Facebook
  • Facebook
  •  
Tweets por el @revistadyna.
Loading…

Anunciarse en DYNA 

© Engineering Journal Dyna 2025 - UK Zhende Publishing Limited

Address: Unit 7 Wilsons Business Park, Manchester M40 8WN United Kingdom

Email: office@revistadyna.com

  • Menu
  • DYNA Publishing
    • DYNA Publishing
    • DYNA
    • DYNA Energy & Sustainability
    • DYNA Management
    • DYNA New Technologies
  • Journal
    • The Journal and its organs
      • The Journal and its organs
      • Editors Board
      • Scientific Board
    • History
    • Mission - Vision and Values
    • Annual survey result
    • Frequent asked questions
    • Dissemination and Indexing
    • It is said about DYNA...
    • Collaborate with DYNA
    • Links of interest for engineering
      • Links of interest for engineering
      • FRIENDLY organizations
      • Contributing organizations
      • Engineering Associations
      • Others engineering journals
      • Other interesting links
  • Authors and Referees
    • Guidelines, rules and forms
    • Dissemination and indexing
    • How researchers can collaborate
  • Papers
    • Papers
    • Search
    • Volumes and issues
    • Most downloaded last year
    • Submission of papers
    • Next issue contents
    • Monographic reports
  • News
    • News & Topic Collections
    • Newsletters
    • Book Review
    • Software review
  • Blogs and Community
    • Blogs and Community
    • Forums
    • How collaborate
  • Subscribing
    • Sign up
  • Advertising
    • Target audience & ad formats
    • Advertising prices
    • Contents for next issue
    • Newsletter
  • Contact
    • How to contact
  • Search
    • In this Journal

Regístrese en un paso con su email y podrá personalizar sus preferencias mediante su perfil


: *   

: *   

:

: *     

 

  

Loading Loading ...