Coffee Crop Detection from UAS Orthomaps with Convolutional Neural Networks

Sergio Arriola-Valverde, Santiago López-Rojas, Daniel Ramírez-Valerio, Eduardo Somarriba-Chavez, Renato Rimolo-Donadio

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

This paper proposes a methodology for the automatic detection of coffee plants from close-range aerial images and deep learning techniques based on the YOLO framework. The data collection methodology, image preprocessing, and neural network training are discussed. Image datasets were collected at different locations in the central region of Costa Rica between 2018 and 2021. Models developed using this methodological approach had average mean accuracies up to 93% ([email protected]) on independent test sets; the detection performance achieved was 92% by using yolov4ext-ghost as a network architecture.

Original languageEnglish
Title of host publication2023 IEEE Conference on AgriFood Electronics, CAFE 2023 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5-9
Number of pages5
ISBN (Electronic)9798350327113
DOIs
StatePublished - 2023
Event1st IEEE Conference on AgriFood Electronics, CAFE 2023 - Torino, Italy
Duration: 25 Sep 202327 Sep 2023

Publication series

Name2023 IEEE Conference on AgriFood Electronics, CAFE 2023 - Proceedings

Conference

Conference1st IEEE Conference on AgriFood Electronics, CAFE 2023
Country/TerritoryItaly
CityTorino
Period25/09/2327/09/23

Keywords

  • coffee
  • convolutional neural networks
  • Costa Rica
  • deep learning
  • machine learning
  • photogrammetry
  • unmanned aerial systems

Fingerprint

Dive into the research topics of 'Coffee Crop Detection from UAS Orthomaps with Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this