GFkuts: A novel multispectral image segmentation method applied to precision agriculture

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

4 Scopus citations

Abstract

Image segmentation enables the precise extraction of several crop traits from multispectral aerial imagery. This paper presents a novel segmentation technique called GFKuts. The method integrates a graph-based optimization algorithm with a k-means Monte Carlo approach. Here, we evaluate the performance of the proposed method against other approaches for image segmentation found in the specialized literature. Results report an improvement on the F1-score accuracy in terms of crop canopy segmentation. These findings are promising for the precise calculation of vegetative indices and other crop trait features.

Original languageEnglish
Title of host publication2020 Virtual Symposium in Plant Omics Sciences, OMICAS 2020 - Conference Proceedings
EditorsJulian Colorado
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665433310
DOIs
StatePublished - 23 Nov 2020
Event2020 Virtual Symposium in Plant Omics Sciences, OMICAS 2020 - Virtual, Online, Colombia
Duration: 23 Nov 202027 Nov 2020

Publication series

Name2020 Virtual Symposium in Plant Omics Sciences, OMICAS 2020 - Conference Proceedings

Conference

Conference2020 Virtual Symposium in Plant Omics Sciences, OMICAS 2020
Country/TerritoryColombia
CityVirtual, Online
Period23/11/2027/11/20

Keywords

  • Multispectral imagery
  • image segmentation
  • precision agriculture

Fingerprint

Dive into the research topics of 'GFkuts: A novel multispectral image segmentation method applied to precision agriculture'. Together they form a unique fingerprint.

Cite this