Estimating melon yield for breeding processes by machine-vision processing of UAV images

A. Kalantar, A. Dashuta, Y. Edan, A. Dafna, A. Gur, I. Klapp

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

4 Scopus citations

Abstract

Monitoring plants, for yield estimation in melon breeding, is a highly labor-intensive task. An algorithmic pipeline for detection and yield estimation of melons from top-view images of a melon's field is presented. The pipeline developed at the individual melon level includes three main stages: melon recognition, feature extraction, and yield estimation. For each region of interest classified as a melon, the melon features were extracted by fitting an ellipse to the melon contour. A regression model that ties the ellipse features to the melon's weight is presented. The modified R2 value of the regression model was 0.94. Comparing yield estimation to ground truth, the average estimation error was 16%. The yield accuracy is highly dependent on the ellipse estimation accuracy, with promising results of only 4% error for the best ellipse-fitted melons.

Original languageEnglish
Title of host publicationPrecision Agriculture 2019 - Papers Presented at the 12th European Conference on Precision Agriculture, ECPA 2019
EditorsJohn V. Stafford
PublisherWageningen Academic Publishers
Pages381-387
Number of pages7
ISBN (Electronic)9789086863372
DOIs
StatePublished - 2019
Externally publishedYes
Event12th European Conference on Precision Agriculture, ECPA 2019 - Montpellier, France
Duration: 8 Jul 201911 Jul 2019

Publication series

NamePrecision Agriculture 2019 - Papers Presented at the 12th European Conference on Precision Agriculture, ECPA 2019

Conference

Conference12th European Conference on Precision Agriculture, ECPA 2019
Country/TerritoryFrance
CityMontpellier
Period8/07/1911/07/19

Bibliographical note

Publisher Copyright:
© Wageningen Academic Publishers 2019

Keywords

  • Active contour
  • Breeding
  • CNN
  • Machine learning
  • Melon
  • Phenotyping
  • Yield estimation

Fingerprint

Dive into the research topics of 'Estimating melon yield for breeding processes by machine-vision processing of UAV images'. Together they form a unique fingerprint.

Cite this