UAV-Based RGB Imagery for Hokkaido Pumpkin (Cucurbita max.) Detection and Yield Estimation

Please use this identifier to cite or link to this item:
https://nbn-resolving.org/urn:nbn:de:gbv:700-202106145080
Open Access logo originally created by the Public Library of Science (PLoS)
Title: UAV-Based RGB Imagery for Hokkaido Pumpkin (Cucurbita max.) Detection and Yield Estimation
Authors: Wittstruck, Lucas
Kühling, Insa
Trautz, Dieter
Kohlbrecher, Maik
Jarmer, Thomas
ORCID of the author: https://orcid.org/0000-0001-8647-3906
https://orcid.org/0000-0003-2873-2425
Abstract: Pumpkins are economically and nutritionally valuable vegetables with increasing popularity and acreage across Europe. Successful commercialization, however, require detailed pre-harvest information about number and weight of the fruits. To get a non-destructive and cost-effective yield estimation, we developed an image processing methodology for high-resolution RGB data from Unmanned aerial vehicle (UAV) and applied this on a Hokkaido pumpkin farmer’s field in North-western Germany. The methodology was implemented in the programming language Python and comprised several steps, including image pre-processing, pixel-based image classification, classification post-processing for single fruit detection, and fruit size and weight quantification. To derive the weight from two-dimensional imagery, we calculated elliptical spheroids from lengths of diameters and heights. The performance of this processes was evaluated by comparison with manually harvested ground-truth samples and cross-checked for misclassification from randomly selected test objects. Errors in classification and fruit geometry could be successfully reduced based on the described processing steps. Additionally, different lighting conditions, as well as shadows, in the image data could be compensated by the proposed methodology. The results revealed a satisfactory detection of 95% (error rate of 5%) from the field sample, as well as a reliable volume and weight estimation with Pearson’s correlation coefficients of 0.83 and 0.84, respectively, from the described ellipsoid approach. The yield was estimated with 1.51 kg m−2 corresponding to an average individual fruit weight of 1100 g and an average number of 1.37 pumpkins per m2. Moreover, spatial distribution of aggregated fruit densities and weights were calculated to assess in-field optimization potential for agronomic management as demonstrated between a shaded edge compared to the rest of the field. The proposed approach provides the Hokkaido producer useful information for more targeted pre-harvest marketing strategies, since most food retailers request homogeneous lots within prescribed size or weight classes.
Citations: Wittstruck L, Kühling I, Trautz D, Kohlbrecher M, Jarmer T.: UAV-Based RGB Imagery for Hokkaido Pumpkin (Cucurbita max.) Detection and Yield Estimation. Sensors. 2021; 21(1):118.
URL: https://repositorium.ub.uni-osnabrueck.de/handle/urn:nbn:de:gbv:700-202106145080
Subject Keywords: remote sensing; drones; random forest; low-cost sensor; winter squash; vegetables; fruit size; fruit weight; Europe
Issue Date: 27-Dec-2020
License name: Attribution 4.0 International
License url: http://creativecommons.org/licenses/by/4.0/
Type of publication: Einzelbeitrag in einer wissenschaftlichen Zeitschrift [article]
Appears in Collections:FB06 - Hochschulschriften
Open-Access-Publikationsfonds

Files in This Item:
File Description SizeFormat 
sensors_Wittstruck_etal_2020.pdf3,96 MBAdobe PDF
sensors_Wittstruck_etal_2020.pdf
Thumbnail
View/Open


This item is licensed under a Creative Commons License Creative Commons