Year: 2022
Type: article
Abstract: The paper presents a pumpkin yield estimation method using images acquired by a UAV. The processing pipeline is fully automated. It consists of orthomosaic generation, a color model collection using a random subset of the data, color segmentation, and finally counting of pumpkin blobs together with assessing the number of pumpkins in each blob. The algorithm was validated by a manual check of 5% of each tested dataset. The precision value ranges between 0.959 and 0.996, recall between 0.971 and 0.987, and F1 score falls between 0.971 and 0.988. This proves the very high efficiency of the processing workflow and its potential value to farmers.
Source: Agronomy
Authors: Henrik Skov Midtiby, Elżbieta Pastucha
Institution: University of Southern Denmark
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: gold
Estimated APC paid: $2,094
OpenAlex ID: W4223940586
