Version 1
: Received: 17 April 2023 / Approved: 18 April 2023 / Online: 18 April 2023 (05:50:50 CEST)
How to cite:
Marin, W.; Mondragon, I. F.; Colorado, J. D. Aerial Identification of Fruit Maturity in Amazonian Palms via Plant-Canopy Modeling. Preprints2023, 2023040496. https://doi.org/10.20944/preprints202304.0496.v1
Marin, W.; Mondragon, I. F.; Colorado, J. D. Aerial Identification of Fruit Maturity in Amazonian Palms via Plant-Canopy Modeling. Preprints 2023, 2023040496. https://doi.org/10.20944/preprints202304.0496.v1
Marin, W.; Mondragon, I. F.; Colorado, J. D. Aerial Identification of Fruit Maturity in Amazonian Palms via Plant-Canopy Modeling. Preprints2023, 2023040496. https://doi.org/10.20944/preprints202304.0496.v1
APA Style
Marin, W., Mondragon, I. F., & Colorado, J. D. (2023). Aerial Identification of Fruit Maturity in Amazonian Palms via Plant-Canopy Modeling. Preprints. https://doi.org/10.20944/preprints202304.0496.v1
Chicago/Turabian Style
Marin, W., Ivan F. Mondragon and Julian D. Colorado. 2023 "Aerial Identification of Fruit Maturity in Amazonian Palms via Plant-Canopy Modeling" Preprints. https://doi.org/10.20944/preprints202304.0496.v1
Abstract
UAV-captured multispectral imagery was used to characterize and associate Moriche’s palm 1 canopy features with the maturity stage of the corresponding fruits. Deep learning models based on 2 convolutional neural networks (CNN) were trained in order to determine correlations between the 3 photosynthetic radiation of the palms with the fruit. Here, we compare several approaches for feature 4 extraction based on vegetation indices and graph-based models. Also, a comprehensive dataset has 5 been collected and labeled, containing plant data for an entire phenological cycle of the Moriche 6 palms. Experimental results reported an average estimation accuracy of 72%, by using the proposed 7 method in dense forests of the Amazonian region.
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.