Abiotic Stress Prediction from RGB-T Images of Banana Plantlets
Abstract
Prediction of stress conditions is important for monitoring plant growth stages, disease detection, and assessment of crop yields. Multi-modal data, acquired from a variety of sensors, offers diverse perspectives and is expected to benefit the prediction process. We present several methods and strategies for abiotic stress prediction in banana plantlets, on a dataset acquired during a two and a half weeks period, of plantlets subject to four separate water and fertilizer treatments. The dataset consists of RGB and thermal images, taken once daily of each plant. Results are encouraging, in the sense that neural networks exhibit high prediction rates (over $90\%$ amongst four classes), in cases where there are hardly any noticeable features distinguishing the treatments, much higher than field experts can supply.
Cite
Text
Levanon et al. "Abiotic Stress Prediction from RGB-T Images of Banana Plantlets." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-65414-6_20Markdown
[Levanon et al. "Abiotic Stress Prediction from RGB-T Images of Banana Plantlets." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/levanon2020eccvw-abiotic/) doi:10.1007/978-3-030-65414-6_20BibTeX
@inproceedings{levanon2020eccvw-abiotic,
title = {{Abiotic Stress Prediction from RGB-T Images of Banana Plantlets}},
author = {Levanon, Sagi and Markovich, Oshry and Gozlan, Itamar and Bakhshian, Ortal and Zvirin, Alon and Honen, Yaron and Kimmel, Ron},
booktitle = {European Conference on Computer Vision Workshops},
year = {2020},
pages = {279-295},
doi = {10.1007/978-3-030-65414-6_20},
url = {https://mlanthology.org/eccvw/2020/levanon2020eccvw-abiotic/}
}