A Deep Learning Dataset for Tomato Pest Leafminer TUTA ABSOLUTA
Published in Zenodo, 2020
Recommended citation: Rubanga, D. P., Mkonyi L., Richard M., Zekeya N., Loyani L.K., Shimada S., & Machuve D. (2020). A Deep Learning Dataset for Tomato Pest Leafminer TUTA ABSOLUTA. Zenodo. https://doi.org/10.5281/ZENODO.4305416
This study was conducted in Tanzania targeting a variety of tomato growers around the country. Two in-house experiments were set up in Arusha and Morogoro regions which are located in the northern and eastern part of the country respectively.The two regions are some of the major areas prone to Tuta absoluta infestation in Tanzania. In each region, we constructed a net house and then planted healthy tomato seedlings (free from other diseases and pests) considering different factors. On the second day after transplanting, Tuta absoluta was introduced to some randomly selected tomato plants by placing 2 to 8 larvae on top of each plant’s leaves. The pest immediately started to mine the leaves. This process was done under the supervision of an agricultural expert.
Tomato plant images at early growth stages were collected using a Canon EOS Kiss X7 camera with a resolution of 5184 x 3456 pixels. The images were taken daily for two consecutive weeks after infestation focusing on capturing the top approximately 30 centimetres from the plant since the plant crown is always affected by the pest in the early growth stages of the plant.
Recommended citation: Rubanga, D.P., Mkonyi L., Richard M., Zekeya N., Loyani L. K., Shimada S., & Machuve D. (2020). A Deep Learning Dataset for Tomato Pest Leafminer TUTA ABSOLUTA. Zenodo Repository. https://doi.org/10.5281/ZENODO.4305416.