TomatoweedDet: a real-field multi-class weed detection dataset and YOLO benchmark for tomato production systems
Alperen Mehmet Sevinç, Çağrı Vakkas Yıldırım, Ahmet Kerim Ağırman · 2026
Read TomatoweedDet: a real-field multi-class weed detection dataset and YOLO benchmark for tomato production systems by Alperen Mehmet Sevinç, Çağrı Vakkas Yıldırım, Ahmet Kerim Ağırman (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13323483.txt.
Description
Alperen Mehmet Sevinç and co-authors release a real-field weed dataset for tomato farming, in a 2026 study from three provinces of Turkiye. Their TomatoWeedDet set holds 32,607 images with 44,165 labelled boxes covering two weed species that earlier detection work largely ignored.
Drone and phone cameras shot fields in Balikesir, Ankara and Aksaray at varied times, soils, light and weather, including rain, mud and shadow. Seven YOLO model versions were trained and compared on precision, recall and mean average precision, with the YOLOv8l model performing best in their benchmark. The authors aim at drone or phone systems that spot weeds live, cut herbicide use and support precision spraying.
Catalog record
| CREATOR | Alperen Mehmet Sevinç, Çağrı Vakkas Yıldırım, Ahmet Kerim Ağırman |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 58433 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |