Kidney bean detection in complex agricultural scenarios based on the kidneyB-YOLO model
Jianjia Qi, Chunxiang Liu, Hongxia Chu · 2025
Read Kidney bean detection in complex agricultural scenarios based on the kidneyB-YOLO model by Jianjia Qi, Chunxiang Liu, Hongxia Chu (2025) 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/pmc-12741056.txt.
Description
Jianjia Qi, Chunxiang Liu, and Hongxia Chu teach a detector to find kidney beans hiding in their own vines, in a 2025 paper. Open-field trellises tangle pods behind leaves, and standard detectors miss the occluded ones. Their kidneyB-YOLO variant adds shifting attention that samples only key spots, a fusion head that sorts conflicting signals, and a loss that favors hard cases.
On a purpose-built pod dataset the model reached 85.9 percent mean average precision while running at over thirty frames per second in a twelve-megabyte package. That speed and size suit field robots and drones that must count yield without a data center.
Catalog record
| CREATOR | Jianjia Qi, Chunxiang Liu, Hongxia Chu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 63 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |