Application of deep learning for real-time detection, localization, and counting of the malignant invasive weed Solanum rostratum Dunal
Shifeng Du, Yashuai Yang, Hongbo Yuan, Man Cheng · 2025
Read Application of deep learning for real-time detection, localization, and counting of the malignant invasive weed Solanum rostratum Dunal by Shifeng Du, Yashuai Yang, Hongbo Yuan, Man Cheng (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-11814178.txt.
Description
Shifeng Du, Yashuai Yang, Hongbo Yuan, and Man Cheng build a system that spots and counts a harmful invasive weed from drone video in real time. The weed, Solanum rostratum, has spread across many countries and threatens farms and ecosystems. Their system, TrackSolanum, chains four parts: a detector that finds the plant, a tracker that follows each plant across frames, and a locator that pins its position. A counter then tallies plants as they cross a line. The study was published in 2024.
Field tests flew at two heights. At 2 meters, the system reached precision of 0.950 and recall of 0.970, with a counting error of 2.438 percent at 17 frames per second. At 3 meters it stayed close, with a 4.634 percent counting error and much faster processing. The authors offer the tool for judging infestations and guiding precise weed control.
Catalog record
| CREATOR | Shifeng Du, Yashuai Yang, Hongbo Yuan, Man Cheng |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 66 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |