Enhancing precision harvesting in smart orchards: a light-weight neural network for apple maturity detection
Linna Hu, Penghao Xue, Weixian Zha, Bin Guo, Jia Li, Xingru Chen, Hao Li · 2026
Read Enhancing precision harvesting in smart orchards: a light-weight neural network for apple maturity detection by Linna Hu, Penghao Xue, Weixian Zha, Bin Guo, Jia Li, Xingru Chen, Hao Li (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/pmc-13190562.txt.
Description
Linna Hu and co-authors slim down an apple-spotting network so orchard robots can judge ripeness on weak hardware, in a 2026 paper. Their model rebuilds a standard detector end to end: a lighter backbone, a fusion neck that sees through leaf clutter, a lean detection head, and a loss tuned for small targets. Rain, glare, and dense clusters are the stated enemies.
On an orchard dataset, accuracy rose 1.7 points over the baseline while the parameter count fell by over a third. Compute fell by a similar share. The authors say the trimmed model fits the edge devices that harvesters actually carry. It is offered as a practical brick in the smart orchard wall.
Catalog record
| CREATOR | Linna Hu, Penghao Xue, Weixian Zha, Bin Guo, Jia Li, Xingru Chen, Hao Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 69 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |