YOLOv8s-Longan: a lightweight detection method for the longan fruit-picking UAV
The experimental results show that the proposed algorithm has good detection ability for densely distributed and mutually occluded longan string fruit under complex backgrounds with a [email protected] of 84.3%. Compared with other YOLOv8 models, the improved model of [email protected] improves by 3.9% and reduces the number of parameters by 20.3%. It satisfies the high accuracy and fast detection requirements for fruit detection in fruit-picking UAV scenarios.
Authors
- Kaixuan Wu (ORCID: https://orcid.org/0009-0009-4480-029X)
- Hengxu Chen
- Hai Lin (ORCID: https://orcid.org/0000-0002-1682-8465)
- Yun Mai (ORCID: https://orcid.org/0000-0002-6011-8874)
- Jun Li (ORCID: https://orcid.org/0000-0003-3716-671X)
- Meiqi Zhang (ORCID: https://orcid.org/0000-0002-1221-5776)
- Linlin Shi
Institutions
- South China Agricultural University (CN)
- Key Laboratory of Guangdong Province (CN)
- Beijing Agricultural Machinery Research Institute (CN)
Publication Details
- Journal
- Frontiers in Plant Science
- Published
- 2025-01-22
- DOI
- https://doi.org/10.3389/fpls.2024.1518294
- Citations
- 3
- Primary Topic
- Smart Agriculture and AI
- Type
- article
- Field-Weighted Citation Impact
- 5.25