RLK-YOLOv8: multi-stage detection of strawberry fruits throughout the full growth cycle in greenhouses based on large kernel convolutions and improved YOLOv8
The RLK-YOLOv8 exhibits outstanding performance in strawberry multi-stage detection and yield estimation tasks, validating the effectiveness of integrating large kernel convolutions and multi-scale feature fusion strategies. The proposed algorithm has demonstrated significant improvements in detection performance across various environments and scenarios.
Authors
- Lei He (ORCID: https://orcid.org/0000-0002-9875-9853)
- Dasheng Wu (ORCID: https://orcid.org/0000-0002-6316-303X)
- Fuchuan Ni (ORCID: https://orcid.org/0000-0002-4942-6171)
- Xinyu Zheng (ORCID: https://orcid.org/0000-0003-1840-214X)
- Siyang Wang (ORCID: https://orcid.org/0009-0004-8733-3103)
- Fang Zheng (ORCID: https://orcid.org/0000-0002-5369-0899)
- Feng Xu (ORCID: https://orcid.org/0009-0005-8507-9161)
- Shangqin Lin
Institutions
- Zhejiang A & F University (CN)
- State Forestry and Grassland Administration (CN)
Publication Details
- Journal
- Frontiers in Plant Science
- Published
- 2025-03-25
- DOI
- https://doi.org/10.3389/fpls.2025.1552553
- Citations
- 4
- Primary Topic
- Smart Agriculture and AI
- Type
- article
- Field-Weighted Citation Impact
- 7.00