A scalable multi-modal learning fruit detection algorithm for dynamic environments
The improved network exhibits distinct improvements, primarily focusing on enhancing the recall rate and AP value, thereby reducing the missed detection rate which exhibiting a reduced number of missed targets and a more accurate prediction frame, indicating its suitability for litchi fruit detection. Therefore, this method significantly enhances the detection accuracy of mature litchi fruits and effectively addresses the challenges of dense occlusion and small target detection, providing crucial technical support for subsequent litchi yield estimation.
Authors
- Mingzhe Liu (ORCID: https://orcid.org/0000-0002-8962-560X)
- Zihao Guo (ORCID: https://orcid.org/0000-0001-7948-2919)
- Yu Li (ORCID: https://orcid.org/0000-0003-3691-0199)
- Jie Li (ORCID: https://orcid.org/0000-0002-9198-5321)
- Liang Mao (ORCID: https://orcid.org/0000-0002-7112-9421)
- Linlin Wang (ORCID: https://orcid.org/0000-0002-2033-9277)
Institutions
- University of Science and Technology Liaoning (CN)
- Shenzhen Polytechnic University (CN)
Publication Details
- Journal
- Frontiers in Neurorobotics
- Published
- 2025-02-07
- DOI
- https://doi.org/10.3389/fnbot.2024.1518878
- Citations
- 2
- Primary Topic
- Smart Agriculture and AI
- Type
- article
- Field-Weighted Citation Impact
- 3.50
Funders
- Shenzhen Polytechnic
- Basic and Applied Basic Research Foundation of Guangdong Province