Identification of sweetpotato virus disease-infected leaves from field images using deep learning
Ablation studies confirm the effectiveness of the proposed data augmentation and APF methods, while comparative experiments demonstrate the model's superiority across various metrics. The proposed method also exhibits excellent detection results in simulated scenarios. In summary, this study successfully deploys a deep learning framework to segment SPVD lesions from field images of sweetpotato foliage, which will contribute to the rapid and intelligent detection of sweetpotato diseases.
Authors
- Xuejun Yue (ORCID: https://orcid.org/0000-0002-9430-7729)
- Lifei Huang (ORCID: https://orcid.org/0000-0002-2107-5808)
- Junzhi Chen (ORCID: https://orcid.org/0000-0002-7139-8947)
- Ziyu Ding (ORCID: https://orcid.org/0009-0002-3998-0643)
- Jianyu Zheng (ORCID: https://orcid.org/0009-0000-0885-1713)
- Biao Chen (ORCID: https://orcid.org/0000-0003-1852-5289)
- Haifeng Li (ORCID: https://orcid.org/0009-0005-0032-7489)
- Fanguo Zeng (ORCID: https://orcid.org/0000-0002-7648-5193)
- Zhangying Wang
- Li Xiao (ORCID: https://orcid.org/0000-0002-5619-4313)
- W. J. Zhong (ORCID: https://orcid.org/0000-0003-2381-6718)
Institutions
- South China Agricultural University (CN)
- Guangdong Academy of Agricultural Sciences (CN)
Publication Details
- Journal
- Frontiers in Plant Science
- Published
- 2024-11-08
- DOI
- https://doi.org/10.3389/fpls.2024.1456713
- Citations
- 2
- Primary Topic
- Smart Agriculture and AI
- Type
- article
- Field-Weighted Citation Impact
- 1.20