Tomato seedling stem and leaf segmentation method based on an improved ResNet architecture
The proposed X-ResNet model exhibits superior segmentation performance, demonstrating high accuracy in phenotypic trait extraction. The strong correlations and low errors between extracted and manually measured data validate the feasibility of 3D point cloud technology for tomato phenotyping. This study provides a valuable benchmark for plant phenotyping research, with significant practical and theoretical implications.
Authors
- Lina Zhang (ORCID: https://orcid.org/0000-0002-4093-1171)
- Yi-Xing Lin
- Shuai Zhao (ORCID: https://orcid.org/0000-0003-1320-4283)
- Ziyi Huang (ORCID: https://orcid.org/0000-0001-7226-6578)
- Xingrui Zhang (ORCID: https://orcid.org/0000-0001-6905-4304)
- Zhiyin Yang (ORCID: https://orcid.org/0000-0002-2749-2901)
- Shengpeng Yu
- Manqi Yang
- Bo Yang (ORCID: https://orcid.org/0009-0000-0020-9638)
- Yang Han (ORCID: https://orcid.org/0009-0004-6237-5630)
Institutions
- Jilin University of Finance and Economics (CN)
- Jilin Agricultural University (CN)
Publication Details
- Journal
- Frontiers in Plant Science
- Published
- 2025-08-28
- DOI
- https://doi.org/10.3389/fpls.2025.1571445
- Primary Topic
- Smart Agriculture and AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00