Lightweight deep neural network for contour detection and extraction of wheat spikes in complex field environments
The proposed framework demonstrates superior performance in complex field scenarios with dense targets and dynamic illumination. The multi-scale feature synergy enhancement mechanism overcomes traditional models' limitations in detecting overlapping spikes. This method not only enables precise spike phenotyping but also provides robust algorithmic support for intelligent field spikelet counting systems, advancing translational applications in crop phenomics.
Authors
- Jianyun Lu (ORCID: https://orcid.org/0000-0001-7187-8871)
- Xin Xu (ORCID: https://orcid.org/0000-0003-3238-745X)
- Jibo Yue (ORCID: https://orcid.org/0000-0001-9766-5313)
- Ziyi Guo (ORCID: https://orcid.org/0000-0002-0811-5086)
- Haiyang Zhang (ORCID: https://orcid.org/0000-0002-3303-8975)
- Juanjuan Zhang (ORCID: https://orcid.org/0000-0002-0071-4973)
- Hongbo Qiao (ORCID: https://orcid.org/0000-0002-9769-3389)
- Xinming Ma (ORCID: https://orcid.org/0000-0001-9137-497X)
Institutions
- Henan Agricultural University (CN)
Publication Details
- Journal
- Plant Methods
- Published
- 2025-08-22
- DOI
- https://doi.org/10.1186/s13007-025-01433-1
- Primary Topic
- Smart Agriculture and AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00