Preeti
A research team has developed an innovative method using unmanned aerial vehicles (UAVs) and deep learning techniques to accurately identify tassel states in maize hybridization fields. This approach improves tassel detection accuracy up to 98% through specific annotation and data augmentation strategies. The study, published in Plant Phenomics, aims to address challenges in tassel detection by developing accurate models and annotated datasets for maize tassels’ dynamic growth stages.
The research evaluated different versions of the RTMDet network model for practical tassel detection applications, selecting the S version for its balanced performance and resource efficiency. The models were trained on various datasets to assess accuracy in detecting tassels at different growth stages, with the RTMDet-NSL-C model achieving the best overall performance.
This method proves effective in accurately identifying tassel states in UAV images, providing a robust solution for real-time maize tassel monitoring and management. The lead researcher highlights the potential for developing an intelligent system based on UAV remote sensing imagery for large-scale analysis of maize hybridization fields, reducing reliance on manual surveys and aiding decision-making.
In summary, this study introduces an innovative method for assessing maize tassel condition using UAV imagery and deep learning, paving the way for intelligent systems based on UAV remote sensing imagery. This advancement enables rapid, large-scale analysis of maize hybridization fields, reducing reliance on manual surveys and enhancing crop management efficiency.
Source link
Source link: https://phys.org/news/2024-06-uav-deep-method-maize-tassel.html
GIPHY App Key not set. Please check settings