Integrating UAV remote sensing and semi-supervised learning for early-stage maize seedling monitoring and geolocation.

Monitoring and managing maize seedlings post-planting is essential for ensuring yield and quality. Unmanned aerial vehicle (UAV) remote sensing technology has been widely integrated for non-destructive detection of maize seedlings. However, significant challenges remain in maize seedling monitoring, such as relatively late monitoring periods, high data annotation costs, and lack of geolocation feedback for missing seedlings. To tackle these issues, this study focused on maize seedlings up to and including the second vegetative leaf (V2) stage. Firstly, the detection performance of both seedlings and missing seedlings was evaluated using a fully labeled dataset, achieving a mean precision of 92.06 ​%, recall of 87.44 ​%, and AP50 of 91.23 ​%. Then, the role of unlabeled data in enhancing the effectiveness of object detection was studied based on the efficient teacher semi-supervised learning framework. Significant improvements were observed when the labeled to unlabeled data ratio ranged from 1:2 to 1:12. The best results for mean precision, recall, and AP50 were improved by 2.69 ​%, 2.65 ​%, and 2.35 ​%, respectively. Additionally, an end-to-end pipeline was developed from image collection to seedling condition analysis, which effectively enhanced the detection of missing seedlings and accurately mapped them to geographical coordinates with an average deviation of 0.462m. This pipeline bridges the gap between missing seedling detection and replanting feedback, providing a feasible and precise detection solution for maize seedlings and supporting efficient field production management.