Potato Miss-Seeding and Double-Seeding Detection Method Based on Machine Vision
Chengyu YangCollege of Engineering, China Agricultural University,Beijing,ChinaSheraliev Mukhiddin Shuhratjon ugliNational Research University,Faculty of Agricultural Mechanization,Tashkent,UzbekistanXu MaoCollege of Engineering, China Agricultural University,Beijing,ChinaDa WangCollege of Engineering, China Agricultural University,Beijing,ChinaXiongzhe HanCollege of Agriculture and Life Sciences, Kangwon National University,Chuncheon,Republic of Korea
2026
ABI
Abstract
To address the lack of effective online monitoring for potato miss-seeding and double-seeding, this study developed a machine vision-based system to optimize planter performance. After evaluating various YOLO models, YOLOv8n was selected and enhanced by integrating the ECA attention mechanism and optimizing the loss function. The improved model achieved a 93.2% recall and a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$95.0 \% \text{mAP}$</tex>, representing significant increases of 12.6% and 4.8% over the baseline. These results provide an efficient, accurate, and practically valuable solution for real-time seeding status monitoring.
Topics
Identifiers
Citations and references
Cited by 00 references