Potato Miss-Seeding and Double-Seeding Detection Method Based on Machine Vision
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$95.0 \% \text{mAP}$, 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.
Fields of Study & Subjects
Smart Agriculture and AI
Spectroscopy and Chemometric Analyses
Potato Plant Research
Publication details
- Journal / source
- 2026 9th International Conference on Advanced Algorithms and Control Engineering (ICAACE)
- Publisher
- IEEE
- Pages
- 555–560
- Publication date
- 20 March 2026