Design and Optimization of a Machine-Vision-Based Complementary Seeding Device for Tray-Type Green Onion Seedling Machines

Green onion (Allium fistulosum L.) is mainly available as factory-produced seedlings. Although factory seedling production highly automated, miss-seeding during the seeding process considerably affects subsequent transplanting and final yield. To solve problem of miss-seeding, current main method manual complementary seeding, which labor-intensive inefficient work. In this study, an automatic machine-vision-based device was proposed to reduce rate a replacement seeding. The performs several functions, including identification holes, control seed case movement, uptake release from suction nozzle array. A majority-mechanism-based tray hole rapid-detection enable real-time holes in under high-speed moving conditions. structural parameters vacuum-generated were optimized through numerical simulations orthogonal experiments, array produced using 3D-printing technology. Finally, installed on tray-type green machine effectiveness confirmed by experiments. results revealed that average values precision, recall, F1 scores for identifying 98.48%, 97.00%, 97.73%, respectively. decreased 5.37% 0.89% after