
Sensors, Journal Year: 2024, Volume and Issue: 24(20), P. 6700 - 6700
Published: Oct. 18, 2024
At present, tomato transplanting in facility agriculture is mainly manual operation. In an attempt to resolve the problems of high labor intensity and low efficiency operation, this paper designs a clip stem automatic seedling picking device based on yolov5 algorithm. First all, through study characteristics seedlings different ages, age suitable for was obtained. Secondly, improved algorithm used determine position shape seedlings. By adding lightweight upsampling operator (CARAFE) loss function, feature extraction ability detection speed stems were improved. The accuracy reached 92.6%, mAP_0.5 95.4%. Finally, verification test carried out with about 40 days old. results show that damage rate 7.2%, success not less than 90.3%. This can provide reference research into machines.
Language: Английский