Design of a Machine Vision-Based Automatic Digging Depth Control System for Garlic Combine Harvester

The digging depth is an important factor affecting the mechanized garlic harvesting quality. At present, of combine harvester (GCH) adjusted manually, which leads to disadvantages such as slow response, poor accuracy, and being very dependent on operator’s experience. To solve this problem, paper proposes a machine vision-based automatic control system for original device. uses improved YOLOv5 algorithm calculate length root at front end clamping conveyor chain in real-time, calculation result sent back feedback. Then, STM32 microcontroller used by expanding contracting electric putter experimental results presented show that detection time 30.4 ms, average accuracy 99.1%, space occupied model deployment 11.4 MB, suits design real-time system. Moreover, excavated roots shorter than before modification, represents lower energy consumption rate impurities harvesting, modified automatically controlled, reducing workload.