In this work, deep learning is employed for accurate and fast detection of vine trunks in vineyard images. More specifically, six well-known object detectors, Faster regions-convolutional neural network (Faster R-CNN), You Only Look Once version 3 (YOLOv3) and version 5 (YOLOv5), EfficientDet-D0, RetinaNet and MobilNet, are tested for real-time vine trunk detection. The models are trained with an in-house dataset designed for the needs of this study, containing 1927 manually annotated vine trunks in 899 different images. Comparative results indicate EfficientDet-D0 as the configuration that allows the faster and most accurate vine trunk detection, achieving Intersection over Union (IU) of 71% and overall Average Precision of 77.9% in 38 ms. The high precision combined with the fast runtime performance, indicate EfficientDet-D0 detector as the most suitable to be integrated into an autonomous harvesting robot for real-time vine trunk detection.
E. Badeka, T. Kalampokas, E. Vrochidou, K. Tziridis, G. A. Papakostas, T. P. Pachidis, V. G. Kaburlasos, “Vision-based vineyard trunk detection and its integration into a grapes harvesting robot”, International Journal of Mechanical Engineering and Robotics Research (IJMERR), vol. 10, no. 7, pp. 374-385, July 2021.