Even though mechanization has dramatically decreased labor requirements, vineyard management costs are still affected by selective operations such as winter pruning. Robotic solutions are becoming more common in agriculture, however, few studies have focused on grapevines. This work aims at fine-tuning and testing two different deep neural networks for: (i) detecting pruning regions (PRs), and (ii) performing organ segmentation of spur-pruned dormant grapevines. The Faster R-CNN network was fine-tuned using 1215 RGB images collected in different vineyards and annotated through bounding boxes. The network was tested on 232 RGB images, PRs were categorized by wood type (W), orientation (Or) and visibility (V), and performance metrics were calculated. PR detection was dramatically affected by visibility. Highest detection was associated with visible intermediate complex spurs in Merlot (0.97), while most represented coplanar simple spurs allowed a 74% detection rate. The Mask R-CNN network was trained for grapevine organs (GOs) segmentation by using 119 RGB images annotated by distinguishing 5 classes (cordon, arm, spur, cane and node). The network was tested on 60 RGB images of light pruned (LP), shoot-thinned (ST) and unthinned control (C) grapevines. Nodes were the best segmented GOs (0.88) and general recall was higher for ST (0.85) compared to C (0.80) confirming the role of canopy management in improving performances of hi-tech solutions based on artificial intelligence. The two fine-tuned and tested networks are part of a larger control framework that is under development for autonomous winter pruning of grapevines.

尽管机械化大大降低了劳动力需求，但葡萄园管理成本仍然受到冬季修剪等选择性操作的影响。机器人解决方案在农业中变得越来越普遍，但很少有研究关注葡萄树。这项工作旨在微调和测试两种不同的深度神经网络：（i）检测修剪区域（PR），以及（ii）对修剪后的休眠葡萄藤进行器官分割。Faster R-CNN 网络使用在不同葡萄园收集的 1215 张 RGB 图像进行微调，并通过边界框进行注释。该网络在 232 个 RGB 图像上进行了测试，PR 按木材类型 (W)、方向 (Or) 和可见性 (V) 进行分类，并计算了性能指标。PR 检测受到可见度的显着影响。最高检出率与梅洛中可见的中间复杂杂散相关（0.97），而大多数代表共面简单杂散的检出率达到 74%。Mask R-CNN 网络使用 119 张 RGB 图像进行葡萄器官 (GO) 分割训练，这些图像通过区分 5 个类别（警戒线、手臂、支刺、手杖和节点）进行注释。该网络在 60 张轻修剪 (LP)、疏枝 (ST) 和未疏枝对照 (C) 葡萄树的 RGB 图像上进行了测试。节点是最好的分段 GO (0.88)，与 C (0.80) 相比，ST (0.85) 的总体召回率更高，这证实了冠层管理在提高基于人工智能的高科技解决方案性能方面的作用。这两个经过微调和测试的网络是一个更大的控制框架的一部分，该框架正在开发中，用于葡萄树的自主冬季修剪。