Aiming at the difficulty in locating the picking points of table grapes in the natural environment, this paper proposed a Yolov5-CBAM-Fourth Detection Layer-Decoupled (Yolov5-CFD) network based on Yolov5 to realize grape and stem recognition. Meanwhile, the fast localization of the picking point was realized using a geometric method. First, to enhance the feature extraction ability of the Backbone module, it was improved by integrating the Convolutional Block Attention Module (CBAM) attention mechanism. Second, aiming at the problem that a small target was difficult to detect, the fourth layer of detection was added to the Neck module. In addition, the paper improved the Head module of Yolov5 by borrowing from Decoupled structure in Yolox, which optimized the classification and regression performance of the network. Further, a geometric method was used to quickly and accurately locate the picking points of table grapes. In order to verify the effectiveness of the proposed network model, about 10,000 grape images were used for training. The results showed that the detection precision, recall, mAP_0.5 and mAP_0.5:0.95 of the Yolov5s-CFD model were 0.857, 0.804, 0.855, 0.642, respectivaly. And the detection precision, recall, mAP_0.5 and mAP_0.5:0.95 of the Yolov5m-CFD model were 0.986, 0.987, 0.993 and 0.910, respectivaly. In addition, the success rate of picking point localization was compared with the corresponding network structure. The results showed that the success rate of picking point positioning of the Yolov5s-CFD model was increased by 11.53% compared with the initial Yolov5s, and the success rate of the Yolov5m-CFD model was increased by 5.84% compared with the initial Yolov5. Although the recognition time of the improved Yolov5 model is increased compared to the initial Yolov5 model, it is still acceptable. It can fully meet the requirements of mechanized picking of table grapes and provide a theoretical basis for mechanized picking of table grapes.

针对自然环境下鲜食葡萄采摘点定位困难的问题，提出了一种基于Yolov5的Yolov5-CBAM-第四检测层解耦（Yolov5-CFD）网络实现葡萄和茎的识别。同时，利用几何方法实现了拾取点的快速定位。首先，为了增强Backbone模块的特征提取能力，通过集成卷积块注意模块（CBAM）注意机制对其进行了改进。其次，针对小目标难以检测的问题，在Neck模块中增加了第四层检测。此外，论文借鉴Yolox中的Decoupled结构改进了Yolov5的Head模块，优化了网络的分类和回归性能。更远，利用几何方法快速准确地定位鲜食葡萄的采摘点。为了验证所提出的网络模型的有效性，使用了大约 10,000 张葡萄图像进行训练。结果表明，Yolov5s-CFD模型的检测精度、召回率、mAP_0.5和mAP_0.5:0.95分别为0.857、0.804、0.855、0.642。Yolov5m-CFD模型的检测精度、召回率、mAP_0.5和mAP_0.5:0.95分别为0.986、0.987、0.993和0.910。此外，将采摘点定位的成功率与相应的网络结构进行了比较。结果表明，Yolov5s-CFD模型的拾取点定位成功率较初期的Yolov5s提高了11.53%，Yolov5m-CFD模型的成功率提高了5%。与最初的 Yolov5 相比提高了 84%。虽然改进后的 Yolov5 模型的识别时间比初始 Yolov5 模型有所增加，但仍然可以接受。充分满足鲜食葡萄机械化采摘要求，为鲜食葡萄机械化采摘提供理论依据。