基于改进YOLOv8n-pose的巨峰葡萄采摘定位方法

打开文本图片集

中图分类号：TP391.4;S663.1 文献标志码：A 文章编号：1001-411X（2026）01-0118-10

Abstract： 【Objective】To accurately and eficiently localize the picking position of Kyoho grapes so as to effectively reduce fruit damage. 【Method】 A grape picking localization method based on improved YOLOv8n-pose was proposed. Firstly， the improved YOLOv8n-pose was utilized to detect keypoints of the grape stem and the vulnerable grapes at the top.Based on the coordinates of these keypoints，a characteristic vector representing the upper boundary pose of the grapes was constructed. This vector was then used to calculate the optimal picking angle.Finally， the optimal picking position was determined through the synergy of the picking point and picking angle. 【Result】 Experimental results showed that the precision （P） ， recall （R） mAP @0.50 and mAl of the improved YOLOv8n-pose increased by 1.7， 0.7， 0.9 and 1.7 percentage points respectively compared to the original model，and increased by 0.4， 0.1， 0.6 and 2.7 percentage points respectively compared to YOLOvl2s-pose.Meanwhile， the number of model parameters was reduced by 5.8% compared to YOLOv8n-pose. The successful localization rate using the proposed method reached 90.8% ，which was an improvement of9.2 percentage points over methods thatdidnotuse the picking angle. 【Conclusion】This study provides a low-damage picking localization method for Kyoho grape harvesting robots.

Key words：Kyoho grape; YOLOv8-pose; Keypoint detection; Picking localization; Picking angle

巨峰葡萄是中国鲜食葡萄市场中的主要品种，目前仍依赖人工采摘，在农业劳动力短缺的背景下[1-3]，采收成本持续增加。（剩余12650字）