Authors

Abstract

Accurate detection of apple stems is crucial for robotic cutting. This study proposed an improved YOLOv8-stem method for apple stem detection in overhead imagery under occlusion conditions. First, several im-provements were made to the YOLOv8 neural network: the conventional convolutional process within the in-termediate neck layer was substituted with the AK Convolution mechanism, a small object detection head was added, and ResBlock+CBAM attention mechanism was incorporated. Second, stem occlusion was determined by analyzing the positional relationship between the detected bounding boxes of stems and apples. The exper-imental results showed that compared to the original YOLOv8, this method improved apple stem detection ac-curacy by 6.0% (from 79.9% to 85.9%) and increased harvesting completeness from 84.2% to 93.2%.

Abstract in Chinese

准确检测苹果茎对于机器人切割至关重要。本研究提出了一种改进的YOLOv8茎检测方法，用于遮挡条件下俯视图像中的苹果茎检测。首先，对YOLOv8神经网络进行了几项改进：用AK卷积机制取代了中间颈层内的传统卷积过程，增加了一个小目标检测头，并引入了ResBlock+CBAM注意力机制。其次，通过分析检测到的茎和苹果边界框之间的位置关系来确定茎的遮挡。实验结果表明，与原始YOLOv8相比，该方法将苹果茎检测准确率提高了6.0%（从79.9%提高到85.9%），收获完整性从84.2%提高到93.2%。