5-fold cross-validation comparison results.

Sugarcane stem node detection is critical for monitoring sugarcane growth, enabling precision cutting, reducing spuriousness, and improving breeding for resistance to downfall. However, in complex field environments, sugarcane stem nodes often suffer from reduced detection accuracy due to background interference and shadowing effects. For this reason, this paper proposes an improved sugarcane stem node detection model based on YOLO11. This study incorporates the ASF-YOLO (Attentional Scale Sequence Fusion based You Only Look Once) mechanism to enhance the feature fusion layer of YOLO11. Additionally, a high-resolution detection layer, P2, is integrated into the fusion module to improve the model’s ability to detect small objects—particularly sugarcane stem nodes—and to better handle multi-scale feature representations. Secondly, to better align with the P2 small-object detection layer, this paper adopts a shared convolutional detection head named LSDECD (Lightweight Shared Detail-Enhanced Convolutional Detection Head), which can better deal with small target detection while reducing the number of model parameters through parameter sharing and detail-enhanced convolution. Using soft-NMS (non-maximum suppression) to replace the original NMS and combining with Shape-IoU, a bounding box regression method that focuses on the shape and scale of the bounding box itself, makes the bounding box regression more accurate, and solves the problem of the impact of detection caused by occlusion and illumination. Finally, to address the increased complexity introduced by the addition of the P2 detection layer and the replacement of the detection head, channel pruning is applied to the model, effectively reducing its overall complexity and parameter count. The experimental results show that the model before pruning has 96.1% and 53.2% mean average precision mAP50 and mAP50:95, respectively, which are 11.9% and 11.1% higher than the original YOLO11n, and the model after pruning also has 10.8% and 9.3% higher than the original YOLO11n, respectively, and the number of parameters is reduced to 279,778, and model size is reduced to 1.3MB. The computational cost decreased from 11.6 GFlops to 6.6 GFlops.

甘蔗茎节检测对于甘蔗生长监测、实现精准切割、降低误检率以及选育抗倒伏品种至关重要。然而在复杂田间环境中，甘蔗茎节常因背景干扰与阴影影响，导致检测精度下降。为此，本文提出一种基于YOLO11的改进型甘蔗茎节检测模型。本研究引入ASF-YOLO（Attentional Scale Sequence Fusion based You Only Look Once，基于注意力尺度序列融合的You Only Look Once）机制，以增强YOLO11的特征融合层。此外，在融合模块中集成高分辨率检测层P2，以提升模型对小目标（尤其是甘蔗茎节）的检测能力，更好地处理多尺度特征表征。其次，为适配新增的P2小目标检测层，本文采用名为LSDECD（Lightweight Shared Detail-Enhanced Convolutional Detection Head，轻量级共享细节增强卷积检测头）的共享卷积检测头，该检测头可通过参数共享与细节增强卷积，在处理小目标检测任务的同时降低模型参数量。使用soft-NMS（non-maximum suppression，非极大值抑制）替换原有的NMS，并结合聚焦于边界框自身形状与尺度的边界框回归方法Shape-IoU，可使边界框回归更为精准，同时解决遮挡与光照对检测结果的影响问题。最后，针对新增P2检测层与替换检测头所带来的复杂度提升问题，本文对模型应用通道剪枝技术，有效降低了模型整体复杂度与参数量。实验结果表明，剪枝前的模型在mAP50与mAP50:95指标上分别达到96.1%与53.2%，较原始YOLO11n提升11.9%与11.1%；剪枝后的模型仍较原始YOLO11n分别提升10.8%与9.3%，且参数量降至279778，模型体积缩减至1.3MB，计算量从11.6 GFlops降至6.6 GFlops。