RF-DETR目标检测与YOLOv12对比研究：基于Transformer与CNN架构在复杂果园环境下针对单类及多类青果检测的标签模糊性分析

RF-DETR Object Detection vs YOLOv12 : A Study of Transformer-based and CNN-based Architectures for Single-Class and Multi-Class Greenfruit Detection in Complex Orchard Environments Under Label Ambiguity

April 17, 2025

作者: Ranjan Sapkota, Rahul Harsha Cheppally, Ajay Sharda, Manoj Karkee

cs.AI

摘要

本研究对RF-DETR目标检测基础模型与YOLOv12目标检测模型在复杂果园环境下的绿果检测性能进行了详细对比，该环境以标签模糊、遮挡及背景融合为特征。为此，开发了一个包含单类别（绿果）和多类别（遮挡与非遮挡绿果）标注的自定义数据集，以评估模型在动态现实条件下的表现。RF-DETR模型采用DINOv2骨干网络及可变形注意力机制，在全局上下文建模方面表现卓越，能有效识别部分遮挡或模糊的绿果。相比之下，YOLOv12利用基于CNN的注意力机制强化局部特征提取，优化了计算效率，更适合边缘部署。在单类别检测中，RF-DETR以0.9464的平均精度（mAP50）位居榜首，证明了其在杂乱场景中定位绿果的卓越能力。尽管YOLOv12N在mAP@50:95上以0.7620领先，RF-DETR在复杂空间场景中持续表现更优。多类别检测方面，RF-DETR以mAP@50为0.8298领先，展现了其区分遮挡与非遮挡果实的能力，而YOLOv12L在mAP@50:95上以0.6622最高，表明其在详细遮挡情境下的分类优势。训练动态分析显示，RF-DETR收敛迅速，特别是在单类别设置下，仅需10个epoch即达到稳定，展示了基于Transformer架构在适应动态视觉数据上的高效性。这些发现验证了RF-DETR在精准农业应用中的有效性，而YOLOv12则适用于快速响应场景。关键词：RF-DETR目标检测，YOLOv12，YOLOv13，YOLOv14，YOLOv15，YOLOE，YOLO World，YOLO，You Only Look Once，Roboflow，检测Transformer，卷积神经网络（CNNs）

English

This study conducts a detailed comparison of RF-DETR object detection base model and YOLOv12 object detection model configurations for detecting greenfruits in a complex orchard environment marked by label ambiguity, occlusions, and background blending. A custom dataset was developed featuring both single-class (greenfruit) and multi-class (occluded and non-occluded greenfruits) annotations to assess model performance under dynamic real-world conditions. RF-DETR object detection model, utilizing a DINOv2 backbone and deformable attention, excelled in global context modeling, effectively identifying partially occluded or ambiguous greenfruits. In contrast, YOLOv12 leveraged CNN-based attention for enhanced local feature extraction, optimizing it for computational efficiency and edge deployment. RF-DETR achieved the highest mean Average Precision (mAP50) of 0.9464 in single-class detection, proving its superior ability to localize greenfruits in cluttered scenes. Although YOLOv12N recorded the highest mAP@50:95 of 0.7620, RF-DETR consistently outperformed in complex spatial scenarios. For multi-class detection, RF-DETR led with an mAP@50 of 0.8298, showing its capability to differentiate between occluded and non-occluded fruits, while YOLOv12L scored highest in mAP@50:95 with 0.6622, indicating better classification in detailed occlusion contexts. Training dynamics analysis highlighted RF-DETR's swift convergence, particularly in single-class settings where it plateaued within 10 epochs, demonstrating the efficiency of transformer-based architectures in adapting to dynamic visual data. These findings validate RF-DETR's effectiveness for precision agricultural applications, with YOLOv12 suited for fast-response scenarios. >Index Terms: RF-DETR object detection, YOLOv12, YOLOv13, YOLOv14, YOLOv15, YOLOE, YOLO World, YOLO, You Only Look Once, Roboflow, Detection Transformers, CNNs