用YOLO在边缘设备实现实时标注，大幅缩短农业数据集准备时间
Real-Time On-the-Go Annotation Framework Using YOLO for Automated Dataset Generation
- 将YOLO部署在边缘设备上，采集图像时即时完成标注
- 预训练+单类标注使模型收敛更快、性能更稳定
- 适合需要快速决策的农业场景，降低人工标注成本
在农业等实时决策场景中，高效准确地标注数据集仍是部署目标检测模型（如YOLO）的关键挑战。传统方法依赖大量事后人工标注，耗时费力。本文提出一种基于边缘设备部署YOLO的实时标注框架，可在图像采集过程中即时完成标注。为全面评估系统性能，我们对比了三种主流YOLO架构（YOLOv5、YOLOv8、YOLOv12）在不同配置下的表现：单类与多类标注、预训练与从零训练。分析涵盖详细统计检验与学习动态，结果表明预训练及单类标注配置在模型收敛速度、性能和鲁棒性方面具有显著优势。实验验证了该框架在大幅缩短数据集准备时间的同时，仍能保持高标注质量。
原文摘要 · Abstract (English)
Efficient and accurate annotation of datasets remains a significant challenge for deploying object detection models such as You Only Look Once (YOLO) in real-world applications, particularly in agriculture where rapid decision-making is critical. Traditional annotation techniques are labor-intensive, requiring extensive manual labeling post data collection. This paper presents a novel real-time annotation approach leveraging YOLO models deployed on edge devices, enabling immediate labeling during image capture. To comprehensively evaluate the efficiency and accuracy of our proposed system, we conducted an extensive comparative analysis using three prominent YOLO architectures (YOLOv5, YOLOv8, YOLOv12) under various configurations: single-class versus multi-class annotation and pretrained versus scratch-based training. Our analysis includes detailed statistical tests and learning dynamics, demonstrating significant advantages of pretrained and single-class configurations in terms of model convergence, performance, and robustness. Results strongly validate the feasibility and effectiveness of our real-time annotation framework, highlighting its capability to drastically reduce dataset preparation time while maintaining high annotation quality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。