Real-Time On-the-Go Annotation Framework Using YOLO for Automated Dataset Generation
This addresses the problem of rapid dataset generation for real-world applications like agriculture, but it is incremental as it applies existing YOLO methods to a new annotation context.
The paper tackles the challenge of labor-intensive dataset annotation for object detection in agriculture by proposing a real-time annotation framework using YOLO models on edge devices, which reduces dataset preparation time while maintaining high quality.
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.