FishingROV/scallop_yolov5s_mosaic_640

该数据集是一个针对FishingROV边缘推理管道优化的衍生格式数据集，基于圣安德鲁斯大学King Scallop数据集创建。它主要用于对象检测任务，特别关注水下环境中的扇贝检测，使用了YOLO（特别是YOLOv5s）模型，并经过mosaic数据增强处理，图像尺寸为640x640。数据集规模在1,000到10,000个样本之间，适用于海洋生物学研究和远程操作车辆（ROV）应用。数据集遵循原始作品的Creative Commons Attribution 4.0 International (CC-BY 4.0)许可证。

This dataset is an optimized derivative format generated for the FishingROV edge inference pipeline, based on the University of St Andrews King Scallop dataset. It is designed for object detection tasks, specifically focusing on scallop detection in underwater environments, utilizing the YOLO (particularly YOLOv5s) model with mosaic data augmentation and an image size of 640x640. The dataset size ranges between 1,000 and 10,000 samples and is suitable for marine biology research and remotely operated vehicle (ROV) applications. It is released under the Creative Commons Attribution 4.0 International (CC-BY 4.0) license in accordance with the original work.