hefy/pyro-sdis

Pyro-SDIS是一个专为使用AI模型进行野火烟雾检测而设计的数据集。该数据集由Pyronear协会与法国消防和救援服务（SDIS）合作开发，包含来自Pyronear摄像头安装的图像，这些图像由Pyronear志愿者精心注释。数据集包含33,636张图像，其中28,103张带有烟雾标记，31,975个烟雾实例。数据集的结构包括图像路径、注释（YOLO格式的边界框）、元数据（如合作伙伴、相机标识、日期等）以及训练和验证集的分割。数据集格式与Ultralytics YOLO框架兼容，便于高效训练目标检测模型。Pyro-SDIS is a dataset designed for wildfire smoke detection using AI models. It is developed in collaboration with the Fire and Rescue Services (SDIS) in France and the dedicated volunteers of the Pyronear association. The dataset contains images from Pyronear cameras, carefully annotated by Pyronear volunteers. It includes 33,636 images, with 28,103 images containing smoke and 31,975 smoke instances. The dataset is structured with image paths, annotations (YOLO-format bounding boxes), metadata (such as partner, camera identifier, date), and splits for training and validation sets. The dataset is formatted to be compatible with the Ultralytics YOLO framework, enabling efficient training of object detection models.