Hajorda/flameye-wildfire-detection

FlamEye是一个用于实时野火检测（火焰和烟雾）的数据集，主要来源于CCTV/监控摄像头。数据集经过合并、去重和增强处理，专门用于训练YOLOv8m模型进行早期火灾检测。数据集包含两个类别：fire（火焰）和smoke（烟雾），并提供了详细的统计信息、来源、处理流程、格式和使用方法。数据集分为训练集（约10,929张图像）、验证集（约3,000张图像）和测试集（约1,500张图像）。每个样本包含图像、图像ID、数据集分割、来源、标注信息（YOLO格式）、是否有火焰和是否有烟雾等字段。

FlamEye is a merged, deduplicated, and augmented dataset for real-time wildfire detection (fire and smoke) from CCTV/surveillance cameras. Built to train YOLOv8m for early-stage fire detection. The dataset contains two classes: fire and smoke, and provides detailed statistics, sources, processing pipeline, format, and usage instructions. The dataset is divided into train (~10,929 images), validation (~3,000 images), and test (~1,500 images) splits. Each example includes image, image_id, split, source, annotations (YOLO format), has_fire, and has_smoke fields.