Dataset for: Fire detection algorithm for complex warehouse scenarios based on YOLOv11n

This is a self-built fire detection dataset containing 19,898 images and corresponding YOLO-format annotations. It is specifically designed to address the challenges of complex warehouse backgrounds and small-scale incipient flames. The dataset is split into training, validation, and testing sets with a ratio of 7:1.5:1.5, including both flame images and non-flame interference images. This dataset is provided to support the findings of the research article: "Fire detection algorithm for complex warehouse scenarios based on YOLOv11n".