AIIA_wildfire Dataset

The AIIA_wildfire dataset is a collection of 2,237 natural disaster images designed for semantic segmentation, focusing on burnt areas, smoke, and fire. It aggregates and standardizes images from three distinct sources: the BLAZE classification dataset (a subset of which we annotated), KAHY trials, and RAS. The dataset is organized by source (BLAZE1, KAHY, RAS), each with standard train/val splits containing .jpg images and corresponding .png label masks. Labels follow a four-class hierarchy (0: background, 1: burnt, 2: smoke, 3: fire). The final composition is 985 images from BLAZE (https://aiia.csd.auth.gr/blaze-fire-classification-segmentation-dataset/) (655 annotated), 584 from KAHY, and 668 from RAS, split into 1,528 training and 655 validation images almost a 70 – 30% split. Details on acquiring the dataset can be found here.AIIA_wildfire数据集是专为语义分割任务打造的2237幅自然灾害图像数据集，聚焦于过火区域、烟雾与火焰三类目标。该数据集整合并标准化了三个不同来源的图像数据：分别为BLAZE分类数据集（我们对其子集进行了人工标注）、KAHY试验数据集以及RAS数据集。数据集按照来源划分为BLAZE1、KAHY、RAS三个子数据集，每个子数据集均配备标准的训练/验证划分集，包含.jpg格式的原始图像与对应的.png格式标签掩码。标签采用四级分类体系：0代表背景，1代表过火区域，2代表烟雾，3代表火焰。数据集最终构成如下：985幅图像来自BLAZE数据集（https://aiia.csd.auth.gr/blaze-fire-classification-segmentation-dataset/，其中655幅为标注样本），584幅来自KAHY数据集，668幅来自RAS数据集；总计包含1528幅训练图像与655幅验证图像，划分比例接近7:3。有关该数据集的获取详情可参阅此处。