火焰和烟雾图像数据集

IntroductionThe dataset consists of images of early fire and smoke dataset. Dataset consists of Early fire and smoke images captured using mobile phones in real-world scenario. Images were captured under a wide variety of lighting conditions (indoor and outdoor scenes), weather, etc. This dataset is well suited for Early Fire and Smoke detection. Dataset could be used for Fire and Smoke recognition, detection, early fire and smoke, anomaly detection etc. Dataset also consists of typical domestic scenes like garbage burning, paper-plastic burning, field crop burning, domestic cooking etc.Dataset FeaturesApprox. 7000+ unique imagesHD resolutionCaptured by 1000+ unique usersEarly Fire and smoke ImagesVarious lighting conditions like daylight, nightOutdoor and Indoor both imagesClassification and detection annotations availableMultiple category annotationsCOCO, PASCAL VOC and YOLO formats

引言
本数据集收录早期火灾与烟雾图像。数据集包含在真实场景下通过手机拍摄的早期火灾与烟雾图像，拍摄场景涵盖多样光照条件（室内与室外场景）、不同天气环境等，非常适用于早期火灾与烟雾检测任务，可应用于火灾与烟雾识别、检测、早期火灾与烟雾监测、异常检测等领域。数据集同时包含各类典型场景图像，如垃圾焚烧、纸塑焚烧、田间农作物焚烧、居家烹饪等。

数据集特征
- 约7000余张独特图像
- 高清分辨率
- 由1000余名不同用户拍摄
- 包含早期火灾与烟雾图像
- 涵盖多种光照条件，如日间、夜间
- 同时包含室外与室内图像
- 提供分类与检测标注
- 支持多类别标注
- 支持COCO、PASCAL VOC及YOLO标注格式

搜集汇总

背景与挑战

背景概述

该数据集是一个专注于早期火焰和烟雾检测的图像集合，包含约7000多张高清图像，由1000多名用户使用手机在真实世界场景中拍摄，覆盖室内外多种光照条件和天气。数据集适用于目标检测任务，提供COCO、PASCAL VOC和YOLO格式的注释，并包括垃圾燃烧等典型家庭场景，旨在支持火灾和烟雾的早期识别与异常检测。