AFAS-YOLOv8

This repository presents a YOLO annotated dataset of high voltage structures that could potentially cause false alarms in a context related to wildfire detection. The presented dataset, consisting of 1,477 thermal and near-infrared images representing different scenarios, including aerial and ground views, aims to establish a valuable reference for future research in this field based on well-established metric results. Attached to this repository is the dataset created and used during the work. If you wish to use the code sample to replicate our work, please use the link found in the 'Related links' section, which leads directly to the official GitHub of the paper.本仓库发布了一套面向野火检测场景、易引发误报警的高压电力结构YOLO（You Only Look Once）标注数据集。 本数据集包含1477幅热红外与近红外图像，涵盖航拍与地面拍摄等多种场景，旨在基于经过充分验证的量化指标结果，为该领域的后续研究提供极具参考价值的基准参考。 本仓库附带了本研究中创建并使用的数据集。若您希望通过代码示例复现我们的研究工作，请使用「相关链接」板块中的链接，该链接将直接跳转至本论文的官方GitHub仓库。

搜集汇总

背景与挑战

背景概述

AFAS-YOLOv8是一个专门用于野火检测中减少误报的YOLO标注数据集，包含1,923张热成像和近红外图像，涵盖空中和地面视角，适用于深度学习和工程研究。数据集由西班牙研究机构资助，文件大小为133 MB，旨在为相关领域提供基准参考。