基于社交媒体图片的地震灾情检测语义分割数据集  

A dataset of semantic segmentation in earthquake disaster detection based on social media images

作　　者：王晓东[1] 杨腾飞 徐誉宁 明梦如 王含 李连欣 许建楼 张冀[1] 张平[1] 王海军 WANG Xiaodong;YANG Tengfei;XU YuNin;MING Mengru;WANG Han;LI Lianxin;XU Jianlou;ZHANG Ji;ZHANG Ping;WANG Haijun(Henan University of Science and Technology,Luoyang 471000,P.R.China;Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,P.R.China;Shandong University of Science and Technology,Qingdao 266590,P.R.China;Luoyang Institute of Science and Technology,Luoyang 471000,P.R.China)

机构地区：[1]河南科技大学,河南洛阳471000 [2]中国科学院空天信息创新研究院,北京100094 [3]山东科技大学,山东青岛266590 [4]洛阳理工学院,河南洛阳471000

出　　处：《中国科学数据（中英文网络版）》2024年第3期395-404,共10页China Scientific Data

基　　金：国家对地观测科学数据中心开放基金项目(NODAOP2022004)。

摘　　要：以社交媒体为代表的志愿者地理数据已成为减灾重要数据源,尤其是其中包含的图片数据,具有很强的灾害态势感知力。但目前对于该数据服务减灾的应用并不多,其主要原因在于具有标注特征的可用图片训练集匮乏,使得包括机器学习、深度学习等技术手段很难发挥作用,从而限制了该类数据反馈灾情信息的能力。本文从实际应用的角度出发,以地震灾害为研究对象,结合包括数据获取、自动化去重、语义标注以及数据增强等方法制作了面向社交媒体图片的灾害语义分割数据集。本数据集主要由社交媒体搜集的原始图片和人工语义标注后的伪彩色图片组成,并采用多人轮番标注以及交叉检验保证数据质量。本数据集对于提高社交媒体数据使用效率以及增强减灾态势感知具有重要作用。Volunteer geographic data,especially from social media,has emerged as a crucial resource for disaster mitigation.Particularly the included imagery can enhance situational awareness during emergencies.However,current applications of this data for disaster relief are primarily limited by a scarcity of annotated images for training,which hinders the efficacy of techniques like machine learning and deep learning,consequently restricting the data's capacity to convey disaster information.Starting from the perspective of practical application,this paper focuses on earthquake disasters as the research subject.By integrating data acquisition,automatic deduplication,semantic annotation,and data augmentation methods,we developed a dataset of semantic segmentation in earthquake disaster detection based on social media images.This dataset mainly consists of original images collected from social media and pseudo-color images with manual semantic annotations.To ensure data quality,multiple annotators work in rotation and cross-check each other's work.This dataset plays a significant role in improving the efficiency of social media data usage and enhancing awareness of disaster reduction efforts.

关 键 词：社交媒体 图片 地震灾害 语义分割 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术] P315.9[天文地球—地震学]