期刊
MULTIMEDIA TOOLS AND APPLICATIONS
卷 79, 期 35-36, 页码 26197-26223出版社
SPRINGER
DOI: 10.1007/s11042-020-09196-8
关键词
Flood detection and severity estimation; Crowdsourced images; Image classification; Deep learning; Convolutional neural networks
类别
资金
- Fundacao para a Ciencia e Tecnologia (FCT) [PTDC/EEI-SCR/1743/2014, PTDC/CTA-OHR/29360/2017, PTDC/CCI-CIF/32607/2017]
- INESC-ID multi-annual funding from the PIDDAC programme [UIDB/50021/2020]
- NVIDIA Corporation
- Fundação para a Ciência e a Tecnologia [PTDC/CCI-CIF/32607/2017, PTDC/CTA-OHR/29360/2017, PTDC/EEI-SCR/1743/2014] Funding Source: FCT
The use of social media data in disaster and crisis management is increasing rapidly. Particularly in connection to flooding events, geo-referenced images shared by citizens can provide situational awareness to emergency responders, as well as assistance to financial loss assessment, giving information that would otherwise be very hard to collect through conventional sensors or remote sensing. Moreover, recent advances in computer vision and deep learning can perhaps support the automated analysis of these data. In this paper, focusing on ground-level images taken by humans during flooding events, we evaluate the use of deep convolutional neural networks for (a) discriminating images showing direct evidence of a flood, and (b) estimating the severity of the flooding event. Considering distinct datasets (i.e., the European Flood 2013 dataset, and data from different editions of the MediaEval Multimedia Satellite Task), we specifically evaluated models based on the DenseNet and EfficientNet neural network architectures, concluding that these classification models can achieve a very high accuracy on this task, thus having a clear potential to complement other sources of information (e.g., satellite imagery) related to flooding events.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据