Details
Original language | English |
---|---|
Pages (from-to) | 301-319 |
Number of pages | 19 |
Journal | ISPRS Journal of Photogrammetry and Remote Sensing |
Volume | 169 |
Early online date | 8 Oct 2020 |
Publication status | Published - Nov 2020 |
Abstract
With increasing urbanization, in recent years there has been a growing interest and need in monitoring and analyzing urban flood events. Social media, as a new data source, can provide real-time information for flood monitoring. The social media posts with locations are often referred to as Volunteered Geographic Information (VGI), which can reveal the spatial pattern of such events. Since more images are shared on social media than ever before, recent research focused on the extraction of flood-related posts by analyzing images in addition to texts. Apart from merely classifying posts as flood relevant or not, more detailed information, e.g. the flood severity, can also be extracted based on image interpretation. However, it has been less tackled and has not yet been applied for flood severity mapping. In this paper, we propose a novel three-step process to extract and map flood severity information. First, flood relevant images are retrieved with the help of pre-trained convolutional neural networks as feature extractors. Second, the images containing people are further classified into four severity levels by observing the relationship between body parts and their partial inundation, i.e. images are classified according to the water level with respect to different body parts, namely ankle, knee, hip, and chest. Lastly, locations of the Tweets are used for generating a map of estimated flood extent and severity. This process was applied to an image dataset collected during Hurricane Harvey in 2017, as a proof of concept. The results show that VGI can be used as a supplement to remote sensing observations for flood extent mapping and is beneficial, especially for urban areas, where the infrastructure is often occluding water. Based on the extracted water level information, an integrated overview of flood severity can be provided for the early stages of emergency response.
Keywords
- Crowdsourcing, Deep convolutional neural networks, Flood severity mapping, Hurricane Harvey, Social media, Volunteered geographic information
ASJC Scopus subject areas
- Physics and Astronomy(all)
- Atomic and Molecular Physics, and Optics
- Engineering(all)
- Engineering (miscellaneous)
- Computer Science(all)
- Computer Science Applications
- Earth and Planetary Sciences(all)
- Computers in Earth Sciences
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 169, 11.2020, p. 301-319.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Flood severity mapping from Volunteered Geographic Information by interpreting water level from images containing people
T2 - A case study of Hurricane Harvey
AU - Feng, Yu
AU - Brenner, Claus
AU - Sester, Monika
N1 - Funding Information: The authors would like to acknowledge the support from the BMBF funded research project “TransMiT – Resource-optimized transformation of combined and separate drainage systems in existing quarters with high population pressure” (BMBF, 033W105A) and “EVUS – Real-Time Prediction of Pluvial Floods and Induced Water Contamination in Urban Areas” (BMBF, 03G0846A). We also gratefully acknowledge the support of NVIDIA Corporation with the donation of a GeForce Titan X GPU used for this research.
PY - 2020/11
Y1 - 2020/11
N2 - With increasing urbanization, in recent years there has been a growing interest and need in monitoring and analyzing urban flood events. Social media, as a new data source, can provide real-time information for flood monitoring. The social media posts with locations are often referred to as Volunteered Geographic Information (VGI), which can reveal the spatial pattern of such events. Since more images are shared on social media than ever before, recent research focused on the extraction of flood-related posts by analyzing images in addition to texts. Apart from merely classifying posts as flood relevant or not, more detailed information, e.g. the flood severity, can also be extracted based on image interpretation. However, it has been less tackled and has not yet been applied for flood severity mapping. In this paper, we propose a novel three-step process to extract and map flood severity information. First, flood relevant images are retrieved with the help of pre-trained convolutional neural networks as feature extractors. Second, the images containing people are further classified into four severity levels by observing the relationship between body parts and their partial inundation, i.e. images are classified according to the water level with respect to different body parts, namely ankle, knee, hip, and chest. Lastly, locations of the Tweets are used for generating a map of estimated flood extent and severity. This process was applied to an image dataset collected during Hurricane Harvey in 2017, as a proof of concept. The results show that VGI can be used as a supplement to remote sensing observations for flood extent mapping and is beneficial, especially for urban areas, where the infrastructure is often occluding water. Based on the extracted water level information, an integrated overview of flood severity can be provided for the early stages of emergency response.
AB - With increasing urbanization, in recent years there has been a growing interest and need in monitoring and analyzing urban flood events. Social media, as a new data source, can provide real-time information for flood monitoring. The social media posts with locations are often referred to as Volunteered Geographic Information (VGI), which can reveal the spatial pattern of such events. Since more images are shared on social media than ever before, recent research focused on the extraction of flood-related posts by analyzing images in addition to texts. Apart from merely classifying posts as flood relevant or not, more detailed information, e.g. the flood severity, can also be extracted based on image interpretation. However, it has been less tackled and has not yet been applied for flood severity mapping. In this paper, we propose a novel three-step process to extract and map flood severity information. First, flood relevant images are retrieved with the help of pre-trained convolutional neural networks as feature extractors. Second, the images containing people are further classified into four severity levels by observing the relationship between body parts and their partial inundation, i.e. images are classified according to the water level with respect to different body parts, namely ankle, knee, hip, and chest. Lastly, locations of the Tweets are used for generating a map of estimated flood extent and severity. This process was applied to an image dataset collected during Hurricane Harvey in 2017, as a proof of concept. The results show that VGI can be used as a supplement to remote sensing observations for flood extent mapping and is beneficial, especially for urban areas, where the infrastructure is often occluding water. Based on the extracted water level information, an integrated overview of flood severity can be provided for the early stages of emergency response.
KW - Crowdsourcing
KW - Deep convolutional neural networks
KW - Flood severity mapping
KW - Hurricane Harvey
KW - Social media
KW - Volunteered geographic information
UR - http://www.scopus.com/inward/record.url?scp=85092314582&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2006.11802
DO - 10.48550/arXiv.2006.11802
M3 - Article
AN - SCOPUS:85092314582
VL - 169
SP - 301
EP - 319
JO - ISPRS Journal of Photogrammetry and Remote Sensing
JF - ISPRS Journal of Photogrammetry and Remote Sensing
SN - 0924-2716
ER -