Mediaeval2019: Flood detection in time sequence satellite images

Pallavi Jain; Bianca Schoen-Phelan; Robert Ross

doi:10.21427/pj3n-kr08

Mediaeval2019: Flood detection in time sequence satellite images

Pallavi Jain, Bianca Schoen-Phelan, Robert Ross

Research output: Contribution to journal › Conference article › peer-review

Abstract

In this work, we present a flood detection technique from time series satellite images for the City-centered satellite sequences (CCSS) task in the MediaEval 2019 competition [1]. This work utilises a three channel feature indexing technique [13] along with a VGG16 pre-trained model for automatic detection of floods. We also compared our result with RGB images and a modified NDWI technique by Mishra et al, 2015 [15]. The result shows that the three channel feature indexing technique performed the best with VGG16 and is a promising approach to detect floods from time series satellite images.

Original language	English
Journal	CEUR Workshop Proceedings
Volume	2670
DOIs	https://doi.org/10.21427/pj3n-kr08
Publication status	Published - 2019
Event	2019 Working Notes of the MediaEval Workshop, MediaEval 2019 - Sophia Antipolis, France Duration: 27 Oct 2019 → 30 Oct 2019

Keywords

flood detection
time series satellite images
City-centered satellite sequences
three channel feature indexing technique
VGG16 pretrained model
automatic detection of floods
RGB images
modified NDWI technique

Access to Document

10.21427/pj3n-kr08Licence: CC BY

Cite this

@article{57adebeb19d14b5ea6ce272b78243cb6,

title = "Mediaeval2019: Flood detection in time sequence satellite images",

abstract = "In this work, we present a flood detection technique from time series satellite images for the City-centered satellite sequences (CCSS) task in the MediaEval 2019 competition [1]. This work utilises a three channel feature indexing technique [13] along with a VGG16 pre-trained model for automatic detection of floods. We also compared our result with RGB images and a modified NDWI technique by Mishra et al, 2015 [15]. The result shows that the three channel feature indexing technique performed the best with VGG16 and is a promising approach to detect floods from time series satellite images.",

keywords = "flood detection, time series satellite images, City-centered satellite sequences, three channel feature indexing technique, VGG16 pretrained model, automatic detection of floods, RGB images, modified NDWI technique",

author = "Pallavi Jain and Bianca Schoen-Phelan and Robert Ross",

note = "Publisher Copyright: {\textcopyright} 2019 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).; 2019 Working Notes of the MediaEval Workshop, MediaEval 2019 ; Conference date: 27-10-2019 Through 30-10-2019",

year = "2019",

doi = "10.21427/pj3n-kr08",

language = "English",

volume = "2670",

journal = "CEUR Workshop Proceedings",

issn = "1613-0073",

publisher = "CEUR-WS",

}

TY - JOUR

T1 - Mediaeval2019

T2 - 2019 Working Notes of the MediaEval Workshop, MediaEval 2019

AU - Jain, Pallavi

AU - Schoen-Phelan, Bianca

AU - Ross, Robert

PY - 2019

Y1 - 2019

N2 - In this work, we present a flood detection technique from time series satellite images for the City-centered satellite sequences (CCSS) task in the MediaEval 2019 competition [1]. This work utilises a three channel feature indexing technique [13] along with a VGG16 pre-trained model for automatic detection of floods. We also compared our result with RGB images and a modified NDWI technique by Mishra et al, 2015 [15]. The result shows that the three channel feature indexing technique performed the best with VGG16 and is a promising approach to detect floods from time series satellite images.

AB - In this work, we present a flood detection technique from time series satellite images for the City-centered satellite sequences (CCSS) task in the MediaEval 2019 competition [1]. This work utilises a three channel feature indexing technique [13] along with a VGG16 pre-trained model for automatic detection of floods. We also compared our result with RGB images and a modified NDWI technique by Mishra et al, 2015 [15]. The result shows that the three channel feature indexing technique performed the best with VGG16 and is a promising approach to detect floods from time series satellite images.

KW - flood detection

KW - time series satellite images

KW - City-centered satellite sequences

KW - three channel feature indexing technique

KW - VGG16 pretrained model

KW - automatic detection of floods

KW - RGB images

KW - modified NDWI technique

UR - https://www.scopus.com/pages/publications/85091553149

U2 - 10.21427/pj3n-kr08

DO - 10.21427/pj3n-kr08

M3 - Conference article

AN - SCOPUS:85091553149

SN - 1613-0073

VL - 2670

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

Y2 - 27 October 2019 through 30 October 2019

ER -

Mediaeval2019: Flood detection in time sequence satellite images

Abstract

Keywords

Access to Document

Fingerprint

Cite this