Exploiting ConvNet diversity for flooding identification

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Exploiting ConvNet diversity for flooding identification. / Nogueira, Keiller; Fadel, Samuel G.; Dourado, Icaro C. et al.
In: IEEE Geoscience and Remote Sensing Letters, Vol. 15, No. 9, 8398414, 09.2018, p. 1446-1450.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

Nogueira, K, Fadel, SG, Dourado, IC, De Werneck, RO, Munoz, JAV, Penatti, OAB, Calumby, RT, Li, LT, Dos Santos, JA & Torres, RDS 2018, 'Exploiting ConvNet diversity for flooding identification', IEEE Geoscience and Remote Sensing Letters, vol. 15, no. 9, 8398414, pp. 1446-1450. https://doi.org/10.1109/LGRS.2018.2845549

APA

Nogueira, K., Fadel, S. G., Dourado, I. C., De Werneck, R. O., Munoz, J. A. V., Penatti, O. A. B., Calumby, R. T., Li, L. T., Dos Santos, J. A., & Torres, R. D. S. (2018). Exploiting ConvNet diversity for flooding identification. IEEE Geoscience and Remote Sensing Letters, 15(9), 1446-1450. Article 8398414. https://doi.org/10.1109/LGRS.2018.2845549

Vancouver

Nogueira K, Fadel SG, Dourado IC, De Werneck RO, Munoz JAV, Penatti OAB et al. Exploiting ConvNet diversity for flooding identification. IEEE Geoscience and Remote Sensing Letters. 2018 Sept;15(9):1446-1450. 8398414. doi: 10.1109/LGRS.2018.2845549

Bibtex

@article{9c11545c66d646f5a1bde2a92e230aa9,
title = "Exploiting ConvNet diversity for flooding identification",
abstract = "Flooding is the world's most costly type of natural disaster in terms of both economic losses and human causalities. A first and essential procedure toward flood monitoring is based on identifying the area most vulnerable to flooding, which gives authorities relevant regions to focus. In this letter, we propose several methods to perform flooding identification in high-resolution remote sensing images using deep learning. Specifically, some proposed techniques are based upon unique networks, such as dilated and deconvolutional ones, whereas others were conceived to exploit diversity of distinct networks in order to extract the maximum performance of each classifier. The evaluation of the proposed methods was conducted in a high-resolution remote sensing data set. Results show that the proposed algorithms outperformed the state-of-the-art baselines, providing improvements ranging from 1% to 4% in terms of the Jaccard Index.",
keywords = "Flooding identification, inundation, MediaEval, natural disaster, remote sensing, satellites",
author = "Keiller Nogueira and Fadel, {Samuel G.} and Dourado, {Icaro C.} and {De Werneck}, {Rafael O.} and Munoz, {Javier A.V.} and Penatti, {Otavio A.B.} and Calumby, {Rodrigo T.} and Li, {Lin Tzy} and {Dos Santos}, {Jefersson A.} and Torres, {Ricardo Da S.}",
year = "2018",
month = sep,
doi = "10.1109/LGRS.2018.2845549",
language = "English",
volume = "15",
pages = "1446--1450",
journal = "IEEE Geoscience and Remote Sensing Letters",
issn = "1545-598X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "9",

}

RIS

TY - JOUR

T1 - Exploiting ConvNet diversity for flooding identification

AU - Nogueira, Keiller

AU - Fadel, Samuel G.

AU - Dourado, Icaro C.

AU - De Werneck, Rafael O.

AU - Munoz, Javier A.V.

AU - Penatti, Otavio A.B.

AU - Calumby, Rodrigo T.

AU - Li, Lin Tzy

AU - Dos Santos, Jefersson A.

AU - Torres, Ricardo Da S.

PY - 2018/9

Y1 - 2018/9

N2 - Flooding is the world's most costly type of natural disaster in terms of both economic losses and human causalities. A first and essential procedure toward flood monitoring is based on identifying the area most vulnerable to flooding, which gives authorities relevant regions to focus. In this letter, we propose several methods to perform flooding identification in high-resolution remote sensing images using deep learning. Specifically, some proposed techniques are based upon unique networks, such as dilated and deconvolutional ones, whereas others were conceived to exploit diversity of distinct networks in order to extract the maximum performance of each classifier. The evaluation of the proposed methods was conducted in a high-resolution remote sensing data set. Results show that the proposed algorithms outperformed the state-of-the-art baselines, providing improvements ranging from 1% to 4% in terms of the Jaccard Index.

AB - Flooding is the world's most costly type of natural disaster in terms of both economic losses and human causalities. A first and essential procedure toward flood monitoring is based on identifying the area most vulnerable to flooding, which gives authorities relevant regions to focus. In this letter, we propose several methods to perform flooding identification in high-resolution remote sensing images using deep learning. Specifically, some proposed techniques are based upon unique networks, such as dilated and deconvolutional ones, whereas others were conceived to exploit diversity of distinct networks in order to extract the maximum performance of each classifier. The evaluation of the proposed methods was conducted in a high-resolution remote sensing data set. Results show that the proposed algorithms outperformed the state-of-the-art baselines, providing improvements ranging from 1% to 4% in terms of the Jaccard Index.

KW - Flooding identification

KW - inundation

KW - MediaEval

KW - natural disaster

KW - remote sensing

KW - satellites

UR - http://www.scopus.com/inward/record.url?scp=85049144059&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/dec1b188-ebdf-3d82-8861-5c42b1b14e77/

U2 - 10.1109/LGRS.2018.2845549

DO - 10.1109/LGRS.2018.2845549

M3 - Journal articles

AN - SCOPUS:85049144059

VL - 15

SP - 1446

EP - 1450

JO - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

SN - 1545-598X

IS - 9

M1 - 8398414

ER -

Recently viewed

Publications

  1. Special issue on Variational Pragmatics
  2. Finite element modeling of laser beam welding for residual stress calculation
  3. An improved method for the analysis of volatile polyfluorinated alkyl substances in environmental air samples
  4. Extension of SEIR compartmental models for constructive Lyapunov control of COVID-19 and analysis in terms of practical stability
  5. In situ synchrotron diffraction of the solidification of Mg4Y3Nd
  6. Sustainability-oriented technology exploration: managerial values, ambidextrous design, and separation drift
  7. What do people do when they use the internet?
  8. Towards a theory of ethnic identity and migration
  9. Next generation wireless energy aware sensors for internet of things
  10. Study of the solidification of AS alloys combining in situ synchrotron diffraction and differential scanning calorimetry
  11. Comparative effectiveness of guided internet-based stress management training versus established in-person group training in employees – study protocol for a pragmatic, randomized, non-inferiority trial
  12. Bifurcation loads of beams of glued-laminated timber with intermediate lateral supports
  13. Solution for the direct kinematics problem of the general stewart-gough platform by using only linear actuators’ orientations
  14. The interaction of precipitation and deformation in a binary Mg-Ca alloy at elevated temperatures
  15. Exploring the Capacity of Water Framework Directive Indices to Assess Ecosystem Services in Fluvial and Riparian Systems
  16. The effectiveness of nudging
  17. Non-target Analysis and Chemometric Evaluation of a Passive Sampler Monitoring of Small Streams
  18. What’s Hot: Machine Learning for the Quantified Self
  19. Study on Mg–Si–Sr ternary alloys for biomedical applications
  20. Determinants of fair own wage perceptions
  21. Learning Analytics an Hochschulen
  22. Human development and the "explosion" of democracy
  23. A Theory-Based Concept for Fostering Sustainability Competencies in Engineering Programs