Graph-Based Early-Fusion for Flood Detection

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

  • Rafael O. De Werneck
  • Icaro C. Dourado
  • Samuel G. Fadel
  • Salvatore Tabbone
  • Ricardo Da S. Torres

Flooding is one of the most harmful natural disasters, as it poses danger to both buildings and human lives. Therefore, it is fundamental to monitor these disasters to define prevention strategies and help authorities in damage control. With the wide use of portable devices (e.g., smartphones), there is an increase of the documentation and communication of flood events in social media. However, the use of these data in monitoring systems is not straightforward and depends on the creation of effective recognition strategies. In this paper, we propose a fusion-based recognition system for detecting flooding events in images extracted from social media. We propose two new graph-based early-fusion methods, which consider multiple descriptions and modalities to generate an effective image representation. Our results demonstrate that the proposed methods yield better results than a traditional early-fusion method and a specialized deep neural network fusion solution.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
Number of pages5
PublisherIEEE - Institute of Electrical and Electronics Engineers Inc.
Publication date29.08.2018
Pages1048-1052
Article number8451011
ISBN (print)978-1-4799-7062-9
ISBN (electronic)9781479970612
DOIs
Publication statusPublished - 29.08.2018
Externally publishedYes
Event25th IEEE International Conference on Image Processing - ICIP 2018 - Athens, Greece
Duration: 07.10.201810.10.2018
Conference number: 25
https://2018.ieeeicip.org/default.asp

    Research areas

  • Early fusion, Flood detection, Graph-based fusion, Image representation, MediaEval

Recently viewed

Publications

  1. On the utility of indirect methods for detecting faking
  2. Effects of linguistic demands of reality-based mathematical tasks
  3. Obstacle Coordinates Transformation from TVS Body-Frame to AGV Navigation-Frame
  4. Spectral Early-Warning Signals for Sudden Changes in Time-Dependent Flow Patterns
  5. Effectiveness of the world network of biosphere reserves in maintaining forest ecosystem functions
  6. Understanding european union law
  7. Frame Diffusion and Institutional Choice in Regional Economic Cooperation
  8. Sozialkybernetik in statu nascendi
  9. Learning from Indigenous Populations and Local Communities
  10. Einführung in das Buch
  11. Zootechnologies
  12. Groupware und Workflow- Konzepte und Systemvergleich
  13. Sufficiency as relations of enoughness
  14. Teaching Provenance to AI
  15. Challenges in calculating two-year college student transfer rates to four-year colleges
  16. Variational pragmatics
  17. Why husbands matter
  18. Sex differences in mental rotation strategy
  19. Slowing resource loops in the clothing industry through Circular Business Model Experimentation
  20. Building capacities for transformative change towards sustainability
  21. Analphabetismus
  22. Toward a modular evaluation approach of real-world laboratories
  23. Multi-level Governance, Policy Implementation and Participation
  24. The potential impacts of insecticides on the life-history traits of bees and the consequences for pollination
  25. Do Online Training offer an effective Option for the Prevention and Health Promotion of Professionals? A systematic Overview and Meta-analysis
  26. Study of intrinsic and extrinsic size effects on shear bands in metallic glasses
  27. Maritime strategies of rising powers
  28. A new approach to semantic sustainability assessment
  29. Substanz, Körper und Affekte
  30. Akteure, Berater und Beobachter, oder: wie kommt Strategie in die Politik?
  31. An Imperfect Union?