Exploiting ConvNet diversity for flooding identification

Research output: Journal contributionsJournal articlesResearchpeer-review

Authors

  • Keiller Nogueira
  • Samuel G. Fadel
  • Icaro C. Dourado
  • Rafael O. De Werneck
  • Javier A.V. Munoz
  • Otavio A.B. Penatti
  • Rodrigo T. Calumby
  • Lin Tzy Li
  • Jefersson A. Dos Santos
  • Ricardo Da S. Torres

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.

Original languageEnglish
Article number8398414
JournalIEEE Geoscience and Remote Sensing Letters
Volume15
Issue number9
Pages (from-to)1446-1450
Number of pages5
ISSN1545-598X
DOIs
Publication statusPublished - 09.2018

    Research areas

  • Flooding identification, inundation, MediaEval, natural disaster, remote sensing, satellites

Recently viewed

Publications

  1. How Much Home Office is Ideal? A Multi-Perspective Algorithm
  2. Phosphorus uptake from struvite is modulated by the nitrogen form applied
  3. How can problems be turned into something good? The role of entrepreneurial learning and error mastery orientation
  4. Scaling-based Least Squares Methods with Implemented Kalman filter Approach for Nano-Parameters Identification
  5. Understanding Low-Code Evolution, Adoption and Ecosystem for Software Development
  6. Reducing mean tardiness in a flexible job shop containing AGVs with optimized combinations of sequencing and routing rules
  7. Artificial intelligence in songwriting and composing - perspectives and challenges in creative practices
  8. Errors in Training Computer Skills
  9. Learning and Re-learning from net- based cooperative learning discourses
  10. Combining flatness based feedforward action with a fractional PI regulator to control the intake valve engine
  11. Offline question answering over linked data using limited resources
  12. Learning in the "Third Space"
  13. Schooling, local knowledge and working memory
  14. Unraveling Privacy Concerns in Complex Data Ecosystems with Architectural Thinking
  15. Using Daily Stretching to Counteract Performance Decreases as a Result of Reduced Physical Activity—A Controlled Trial
  16. Fusion of knowledge bases for better navigation of wheeled mobile robotic group with 3D TVS
  17. Reciprocal Relationships Between Dispositional Optimism and Work Experiences
  18. Teachers’ temporary support and worked-out examples as elements of scaffolding in mathematical modeling
  19. Introduction
  20. Application of feedforward artificial neural network in Muskingum flood routing
  21. Who can nudge for sustainable development? How nudge source renders dynamic norms (in-)effective in eliciting sustainable behavior
  22. Toward a methodical framework for comprehensively assessing forest multifunctionality
  23. Comparative study on the dehydrogenation properties of TiCl4-doped LiAlH4 using different doping techniques
  24. The Low-Code Phenomenon: Mapping the Intellectual Structure of Research
  25. Understanding Partnering Strategies in the Low-Code Platform Ecosystem
  26. Analyzing Talk and Text II: Thematic Analysis
  27. Discourse pragmatics
  28. Robustness of coherent sets computations
  29. The role of learning strategies for performance in mathematics courses for engineers
  30. Model and Validation of the Electromagnetic Interference Produced by Power Transmission Lines in Robotic Systems