Flood Level Prediction via Human Pose Estimation from Social Media Images

Author(s)

• Khanh-An C. Quan, Vietnam National UniversityFollow
• Vinh-Tiep Nguyen, Vietnam National UniversityFollow
• Tan-Cong Nguyen, Vietnam National UniversityFollow
• Tam V. Nguyen, University of DaytonFollow

Document Type

Conference Paper

Publication Date

6-1-2020

Publication Source

ICMR '20: Proceedings of the 2020 International Conference on Multimedia Retrieval

Abstract

Floods are the most common natural and among the most dangerous disasters in the world. It is important to get up-to-date information about flooding and the flood level for flood preparation and prevention. In this paper, we propose an efficient method to determine the flood level from daily activity photos on social media. Our method is based on the idea of matching the water level with human pose to determine the level of severity of flooding. Extensive experiments conducted on the dataset of Multimodal Flood Level Estimation show the superiority of our proposed method. We achieve the first rank in MediaEval 2019 and this demonstrates the potential applications of our method to analyze flood information.

Inclusive pages

479–485

ISBN/ISSN

9781450370875

Publisher

Association for Computing Machinery

Keywords

Flood Prediction, Human Pose Estimation, Social Media

eCommons Citation

Quan, Khanh-An C.; Nguyen, Vinh-Tiep; Nguyen, Tan-Cong; and Nguyen, Tam V., "Flood Level Prediction via Human Pose Estimation from Social Media Images" (2020). Computer Science Faculty Publications. 211.
https://ecommons.udayton.edu/cps_fac_pub/211