Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Unconstrained Flood Event Detection Using Adversarial Data Augmentation

Abstract: 

Nowadays, the world faces extreme climate changes, resulting in an increase of natural disaster events and their severities. In these conditions, the necessity of disaster information management systems has become more imperative. Specifically, in this paper, the problem of flood event detection from images with real-world conditions is addressed. That is, the images may be taken in several conditions, including day, night, blurry, clear, foggy, rainy, different lighting conditions, etc. All these abnormal scenarios significantly reduce the performance of the learning algorithms. In addition, many existing image classification methods use datasets that usually include high-resolution images without considering real-world noise. In this paper, we propose a new image classification framework based on adversarial data augmentation and deep learning algorithms to address the aforementioned problems. We validate the performance of the flood event detection framework on a real-world noisy visual dataset collected from social networks.

up
0 users have voted:

Paper Details

Authors:
Samira Pouyanfar, Yudong Tao, Saad Sadiq, Haiman Tian, Yuexuan Tu, Tianyi Wang, Shu-Ching Chen, Mei-Ling Shyu
Submitted On:
18 September 2019 - 10:55am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Yudong Tao
Paper Code:
MA.L6.2
Document Year:
2019
Cite

Document Files

ICIP2019_slides_final.pptx

(48)

Subscribe

[1] Samira Pouyanfar, Yudong Tao, Saad Sadiq, Haiman Tian, Yuexuan Tu, Tianyi Wang, Shu-Ching Chen, Mei-Ling Shyu, "Unconstrained Flood Event Detection Using Adversarial Data Augmentation", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4681. Accessed: Jun. 06, 2020.
@article{4681-19,
url = {http://sigport.org/4681},
author = {Samira Pouyanfar; Yudong Tao; Saad Sadiq; Haiman Tian; Yuexuan Tu; Tianyi Wang; Shu-Ching Chen; Mei-Ling Shyu },
publisher = {IEEE SigPort},
title = {Unconstrained Flood Event Detection Using Adversarial Data Augmentation},
year = {2019} }
TY - EJOUR
T1 - Unconstrained Flood Event Detection Using Adversarial Data Augmentation
AU - Samira Pouyanfar; Yudong Tao; Saad Sadiq; Haiman Tian; Yuexuan Tu; Tianyi Wang; Shu-Ching Chen; Mei-Ling Shyu
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4681
ER -
Samira Pouyanfar, Yudong Tao, Saad Sadiq, Haiman Tian, Yuexuan Tu, Tianyi Wang, Shu-Ching Chen, Mei-Ling Shyu. (2019). Unconstrained Flood Event Detection Using Adversarial Data Augmentation. IEEE SigPort. http://sigport.org/4681
Samira Pouyanfar, Yudong Tao, Saad Sadiq, Haiman Tian, Yuexuan Tu, Tianyi Wang, Shu-Ching Chen, Mei-Ling Shyu, 2019. Unconstrained Flood Event Detection Using Adversarial Data Augmentation. Available at: http://sigport.org/4681.
Samira Pouyanfar, Yudong Tao, Saad Sadiq, Haiman Tian, Yuexuan Tu, Tianyi Wang, Shu-Ching Chen, Mei-Ling Shyu. (2019). "Unconstrained Flood Event Detection Using Adversarial Data Augmentation." Web.
1. Samira Pouyanfar, Yudong Tao, Saad Sadiq, Haiman Tian, Yuexuan Tu, Tianyi Wang, Shu-Ching Chen, Mei-Ling Shyu. Unconstrained Flood Event Detection Using Adversarial Data Augmentation [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4681