A Comparison of Deep Learning Algorithms on Image Data for Detecting Floodwater on Roadways

Salih Sarp1, Murat Kuzlu2, Yanxiao Zhao1, Mecit Cetin2 and Ozgur Guler3

  1. College of Engineering, Virginia Commonwealth University
    Richmond, USA
    {sarps, yzhao7}@vcu.edu
  2. Batten College of Engineering & Technology, Old Dominion University
    Norfolk, VA, USA
    {mkuzlu, mcetin}@odu.edu
  3. eKare, Inc.
    Fairfax, VA, USA
    oguler@ekare.ai

Abstract

Object detection and segmentation algorithms evolved significantly in the last decade. Simultaneous object detection and segmentation paved the way for real-time applications such as autonomous driving. Detection and segmentation of (partially) flooded roadways are essential inputs for vehicle routing and traffic management systems. This paper proposes an automatic floodwater detection and segmentation method utilizing the Mask Region-Based Convolutional Neural Networks (Mask-R-CNN) and Generative Adversarial Networks (GAN) algorithms. To train the model, manually labeled images with urban, suburban, and natural settings are used. The performances of the algorithms are assessed in accurately detecting the floodwater captured in images. The results show that the proposed Mask-R-CNN-based floodwater detection and segmentation outperform previous studies, whereas the GAN-based model has a straightforward implementation compared to other models.

Key words

Floodwater detection; Mask-R-CNN; GAN; object detection and segmentation

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS210313058S

Publication information

Volume 19, Issue 1 (January 2022)
Year of Publication: 2022
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Sarp, S., Kuzlu, M., Zhao, Y., Cetin, M., Guler, O.: A Comparison of Deep Learning Algorithms on Image Data for Detecting Floodwater on Roadways. Computer Science and Information Systems, Vol. 19, No. 1, 397-414. (2022), https://doi.org/10.2298/CSIS210313058S