Document Type
Article
Publication Date
2022
DOI
10.2298/CSIS210313058S
Publication Title
Computer Science and Information Systems
Volume
19
Issue
1
Pages
397-414
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.
Original Publication Citation
Sarp, S., Kuzlu, M., Zhao, Y., Cetin, M., & Guler, O. (2022). A comparison of deep learning algorithms on image data for detecting floodwater on roadways. Computer Science and Information Systems, 19(1), 397-414. https://doi.org/10.2298/CSIS210313058S
ORCID
0000-0002-8719-2353 (Kuzlu), 0000-0003-2003-9343 (Cetin)
Repository Citation
Salih, Sarp; Murat, Kuzlu; Yanxiao, Zhao; and Mecit, Cetin, "A Comparison of Deep Learning Algorithms on Image Data for Detecting Floodwater on Roadways" (2022). Engineering Technology Faculty Publications. 155.
https://digitalcommons.odu.edu/engtech_fac_pubs/155
Included in
Artificial Intelligence and Robotics Commons, Hydrology Commons, Theory and Algorithms Commons, Transportation Commons
Comments
"Computer Science and Information Systems allows authors to deposit author's post-print (accepted version) and publisher's version/PDF in an institutional repository and non-commercial subject-based repositories, such as arXiv or to publish it on an author's personal website (including social networking sites, such as ResearchGate, Academia.edu, etc.) and/or departmental website, at any time after publication. Full bibliographic information (authors, article title, journal title, volume, issue, pages) about the original publication must be provided and a link must be made to the article's DOI."