EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving Image Segmentation in Adverse Conditions for Coastal Infrastructure Monitoring

Pedro V. Rubinstein, Ricardo L. Kauer, Alexandre G. Cardeman, Marcelo Abelheira, Pedro Cruz, Rodrigo S. Couto, Luís Henrique M. K. Costa

Journal of Internet Services and Applications · 29.05.2026 · 17 (1) · 203-213

DOI: 10.5753/jisa.2026.6670 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Internet Services and Applications, online erschienen am 29.05.2026. Verfasst von Pedro V. Rubinstein und 6 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Smart cities increasingly rely on AI-driven solutions to improve citizen safety. In coastal regions such as Rio de Janeiro, Brazil, maritime risks present significant challenges, as exemplified by the collapse of the Tim Maia Bike lane. This paper proposes a method for monitoring the coastal infrastructure using a custom segmentation model based on YOLO, aiming to reduce the need for continuous human supervision. However, the external placement of cameras introduces lighting and weather-related challenges, which complicate accurate segmentation. To address these issues, we investigate how domain-specific data augmentation techniques affect model performance under adverse visual conditions. As a case study, we apply this method to develop a system for the Tim Maia Bike lane, with the improved models achieving 97.6% mAP50-95 throughout the day. Furthermore, we analyze the correlation between our system’s outputs and environmental measurements obtained from an ocean buoy. Our findings highlight the potential for integrating AI-based monitoring into broader urban risk management frameworks to provide real-time protection for coastal infrastructure.

Zitieren

APA

Rubinstein, P. V., Kauer, R. L., Cardeman, A. G., Abelheira, M., Cruz, P., Couto, R. S., & Costa, L. H. M. K. (2026). Improving Image Segmentation in Adverse Conditions for Coastal Infrastructure Monitoring. Journal of Internet Services and Applications, 17(1), 203-213. https://doi.org/10.5753/jisa.2026.6670

Vancouver

Rubinstein PV, Kauer RL, Cardeman AG, Abelheira M, Cruz P, Couto RS, et al. Improving Image Segmentation in Adverse Conditions for Coastal Infrastructure Monitoring. Journal of Internet Services and Applications. 2026;17(1):203-213. doi:10.5753/jisa.2026.6670

BibTeX
@article{Rubinstein2026,
  author = {Rubinstein, Pedro V. and Kauer, Ricardo L. and Cardeman, Alexandre G. and Abelheira, Marcelo and Cruz, Pedro and Couto, Rodrigo S. and Costa, Luís Henrique M. K.},
  title = {Improving Image Segmentation in Adverse Conditions for Coastal Infrastructure Monitoring},
  journal = {Journal of Internet Services and Applications},
  year = {2026},
  volume = {17},
  number = {1},
  pages = {203--213},
  doi = {10.5753/jisa.2026.6670}
}
Kostenlos starten →