EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Unsupervised Marine Radar Oil Spill Detection via an Autoencoder–IAEA Synergistic Framework

Ran Ji, Baozhu Jia, Zhiqiang Zhao, Jin Xu, Zekun Guo, Xingchen Luo, Yuanyuan Huang, Gaorui Tu

Remote Sensing · 28.10.2026 · 18 (21) · 3700

DOI: 10.3390/rs18213700 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 28.10.2026. Verfasst von Ran Ji und 7 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Basic and Applied Basic Research Foundation, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Marine oil spill accidents pose serious threats to marine ecosystems and coastal economic development. X-band marine radar provides an effective means for nearshore oil spill monitoring, yet accurate oil film segmentation remains challenging because of grayscale overlap between oil films and sea clutter, range-dependent echo attenuation, and noise interference. To address these challenges, an unsupervised oil spill detection method integrating HBA-AE ROI extraction with IAEA fine segmentation is proposed. In the coarse detection stage, an autoencoder (AE) maps pixel grayscale intensity, local mean, and local standard deviation into a compact two-dimensional latent space. The AE-derived latent representation is further optimized by HBA to enhance oil film–sea clutter separability, after which K-Means clustering identifies candidate oil spill ROIs. In the subsequent fine segmentation stage, the extracted ROI constrains the search domain, while the Improved Alpha Evolution Algorithm (IAEA) maximizes the three-class Otsu between-class variance to determine the optimal dual thresholds for oil film delineation. Experiments using X-band marine radar data collected during the Dalian 7·16 oil spill accident were conducted against seven representative methods. The proposed framework achieved a Precision of 97.20%, an F1-score of 86.60%, and an IoU of 76.40%, demonstrating superior oil film segmentation accuracy and effective false-alarm suppression under complex sea-clutter conditions. It also maintained a favorable balance between segmentation accuracy and computational efficiency, demonstrating its potential for marine oil spill monitoring under the investigated radar observation conditions.

Förderung

  • Guangdong Basic and Applied Basic Research Foundation
  • National Natural Science Foundation of China

Zitieren

APA

Ji, R., Jia, B., Zhao, Z., Xu, J., Guo, Z., Luo, X., Huang, Y., & Tu, G. (2026). Unsupervised Marine Radar Oil Spill Detection via an Autoencoder–IAEA Synergistic Framework. Remote Sensing, 18(21), 3700. https://doi.org/10.3390/rs18213700

Vancouver

Ji R, Jia B, Zhao Z, Xu J, Guo Z, Luo X, et al. Unsupervised Marine Radar Oil Spill Detection via an Autoencoder–IAEA Synergistic Framework. Remote Sensing. 2026;18(21):3700. doi:10.3390/rs18213700

BibTeX
@article{Ji2026,
  author = {Ji, Ran and Jia, Baozhu and Zhao, Zhiqiang and Xu, Jin and Guo, Zekun and Luo, Xingchen and Huang, Yuanyuan and Tu, Gaorui},
  title = {Unsupervised Marine Radar Oil Spill Detection via an Autoencoder–IAEA Synergistic Framework},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {21},
  pages = {3700},
  doi = {10.3390/rs18213700}
}
Kostenlos starten →