A SLIC-KMeans-GJO Method for Oil Spill Detection in Marine Radar Image.
Saved in:
| Title: | A SLIC-KMeans-GJO Method for Oil Spill Detection in Marine Radar Image. |
|---|---|
| Authors: | Xu, Jin1,2,3 (AUTHOR), Sun, Mengxin1,2,3 (AUTHOR), Dong, Haihui1,2,3 (AUTHOR) donghh@gdou.edu.cn, Guo, Zekun1,2,3,4 (AUTHOR), Deng, Yutong1,2,3,5 (AUTHOR), Chen, Binghui1,2,3 (AUTHOR), Tu, Gaorui1,2,3 (AUTHOR), Yan, Minghao1,2,3 (AUTHOR), Qian, Lihui4 (AUTHOR), Wu, Peng5 (AUTHOR) |
| Source: | Remote Sensing. Apr2026, Vol. 18 Issue 7, p1096. 23p. |
| Subjects: | K-means clustering, Optimization algorithms, Image segmentation, Signal denoising, Oil spill management, Online monitoring systems |
| Abstract: | Highlights: What are the main findings? A novel lightweight SLIC-based ROI extraction method is proposed, which effectively suppresses noise and preserves fine edges for oil slicks in X-band radar images. An improved Golden Jackal Optimizer (GJO) segmentation strategy is developed to achieve adaptive initialization and enhanced optimization via Levy flight and stochastic perturbation. What are the implications of the main findings? The method provides a more reliable and cleaner ROI for oil slick monitoring, forming a superior preprocessing step for subsequent analysis. The strategy enables more precise and robust segmentation of oil film targets, significantly reducing false detections in automated maritime monitoring systems. Oil slicks pose a severe threat to marine ecosystems, making accurate and real-time detection increasingly urgent. Marine X-band radar has become an essential tool for oil slick monitoring due to its high temporal resolution and its ability to sensitively capture the damping of capillary waves on the sea surface caused by oil films. Building upon this, an unsupervised and lightweight SLIC-KMeans-GJO detection framework is proposed. The method first generates superpixels by using Simple Linear Iterative Clustering (SLIC) and then applies K-means clustering to extract region of interest (ROI). An improved Golden Jackal Optimizer (GJO) is adaptively initialized based on the grayscale distribution and information entropy. To enhance optimization performance, Lévy flight and stochastic perturbation mechanisms are incorporated to improve global exploration and local convergence precision. Experimental results demonstrate that the proposed method significantly outperforms conventional thresholding approaches and other intelligent optimization-based segmentation algorithms in terms of noise suppression, target identification accuracy, and discrimination precision for oil slick targets. It effectively mitigates over-segmentation and false detections while preserving fine edge details and the true spatial extent of oil slicks. The proposed framework offers a novel and practical solution for real-time oil slick monitoring, holding strong potential for operational maritime emergency response. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? A novel lightweight SLIC-based ROI extraction method is proposed, which effectively suppresses noise and preserves fine edges for oil slicks in X-band radar images. An improved Golden Jackal Optimizer (GJO) segmentation strategy is developed to achieve adaptive initialization and enhanced optimization via Levy flight and stochastic perturbation. What are the implications of the main findings? The method provides a more reliable and cleaner ROI for oil slick monitoring, forming a superior preprocessing step for subsequent analysis. The strategy enables more precise and robust segmentation of oil film targets, significantly reducing false detections in automated maritime monitoring systems. Oil slicks pose a severe threat to marine ecosystems, making accurate and real-time detection increasingly urgent. Marine X-band radar has become an essential tool for oil slick monitoring due to its high temporal resolution and its ability to sensitively capture the damping of capillary waves on the sea surface caused by oil films. Building upon this, an unsupervised and lightweight SLIC-KMeans-GJO detection framework is proposed. The method first generates superpixels by using Simple Linear Iterative Clustering (SLIC) and then applies K-means clustering to extract region of interest (ROI). An improved Golden Jackal Optimizer (GJO) is adaptively initialized based on the grayscale distribution and information entropy. To enhance optimization performance, Lévy flight and stochastic perturbation mechanisms are incorporated to improve global exploration and local convergence precision. Experimental results demonstrate that the proposed method significantly outperforms conventional thresholding approaches and other intelligent optimization-based segmentation algorithms in terms of noise suppression, target identification accuracy, and discrimination precision for oil slick targets. It effectively mitigates over-segmentation and false detections while preserving fine edge details and the true spatial extent of oil slicks. The proposed framework offers a novel and practical solution for real-time oil slick monitoring, holding strong potential for operational maritime emergency response. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18071096 |
