Oil spill detection in SAR images based on improved mask R-CNN model

Jie Zhang; Bo Ai; Hengshuai Shang; Benshuai Li

doi:10.1117/12.3010303

15 November 2023 Oil spill detection in SAR images based on improved mask R-CNN model

Jie Zhang, Bo Ai, Hengshuai Shang, Benshuai Li

Proceedings Volume 12815, International Conference on Remote Sensing, Mapping, and Geographic Systems (RSMG 2023); 128150B (2023) https://doi.org/10.1117/12.3010303
Event: International Conference on Remote Sensing, Mapping, and Geographic Systems (RSMG 2023), 2023, Kaifeng, China

Abstract

With the aggravation of marine oil spill pollution, the safety of the marine ecosystem and the development of the marine industry are threatened. Synthetic aperture radar (SAR) has become an important tool for detecting oil spill pollution. In order to further improve the accuracy of oil spill detection, this paper adopts Mask R-CNN model for oil spill detection of SAR oil spill images and improves the non-maximum suppression algorithm. Through experimental validation, the SAR image oil spill detection method based on the improved Mask R-CNN model proposed in this paper successfully improved the S2AR oil spill detection precision rate, recall rate and F1 score, in which the oil spill detection accuracy reached 91.5%, an improvement of 9.1% compared with the traditional model. Therefore, the research in this paper has certain practical significance and value for improving the application and promotion of SAR images in marine oil spill detection.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Jie Zhang, Bo Ai, Hengshuai Shang, and Benshuai Li "Oil spill detection in SAR images based on improved mask R-CNN model", Proc. SPIE 12815, International Conference on Remote Sensing, Mapping, and Geographic Systems (RSMG 2023), 128150B (15 November 2023); https://doi.org/10.1117/12.3010303

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available