A Hybrid Quantum Optimization Framework for Oil Spill Detection Using Marine Radar.
Saved in:
| Title: | A Hybrid Quantum Optimization Framework for Oil Spill Detection Using Marine Radar. |
|---|---|
| Authors: | Dong, Haihui1,2 (AUTHOR), Loon, Siow Chee1,2 (AUTHOR), Xu, Jin2,3 (AUTHOR) jinxu@gdou.edu.cn, Wang, Haixia1,3 (AUTHOR) |
| Source: | Remote Sensing. Oct2026, Vol. 18 Issue 19, p3433. 29p. |
| Subjects: | Quantum computing, Optimization algorithms, Image processing, Thresholding algorithms, Oil spill management, Radar |
| Abstract: | Highlights: What are the main findings? A two-stage framework combining QGJO-GRNN for candidate extraction and QHHO for threshold optimization is proposed to overcome low contrast and noise in marine radar imagery. The proposed method has achieved good performance in oil spill detection of shipborne marine radar. What are the implications of the main findings? The proposed method has achieved good performance in oil spill detection of shipborne marine radar. The findings clarify that the practical gain mainly stems from ROI-guided cascade processing and scattering-prior-driven sample collection, while quantum encoding primarily improves convergence stability, offering guidance for future multi-scene validation and extension to more complex thresholding objectives. Oil spills at sea pose a serious threat to marine ecosystems and coastal economic development. Therefore, rapid and accurate detection of oil spills is crucial for emergency response and environmental protection. Marine radar offers unique advantages in short-range, continuous, and all-weather monitoring, making it an important supplementary tool for oil spill detection. However, oil film targets in marine radar images exhibit low contrast and a low signal-to-noise ratio, and are easily affected by factors such as clutter and co-frequency interference, making it difficult for traditional detection methods to achieve accurate extraction. To address these issues, this paper proposes a two-stage framework for oil spill detection utilizing marine radar, which consists of candidate region extraction using a QGJO-optimized feature-weighted GRNN and precise segmentation using QHHO-based threshold optimization. The methodology begins with candidate region extraction, wherein pixel-level multidimensional scattering features are designed and scattering priors are leveraged to automate sample collection without manual annotation. A feature-weighted generalized regression neural network (GRNN) is subsequently constructed, with its parameters and feature weights jointly optimized via the Quantum Golden Jackal Optimization (QGJO) algorithm, thereby enabling efficient delineation of oil-film candidate regions. The subsequent object detection stage then formulates oil slick extraction as a single-threshold binary classification problem, for which the Quantum Harris–Hawk Optimization (QHHO) algorithm is adopted to autonomously determine the optimal segmentation threshold. Finally, morphological post-processing is performed to suppress residual noise and produce precise, continuous oil film contours. Results verify that the proposed method effectively reconciles detection completeness with false-alarm control, constituting an efficient and deployable solution for shipborne radar-based oil spill monitoring. [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.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 197921067 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A Hybrid Quantum Optimization Framework for Oil Spill Detection Using Marine Radar. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Dong%2C+Haihui%22">Dong, Haihui</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Loon%2C+Siow+Chee%22">Loon, Siow Chee</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Xu%2C+Jin%22">Xu, Jin</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<i> jinxu@gdou.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Wang%2C+Haixia%22">Wang, Haixia</searchLink><relatesTo>1,3</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Oct2026, Vol. 18 Issue 19, p3433. 29p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Quantum+computing%22">Quantum computing</searchLink><br /><searchLink fieldCode="DE" term="%22Optimization+algorithms%22">Optimization algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Image+processing%22">Image processing</searchLink><br /><searchLink fieldCode="DE" term="%22Thresholding+algorithms%22">Thresholding algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Oil+spill+management%22">Oil spill management</searchLink><br /><searchLink fieldCode="DE" term="%22Radar%22">Radar</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Highlights: What are the main findings? A two-stage framework combining QGJO-GRNN for candidate extraction and QHHO for threshold optimization is proposed to overcome low contrast and noise in marine radar imagery. The proposed method has achieved good performance in oil spill detection of shipborne marine radar. What are the implications of the main findings? The proposed method has achieved good performance in oil spill detection of shipborne marine radar. The findings clarify that the practical gain mainly stems from ROI-guided cascade processing and scattering-prior-driven sample collection, while quantum encoding primarily improves convergence stability, offering guidance for future multi-scene validation and extension to more complex thresholding objectives. Oil spills at sea pose a serious threat to marine ecosystems and coastal economic development. Therefore, rapid and accurate detection of oil spills is crucial for emergency response and environmental protection. Marine radar offers unique advantages in short-range, continuous, and all-weather monitoring, making it an important supplementary tool for oil spill detection. However, oil film targets in marine radar images exhibit low contrast and a low signal-to-noise ratio, and are easily affected by factors such as clutter and co-frequency interference, making it difficult for traditional detection methods to achieve accurate extraction. To address these issues, this paper proposes a two-stage framework for oil spill detection utilizing marine radar, which consists of candidate region extraction using a QGJO-optimized feature-weighted GRNN and precise segmentation using QHHO-based threshold optimization. The methodology begins with candidate region extraction, wherein pixel-level multidimensional scattering features are designed and scattering priors are leveraged to automate sample collection without manual annotation. A feature-weighted generalized regression neural network (GRNN) is subsequently constructed, with its parameters and feature weights jointly optimized via the Quantum Golden Jackal Optimization (QGJO) algorithm, thereby enabling efficient delineation of oil-film candidate regions. The subsequent object detection stage then formulates oil slick extraction as a single-threshold binary classification problem, for which the Quantum Harris–Hawk Optimization (QHHO) algorithm is adopted to autonomously determine the optimal segmentation threshold. Finally, morphological post-processing is performed to suppress residual noise and produce precise, continuous oil film contours. Results verify that the proposed method effectively reconciles detection completeness with false-alarm control, constituting an efficient and deployable solution for shipborne radar-based oil spill monitoring. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>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.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=197921067 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/rs18193433 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 29 StartPage: 3433 Subjects: – SubjectFull: Quantum computing Type: general – SubjectFull: Optimization algorithms Type: general – SubjectFull: Image processing Type: general – SubjectFull: Thresholding algorithms Type: general – SubjectFull: Oil spill management Type: general – SubjectFull: Radar Type: general Titles: – TitleFull: A Hybrid Quantum Optimization Framework for Oil Spill Detection Using Marine Radar. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Dong, Haihui – PersonEntity: Name: NameFull: Loon, Siow Chee – PersonEntity: Name: NameFull: Xu, Jin – PersonEntity: Name: NameFull: Wang, Haixia IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 10 Text: Oct2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 20724292 Numbering: – Type: volume Value: 18 – Type: issue Value: 19 Titles: – TitleFull: Remote Sensing Type: main |
| ResultId | 1 |
