GreyWolfLSM: an accurate oil spill detection method based on level set method from synthetic aperture radar imagery

Aghaei, Nastaran; Akbarizadeh, Gholamreza; Kosarian, Abdolnabi

doi:10.1080/22797254.2022.2037468

Cited by 45 publications

(14 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…𝐷 ℎ = 0.1 * (𝑈 𝑤 /8.5) 2 /24 (7) 𝐷 ℎ is the horizontal dispersion coefficient which governs the spread of oil over the time [32] given by Equation (7). Beyond certain period say more than 24 hours, it is likely that dispersion will reduce.…”

Section: Proposed Methodology For Oil Spillmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Oil Spill Trajectory on the Ocean Surface Using Mathematical Modeling

Dhavalikar¹,

Choudhari²

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

A simplistic mathematical model based on the law of motion, for predicting oil spill trajectory on the ocean surface utilizing random walk technique is proposed in this paper. Validation of the proposed model is performed by comparing results with the General NOAA Operational Modeling Environment (GNOME) model and the available set of periodic Sentinel -1 Synthetic Aperture Radar (SAR) images of the contingency location (Corsica oil spill incident in the Mediterranean Sea). SAR images are processed for speckle noise removal, dark spot detection, feature extraction and classification of dark spots as oil spills and look-alikes for suitability of comparison. The accuracy of prediction is evaluated using Centroid Skill Score (CSS) metric and is compared with that of the prediction results from MEDSLIK -II model. The results of proposed model are found to be in good agreement with available SAR images. The simulation also showed that using an hourly wind and ocean current data on the study region, more accurate prediction of the trajectory is possible.

show abstract

Section: Proposed Methodology For Oil Spillmentioning

confidence: 99%

“…which is beyond the present scope of work. Equation (7) for horizontal oil dispersion coefficient (𝐷 ℎ ) is considered from literature [32]. From Equation (7) it can be noted that 𝐷 ℎ is of the order of 5e-5 to 5e-3 for the wind velocity of 1 to 10 m/s.…”

Section: Effect Of Dispersion Coefficientmentioning

confidence: 99%

Prediction of Oil Spill Trajectory on the Ocean Surface Using Mathematical Modeling

Dhavalikar¹,

Choudhari²

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…YNTHETIC aperture radar (SAR) is widely used for ocean ship monitoring. Classic methods extract features using expert experience to search for ships [1], [2], e.g., constant false alarm rate (CFAR) [3] and template-based matching [4]. Modern methods use convolutional neural networks (CNNs) [5], [6] to extract features with less human involvement, receiving more attention in SAR community.…”

Section: Introductionmentioning

confidence: 99%

A Mask Attention Interaction and Scale Enhancement Network for SAR Ship Instance Segmentation

Zhang

2022

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

Most of existing synthetic aperture radar (SAR) ship instance segmentation models do not achieve mask interaction or offer limited interaction performance. Besides, their multi-scale ship instance segmentation performance is moderate especially for small ships. To solve these problems, we propose a mask attention interaction and scale enhancement network (MAI-SE-Net) for SAR ship instance segmentation. MAI uses an atrous spatial pyramid pooling (ASPP) to gain multi-resolution feature responses, a non-local block (NLB) to model long-range spatial dependencies, and a concatenation shuffle attention block (CSAB) to improve interaction benefits. SE uses a content-aware reassembly of features block (CARAFEB) to generate an extra pyramid bottom-level to boost small ship performance, a feature balance operation (FBO) to improve scale feature description, and a global context block (GCB) to refine features. Experimental results on two public SSDD and HRSID datasets reveal that MAI-SE-Net outperforms the other nine competitive models, better than the suboptimal model by 4.7% detection AP and 3.4% segmentation AP on SSDD and by 3.0% detection AP and 2.4% segmentation AP on HRSID.

show abstract

“…Therefore, the application of a radar system in detecting sea surface targets plays an important role and is of significance. 4 It is found after extensive studies that, when a radar sensor is used to detect sea surface targets, two different radar systems are involved: the synthetic aperture radar (SAR) system and the pulse Doppler (PD) radar system. 5 For the SAR system, the ability of surface moving target detection benefits from its high resolution, and the operation of clutter suppression is not necessitated in the vast majority of cases.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, it is not affected by different weather conditions and can work day and night. Therefore, the application of a radar system in detecting sea surface targets plays an important role and is of significance 4 . It is found after extensive studies that, when a radar sensor is used to detect sea surface targets, two different radar systems are involved: the synthetic aperture radar (SAR) system and the pulse Doppler (PD) radar system 5 …”

Section: Introductionmentioning

confidence: 99%

Scheme to implement moving target detection of coastal defense radar in complicated sea conditions

Hou

Zhang

et al. 2022

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

.Although the data on a particular complicated sea conditions are available, it is difficult to collect the data on various complicated sea conditions simultaneously. When the sea conditions change, the test results of the detection network based on the data of simple sea conditions may be unacceptable. It is proposed that the VGG16, pix2pixHD, and cycleGAN methods should be applied to establish related datasets of different complicated sea conditions. After the unified image quality assessment indicators are determined, it is found that the images generated by the VGG16 network are most in line with the subsequent target detection standards. The real images of complicated sea conditions have the smallest root-mean-square error, the largest peak signal-to-noise ratio, and the best regression coefficient (R2). Meanwhile, the improved Faster R-CNN is introduced for target detection of small sample datasets. First, the ResNet50_FPN module, as the backbone feature extractor, is used to improve the detection performance of small-sized objects. Moreover, because there are many small target objects to be detected, the ROI Align module is preferred, for it is more accurate. Finally, the Softer-NMS algorithm is selected to significantly improve the positioning accuracy through confidence estimation. Compared with some previous Faster R-CNN methods, the accuracy and missed detection rate of the proposed method outperform other networks, with a mean average precision of 85.11%.

show abstract

GreyWolfLSM: an accurate oil spill detection method based on level set method from synthetic aperture radar imagery

Cited by 45 publications

References 44 publications

Prediction of Oil Spill Trajectory on the Ocean Surface Using Mathematical Modeling

Prediction of Oil Spill Trajectory on the Ocean Surface Using Mathematical Modeling

A Mask Attention Interaction and Scale Enhancement Network for SAR Ship Instance Segmentation

Scheme to implement moving target detection of coastal defense radar in complicated sea conditions

Contact Info

Product

Resources

About