Oil Spill Detection with Multiscale Conditional Adversarial Networks with Small-Data Training

Li, Yongqing; Lyu, Xinrong; Frery, Alejandro C.; Ren, Peng

doi:10.3390/rs13122378

Cited by 30 publications

(6 citation statements)

References 43 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ref. [53] addresses the problem of training an oil spill detection model with limited data by proposing a multi-scale conditional adversarial network (MCAN) comprised of adversarial networks at multiple scales. The multi-scale architecture comprehensively captures both global and local oil spill characteristics, while adversarial training enhances the model's representational power through generated data.…”

Section: Advancements In Deep Learning Technologiesmentioning

confidence: 99%

A Novel Multi-Scale Feature Map Fusion for Oil Spill Detection of SAR Remote Sensing

Li,

Yang,

Yang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

The efficient and timely identification of oil spill areas is crucial for ocean environmental protection. Synthetic aperture radar (SAR) is widely used in oil spill detection due to its all-weather monitoring capability. Meanwhile, existing deep learning-based oil spill detection methods mainly rely on the classical U-Net framework and have achieved impressive results. However, SAR images exhibit high noise, blurry boundaries, and irregular shapes of target areas, as well as speckles and shadows, which lead to the loss of performance in existing algorithms. In this paper, we propose a novel network architecture to achieve more precise segmentation of oil spill areas by reintroducing rich semantic contextual information before obtaining the final segmentation mask. Specifically, the proposed architecture can re-fuse feature maps from different levels at the decoder end. We design a multi-convolutional layer (MCL) module to extract basic feature information from SAR images, and a feature extraction module (FEM) module further extracts and fuses feature maps generated by the U-Net decoder at different levels. Through these operations, the network can learn rich global and local contextual information, enable sufficient interaction of feature information at different stages, enhance the model’s contextual awareness, and improve its ability to recognize complex textures and blurry boundaries, thereby enhancing the segmentation accuracy of SAR images. Compared to many U-Net based segmentation networks, our method shows promising results and achieves state-of-the-art performance on multiple evaluation metrics.

show abstract

Section: Advancements In Deep Learning Technologiesmentioning

confidence: 99%

A Novel Multi-Scale Feature Map Fusion for Oil Spill Detection of SAR Remote Sensing

Li,

Yang,

Yang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…[27] employs a random forest-like strategy, achieving superior classification accuracy without overfitting, even with much smaller training datasets than commonly studied in deep learning literature for image classification tasks. In [28], a multi-scale model was applied to detect oil spills on the sea surface, achieving accurate detection results with very few training samples. In [29], a training strategy involving mutual guidance was used to create a powerful hyperspectral image classification framework trained on a small dataset.…”

Section: Introductionmentioning

confidence: 99%

Stripe Extraction of Oceanic Internal Waves Using PCGAN with Small-Data Training

Duan,

Barintag,

Meng

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Playing a crucial role in ocean activities, internal solitary waves (ISWs) are of significant importance. Currently, the use of deep learning for detecting ISWs in synthetic aperture radar (SAR) imagery is gaining growing attention. However, these approaches often demand a considerable number of labeled images, which can be challenging to acquire in practice. In this study, we propose an innovative method employing a pyramidal conditional generative adversarial network (PCGAN). At each scale, it employs the framework of a conditional generative adversarial network (CGAN), comprising a generator and a discriminator. The generator works to produce internal wave patterns as authentically as possible, while the discriminator is designed to differentiate between images generated by the generator and reference images. The architecture based on pyramids adeptly captures the encompassing as well as localized characteristics of internal waves. The incorporation of upsampling further bolsters the model’s ability to recognize fine-scale internal wave stripes. These attributes endow the PCGAN with the capacity to learn from a limited amount of internal wave observation data. Experimental results affirm that the PCGAN, trained with just four internal wave images, can accurately detect internal wave stripes in the test set. Through comparative experiments with other segmentation models, we demonstrate the effectiveness and robustness of PCGAN.

show abstract

“…A contamination probability model of the oil-spill area over the Caspian region showed that the contamination probability is more than 50 % in the shoreline range of 464 km to 508 km [26]. Besides, Li et al [27] proposed a multiscale conditional adversarial network to identify the large area of oil-spill using ERS-1, ERS-2, and Envisat-1 satellite data. Similarly, an adversarial learning approach is implemented to forecast the wind field correction and oil-spill drift detection [28].…”

Section: Introductionmentioning

confidence: 99%

Clustering of Marine Oil-Spill Extent Using Sentinel-1 Dual-Polarimetric Scattering Spectrum

Paul,

Dey,

Marino

et al. 2023

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

View full text Add to dashboard Cite

Oil spills pose a significant threat to the maritime ecosystem. Identifying an oil spill is vital to assess its spread and drift to nearby coastal areas. Synthetic Aperture Radar (SAR) sensors are viable for mapping and monitoring marine oil spills. This study proposes a new technique that utilizes the dual-polarimetric Sentinel-1 SAR data. The method is based on projecting the 2 × 2 covariance matrix onto distinct random realizations of the normalized scattering configuration. We then obtain the dual-polarimetric spectrum of the scattering-type parameter, θDP. The θDP spectrum is then used in the unsupervised K-means clustering technique to segment oil spills from the rest. The cluster findings are then compared to the accuracies obtained using the standard scattering-type parameters from the eigen-decomposition approach (VV, VH) intensities and Otsu thresholding of [H + α + A] parameter. We demonstrate the proposed approach by clustering marine oil-spill extent over parts of India, Kuwait, the United Arab Emirates, and the Mediterranean Sea obtained by Sentinel-1 SAR images. We observed that the clustering accuracy of the proposed technique outperforms the ones obtained from the channel (i.e., VV and VH) intensities, Otsu thresholding of [H + α + A] parameter, and the eigen-decomposition based method. The proposed approach improves the overall accuracy by ≈ 8 % and ≈ 20 % respectively over different study areas.

show abstract

Oil Spill Detection with Multiscale Conditional Adversarial Networks with Small-Data Training

Cited by 30 publications

References 43 publications

A Novel Multi-Scale Feature Map Fusion for Oil Spill Detection of SAR Remote Sensing

A Novel Multi-Scale Feature Map Fusion for Oil Spill Detection of SAR Remote Sensing

Stripe Extraction of Oceanic Internal Waves Using PCGAN with Small-Data Training

Clustering of Marine Oil-Spill Extent Using Sentinel-1 Dual-Polarimetric Scattering Spectrum

Contact Info

Product

Resources

About