Oil Spill Identification from Satellite Images Using Deep Neural Networks

Marios Krestenitis,Georgios Orfanidis,Ioannis Kompatsiaris,Konstantinos Avgerinakis,Konstantinos Ioannidis,Stefanos Vrochidis

doi:10.3390/rs11151762

Marios Krestenitis, Georgios Orfanidis + Show 4 more

Open Access

https://doi.org/10.3390/rs11151762

Copy DOI

Abstract

Oil spill is considered one of the main threats to marine and coastal environments. Efficient monitoring and early identification of oil slicks are vital for the corresponding authorities to react expediently, confine the environmental pollution and avoid further damage. Synthetic aperture radar (SAR) sensors are commonly used for this objective due to their capability for operating efficiently regardless of the weather and illumination conditions. Black spots probably related to oil spills can be clearly captured by SAR sensors, yet their discrimination from look-alikes poses a challenging objective. A variety of different methods have been proposed to automatically detect and classify these dark spots. Most of them employ custom-made datasets posing results as non-comparable. Moreover, in most cases, a single label is assigned to the entire SAR image resulting in a difficulties when manipulating complex scenarios or extracting further information from the depicted content. To overcome these limitations, semantic segmentation with deep convolutional neural networks (DCNNs) is proposed as an efficient approach. Moreover, a publicly available SAR image dataset is introduced, aiming to consist a benchmark for future oil spill detection methods. The presented dataset is employed to review the performance of well-known DCNN segmentation models in the specific task. DeepLabv3+ presented the best performance, in terms of test set accuracy and related inference time. Furthermore, the complex nature of the specific problem, especially due to the challenging task of discriminating oil spills and look-alikes is discussed and illustrated, utilizing the introduced dataset. Results imply that DCNN segmentation models, trained and evaluated on the provided dataset, can be utilized to implement efficient oil spill detectors. Current work is expected to contribute significantly to the future research activity regarding oil spill identification and SAR image processing.

Highlights

Sea oil pollution is considered a major threat to oceanic and coastal ecosystems, as well as for various naval-related human activities
IoU is measured for every class of the dataset resulting to the mean IoU as the average IoU measured over each class
Regarding the UNet and the LinkNet architecture, the extracted results are promising in terms of mean IoU, despite of their naive architecture, considering that atrous convolution or a pyramid pooling module is not applied

Summary

Introduction

Sea oil pollution is considered a major threat to oceanic and coastal ecosystems, as well as for various naval-related human activities. Oil spills are depicted as black spots, contrary to the brighter regions which are usually related with unspoiled polluted sea areas [2,4]. Similar dark instances could be identified in SAR images that might correspond to potential oil spills. Oceanic natural phenomena such as low wind speed regions, weed beds and algae blooms, wave shadows behind land, grease ice, etc. These dark regions are frequently categorized as look-alikes, rendering the oil spill detection problem even more challenging

Methods

Results

Conclusion