Satellite Imagery Protecting Europe’s Oceans

The ocean is a precious resource that all Europeans make use of in one way or another. Over 200 million of us live near the sea, and even people who dwell inland benefit from using it for transport, food, or leisure.

Unfortunately, protecting this natural resource is complex and multi-faceted; it must be kept healthy while sustainably supporting the different businesses and individuals who rely on it, and who often have conflicting needs. Additionally, it is under threat from pollution, climate change, flooding, erosion, sea level rise, extreme weather events, and overfishing.

Regulatory agencies mandated to protect the marine environment must monitor it closely, and do so by integrating multiple sources of data. By comparing satellite imagery with vessel traffic reports they can extract the most accurate information possible about the vast, and often remote, marine environment. The International Maritime Organisation (IMO) calls this Maritime Domain Awareneness (MDA), and it is crucial, because when decision-makers understand the situation precisely they are empowered to act quickly and effectively.

Satellite imagery is a core component of maritime monitoring services – it provides a cost-effective method for monitoring even the most remote areas. And compared to aerial or UAV imagery it offers operational simplicity by cutting out the need for air traffic control.

“Optical satellites are one of the most powerful items in the maritime monitoring toolkit,” says Dr. Melanie Rankl, Maritime Account Manager at European Space Imaging.

“Medium resolution images, such as the 10 m ones from ESA’s Sentinel-2 Mission, are ideal for getting a large area overview of the situation, but a 30 cm image from the WorldView constellation lets you zoom in on a particular area. You can identify individual vessels and whether they are towing full fishing nets or carrying cargo.”

In an emergency, new images can be collected very quickly, which is critical for enabling agencies to respond rapidly. These images can then be compared with a very high resolution image that can be obtain from European Space Imaging’s archive that stretches back more than 20 years, allowing the user to monitor changes and when they occurred.

“Unfortunately cloud cover can be a real problem when trying to obtain an optical image,” says Dr. Rankl, “which is why European Space Imaging monitors the weather situation in real-time as we plan our image collections – it gives us the best chance of collecting a cloud-free image.”

European Space Imaging has been supporting long-term EU earth observation services such as CleanSeaNet, and COPERNICUS for over a decade, and is proud to be a European company working towards keeping our oceans clean, healthy, safe, and sustainable.

This article was originally published on March 5 2018 in issue 471 of The Parliament magazine.

Share on facebook
Share on twitter
Share on linkedin

Related Stories

Scroll to Top

Architecture of ResNet34-UNet model

UNet architecture for semantic segmentation with ResNet34 as encoder or feature extraction part. ResNet34 is used as an encoder or feature extractor in the contracting path and the corresponding symmetric expanding path predicts the dense segmentation output.

Architecture of VGG16-UNet model

UNet architecture for semantic segmentation with VGG16 as the encoder or feature extractor. VGG16 is used as an encoder or feature extractor in the contracting path and the corresponding symmetric expanding path predicts the dense segmentation output.

Architecture of ResNet34-FCN model

In this model, ResNet34 is used for feature extraction and the FCN operation remains as is. The feature of ResNet architecture is exploited where just like VGG, as the number of filters double, the feature map size gets halved. This gives a similarity to VGG and ResNet architecture while supporting deeper architecture and addressing the issue of vanishing gradients while also being faster. The fully connected layer at the output of ResNet34 is not used and instead converted to fully convolutional layer by means of 1×1 convolution.

Architecture of VGG16-FCN model

In this model, VGG16 is used for feature extraction which also performs the function of an encoder. The fully connected layer of the VGG16 is not used and instead converted to fully convolutional layer by means of 1×1 convolution.

X