Another year delivering 100% success rate to the European Commission’s CwRS Programme for European Space Imaging

Despite the challenges incurred from COVID-19 in 2020, European Space Imaging has once again finalised the collection of Very High Resolution (VHR) satellite imagery for the European Commission as part of their Controls with Remote Sensing (CwRS) programme.

Acquiring a total of 361,991 square kilometres, this is the fourth year in a row that the company has proficiently completed the collection with a success rate of 100% further enhancing the company’s reputation for reliability as Europe’s leading VHR satellite imagery provider.

“Given the unanticipated circumstances that we faced in 2020, we are extremely proud to once again deliver a success rate of 100% for this important and often demanding project,” said Adrian Zevenbergen, European Space Imaging’s Managing Director. “Our staff worked tirelessly to adapt to the new workflows required to battle the pandemic whilst also ensuring our customer’s projects were not adversely affected. Their dedication to this campaign is evident by this project’s outcome.”

The CwRS programme monitors agricultural land for which farmers have been granted subsidies under the EU’s Common Agricultural Policy (CAP), amounting to approximately €40 billion per year. European Space Imaging has been the major provider of Very High Resolution satellite data to the programme since 2003.

European Space Imaging had 676 acquisition windows for each of the 609 agricultural zones spread all over Europe using the WorldView-2, WorldView-3 and GeoEye-1 sensors. In addition, they also utilized their partnership with SI Imaging Services to provide imagery from Kompsat-3 and Kompsat-3A.

“This year we again saw the same weather challenges over Ireland and the UK as previous years. Despite this we were able to collect almost the entire coverage area zones with less than 10% cloud cover, close to 41% of this was completely cloud-free” said Dr. Melanie Rankl, Project Manager at European Space Imaging. “The added advantage of operating our own ground station ensured that the imagery was delivered in near-real time; an enormous benefit to the EU Member States in managing their deadlines”.

From its ground station in Munich, European Space Imaging takes into account real-time weather conditions before directly tasking the world’s most advanced satellite constellation: WorldView-1, GeoEye-1, WorldView-2 and WorldView-3. Direct tasking allows the company to minimise cloud cover, increase collection efficiency, enable customer flexibility and shorten delivery times.

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