Ground
station (cDAF)

European Space Imaging owns and operates a constellation Direct Access Facility (cDAF) at the German Aerospace Center (DLR) near Munich. From here we have a direct uplink and downlink to the WorldView satellites as they pass over Europe and North Africa, allowing us to optimise our image collection strategies and rapidly deliver the highest quality data to our clients.

Optimised Collection Strategy

European Space Imaging is unique amongst ground station operators because we plan our collections taking into account the real-time weather situation, rather than using the weather forecast. In the minutes before the satellite is tasked with collecting an image our staff monitor the radar for clouds, and use that information to make the smartest choice about which images to collect. This allows:

Minimal levels of cloud cover
Optimised collection capacity
• Last minute updates to satellite tasking plans

Cone Map

Rapid Delivery

Actionable intelligence can’t arrive next week. When crucial decision require the most up-to-date information, we are able to deliver. Because our operations personnel are stationed at the antenna, “rush” orders can be delivered in as little as 30 minutes after collection. 

To find out if your project qualifies for rush delivery service, contact our sales team.

29JUL2019_Southern-France-Fires_WV2_EUSI_1200x800
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