Since the launch of the first commercial VHR satellite, we at European Space Imaging have committed ourselves to providing much more than the world’s highest quality satellite imagery.

We provide solutions. Utilising our multi-mission ground station at the German Aerospace Center, our team of geospatial experts are able to bring together unique partnerships, innovative techniques and tailored services to achieve results for any project.

VHR SATELLITE IMAGERY

Giving unrivaled perspective of events on the ground and at sea, our satellite imagery offers the resolution, frequency, spectral bands, accuracy and historical archive to drive innovation and solve problems.

MAPPING SOLUTIONS

Vital for infrastructure, transportation and emergency response applications, our advanced mapping solutions mean you spend less time making maps and more time making progress.

3D Products

Not all data is created equal. Digital Elevation Models (DEM) and advanced 3D visualisations answer crucial questions, provide unique insights and give decision makers the data they require for success.

Custom Solutions

One size never fits all in the rapidly changing world of geospatial analytics. We partner with top companies around the globe to create tailored and scalable solutions that leverage advanced computing, innovative workflows and the highest quality data.

COMBINING VHR SATELLITE IMAGERY AND DEEP LEARNING TO DETECT LANDFILLS

Satellite imagery and remote sensing has been used extensively for monitoring land usage and land cover. With increasing availability of Very High Resolution (VHR)…

Meet us in person or virtually

Check our events page to see upcoming conferences, web series and presentations

Available Constellations

WORLDVIEW LEGION

WORLDVIEW

aleph-1

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