Prince Harry and Meghan Markle were married at St George’s Chapel in the ground of Windsor Castle on Saturday, and European Space Imaging was lucky to witness the event via satellite.
An estimated 150,000 people turned up to line the streets of Windsor, and they are clearly visible in the very high resolution image captured by the WorldView-2 mission.
They can be seen neatly packed into the courtyard of the chapel, and along the roads the couple drove down after the ceremony: the B3022, Park St, and The Long Walk.
“The very high resolution imagery captured by the WorldView Constellation is perfect for showing crowds of people,” said Adrian Zevenbergen, European Space Imaging’s Managing Director.
People can be seen walking through the streets on their way to wait at The Long Walk. 19/5/2018 by WorldView-2 © European Space Imaging
Crowds wait along the length of The Long Walk to see the couple leaving in their car. 19/5/2018 by WorldView-2 © European Space Imaging
Masses of people and neatly arranged guards wait outside St George’s Chapel, Windsor. 19/5/2018 by WorldView-2 © European Space Imaging
Skye Boag, Marketing Manager EUSI have delivered over one million sq km of cloud free satellite data to the Copernicus VHR2021 campaign in cooperation with
We are excited to announce that European Space Imaging are rebranding to the acronym of EUSI. After more than 20 years in the Earth Observation business,
WorldView satellites and full sensor capacity offering from European Space Imaging.
Discover the full service offering from European Space Imaging within this brochure. Learn more about our satellite capacity including resolution and revisit rates, 3D models,
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.
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.
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.
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.