Discover
What's

NEW

FIND WHAT YOU'RE LOOKING FOR

Resource Type

Industry

Application

Bathymetry

Accurate and high resolution bathymetric data is a necessity for a wide range of coastal oceanographic research and is especially important when studying the environmental health of benthic habitats that are often disturbed by human or natural phenomena. Utilising the WorldView-2 and WorldView-3 satellites, we are able to see further

BEIRUT, LEBANON: Satellite Images Show Explosion Damage

At least 100 people have died and 4,000 people have been wounded in a massive explosion in Beirut, Lebanon on Tuesday 4th August 2020. Very High Resolution (VHR) satellite images captured only hours ago with WorldView-2 by European Space Imaging highlight the scope of the damage to the surrounding blast

Border Control in Melilla: A Very High Resolution Look

Very High Resolution (VHR) satellite imagery supplied by European Space Imaging plays a crucial role in monitoring high traffic migration areas like Melilla, Spain where large groups of migrants rush fences in an attempt to take advantage of blind spots and gaps between guards. The power of VHR data lies

Combing 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) satellite imagery captured within shorter revisit times, it has become possible to detect landfills both in terms of size and the types of waste being dumped.

Constellation Direct Access Facility (cDAF)

With our multi-mission ground station, European Space Imaging operates Maxar’s WorldView Satellite Constellation as they pass over Europe and North Africa. By utilising our ability to task locally, we greatly increase the effective collection capacity of the satellites to obtain the greatest quality image with minimal cloud coverage. Detailed collection

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