Discover
What's

NEW

FIND WHAT YOU'RE LOOKING FOR

Resource Type

Industry

Application

Digitising the Third Dimension

Digital Surface Models (DSM) are key components for urban planning, biomass estimation and many more tasks where 3-dimensional data is required. Traditionally, the imagery for those DSMs is collected by two or more shots in sequence within a few seconds. With the current and in particular the future optical systems

Download All INCITE Reports

FROM URBAN TO RURAL: Enabling Sustainable Urban Planning and Development Using Satellite Imagery | It is estimated that 55% of the world’s population lives in urban areas. This number is expected to increase to 68% by 2050. Studies have shown that urbanisation combined with the overall growth of the world’s

Dr Wolfgang Steinborn Awarded DDGI’s Golden Badge of Honor

Dr Wolfgang Steinborn, a Senior Advisor at European Space Imaging, has been awarded the prestigious golden badge of honor by the German Umbrella Organization for Geo-Information (DDGI). This elite award is highly exclusive – only three people have been decorated with it since the organization was established in 1994, almost

Ecopia GFX with European Space Imaging

Ecopia Global Feature Extraction (GFX) with European Space Imaging is a unique partnership that utilises the freshest, highest quality satellite imagery along with the most advanced artificial intelligence from Ecopia.ai (Ecopia) to offer accurate geospatial feature extraction at continent-wide scale. The product comes with up to 12 core features eligible

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