Discover
What's

NEW

FIND WHAT YOU'RE LOOKING FOR

Resource Type

Industry

Application

European Space Imaging Partner in Newly Launched MARSAT Consortium

MARSAT consortium announced it is ready to provide innovative space-based applications using satellite-derived information for the maritime and coastal industry. MARSAT’s main goal is to create integrated satellite-based services to improve safety and efficiency in shipping, offshore industries, emergency response and rescue operations. “MARSAT is an ambitious project, which brings

European Space Imaging Starts Distribution of WorldView-4 Satellite Imagery

A new ground station and a unique 30 cm satellite constellation enable unprecedented capabilities. European Space Imaging announced today that the company has started operations of its new ground station with access to the entire satellite fleet of its WorldView Global Alliance partner DigitalGlobe. The Munich-based company is now in

European Space Imaging Wins Additional Supply Contract to European Commission

The Munich-based company has been awarded another major supply contract for VHR satellite data and services to support checks within the EU Common Agricultural Policy (CAP). European Space Imaging announced today that the company has signed an additional multi-year framework supply contract with the European Commission for the provision of

European Space Imaging, €20 Million Maritime Contract

European Space Imaging has been awarded its third major contract for the provision of very high resolution optical satellite data to the European Maritime Safety Agency (EMSA), ranking number one among a strong field of European competitors to provide all data sets and strengthening their position as Europe’s leading provider

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