Play Video

GEOSeries Episode 1 - Now You See: High Frequency Collections, Rapid Revisit & Unique Datasets

The first episode aired on Thursday 18 March 2021 and was moderated by Aravind Ravichandran, Founder of TerraWatch Space. He was joined by Thomas VanMatre, Vice-President of Global Business Development at Satellogic and Pascal Schichor, Sales Director at European Space Imaging. During the session the capacities of the NuSat satellites including their global coverage and rapid revisits, how the imagery can complement 30 cm data, as well as the future planned satellite launches by Satellogic was discussed. The future of Earth Observation through the power of hyperspectral imagery, what it is, the benefits of this data and how you can access it along with the unique benefits of the European Space Imaging / Satellogic partnership for the European market was also explored.

Through this partnership, European Space Imaging has expanded their satellite portfolio to include multispectral imagery with a resolution 0.7 – 1m as well as hyperspectral imagery from the recently launched Aleph-1 Constellation. The inclusion of this data now gives the company access to 25 orbiting satellites ranging from 0.3 – 1 m with a combined daily revisit of close to 10 times a day.

More Videos

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