More than 80 people have been killed and thousands of homes destroyed by forest fires in Attica, Greece.
In the wake of devastating forest fires across the Attica Region in Greece, European Space Imaging has collected satellite images that show the extent of the damage.
These images of the area in between the towns of Rafina and Mati were collected by the GeoEye-1 satellite, which has five spectral sensors, including a very near-infrared band that is especially useful for detecting burnt areas.
The scenes above are pictured in natural colour and in near infrared, which highlights living vegetation in red. This allows for easy visual comparison, quickly identifying the areas where fire has damaged the vegetation and surrounding houses.
European Space Imaging partner DigitalGlobe has released additional imagery of the event, see it here on The Guardian.
The European Maritime Safety Agency (EMSA) has awarded European Space Imaging (EUSI) and Airbus a 24 month contract for the delivery of the Very High
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.
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.