Based in Munich, Germany and established in 2002, European Space Imaging is the leading premium supplier of global Very High Resolution (VHR) satellite imagery and derived Earth Observation services to customers in Europe and North Africa.
Through their longstanding partnership with Maxar Technologies, European Space Imaging was the first European company to bring 30 cm resolution satellite imagery to the EU market and is subsequently the longest and most trusted EU provider of True 30 cm resolution imagery. With access to the WorldView constellation through their ground-station located at the German Aerospace Centre, and the ability for direct satellite tasking and local data downlink, the company is able to deliver imagery in near-real time.
In addition to fresh acquisitions, customers can benefit from an extensive image archive containing billions of square kilometers of satellite imagery spanning more than two decades. Staying ahead of the competition, European Space Imaging also provide 15 cm HD, a proprietary technology from Maxar that intelligently increases pixel resolution to enhance clarity and feature detection.
European Space Imaging has access to satellites at resolutions 30 cm – 1 m and a combined daily revisit of close to 10 times a day in panchromatic, multispectral, hyperspectral and video. They continue to engage in innovative partnerships to deliver the latest earth observation technological advances including a range of 3D products, analytic tools and imagery solutions.
Our multi-mission ground station, located at the German Aerospace Center (DLR) near Munich, allows us to directly connect to the WorldView satellite constellation.
What does that mean?
Low Latency. Latency refers to how long it takes between image collection and deliver to the end user. Other suppliers might have to wait for imagery to be downloaded and processed offsite. This can last hours or even days. We, on the other hand, download the images immediately and can deliver urgent orders in as little as 30 minutes after collection.
Find opportunities to work at one of the most respected geospatial service companies.
adrian zevenbergen
Managing Director
Pascal Schichor
Sales Director
Susanne Hain
Customer Support Director
European Space Imaging established in Munich, Germany. To lead with the best, a partnership with Space Imaging / GeoEye was formed.
Initial cooperation with the EU Commission & other government bodies established a relationship that continues to this day.
In partnership with Maxar and Space Imaging Middle East we formed the WorldView Global Alliance, to ensure we could continue delivering the highest resolution satellite data available.
We made a significant investment in the antenna at the ground station near Munich, which now allows us a direct uplink and downlink to all the WorldView satellites.
Strategic partnerships with Ecopia.AI and Satellogic established to remarkably expand our asset portfolio
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.