Our Team

European Space Imaging’s team of geospatial experts are based in Munich, Germany, and have a reputation for expert and personalized customer service.

adrian-zevenbergen

Adrian Zevenbergen

MANAGING DIRECTOR

administration & accounting

Cate-Buckley

Cate Buckley

Stefanie Wein final

Stefanie Wein

SALES & MARKETING

Pascal-600x480

Pascal Schichor

Arnaud-headshot

Arnaud Durand

Melanie Rankl

Melanie Rankl

Silvester-Fischer

Silvester Fischer

Henning-New-2

Henning Götz

Bennie

Benjamin Lieberknecht

Maria Hochleitner final

Maria Hochleitner

Moni

Monika Voigt

Skye Boag

Skye Boag

Matthew Shelnut

Matthew Shelnut

MEET US IN PERSON OR VIRTUALLY

Check our events page to see upcoming conferences, web series and presentations

cUSTOMER sUPPORT

Susanne-Hain

Susanne Hain

Agnieszka-Walczynska

Agnieszka Walczynska

Thierry

Thierry Buettel

sigita_BW

Sigita Grinfelde

Caroline-copy

Caroline Kertels

Agne

Agne Valukonyte

Jones-Graosque

Jones Graosque

Ayke-Schlusina

Ayke Schlusina

Alexandra-Matei

Alexandra Matei

Tobias

Tobias Hettiger

Anton Scharpf final

Anton Scharpf

DEVELOPMENT

Brian

Brian Langley

Walther

Walther Pohl

Mikus Midegs final

Mikus Midegs

OPPERATIONS

Ansgar

Ansgar Kornhoff

Ulla-Feicht

Ulla Feicht

Nico

Nicolai Drost

Tine

Tine Flingelli

Sylvia

Sylvia Printz

Kamila

Kamila Cwik

Gonul

Gönül Uluca

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