Satellite Imagery For

Research
& Education

research-2

supporting innovation with the highest quality data

Explore the Past

Browse our archive with billions of square km dating back to 1999

Identify Materials

Locate and classify man-made materials and geologic minerals on Earth’s Surface

Detect Small Objects

See road markings, structural details, animals and individual plants

European Space Imaging offers satellite image data of unmatched resolution and quality. Make sure you are using the best data for your study, so that you get the best results possible. See more than you ever imagined.

Need imagery on a low budget?

We offer an 80% discount to qualified projects from academic and research institutes

Detailed Analysis

Very high resolution satellite imagery is clear enough to show road lines, sidewalks, vehicles, small structures and even people. This allows for precise analytics for city development. It is ideal for:

  • Studying Traffic Patterns
  • Monitoring Animal Herds
  • Small Feature Identification
  • Verifying Property Lines
  • Mapping Road Features
  • Precise Calculations

Historical Archive

We have been collecting satellite imagery since 1999, during which time we have amassed an invaluable library documenting changes on the Earth’s surface for the past twenty years. Analysis of this data can yield valuable insights into how the Earth has changed, and how it is likely to change next. Here are some examples of what this archive is being used for:

  • Environment monitoring
  • Global warming impact assessments
  • Urban development monitoring
  • Soil losses monitoring
  • Disaster impact monitoring
  • Forest fire and crime prediction software
  • Automated counting of objects such as cars, shipping containers, and houses
  • Monitoring present and historical change of glaciers, dams, and rivers
  • Detecting illegal activity such as logging and oil spills

Learn More About

MATERIAL IDENTIFICATION

We have access to hundreds of multispectral and hyperspectral band combinations – allowing you to see more of what is actually happening on the ground. Multispectral imagery can assist in building inspection, synthetic material identification, vegetation health analysis and water depth assessment. Short-wave infrared (SWIR) imagery can even see through smoke, detect heat and identify geological minerals.

Everyday innovative discoveries are being made by leveraging the power of multispectral bands.

Chinese-camp-true-colorChinese-camp-false-color

Learn More About

Download the Latest Edition of INCITE

Seeing Through the Trees: Monitoring Agriculture and Forestry Using Satellite Imagery

The definitive guide to acquiring and using satellite imagery to innovate the agriculture industry.

Discover
What's

NEW

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