INTERNAL USE LICENSE SUMMARY

INTERNAL USE LICENSE SUMMARY

DISCLAIMER: This is not a license. This is a summary of European Space Imaging’s / Maxar’s Internal Use License that highlights its key terms. Please read the full Internal Use License text for the exact (and legally binding) terms that apply.

You can license Maxar products pursuant to an INTERNAL USE LICENSE if:

  • You are an individual person who wants to use the Product for your own purposes;
  • You represent a legal entity, such as a company, that wants to use the Product for its own internal business purposes; or
  • You represent a government agency that wants to use the Product for its own internal purposes

Under an Internal Use License, you and your authorized users are free to:

  • develop derivatives of the Product by formatting, editing, digitizing and/or combining with other data; or extracting geographic features, human-made features, persons or animals and related data via identification, measurement, and/or analysis; and
  • store, access and reproduce the Product and derivatives

Unlimited Authorized Users: You can let an unlimited number of your employees and contractors use the Product.

Online Display. You may also display an extract of the product or a derivative on a website in a non-extractable and non-downloadable format. However, Information Products may not be displayed online.

For internal use only:

  • You may only use the products and derivatives for your internal purposes.
  • You may not use the products or derivatives for commercial purposes. Commercial purposes include publishing, reselling, or using on behalf of another company.

Data Derivatives can be used for all uses:

  • “Data Derivatives” are a specific type of derivative that you are permitted to use for any and all purposes.
  • Generally, Data Derivatives are derivatives that do not contain source data, and which are irreversible and uncoupled from the source product.
  • Different Products specify different types of Data Derivatives. Check the Internal Use License for details.

With no right to share:

  • You may not share the Product or derivatives outside of your legal entity.
  • You may not share the Product with affiliates of your company.

For the term you choose:

  • Your license can be perpetualor for a one-year term (which can be renewed annually).

ELIGIBLE PRODUCTS:

Advanced Elevation Series

Basemap +Daily (offline)

Basemap +Metro (offline)

Basemap +Refresh (offline)

Basemap +Vivid (offline)

Basemap Standard (offline)

DYNAMIC Imagery

Ecopia Building Footprints Powered by Maxar

Human Landscape

Imagery Analysis Reports

Map-Ready (Ortho)

MDA RADARSAT-2 Products

Mosaics

AW3D Standard and Enhanced Products

SWIR

System-Ready (Basic Stereo)

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