Discover
What's

NEW

FIND WHAT YOU'RE LOOKING FOR

Resource Type

Industry

Application

15 cm HD Imagery by Maxar

When your organisation’s business decisions require you to identify small features on the ground, an improved visual experience is key. The identification of objects such as road lines, individual plants, building edges and vehicles often requires the highest level of visual clarity. True 30 cm resolution imagery has long been

30 cm Satellite Imagery as an Alternative to Aerial Data

Remote sensing projects can often begin with the question “Should I use aerial imagery or satellite imagery?”. This question may come up again and again over the course of long term projects where unforeseen circumstances change the ability to collect data, the reliability of the data or the scope of

30 cm WorldView-3 Imagery Products Available Now

European Space Imaging is excited to announce we are now accepting orders for 30 cm WorldView-3 satellite imagery products. According to DigitalGlobe users can expect from smaller pixel resolution an “ability to resolve smaller features, see greater textures, extract features more accurately, have better photo interpretation, and simply enjoy a

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