Geospatial information in the form of satellite imagery and its derived applications have wide reaching capabilites to optimise workflows and disrupt entire industries. The ability to capture geospatially accurate Very High Resolution (VHR) satellite images from anywhere on Earth gives analysts, CEOs, commanders, rescuers and researchers unparalleled insights and opens the doors to endless possibilities.
Browse the INCITE Library and download them all for FREE.
Agricultural paying agencies across Europe face increasing challenges in maintaining accurate and up-to-date Land Parcel Identification Systems (LPIS), ensuring compliance with the Common Agricultural Policy (CAP) and supporting sustainable agricultural practices.
With the successful launch of Maxar Intelligence’s second set of WorldView Legion satellites, European Space Imaging (EUSI) will soon offer up to eight daily collection opportunities in key latitudes across Europe and North Africa – a number that will increase after the final WorldView Legion satellites are launched and all six satellites are operational.
Three land-surveying authorities finished large-scale mapping projects using very high resolution satellite images in 2024. These are the challenges, solutions and results:
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.