Generation of the NIR spectral Band for Satellite Images with Convolutional Neural Networks

no code implementations • 13 Jun 2021 • Svetlana Illarionova, Dmitrii Shadrin, Alexey Trekin, Vladimir Ignatiev, Ivan Oseledets

The near-infrared (NIR) spectral range (from 780 to 2500 nm) of the multispectral remote sensing imagery provides vital information for the landcover classification, especially concerning the vegetation assessment.

Colorization Generative Adversarial Network +1

Object-Based Augmentation Improves Quality of Remote Sensing Semantic Segmentation

no code implementations • 12 May 2021 • Svetlana Illarionova, Sergey Nesteruk, Dmitrii Shadrin, Vladimir Ignatiev, Mariia Pukalchik, Ivan Oseledets

To overcome these data restrictions, it is common to consider various approaches including data augmentation techniques.

Image Augmentation Object +4