Deep learning background
Rémi Cresson · 2020
Deep learning is becoming increasingly important to solve a number of image processing tasks. Among common algorithms, Convolutional Neural Network (CNN)- and Recurrent Neural Network (RNN)-based systems achieve state-of-the-art results on satellite and aerial imagery in many applications. CNN achieve state-of-the-art results on images. CNNs are designed to extract features in images, enabling image recognition, object detection, and semantic segmentation. RNN are suited for sequential data analysis, such as speech recognition and action recognition tasks. Pooling, and convolutions with stride, can be viewed as a subsampling process, which does modify the output size, and the output physical spacing. Depending on the implementation, it can also keep partially sampled items at borders. There are challenges remaining ahead to process real-world remote sensing images with deep learning. One crucial point is software implementation.