A review of technical factors to consider when designing neural networks for semantic segmentation of Earth Observation imagery

TL;DR

This review comprehensively discusses neural network design considerations and data preprocessing techniques crucial for effective semantic segmentation of Earth Observation imagery, covering CNNs, RNNs, GANs, transformers, and data strategies.

Contribution

It provides an up-to-date overview of neural network architectures and data handling methods specifically tailored for remote sensing image segmentation tasks.

Findings

Highlights design patterns for CNNs, RNNs, GANs, and transformers.

Summarizes data preprocessing and augmentation strategies.

Discusses transfer learning and domain adaptation techniques.

Abstract

Semantic segmentation (classification) of Earth Observation imagery is a crucial task in remote sensing. This paper presents a comprehensive review of technical factors to consider when designing neural networks for this purpose. The review focuses on Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs), and transformer models, discussing prominent design patterns for these ANN families and their implications for semantic segmentation. Common pre-processing techniques for ensuring optimal data preparation are also covered. These include methods for image normalization and chipping, as well as strategies for addressing data imbalance in training samples, and techniques for overcoming limited data, including augmentation techniques, transfer learning, and domain adaptation. By encompassing both the technical aspects of neural network design and the data-related considerations, this review provides researchers and practitioners with a comprehensive and up-to-date understanding of the factors involved in designing effective neural networks for semantic segmentation of Earth Observation imagery.