Survey of Deep-Learning Approaches for Remote Sensing Observation Enhancement

Abstract

Deep Learning, and Deep Neural Networks in particular, have established themselves as the new norm in signal and data processing, achieving state-of-the-art performance in image, audio, and natural language understanding. In remote sensing, a large body of research has been devoted to the application of deep learning for typical supervised learning tasks such as classification. Less yet equally important effort has also been allocated to addressing the challenges associated with the enhancement of low-quality observations from remote sensing platforms. Addressing such channels is of paramount importance, both in itself, since high-altitude imaging, environmental conditions, and imaging systems trade-offs lead to low-quality observation, as well as to facilitate subsequent analysis, such as classification and detection. In this paper, we provide a comprehensive review of deep-learning methods for the enhancement of remote sensing observations, focusing on critical tasks including single and multi-band super-resolution, denoising, restoration, pan-sharpening, and fusion, among others. In addition to the detailed analysis and comparison of recently presented approaches, different research avenues which could be explored in the future are also discussed.

U-Net Convolutional Networks for Mining Land Cover Classification Based on High-Resolution UAV Imagery

“…Based on deep learning, models can improve their performance based on past results or new data sources [13]. Deep learning provides many advantages for humans for predicting natural hazards [14], [15], and helping to make intelligent decisions in real-time without humans intervention [16]. In addition to their applications in social technology, deep learning has been used in various remote sensing analyses, such as detecting ships, turtles, or houses [17]- [19].…”

FusAtNet: Dual Attention based SpectroSpatial Multimodal Fusion Network for Hyperspectral and LiDAR Classification

“…In the recent past, many ad-hoc and conventional techniques have been introduced for the fusion of HSI and Li-DAR modalities due to their ability of digging the latent representations and features from the raw data [6,7]. Besides, the concerned fusion strategies have been applied for different application scenarios as visible in [8,9,10,11,12], where conventional methods such as support vector machines (SVM), random forests (RF), rotation forests (RoF) etc.…”

Deep learning based automated analysis of archaeo‐geophysical images

“…Moreover, automated image segmentation and pattern recognition have been emphasized in image analysis due to the need for processing a large number of images, which is a laborious task. Recently, advances in machine learning and deep learning algorithms, and the increasing availability of large labeled/annotated datasets (such as ImageNet, AlexNet, ResNet, Inception‐V4 databases) and pre‐trained models, are leading to remarkable improvements in the automated analysis of images, attracting especially the attention of the scientific community mostly in clinical studies (Miotto, Wang, Wang, Jiang & Dudley, ; Caixinha & Nunes, ; Yang, Xie, Liu, Cao, & Guo, ), in remote sensing (Ma et al, ; Tsagkatakis, Aidini, Fotiadou, & Giannopoulos, ) and in microbiology (Qu, Guo, Liu, Lin, & Zou, ).…”