Deep learning in remote sensing: a review

By Xiaoxiang Zhu, Devis Tuia, Lichao Mou, Gui-Song Xia, Liangpei Zhang, Feng Xu, Friedrich Fraundorfer. arXiv.org, 2017

1,896 citations recorded by the source corpus.

Standing at the paradigm shift towards data-intensive science, machine learning techniques are becoming increasingly important. In particular, as a major breakthrough in the field, deep learning has proven as an extremely powerful tool in many fields. Shall we embrace deep learning as the key to all? Or, should we resist a 'black-box' solution? There are controversial opinions in the remote sensing community. In this article, we analyze the challenges of using deep learning for remote sensing data analysis, review the recent advances, and provide resources to make deep learning in remote sensing ridiculously simple to start with. More importantly, we advocate remote sensing scientists to bring their expertise into deep learning, and use it as an implicit general model to tackle unprecedented large-scale influential challenges, such as climate change and urbanization.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Transportation

View Paper: https://www.semanticscholar.org/paper/441fbfdcc77187c9f9c41166b5fd42de04de1427

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

In Transportation

Citations in the corpus

A cloud detection algorithm for satellite imagery based on deep learning (2019, methodology): “Existing machine learning based methods, such as the neural networks approach investigated in (Hughes and Hayes, 2014), were found to perform sub par compared to the Fmask algorithm (Zhu, 2017).”
Deep learning classifiers for hyperspectral imaging: A review (2019, positive): “These models have become an inspiration for the development of new and improved HSI data classifiers, marking a clear trend since 2017 (Petersson et al., 2016; Ghamisi et al., 2017a; Zhu et al., 2017).”
Deep learning in environmental remote sensing: Achievements and challenges (2020, background): “DL has recently created huge breakthroughs in the remote sensing field, and these breakthroughs have been summarized in several review articles (John E. Ball et al., 2017; Ma et al., 2019; Zhang et al., 2016b; Zhu et al., 2017).”
Deep Learning in Multimodal Remote Sensing Data Fusion: A Comprehensive Review (2022, methodology): “, 2016) Introducing typical DL models and their applications in RS tasks (Zhu et al., 2017) Reviewing DL models and related algorithms in RS domains followed by a list of resources (Hong et al.”
Evaluation of Different Machine Learning Methods and Deep-Learning Convolutional Neural Networks for Landslide Detection (2019, background): “More recently, deep-learning methods and, above all, convolutional neural networks (CNNs) have achieved fairly good results in various image analysis tasks in computer vision [30,31].”
Hyperspectral Image Denoising Employing a Spatial–Spectral Deep Residual Convolutional Neural Network (2018, methodology): “DL has also been introduced into the geoscience and remote sensing community for data interpretation, analysis, and application [28]–[29], including aerial scene classification [30], synthetic aperture radar (SAR) image interpretation [31], pansharpening [32], and so on.”
Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders (2018, background): “have proven particularly beneficial for modeling physical relationships that are complicated, cannot be generalized or are not well-understood [18].”
Tackling Climate Change with Machine Learning (2019, background): “[324] Xiao Xiang Zhu, Devis Tuia, Lichao Mou, Gui-Song Xia, Liangpei Zhang, Feng Xu, and Friedrich Fraundorfer.”
Advanced Multi-Sensor Optical Remote Sensing for Urban Land Use and Land Cover Classification: Outcome of the 2018 IEEE GRSS Data Fusion Contest (2019, background): “Recently, classifiers based on deep learning are being extensively used in remote sensing [24].”
Building Instance Classification Using Street View Images (2018, background): “Surveys about the applications of deep learning techniques to land-use classiﬁcation with remote sensing images are proposed in [53, 54].”
A Review on Deep Learning in UAV Remote Sensing (2021, methodology): “Also, focusing on classification, Zhu et al. [215] summarized most of the current information to understand the DL methods used for this task.”
A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists (2017, methodology): “Main RS applications, reviewed in [Zhu et al., 2017], include using CNN to classify or segment hyperspectral or Synthetic Aperture Radar (SAR) images (assigning classes to each pixel on an image for what they are, e.”
Mapping dominant leaf type based on combined Sentinel-1/-2 data – Challenges for mountainous countries (2021, background): “Since being proposed by Hinton et al. (2006), there has been increasing interest in using deep learning in earth observations (Zhu et al., 2017; Rammer and Seidl, 2019; Ma et al., 2019; Hoeser and Kuenzer, 2020), and lately also for classifying tree species (e. g. Fricker et al., 2019; Hartling et…”
Self-Supervised Learning in Remote Sensing: A review (2022, background): “Meanwhile, the success of deep learning did also spark remarkable progress in remote sensing [8].”
Detecting Mammals in UAV Images: Best Practices to address a substantially Imbalanced Dataset with Deep Learning (2018, background): “CNNs are nowadays the base building blocks of most computer vision pipelines and have also proven to be extremely successful in remote sensing (Zhu et al., 2017).”