DeepSat: a learning framework for satellite imagery

By Saikat Basu, Sangram Ganguly, Supratik Mukhopadhyay, Robert DiBiano, Manohar Karki, R. Nemani. 2015

377 citations recorded by the source corpus.

Satellite image classification is a challenging problem that lies at the crossroads of remote sensing, computer vision, and machine learning. Due to the high variability inherent in satellite data, most of the current object classification approaches are not suitable for handling satellite datasets. The progress of satellite image analytics has also been inhibited by the lack of a single labeled high-resolution dataset with multiple class labels. The contributions of this paper are twofold -- (1) first, we present two new satellite datasets called SAT-4 and SAT-6, and (2) then, we propose a classification framework that extracts features from an input image, normalizes them and feeds the normalized feature vectors to a Deep Belief Network for classification. On the SAT-4 dataset, our best network produces a classification accuracy of 97.95% and outperforms three state-of-the-art object recognition algorithms, namely - Deep Belief Networks, Convolutional Neural Networks and Stacked Denoising Autoencoders by ~11%. On SAT-6, it produces a classification accuracy of 93.9% and outperforms the other algorithms by ~15%. Comparative studies with a Random Forest classifier show the advantage of an unsupervised learning approach over traditional supervised learning techniques. A statistical analysis based on Distribution Separability Criterion and Intrinsic Dimensionality Estimation substantiates the effectiveness of our approach in learning better representations for satellite imagery.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology, Ocean Engineering

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Media Technology

In Ocean Engineering

Citations in the corpus

EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification (2017, methodology): “analyzed deep belief networks, basic CNNs, and stacked denoising autoencoders on the SAT-6 dataset [1].”
Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities (2020, neutral): “4& 6 [126], RSSCN7 [125], Brazilian Coffee Scene [85], RSC11 [128], SIRI-WHU [127], RSCI-CB [129], AID [79], NWPU-RESISC45 [80], OPTIMAL-31 [74], EuroSAT [130],”
Introducing Eurosat: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification (2018, background): “de/downloads popular remote sensing datasets UCM [2], AID [8], SAT-6 [1] and BCS [4].”
Learning Sparse Feature Representations Using Probabilistic Quadtrees and Deep Belief Nets (2015, methodology): “Deep Belief Networks have also been used for analyzing satellite imagery [5] as well as texture datasets [6].”
Satellite Imagery Classification Based on Deep Convolution Network (2016, methodology): “Hyper-parameters search and model performance evaluation were conducted on the DeepSat dataset [1], which is a benchmark database of satellite imagery classification.”
Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review (2020, background): “EuroSAT introduced by [122] (multi-labelled patches) and SAT-4 and SAT-6 datasets by [43] (single-labelled patches), are some examples of patch level labelled datasets released to the community.”
Machine Learning for the Geosciences: Challenges and Opportunities (2017, background): “local scales [92], and classifying objects such as trees and buildings in high-resolution satellite images [93].”
SEN12MS - A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion (2019, background): “SAT-4 500,000 28× 28 Color aerial imagery (R, G, B, NIR) 4 agricultural classes over continental USA (Basu et al., 2015)”
Origin-destination trips by purpose and time of day inferred from mobile phone data (2015, methodology): “T he excessive exploitation of petroleum and coal affect not only the security of energy supply but also air quality and climate change. for cleaner These shortcomings have triggered the search alternative fuels for transportation 1–3 .”
DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution (2017, methodology): “Similar approaches have been applied to satellite datasets for image classication [2] and resolution enhancement [44].”