We propose an end-to-end framework for the dense, pixelwise classification of satellite imagery with convolutional neural networks (CNNs). In our framework, CNNs are directly trained to produce classification maps out of the input images. We first devise a fully convolutional architecture and demonstrate its relevance to the dense classification problem. We then address the issue of imperfect training data through a two-step training approach: CNNs are first initialized by using a large amount of possibly inaccurate reference data, and then refined on a small amount of accurately labeled data. To complete our framework, we design a multiscale neuron module that alleviates the common tradeoff between recognition and precise localization. A series of experiments show that our networks consider a large amount of context to provide fine-grained classification maps.

/pdf/convolutional-neural-networks-for-large-scale-remote-sensing-1y0s3rxhig.pdf

Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification

In this paper, we evaluate the generalization power of deep features (ConvNets) in two new scenarios: aerial and remote sensing image classification. We evaluate experimentally ConvNets trained for recognizing everyday objects for the classification of aerial and remote sensing images. ConvNets obtained the best results for aerial images, while for remote sensing, they performed well but were outperformed by low-level color descriptors, such as BIC. We also present a correlation analysis, showing the potential for combining/fusing different ConvNets with other descriptors or even for combining multiple ConvNets. A preliminary set of experiments fusing ConvNets obtains state-of-the-art results for the well-known UCMerced dataset.

/pdf/do-deep-features-generalize-from-everyday-objects-to-remote-1urgf3djk4.pdf

Do deep features generalize from everyday objects to remote sensing and aerial scenes domains

We explore the use of convolutional neural networks for the semantic classification of remote sensing scenes. Two recently proposed architectures, CaffeNet and GoogLeNet, are adopted, with three different learning modalities. Besides conventional training from scratch, we resort to pre-trained networks that are only fine-tuned on the target data, so as to avoid overfitting problems and reduce design time. Experiments on two remote sensing datasets, with markedly different characteristics, testify on the effectiveness and wide applicability of the proposed solution, which guarantees a significant performance improvement over all state-of-the-art references.

Land Use Classification in Remote Sensing Images by Convolutional Neural Networks

In recent years, deep learning (DL), a rebranding of neural networks (NNs), has risen to the top in numerous areas, namely computer vision (CV), speech recognition, and natural language processing. Whereas remote sensing (RS) possesses a number of unique challenges, primarily related to sensors and applications, inevitably RS draws from many of the same theories as CV, e.g., statistics, fusion, and machine learning, to name a few. This means that the RS community should not only be aware of advancements such as DL, but also be leading researchers in this area. Herein, we provide the most comprehensive survey of state-of-the-art RS DL research. We also review recent new developments in the DL field that can be used in DL for RS. Namely, we focus on theories, tools, and challenges for the RS community. Specifically, we focus on unsolved challenges and opportunities as they relate to (i) inadequate data sets, (ii) human-understandable solutions for modeling physical phenomena, (iii) big data, (iv) nontraditional heterogeneous data sources, (v) DL architectures and learning algorithms for spectral, spatial, and temporal data, (vi) transfer learning, (vii) an improved theoretical understanding of DL systems, (viii) high barriers to entry, and (ix) training and optimizing the DL.

Comprehensive survey of deep learning in remote sensing: theories, tools, and challenges for the community

Artificial neural networks (ANNs) have been widely used for the analysis of remotely sensed imagery. In particular, convolutional neural networks (CNNs) are gaining more and more attention in this field. CNNs have proved to be very effective in areas such as image recognition and classification, especially for the classification of large sets composed by two-dimensional images. However, their application to multispectral and hyperspectral images faces some challenges, especially related to the processing of the high-dimensional information contained in multidimensional data cubes. This results in a significant increase in computation time. In this paper, we present a new CNN architecture for the classification of hyperspectral images. The proposed CNN is a 3-D network that uses both spectral and spatial information. It also implements a border mirroring strategy to effectively process border areas in the image, and has been efficiently implemented using graphics processing units (GPUs). Our experimental results indicate that the proposed network performs accurately and efficiently, achieving a reduction of the computation time and increasing the accuracy in the classification of hyperspectral images when compared to other traditional ANN techniques.

A new deep convolutional neural network for fast hyperspectral image classification

A data-driven strategy for short-term electric load forecasting using dynamic mode decomposition model

Apache Spark a Big Data Analytics Platform for Smart Grid

This work considers the classification of power quality disturbances based on VMD (Variational Mode Decomposition) and EWT (Empirical Wavelet Transform) using SVM (Support Vector Machine). Performance comparison of VMD over EWT is done for producing feature vectors that can extract salient and unique nature of these disturbances. In this paper, these two adaptive signal processing methods are used to produce three Intrinsic Mode Function (IMF) components of power quality signals. Feature vectors produced by finding sines and cosines of statistical parameter vector of three different IMF candidates are used for training SVM. Validation for six different classes of power qualities including normal sinusoidal signal, sag, swell, harmonics, sag with harmonics, swell with harmonics is performed using synthetic data in MATLAB. Classification results using SVM shows that VMD outperforms over EWT for feature extraction process and the classification accuracy is tabled.

/pdf/performance-comparison-of-variational-mode-decomposition-i15pqlp85v.pdf

Performance Comparison of Variational Mode Decomposition over Empirical Wavelet Transform for the Classification of Power Quality Disturbances Using Support Vector Machine

S. Sachin Kumar

Papers

A data-driven strategy for short-term electric load forecasting using dynamic mode decomposition model

Apache Spark a Big Data Analytics Platform for Smart Grid

Performance Comparison of Variational Mode Decomposition over Empirical Wavelet Transform for the Classification of Power Quality Disturbances Using Support Vector Machine

Detecting Android malware using Long Short-term Memory (LSTM)

Evaluating deep learning approaches to characterize and classify the DGAs at scale