Deep Convolutional Neural Networks for the Classification of Snapshot Mosaic Hyperspectral Imagery

  title={Deep Convolutional Neural Networks for the Classification of Snapshot Mosaic Hyperspectral Imagery},
  author={Konstantina Fotiadou and Grigorios Tsagkatakis and Panagiotis Tsakalides},
  booktitle={Computational Imaging},
Spectral information obtained by hyperspectral sensors enables better characterization, identification and classification of the objects in a scene of interest. Unfortunately, several factors have to be addressed in the classification of hyperspectral data, including the acquisition process, the high dimensionality of spectral samples, and the limited availability of labeled data. Consequently, it is of great importance to design hyperspectral image classification schemes able to deal with the… 

Figures from this paper

Modified Convolutional Neural Networks Architecture for Hyperspectral Image Classification (Extra‐Convolutional Neural Networks)

An extra-convolution technique (ExCNN) is proposed, where the authors add layers of global convolutions on the classified images, outgoing from classical CNN, and the results obtained are compared with other similar methods of the state of art, and show the effectiveness of the proposed method.

On the Impact of Tensor Completion in the Classification of Undersampled Hyperspectral Imagery

This work studies the problem of efficient estimation of missing hyperspectral measurements and the impact of the reconstruction quality on the subsequent task of classification, and explores two cutting edge techniques for undersampled signal recovery, namely matrix and tensor completion.

Task-Driven Learned Hyperspectral Data Reduction Using End-to-End Supervised Deep Learning

This work proposes a novel supervised deep learning approach for combining data reduction and image analysis in an end-to-end architecture that can produce more accurate results than existing popular data reduction methods, and can be used in a wide range of problem settings.

Classification of Compressed Remote Sensing Multispectral Images via Convolutional Neural Networks

This work considers the encoding of multispectral observations into high-order tensor structures which can naturally capture multi-dimensional dependencies and correlations, and proposes a resource-efficient compression scheme based on quantized low-rank tensor completion.

Deep Learning for Multilabel Land Cover Scene Categorization Using Data Augmentation

A data augmentation technique that can drastically increase the size of a smaller data set to copious amounts is proposed that outperforms the current state of the art by more than 6% in terms of the F-score metric.

TanDEM-X Forest Mapping Using Convolutional Neural Networks

This study aims to highlight the relevance of domain-related features for the extraction of the information of interest thanks to their joint nonlinear processing through CNN, focusing on the main InSAR features as the backscatter, coherence, and volume decorrelation, as well as the acquisition geometry through the local incidence angle.

A CNN-Based Fusion Method for Feature Extraction from Sentinel Data

This work proposes to estimate missing optical features through data fusion and deep-learning, and results are very promising, showing a significant gain over baseline methods according to all performance indicators.

Survey of Deep-Learning Approaches for Remote Sensing Observation Enhancement

This paper provides 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.

HyKo: A Spectral Dataset for Scene Understanding

This work presents datasets containing urban traffic and rural road scenes recorded using hyperspectral snap-shot sensors mounted on a moving car, and explains the recoding platform and method, the associated data format along with a code library for easy data consumption.



Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks

This paper proposes a 3-D CNN-based FE model with combined regularization to extract effective spectral-spatial features of hyperspectral imagery and reveals that the proposed models with sparse constraints provide competitive results to state-of-the-art methods.

Deep supervised learning for hyperspectral data classification through convolutional neural networks

This work proposes a deep learning based classification method that hierarchically constructs high-level features in an automated way and exploits a Convolutional Neural Network to encode pixels' spectral and spatial information and a Multi-Layer Perceptron to conduct the classification task.

Deep Feature Learning for Hyperspectral Image Classification and Land Cover Estimation

This work proposes the introduction of the multi-label classification framework where classifiers are trained to predict multiple labels per pixel, and investigates the Stacked Sparse Autoencoders framework, an example of a deep learning network, for descriptive feature extraction.

Large patch convolutional neural networks for the scene classification of high spatial resolution imagery

This work proposes a practical CNN architecture for HSR-RS scene classification, named the large patch convolutional neural network (LPCNN), and experiments confirm that the proposed LPCNN can learn effective local features to form an effective representation for different land-use scenes, and can achieve a performance that is comparable to the state-of-the-art on public HSR -RS scene datasets.

Deep learning for multi-label land cover classification

This work investigates feature learning as a feature extraction process in order to identify the underlying explanatory patterns hidden in low-level satellite data for the purpose of multi-label classification.

Classification of hyperspectral remote sensing images with support vector machines

This paper addresses the problem of the classification of hyperspectral remote sensing images by support vector machines by understanding and assessing the potentialities of SVM classifiers in hyperdimensional feature spaces and concludes that SVMs are a valid and effective alternative to conventional pattern recognition approaches.

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

An end-to-end framework for the dense, pixelwise classification of satellite imagery with convolutional neural networks (CNNs) and design a multiscale neuron module that alleviates the common tradeoff between recognition and precise localization is proposed.

Best-bases feature extraction algorithms for classification of hyperspectral data

A set of best-bases feature extraction algorithms that are simple, fast, and highly effective for classification of hyperspectral data are proposed.

Building detection in very high resolution multispectral data with deep learning features

An automated building detection framework from very high resolution remote sensing data based on deep convolutional neural networks based on a supervised classification procedure employing a very large training dataset is proposed.

ImageNet classification with deep convolutional neural networks

A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.