Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

36811 · Oct 201919922001200920182026
48 results for hyperspectral imagery

EarthMapper offers a tool for semantic segmentation of remote sensing imagery.

problem Lack of annotated data for remote sensing sensors like hyperspectral imagery.
method Self-taught spatial-spectral feature extraction, various classifiers, and post-processing models.
result Evaluated on Indian Pines and Pavia University datasets, demonstrating state-of-the-art performance.

The paper classifies U.S. crop types using hyperspectral satellite imagery.

problem Classifying crop types from hyperspectral satellite imagery.
method Gaussian Bayesian models and neural networks applied to NASA data.
result Bayesian methods outperform standard LDA and QDA.

Paper introduces kernel methods for detecting anomalous changes in remote sensing imagery.

problem Detecting anomalous changes in remote sensing imagery.
method Nonlinear extension of Gaussian and elliptically contoured distribution algorithms using reproducing kernel Hilbert space.
result Improved detection accuracy and reduced false-alarm rates compared to linear formulations.

Deep learning for Venus images uses high-res hyperspectral data to simulate ground truth.

problem Lack of accurate ground truth data for training deep neural networks in remote sensing.
method Unmixing high-resolution hyperspectral images to simulate ground truth for training a CNN.
result The model can classify mid-resolution Venus images successfully.

This paper improves land cover classification using global spatial features in CNN.

problem Limited classification accuracy and universality of traditional remote sensing image classification methods.
method Integrates global spatial features into a dual-branch CNN for hyperspectral/SAR imagery classification.
result The proposed method outperforms traditional single-channel CNN methods.

Paper compares two possibilistic segmentation methods for SAS imagery.

problem Segmenting synthetic aperture sonar images into different seafloor environments.
method Comparison of Possibilistic Fuzzy Local Information C-Means (PFLICM) and Possibilistic K-Nearest Neighbors (PKNN) algorithms.
result PKNN outperforms PFLICM in segmentation performance on SAS images.

This paper introduces a new unsupervised method for dimensionality reduction via regression (DRR). The algorithm belongs to the family of invertible transforms that generalize Principal Component Analysis (PCA) by using curvilinear instead of linear features. DRR identifies the nonlinear features through multivariate r…

2016-01-31abs ↗pdf ↗

3-D-CNN fusion improves high-resolution HS images from noisy MS and HS data.

problem Improving high-resolution hyperspectral images from noisy multispectral and hyperspectral data.
method 3-D-Convolutional Neural Network (3-D-CNN) for image fusion, followed by dimensionality reduction.
result The proposed method significantly reduces computational time and noise robustness compared to conventional methods.

Efficient deep learning for hyperspectral image classification using active learning.

problem Lack of good-quality labeled samples for deep learning in hyperspectral images.
method Weighted incremental dictionary learning for active selection of training samples.
result The proposed algorithm improves deep learning efficiency and effectiveness in hyperspectral image classification.

A deep clustering method for hyperspectral images improves clustering performance by constraining intra-class distances.

problem Clustering performance degradation in hyperspectral images due to high dimensionality.
method Intra-class distance constrained deep clustering algorithm using auto-encoder network.
result The proposed algorithm outperforms state-of-the-art methods in clustering hyperspectral images.

A deep learning system classifies hyperspectral images using denoising autoencoders and pixel mixtures.

problem Hyperspectral image segmentation and classification challenges.
method Multiple class-based denoising autoencoders, mixed pixel training augmentation, and morphological operations.
result High performance on the Salinas dataset, verified by deep neural network and morphological hole-filling.

Ladder Networks improve semi-supervised hyperspectral image classification.

problem Semi-supervised hyperspectral image classification with limited labeled data.
method Jointly optimizing a supervised and unsupervised cost in a Ladder Network.
result Convolutional Ladder Network achieves state-of-the-art performance with minimal labeled data.

Deep learning classifies land use from high-resolution aerial imagery.

problem Variations in land features in aerial imagery due to sensor settings and context.
method Used deep convolutional neural networks to classify land use from VHR orthophoto mosaics.
result Deep learning can accurately classify land use from high-resolution visible band multispectral imagery.

The paper develops a machine learning framework for estimating soil moisture using VNIR hyperspectral data.

problem Estimating soil moisture content using VNIR hyperspectral data.
method Regression framework with feature selection, preprocessing, and supervised machine learning models.
result Extremely randomized trees model without preprocessing provides the best estimation performance.

SaR-SVM-STV improves hyperspectral image classification with shape-adaptive reconstruction and denoising.

problem Classifying hyperspectral images with limited labeled data.
method Shape-adaptive Reconstruction (SaR) for pixel preprocessing, SVM for probability estimation, and Smoothed Total Variation (STV) for denoising.
result SaR-SVM-STV outperforms SVM-STV with fewer labeled data.

Paper presents a graph-based semi-supervised method for hyperspectral image classification.

problem Hyperspectral image classification with limited labeled data.
method Novel superpixel algorithm based on spectral covariance matrix, followed by superpixel graph construction and classification.
result The method outperforms state-of-the-art approaches, especially in scenarios with minimal labeled data.

MDGCN improves hyperspectral image classification by dynamically updating graphs.

problem Traditional CNNs struggle with irregular image regions and class boundaries.
method MDGCN uses dynamic graph convolution on hyperspectral images, adapting to local regions.
result MDGCN outperforms state-of-the-art methods on benchmark datasets.

Attention-based CNNs improve band selection in hyperspectral images.

problem Selecting informative bands from hyperspectral images for accurate classification.
method Attention-based convolutional neural networks reusing activations at different depths.
result Deep models with attention mechanisms achieve high-quality classification and identify significant bands.

Novel graph-based framework for hyperspectral image classification using superpixels.

problem High classification accuracy with limited labelled data in hyperspectral images.
method Superpixel method for defining local regions, spectral and spatial features extraction, contracted graph representation, semi-supervised classifier.
result Our approach produces accurate classifications with minimal labelled data, outperforming state-of-the-art techniques.

Paper proposes a new method to handle spectral variability in hyperspectral unmixing.

problem Spectral variability within endmember classes affects unmixing performance.
method Adaptive bundles and double sparsity to promote sparsity on spectra and classes.
result Successfully determines variable number of classes and estimates their abundances.

A 3-stage method enhances hyperspectral image classification accuracy.

problem Classifying detailed classes in hyperspectral images with limited labeled data.
method Uses Nested Sliding Window and PCA for spatial consistency, SVM for spectral estimation, and TV model for spatial smoothing.
result Our method outperforms state-of-the-art algorithms, especially in scenarios with small training sets.

Flexible band grouping and kernel fusion for hyperspectral image processing.

problem Large dimensionality in hyperspectral imaging.
method Non-contiguous and contiguous band grouping for dimensionality reduction; improved visual clustering; unsupervised clustering algorithms; diverse features via different proximity metrics and kernel functions; ll_{\infty}-norm multiple kernel learning.
result Heterogeneous features and kernels lead to performance gain.

We consider the problem of subspace estimation in a Bayesian setting. Since we are operating in the Grassmann manifold, the usual approach which consists of minimizing the mean square error (MSE) between the true subspace UU and its estimate U^\hat{U} may not be adequate as the MSE is not the natural metric in the Gra…

2011-01-18abs ↗pdf ↗

A novel framework combines deep metric learning and conditional random field for hyperspectral image classification.

problem Improving classification performance in hyperspectral image processing with limited labeled data.
method Combines spectrum-based deep metric learning and conditional random field. Uses center loss for spectrum-based features and Gaussian edge potentials for pixel-wise classification.
result Demonstrates advantages in classification accuracy and computation cost compared to classical methods.

JigsawHSI improves land-use classification using hyperspectral images.

problem Land-use land-cover classification in hyperspectral images.
method Convolutional Neural Network (CNN) tailored for geoscientific analysis, using Jigsaw architecture.
result JigsawHSI achieves state-of-the-art performance in land-use classification.

Paper explores deep learning for translating motor imagery to robotic grasp synthesis.

problem Challenges in equipping machines with the ability to grasp objects based on sensory information.
method Investigates deep conditional generative models for learning integrated object-action representations.
result Demonstrates the capacity of generative models to capture and generate multimodal, multi-finger grasp configurations.

Researchers organize and analyze a large public safety imagery dataset.

problem Efficiently organizing and analyzing a vast public safety imagery dataset.
method Hierarchical organization approach using Lincoln Laboratory Supercomputing Cluster for compute and storage.
result Successfully organized and evaluated the dataset with large-scale imagery inference across terabytes of data.