Shadow-Aware Nonlinear Spectral Unmixing With Spatial Regularization

Current shadow-aware hyperspectral unmixing (HySU) methods often suffer from noisy abundance maps and inaccurate abundance estimation of shadowed pixels, as these are characterized by low reflectance values and signal-to-noise ratio. In order to achieve a shadow-insensitive abundance estimation, in this article, we propose a novel spatial–spectral shadow-aware mixing (S3AM) model. The approach models shadows by considering diffuse solar illumination and secondary illumination from neighboring pixels. Besides, spatial regularization using shadow-aware weighted total variation (TV) is employed. Specifically, pixels in the local neighborhood of a target pixel simultaneously consider spectral similarity measures derived from the imagery, elevation similarity measures derived from a digital surface model (DSM), and the impact of shadows. The sky view factor $F$ , needed as input for the model, is also derived from available DSMs. The proposed approach is extensively validated and compared with state-of-the-art methods on two datasets. Results demonstrate that the S3AM yields superior abundance estimation maps for real scenarios, by decreasing the noise in the results and achieving more accurate reconstructions in the presence of shadows.

• Publication year

  2023

• Venue

  IEEE Transactions on Geoscience and Remote Sensing

• Publication date

  Unknown publication date

• Fields of study

  Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1109/TGRS.2023.3289570
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Supervised Nonlinear Hyperspectral Unmixing with Automatic Shadow Compensation using Multi-swarm Particle Swarm Optimization

  2022influential reference
• Shadow-Aware Nonlinear Spectral Unmixing for Hyperspectral Imagery

  2022influential reference
• DLR HySU - A Benchmark Dataset for Spectral Unmixing

  2021influential reference
• Sparsity-Enhanced Convolutional Decomposition: A Novel Tensor-Based Paradigm for Blind Hyperspectral Unmixing

  2021cited by this paper
• Endmember-Guided Unmixing Network (EGU-Net): A General Deep Learning Framework for Self-Supervised Hyperspectral Unmixing

  2021cited by this paper
• Hyperspectral Shadow Removal via Nonlinear Unmixing

  2021influential reference
• Illumination Invariant Hyperspectral Image Unmixing Based on a Digital Surface Model

  2020cited by this paper
• Shadow Detection and Restoration for Hyperspectral Images Based on Nonlinear Spectral Unmixing

  2020influential reference
• Particle Swarm Optimization

  2019cited by this paper
• Nonconvex-Sparsity and Nonlocal-Smoothness-Based Blind Hyperspectral Unmixing

  2019cited by this paper
• AIRCRAFT BASED REAL TIME BUNDLE ADJUSTMENT AND DIGITAL SURFACE MODEL GENERATION

  2019cited by this paper
• Nonlinear Hyperspectral Unmixing With Graphical Models

  2019influential reference
• Band-Wise Nonlinear Unmixing for Hyperspectral Imagery Using an Extended Multilinear Mixing Model

  2018cited by this paper
• Modern Trends in Hyperspectral Image Analysis: A Review

  2018cited by this paper
• Hyperspectral Image Unmixing With LiDAR Data-Aided Spatial Regularization

  2017cited by this paper
• A survey of methods incorporating spatial information in image classification and spectral unmixing

  2016cited by this paper
• Airborne Imaging Spectrometer HySpex

  2016cited by this paper
• A Multilinear Mixing Model for Nonlinear Spectral Unmixing

  2016influential reference
• Fully constrained linear spectral unmixing based global shadow compensation for high resolution satellite imagery of urban areas

  2015cited by this paper
• Hyperspectral Unmixing With Spectral Variability Using a Perturbed Linear Mixing Model

  2015cited by this paper
• Nonlocal Structure Tensor Functionals for Image Regularization

  2015cited by this paper
• A Novel Approach for Efficient $p$-Linear Hyperspectral Unmixing

  2015cited by this paper
• System for Automated Geoscientific Analyses (SAGA) v. 2.1.4

  2015cited by this paper
• Non-Local Sparse Unmixing for Hyperspectral Remote Sensing Imagery

  2014cited by this paper
• Incorporating spatial information in spectral unmixing: A review

  2014cited by this paper
• A Review of Nonlinear Hyperspectral Unmixing Methods

  2014influential reference
• Nonlinear Unmixing of Hyperspectral Images: Models and Algorithms

  2013influential reference
• Enhancing Spectral Unmixing by Local Neighborhood Weights

  2012cited by this paper
• Automated Extraction of Image-Based Endmember Bundles for Improved Spectral Unmixing

  2012cited by this paper
• Total Variation Spatial Regularization for Sparse Hyperspectral Unmixing

  2012cited by this paper
• Hyperspectral Unmixing Overview: Geometrical, Statistical, and Sparse Regression-Based Approaches

  2012cited by this paper
• Nonlinear unmixing of hyperspectral images using a generalized bilinear model

  2011cited by this paper
• Learning Discriminative Sparse Representations for Modeling, Source Separation, and Mapping of Hyperspectral Imagery

  2011cited by this paper
• Enhancing Hyperspectral Image Unmixing With Spatial Correlations

  2010cited by this paper
• Spectral unmixing using linear unmixing under spatial autocorrelation constraints

  2010cited by this paper
• Comparative study between a new nonlinear model and common linear model for analysing laboratory simulated‐forest hyperspectral data

  2009influential reference
• Characteristics of shadow and removal of its effects for remote sensing imagery

  2009cited by this paper
• Nonlinear mixture model for hyperspectral unmixing

  2009influential reference
• A quantitative and comparative analysis of endmember extraction algorithms from hyperspectral data

  2004cited by this paper
• Spectral unmixing

  2002influential reference
• Algorithm for de-shadowing spectral imagery

  2002influential reference
• Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery

  2001cited by this paper
• Iterative spectral unmixing (ISU)

  1999cited by this paper
• Remote Sensing: The Image Chain Approach

  1996influential reference
• The Spectral Image Processing System (SIPS) - Interactive visualization and analysis of imaging spectrometer data

  1993cited by this paper

• No citing papers are available for this paper.