Intrinsic Image Recovery From Remote Sensing Hyperspectral Images

In this paper, a novel reflectance model is proposed to recover intrinsic images from remote sensing hyperspectral images (HSIs). Intrinsic image recovery is a well-known challenging and underconstrained problem in computer vision, and it becomes even more severely illposed for HSIs. To reduce the uncertainties and improve the recovery accuracy, two kinds of priors are introduced: 1) shading prior which describes the geometric relation between illuminate and object surface and 2) reflectance prior based on L1-graph coding, which describes the relation between pigment density with reflectance. These priors can effectively eliminate the reflectance inhomogeneity caused by surface normal changes or pigment density variations other than material changes. Then, a noniterative optimization method is proposed to combine the shading prior and reflectance prior, with which closed-form solutions can be derived and thus avoided falling into local optimums. The experimental results demonstrate that the proposed method can efficiently improve the spectral reflectance homogeneity within a class while preserving the image boundaries; it also produces a competitive performance with the state of the art when utilizing the extracted intrinsic hyperspectral reflectance feature in the task of HSI classification.

• Publication year

  2019

• Venue

  IEEE Transactions on Geoscience and Remote Sensing

• Publication date

  2019-01-01

• Fields of study

  Computer Science, Environmental Science

• Identifiers
  DOI 10.1109/TGRS.2018.2853178
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Radiation Sources

  2018cited by this paper
• Extinction Profiles Fusion for Hyperspectral Images Classification

  2018cited by this paper
• A New Spatial–Spectral Feature Extraction Method for Hyperspectral Images Using Local Covariance Matrix Representation

  2018cited by this paper
• PCA-Based Edge-Preserving Features for Hyperspectral Image Classification

  2017cited by this paper
• Superpixel-Based Intrinsic Image Decomposition of Hyperspectral Images

  2017cited by this paper
• Discriminative Graph-Based Fusion of HSI and LiDAR Data for Urban Area Classification

  2017cited by this paper
• Multimorphological Superpixel Model for Hyperspectral Image Classification

  2017cited by this paper
• Nonlinear Multiple Kernel Learning With Multiple-Structure-Element Extended Morphological Profiles for Hyperspectral Image Classification

  2016cited by this paper
• Discriminative Multiple Kernel Learning for Hyperspectral Image Classification

  2016cited by this paper
• Intrinsic Scene Decomposition from RGB-D Images

  2015cited by this paper
• Classification of Hyperspectral Images by Exploiting Spectral–Spatial Information of Superpixel via Multiple Kernels

  2015cited by this paper
• Intrinsic Image Decomposition for Feature Extraction of Hyperspectral Images

  2015influential reference
• Multiclass feature learning for hyperspectral image classification: sparse and hierarchical solutions

  2015cited by this paper
• Intrinsic Decomposition of Image Sequences from Local Temporal Variations

  2015cited by this paper
• Spectral–Spatial Hyperspectral Image Classification Based on KNN

  2015cited by this paper
• Feature Extraction of Hyperspectral Images With Image Fusion and Recursive Filtering

  2014cited by this paper
• Spectral–Spatial Hyperspectral Image Classification With Edge-Preserving Filtering

  2014cited by this paper
• Hyperspectral and LiDAR Data Fusion: Outcome of the 2013 GRSS Data Fusion Contest

  2014cited by this paper
• A Simple Model for Intrinsic Image Decomposition with Depth Cues

  2013cited by this paper
• Intrinsic Image Decomposition Using Optimization and User Scribbles

  2013cited by this paper
• Intrinsic Scene Properties from a Single RGB-D Image

  2013cited by this paper
• Feature Mining for Hyperspectral Image Classification

  2013cited by this paper
• Color Constancy, Intrinsic Images, and Shape Estimation

  2012cited by this paper
• Rich Intrinsic Image Decomposition of Outdoor Scenes from Multiple Views

  2012cited by this paper
• Shape, albedo, and illumination from a single image of an unknown object

  2012cited by this paper
• Hyperspectral Image Classification With Independent Component Discriminant Analysis

  2011cited by this paper
• Locality-Preserving Discriminant Analysis in Kernel-Induced Feature Spaces for Hyperspectral Image Classification

  2011cited by this paper
• Extended profiles with morphological attribute filters for the analysis of hyperspectral data

  2010cited by this paper
• Morphological Attribute Profiles for the Analysis of Very High Resolution Images

  2010cited by this paper
• Classification of hyperspectral images with Extended Attribute Profiles and feature extraction techniques

  2010cited by this paper
• Make3D: Learning 3D Scene Structure from a Single Still Image

  2009cited by this paper
• Classification of Very High Spatial Resolution Imagery Using Mathematical Morphology and Support Vector Machines

  2009cited by this paper
• Limitations of Principal Components Analysis for Hyperspectral Target Recognition

  2008cited by this paper
• Composite kernels for hyperspectral image classification

  2006cited by this paper
• Classification of hyperspectral data from urban areas based on extended morphological profiles

  2005cited by this paper
• Recovering intrinsic images from a single image

  2005cited by this paper
• Classification and feature extraction for remote sensing images from urban areas based on morphological transformations

  2003cited by this paper
• Morphological Image Analysis: Principles and Applications

  2003cited by this paper
• Lambertian reflectance and linear subspaces

  2001cited by this paper
• A new approach for the morphological segmentation of high-resolution satellite imagery

  2001cited by this paper
• Photometric Stereo with General, Unknown Lighting

  2001cited by this paper
• Supervised classification in high-dimensional space: geometrical, statistical, and asymptotical properties of multivariate data

  1998cited by this paper
• Color vision and image intensities: When are changes material?

  1982cited by this paper
• On the mean accuracy of statistical pattern recognizers

  1968cited by this paper
• Ieee Transactions on Pattern Analysis and Machine Intelligence Shape, Illumination, and Reflectance from Shading

  year unknowncited by this paper

• Learning Retinex Prior for Compressive Hyperspectral Image Reconstruction

  2026cites this paper
• Lidar-Guided Fast Multimodal Hyperspectral Unmixing

  2025cites this paper
• Spectral Compressive Imaging via Chromaticity-Intensity Decomposition

  2025cites this paper
• HugIpuNet: Hybrid Updating Graph Motivated Illumination-Wise Property Unification Network for Hyperspectral and DSM Joint Classification

  2025cites this paper
• Debris-Flow Erosion Volume Estimation Using a Single High-Resolution Optical Satellite Image

  2025cites this paper
• Digital Surface Model-Embedded Intrinsic Hyperspectral Unmixing

  2025cites this paper
• Intrinsic Hyperspectral Image Recovery for UAV Strips Stitching

  2024cites this paper
• MAMInet II: Illumination-Insensitive Modalitywise Assimilation Guided Multistage Interaction Network for Hyperspectral and LiDAR Joint Classification

  2024cites this paper
• Cross-modal three-dimensional intrinsic image decomposition for hyperspectral and LiDAR image joint classification

  2024cites this paper
• A Multimodal Hyperspectral Unmixing Method Under Spectral Variability

  2024cites this paper
• DMSCA: deep multiscale cross-modal attention network for hyperspectral and light detection and ranging data fusion and joint classification

  2024cites this paper
• PID-HLfusion: Pluggable Progressive Illumination Driven Hyperspectral and LiDAR Data Fusion Considering Crossmodal Geometric Structures

  2024influential citation
• HI2D2FNet: Hyperspectral Intrinsic Image Decomposition Guided Data Fusion Network for Hyperspectral and LiDAR Classification

  2023cites this paper
• Shadow-Less Intrinsic Hyperspectral Point Cloud Generation From HSIs and LiDAR

  2023cites this paper
• Hyperspectral Intrinsic Image Decomposition Based on Physical Prior-Driven Unsupervised Learning

  2023influential citation
• Intrinsic Decomposition Embedded Spectral Unmixing for Satellite Hyperspectral Images With Endmembers From UAV Platform

  2023cites this paper
• Shadow Mask-Driven Multimodal Intrinsic Image Decomposition for Hyperspectral and LiDAR Data Fusion

  2023influential citation
• Deep Intrinsic Decomposition With Adversarial Learning for Hyperspectral Image Classification

  2023cites this paper
• Unsupervised Satellite Video Deep Intrinsic Decomposition Using Physical Prior Constraints

  2023cites this paper
• Multitemporal Intrinsic Image Decomposition With Temporal–Spatial Energy Constraints for Remote Sensing Image Analysis

  2022cites this paper
• Intrinsic Satellite Video Decomposition With Motion Target Energy Constraint

  2022cites this paper
• Satellite Video Intrinsic Decomposition

  2022cites this paper
• Hyperspectral Intrinsic Image Decomposition with Enhanced Spatial Information

  2022cites this paper
• Intrinsic Hyperspectral Image Decomposition With DSM Cues

  2022influential citation
• Supervoxel-Based Intrinsic Scene Properties From Hyperspectral Images and LiDAR

  2022cites this paper
• Unsupervised Change Detection in Hyperspectral Images using Feature Fusion Deep Convolutional Autoencoders

  2021influential citation
• Progressive Spatial–Spectral Joint Network for Hyperspectral Image Reconstruction

  2021cites this paper
• Feature Extraction for Hyperspectral Imagery: The Evolution From Shallow to Deep: Overview and Toolbox

  2020cites this paper
• Semisupervised classification of hyperspectral images with low-rank representation kernel.

  2020cites this paper
• Intrinsic Scene Properties From Hyperspectral Images and LiDAR

  2019cites this paper
• Analysis of PCA Based Feature Extraction Methods for Classification of Hyperspectral Image

  2019cites this paper