Shadow Detection and Restoration for Hyperspectral Images Based on Nonlinear Spectral Unmixing
Shadows are frequently observable in high-resolution images, raising challenges in image interpretation, such as classification and object detection. In this paper, we propose a novel framework for shadow detection and restoration of atmospherically corrected hyperspectral images based on nonlinear...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/23/3985 |
| _version_ | 1797545598913609728 |
|---|---|
| author | Guichen Zhang Daniele Cerra Rupert Müller |
| author_facet | Guichen Zhang Daniele Cerra Rupert Müller |
| author_sort | Guichen Zhang |
| collection | DOAJ |
| description | Shadows are frequently observable in high-resolution images, raising challenges in image interpretation, such as classification and object detection. In this paper, we propose a novel framework for shadow detection and restoration of atmospherically corrected hyperspectral images based on nonlinear spectral unmixing. The mixture model is applied pixel-wise as a nonlinear combination of endmembers related to both pure sunlit and shadowed spectra, where the former are manually selected from scenes and the latter are derived from sunlit spectra following physical assumptions. Shadowed pixels are restored by simulating their exposure to sunlight through a combination of sunlit endmembers spectra, weighted by abundance values. The proposed framework is demonstrated on real airborne hyperspectral images. A comprehensive assessment of the restored images is carried out both visually and quantitatively. With respect to binary shadow masks, our framework can produce soft shadow detection results, keeping the natural transition of illumination conditions on shadow boundaries. Our results show that the framework can effectively detect shadows and restore information in shadowed regions. |
| first_indexed | 2024-03-10T14:17:36Z |
| format | Article |
| id | doaj.art-8d6ae6ac7f19466aa742dbdf4902a295 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T14:17:36Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-8d6ae6ac7f19466aa742dbdf4902a2952023-11-20T23:38:52ZengMDPI AGRemote Sensing2072-42922020-12-011223398510.3390/rs12233985Shadow Detection and Restoration for Hyperspectral Images Based on Nonlinear Spectral UnmixingGuichen Zhang0Daniele Cerra1Rupert Müller2Department of Photogrammetry and Remote Sensing, German Aerospace Center (DLR), 88234 Wessling, GermanyDepartment of Photogrammetry and Remote Sensing, German Aerospace Center (DLR), 88234 Wessling, GermanyDepartment of Photogrammetry and Remote Sensing, German Aerospace Center (DLR), 88234 Wessling, GermanyShadows are frequently observable in high-resolution images, raising challenges in image interpretation, such as classification and object detection. In this paper, we propose a novel framework for shadow detection and restoration of atmospherically corrected hyperspectral images based on nonlinear spectral unmixing. The mixture model is applied pixel-wise as a nonlinear combination of endmembers related to both pure sunlit and shadowed spectra, where the former are manually selected from scenes and the latter are derived from sunlit spectra following physical assumptions. Shadowed pixels are restored by simulating their exposure to sunlight through a combination of sunlit endmembers spectra, weighted by abundance values. The proposed framework is demonstrated on real airborne hyperspectral images. A comprehensive assessment of the restored images is carried out both visually and quantitatively. With respect to binary shadow masks, our framework can produce soft shadow detection results, keeping the natural transition of illumination conditions on shadow boundaries. Our results show that the framework can effectively detect shadows and restore information in shadowed regions.https://www.mdpi.com/2072-4292/12/23/3985hyperspectral imageryshadowdetectionrestorationnonlinear unmixingHySpex |
| spellingShingle | Guichen Zhang Daniele Cerra Rupert Müller Shadow Detection and Restoration for Hyperspectral Images Based on Nonlinear Spectral Unmixing Remote Sensing hyperspectral imagery shadow detection restoration nonlinear unmixing HySpex |
| title | Shadow Detection and Restoration for Hyperspectral Images Based on Nonlinear Spectral Unmixing |
| title_full | Shadow Detection and Restoration for Hyperspectral Images Based on Nonlinear Spectral Unmixing |
| title_fullStr | Shadow Detection and Restoration for Hyperspectral Images Based on Nonlinear Spectral Unmixing |
| title_full_unstemmed | Shadow Detection and Restoration for Hyperspectral Images Based on Nonlinear Spectral Unmixing |
| title_short | Shadow Detection and Restoration for Hyperspectral Images Based on Nonlinear Spectral Unmixing |
| title_sort | shadow detection and restoration for hyperspectral images based on nonlinear spectral unmixing |
| topic | hyperspectral imagery shadow detection restoration nonlinear unmixing HySpex |
| url | https://www.mdpi.com/2072-4292/12/23/3985 |
| work_keys_str_mv | AT guichenzhang shadowdetectionandrestorationforhyperspectralimagesbasedonnonlinearspectralunmixing AT danielecerra shadowdetectionandrestorationforhyperspectralimagesbasedonnonlinearspectralunmixing AT rupertmuller shadowdetectionandrestorationforhyperspectralimagesbasedonnonlinearspectralunmixing |