Hyperspectral Panoramic Image Stitching Using Robust Matching and Adaptive Bundle Adjustment
Remote-sensing developments such as UAVs heighten the need for hyperspectral image stitching techniques that can obtain information on a large area through various parts of the same scene. State-of-the-art approaches often suffer from accumulation errors and high computational costs for large-scale...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/16/4038 |
| _version_ | 1827625598777819136 |
|---|---|
| author | Yujie Zhang Xiaoguang Mei Yong Ma Xingyu Jiang Zongyi Peng Jun Huang |
| author_facet | Yujie Zhang Xiaoguang Mei Yong Ma Xingyu Jiang Zongyi Peng Jun Huang |
| author_sort | Yujie Zhang |
| collection | DOAJ |
| description | Remote-sensing developments such as UAVs heighten the need for hyperspectral image stitching techniques that can obtain information on a large area through various parts of the same scene. State-of-the-art approaches often suffer from accumulation errors and high computational costs for large-scale hyperspectral remote-sensing images. In this study, we aim to generate high-precision hyperspectral panoramas with less spatial and spectral distortion. We introduce a new stitching strategy and apply it to hyperspectral images. The stitching framework was built as follows: First, a single band obtained by signal-to-noise ratio estimation was chosen as the reference band. Then, a feature-matching method combining the SuperPoint and LAF algorithms was adopted to strengthen the reliability of feature correspondences. Adaptive bundle adjustment was also designed to eliminate misaligned artifact areas and occasional accumulation errors. Lastly, a spectral correction method using covariance correspondences is proposed to ensure spectral consistency. Extensive feature-matching and image-stitching experiments on several hyperspectral datasets demonstrate the superiority of our approach over the state of the art. |
| first_indexed | 2024-03-09T12:38:55Z |
| format | Article |
| id | doaj.art-74b0b2dae0f24a449890c3fc834ca2e8 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T12:38:55Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-74b0b2dae0f24a449890c3fc834ca2e82023-11-30T22:20:16ZengMDPI AGRemote Sensing2072-42922022-08-011416403810.3390/rs14164038Hyperspectral Panoramic Image Stitching Using Robust Matching and Adaptive Bundle AdjustmentYujie Zhang0Xiaoguang Mei1Yong Ma2Xingyu Jiang3Zongyi Peng4Jun Huang5Electronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaRemote-sensing developments such as UAVs heighten the need for hyperspectral image stitching techniques that can obtain information on a large area through various parts of the same scene. State-of-the-art approaches often suffer from accumulation errors and high computational costs for large-scale hyperspectral remote-sensing images. In this study, we aim to generate high-precision hyperspectral panoramas with less spatial and spectral distortion. We introduce a new stitching strategy and apply it to hyperspectral images. The stitching framework was built as follows: First, a single band obtained by signal-to-noise ratio estimation was chosen as the reference band. Then, a feature-matching method combining the SuperPoint and LAF algorithms was adopted to strengthen the reliability of feature correspondences. Adaptive bundle adjustment was also designed to eliminate misaligned artifact areas and occasional accumulation errors. Lastly, a spectral correction method using covariance correspondences is proposed to ensure spectral consistency. Extensive feature-matching and image-stitching experiments on several hyperspectral datasets demonstrate the superiority of our approach over the state of the art.https://www.mdpi.com/2072-4292/14/16/4038feature matchinghyperspectral imagesimage stitching |
| spellingShingle | Yujie Zhang Xiaoguang Mei Yong Ma Xingyu Jiang Zongyi Peng Jun Huang Hyperspectral Panoramic Image Stitching Using Robust Matching and Adaptive Bundle Adjustment Remote Sensing feature matching hyperspectral images image stitching |
| title | Hyperspectral Panoramic Image Stitching Using Robust Matching and Adaptive Bundle Adjustment |
| title_full | Hyperspectral Panoramic Image Stitching Using Robust Matching and Adaptive Bundle Adjustment |
| title_fullStr | Hyperspectral Panoramic Image Stitching Using Robust Matching and Adaptive Bundle Adjustment |
| title_full_unstemmed | Hyperspectral Panoramic Image Stitching Using Robust Matching and Adaptive Bundle Adjustment |
| title_short | Hyperspectral Panoramic Image Stitching Using Robust Matching and Adaptive Bundle Adjustment |
| title_sort | hyperspectral panoramic image stitching using robust matching and adaptive bundle adjustment |
| topic | feature matching hyperspectral images image stitching |
| url | https://www.mdpi.com/2072-4292/14/16/4038 |
| work_keys_str_mv | AT yujiezhang hyperspectralpanoramicimagestitchingusingrobustmatchingandadaptivebundleadjustment AT xiaoguangmei hyperspectralpanoramicimagestitchingusingrobustmatchingandadaptivebundleadjustment AT yongma hyperspectralpanoramicimagestitchingusingrobustmatchingandadaptivebundleadjustment AT xingyujiang hyperspectralpanoramicimagestitchingusingrobustmatchingandadaptivebundleadjustment AT zongyipeng hyperspectralpanoramicimagestitchingusingrobustmatchingandadaptivebundleadjustment AT junhuang hyperspectralpanoramicimagestitchingusingrobustmatchingandadaptivebundleadjustment |