Image stitching algorithm based on two-stage optimal seam line search
Traditional feature matching algorithms often struggle with poor performance in scenarios involving local detail deformations under varying perspectives. Additionally, traditional optimal seamline search-based image stitching algorithms tend to overlook structural and texture information, resulting...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-12-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157824003458 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846100632058986496 |
|---|---|
| author | Guijin Han Yuanzheng Zhang Mengchun Zhou |
| author_facet | Guijin Han Yuanzheng Zhang Mengchun Zhou |
| author_sort | Guijin Han |
| collection | DOAJ |
| description | Traditional feature matching algorithms often struggle with poor performance in scenarios involving local detail deformations under varying perspectives. Additionally, traditional optimal seamline search-based image stitching algorithms tend to overlook structural and texture information, resulting in ghosting and visible seams. To address these issues, this paper proposes an image stitching algorithm based on a two-stage optimal seamline search. The algorithm leverages a Homography Network as the foundation, incorporating a homography detail-aware network (HDAN) for feature point matching. By introducing a cost volume in the feature matching layer, the algorithm enhances the description of local detail deformation relationships, thereby improving feature matching performance under different perspectives. The two-stage optimal seamline search algorithm designed for image fusion introduces gradient and structural similarity features on top of traditional color-based optimal seamline search algorithms. The algorithm steps include: (1) Searching for structurally similar regions, i.e., high-frequency regions in high-gradient images, and using a color-based graph cut algorithm to search for seamlines within all high-frequency regions, excluding horizontal seamlines; (2) Using a dynamic programming algorithm to complete each vertical seamline, where the pixel energy is comprehensively calculated based on its differences in color and gradient with the surrounding area. The complete seamline energies are then calculated using color, gradient, and structural similarity differences within the seamline neighborhood, and the seamline with the minimum energy is selected as the optimal seamline. A simulation experiment was conducted using 30 image pairs from the UDIS-D dataset (Unsupervised Deep Image Stitching Dataset). The results demonstrate significant improvements in PSNR and SSIM metrics compared to other image stitching algorithms, with PSNR improvements ranging from 5.63% to 11.25% and SSIM improvements ranging from 11.09% to 24.54%, confirming the superiority of this algorithm in image stitching tasks. The proposed image stitching algorithm based on two-stage optimal seamline search, whether evaluated through subjective visual perception or objective data comparison, outperforms other algorithms by enhancing the natural transition of seamlines in terms of structure and texture, reducing ghosting and visible seams in stitched images. |
| format | Article |
| id | doaj-art-a9e1d18e0cb142a18cafb2e064d42d7d |
| institution | Kabale University |
| issn | 1319-1578 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj-art-a9e1d18e0cb142a18cafb2e064d42d7d2024-12-30T04:15:31ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782024-12-013610102256Image stitching algorithm based on two-stage optimal seam line searchGuijin Han0Yuanzheng Zhang1Mengchun Zhou2School of Automation Xi’an University of Posts and Telecommunications, Xi’an 710121, ChinaSchool of Automation Xi’an University of Posts and Telecommunications, Xi’an 710121, China; Corresponding author.School of Engineering Management at Beijing Jiaotong University, Beijing 100044, ChinaTraditional feature matching algorithms often struggle with poor performance in scenarios involving local detail deformations under varying perspectives. Additionally, traditional optimal seamline search-based image stitching algorithms tend to overlook structural and texture information, resulting in ghosting and visible seams. To address these issues, this paper proposes an image stitching algorithm based on a two-stage optimal seamline search. The algorithm leverages a Homography Network as the foundation, incorporating a homography detail-aware network (HDAN) for feature point matching. By introducing a cost volume in the feature matching layer, the algorithm enhances the description of local detail deformation relationships, thereby improving feature matching performance under different perspectives. The two-stage optimal seamline search algorithm designed for image fusion introduces gradient and structural similarity features on top of traditional color-based optimal seamline search algorithms. The algorithm steps include: (1) Searching for structurally similar regions, i.e., high-frequency regions in high-gradient images, and using a color-based graph cut algorithm to search for seamlines within all high-frequency regions, excluding horizontal seamlines; (2) Using a dynamic programming algorithm to complete each vertical seamline, where the pixel energy is comprehensively calculated based on its differences in color and gradient with the surrounding area. The complete seamline energies are then calculated using color, gradient, and structural similarity differences within the seamline neighborhood, and the seamline with the minimum energy is selected as the optimal seamline. A simulation experiment was conducted using 30 image pairs from the UDIS-D dataset (Unsupervised Deep Image Stitching Dataset). The results demonstrate significant improvements in PSNR and SSIM metrics compared to other image stitching algorithms, with PSNR improvements ranging from 5.63% to 11.25% and SSIM improvements ranging from 11.09% to 24.54%, confirming the superiority of this algorithm in image stitching tasks. The proposed image stitching algorithm based on two-stage optimal seamline search, whether evaluated through subjective visual perception or objective data comparison, outperforms other algorithms by enhancing the natural transition of seamlines in terms of structure and texture, reducing ghosting and visible seams in stitched images.http://www.sciencedirect.com/science/article/pii/S1319157824003458Image stitching technologyImage registrationHomography networkImage fusionOptimal seamline algorithmMulti-band feature fusion |
| spellingShingle | Guijin Han Yuanzheng Zhang Mengchun Zhou Image stitching algorithm based on two-stage optimal seam line search Journal of King Saud University: Computer and Information Sciences Image stitching technology Image registration Homography network Image fusion Optimal seamline algorithm Multi-band feature fusion |
| title | Image stitching algorithm based on two-stage optimal seam line search |
| title_full | Image stitching algorithm based on two-stage optimal seam line search |
| title_fullStr | Image stitching algorithm based on two-stage optimal seam line search |
| title_full_unstemmed | Image stitching algorithm based on two-stage optimal seam line search |
| title_short | Image stitching algorithm based on two-stage optimal seam line search |
| title_sort | image stitching algorithm based on two stage optimal seam line search |
| topic | Image stitching technology Image registration Homography network Image fusion Optimal seamline algorithm Multi-band feature fusion |
| url | http://www.sciencedirect.com/science/article/pii/S1319157824003458 |
| work_keys_str_mv | AT guijinhan imagestitchingalgorithmbasedontwostageoptimalseamlinesearch AT yuanzhengzhang imagestitchingalgorithmbasedontwostageoptimalseamlinesearch AT mengchunzhou imagestitchingalgorithmbasedontwostageoptimalseamlinesearch |