Camera pose estimation framework for array-structured images
Despite the significant progress in camera pose estimation and structure-from-motion reconstruction from unstructured images, methods that exploit a priori information on camera arrangements have been overlooked. Conventional state-of-the-art methods do not exploit the geometric structure to recov...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Electronics and Telecommunications Research Institute (ETRI)
2022-02-01
|
| Series: | ETRI Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.4218/etrij.2021-0303 |
| _version_ | 1818365139623084032 |
|---|---|
| author | Min-Jung Shin Woojune Park Jung Hee Kim Joonsoo Kim Kuk-Jin Yun Suk-Ju Kang |
| author_facet | Min-Jung Shin Woojune Park Jung Hee Kim Joonsoo Kim Kuk-Jin Yun Suk-Ju Kang |
| author_sort | Min-Jung Shin |
| collection | DOAJ |
| description | Despite the significant progress in camera pose estimation and structure-from-motion reconstruction from unstructured images, methods that exploit a priori information on camera arrangements have been overlooked. Conventional state-of-the-art methods do not exploit the geometric structure to recover accurate camera poses from a set of patch images in an array for mosaic-based imaging that creates a wide field-of-view image by sewing together a collection of regular images. We propose a camera pose estimation framework that exploits the array-structured image settings in each incremental reconstruction step. It consists of the two-way registration, the 3D point outlier elimination and the bundle adjustment with a constraint term for consistent rotation vectors to reduce reprojection errors during optimization. We demonstrate that by using individual images' connected structures at different camera pose estimation steps, we can estimate camera poses more accurately from all structured mosaic-based image sets, including omnidirectional scenes. |
| first_indexed | 2024-12-13T22:15:31Z |
| format | Article |
| id | doaj.art-012df5da1e894567a9325a72613fcbd9 |
| institution | Directory Open Access Journal |
| issn | 1225-6463 |
| language | English |
| last_indexed | 2024-12-13T22:15:31Z |
| publishDate | 2022-02-01 |
| publisher | Electronics and Telecommunications Research Institute (ETRI) |
| record_format | Article |
| series | ETRI Journal |
| spelling | doaj.art-012df5da1e894567a9325a72613fcbd92022-12-21T23:29:34ZengElectronics and Telecommunications Research Institute (ETRI)ETRI Journal1225-64632022-02-01441102310.4218/etrij.2021-030310.4218/etrij.2021-0303Camera pose estimation framework for array-structured imagesMin-Jung ShinWoojune ParkJung Hee KimJoonsoo KimKuk-Jin YunSuk-Ju KangDespite the significant progress in camera pose estimation and structure-from-motion reconstruction from unstructured images, methods that exploit a priori information on camera arrangements have been overlooked. Conventional state-of-the-art methods do not exploit the geometric structure to recover accurate camera poses from a set of patch images in an array for mosaic-based imaging that creates a wide field-of-view image by sewing together a collection of regular images. We propose a camera pose estimation framework that exploits the array-structured image settings in each incremental reconstruction step. It consists of the two-way registration, the 3D point outlier elimination and the bundle adjustment with a constraint term for consistent rotation vectors to reduce reprojection errors during optimization. We demonstrate that by using individual images' connected structures at different camera pose estimation steps, we can estimate camera poses more accurately from all structured mosaic-based image sets, including omnidirectional scenes.https://doi.org/10.4218/etrij.2021-0303camera pose estimationmosaic-based imageomnidirectional imagestructure from motion |
| spellingShingle | Min-Jung Shin Woojune Park Jung Hee Kim Joonsoo Kim Kuk-Jin Yun Suk-Ju Kang Camera pose estimation framework for array-structured images ETRI Journal camera pose estimation mosaic-based image omnidirectional image structure from motion |
| title | Camera pose estimation framework for array-structured images |
| title_full | Camera pose estimation framework for array-structured images |
| title_fullStr | Camera pose estimation framework for array-structured images |
| title_full_unstemmed | Camera pose estimation framework for array-structured images |
| title_short | Camera pose estimation framework for array-structured images |
| title_sort | camera pose estimation framework for array structured images |
| topic | camera pose estimation mosaic-based image omnidirectional image structure from motion |
| url | https://doi.org/10.4218/etrij.2021-0303 |
| work_keys_str_mv | AT minjungshin cameraposeestimationframeworkforarraystructuredimages AT woojunepark cameraposeestimationframeworkforarraystructuredimages AT jungheekim cameraposeestimationframeworkforarraystructuredimages AT joonsookim cameraposeestimationframeworkforarraystructuredimages AT kukjinyun cameraposeestimationframeworkforarraystructuredimages AT sukjukang cameraposeestimationframeworkforarraystructuredimages |