Line-Based Geometric Consensus Rectification and Calibration From Single Distorted Manhattan Image
Recent advances in single image rectification and intrinsic calibration has been addressed by employing line information on the distorted image. The core issues of this technique are the separation of rectification and calibration procedures, and the suffering of geometric nonconformity. In this wor...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8867930/ |
| _version_ | 1818737308039380992 |
|---|---|
| author | Mi Zhang Xiangyun Hu Jian Yao Like Zhao Jiancheng Li Jianya Gong |
| author_facet | Mi Zhang Xiangyun Hu Jian Yao Like Zhao Jiancheng Li Jianya Gong |
| author_sort | Mi Zhang |
| collection | DOAJ |
| description | Recent advances in single image rectification and intrinsic calibration has been addressed by employing line information on the distorted image. The core issues of this technique are the separation of rectification and calibration procedures, and the suffering of geometric nonconformity. In this work, we propose a novel Geometric Consensus Rectification and Calibration algorithm, which we refer to as GCRC framework. We show how the geometric consensus rectification and calibration can be performed in a unified framework and solve the above issues. The proposed GCRC not only guarantees the geometrical consensus on the rectified images, but allows us to perform the robust intrinsic parameters estimation with the grouped circular arcs. Through “grouping by voting” in a unified framework, the geometric consensus rectification and calibration are robustly conducted on single distorted Manhattan images. Experiments on a number of distorted images, including the simulated YorkUrbanDB dataset, Panoramic Fisheye dataset, checkerboard image, and Internet images, demonstrate that the GCRC significantly improve the performance of geometrically consensus rectification and intrinsic parameters estimation. In particular, the GCRC shows relatively small variations with a different number of lines, which outperforms various previous approaches. |
| first_indexed | 2024-12-18T00:50:58Z |
| format | Article |
| id | doaj.art-63673b1170034dc59b1a4afcfbee0a02 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T00:50:58Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-63673b1170034dc59b1a4afcfbee0a022022-12-21T21:26:40ZengIEEEIEEE Access2169-35362019-01-01715640015641210.1109/ACCESS.2019.29471778867930Line-Based Geometric Consensus Rectification and Calibration From Single Distorted Manhattan ImageMi Zhang0https://orcid.org/0000-0003-4949-979XXiangyun Hu1Jian Yao2Like Zhao3Jiancheng Li4Jianya Gong5School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaCollege of Information Science and Engineering, Henan University of Technology, Zhengzhou, ChinaSchool of Geodesy and Geomatics, Wuhan University, Wuhan, ChinaSchool of Remote Sensing and Information Engineering, Wuhan University, Wuhan, ChinaRecent advances in single image rectification and intrinsic calibration has been addressed by employing line information on the distorted image. The core issues of this technique are the separation of rectification and calibration procedures, and the suffering of geometric nonconformity. In this work, we propose a novel Geometric Consensus Rectification and Calibration algorithm, which we refer to as GCRC framework. We show how the geometric consensus rectification and calibration can be performed in a unified framework and solve the above issues. The proposed GCRC not only guarantees the geometrical consensus on the rectified images, but allows us to perform the robust intrinsic parameters estimation with the grouped circular arcs. Through “grouping by voting” in a unified framework, the geometric consensus rectification and calibration are robustly conducted on single distorted Manhattan images. Experiments on a number of distorted images, including the simulated YorkUrbanDB dataset, Panoramic Fisheye dataset, checkerboard image, and Internet images, demonstrate that the GCRC significantly improve the performance of geometrically consensus rectification and intrinsic parameters estimation. In particular, the GCRC shows relatively small variations with a different number of lines, which outperforms various previous approaches.https://ieeexplore.ieee.org/document/8867930/Manhattan imageline detectiongeometric consensus rectificationcamera calibrationsingle image undistortion |
| spellingShingle | Mi Zhang Xiangyun Hu Jian Yao Like Zhao Jiancheng Li Jianya Gong Line-Based Geometric Consensus Rectification and Calibration From Single Distorted Manhattan Image IEEE Access Manhattan image line detection geometric consensus rectification camera calibration single image undistortion |
| title | Line-Based Geometric Consensus Rectification and Calibration From Single Distorted Manhattan Image |
| title_full | Line-Based Geometric Consensus Rectification and Calibration From Single Distorted Manhattan Image |
| title_fullStr | Line-Based Geometric Consensus Rectification and Calibration From Single Distorted Manhattan Image |
| title_full_unstemmed | Line-Based Geometric Consensus Rectification and Calibration From Single Distorted Manhattan Image |
| title_short | Line-Based Geometric Consensus Rectification and Calibration From Single Distorted Manhattan Image |
| title_sort | line based geometric consensus rectification and calibration from single distorted manhattan image |
| topic | Manhattan image line detection geometric consensus rectification camera calibration single image undistortion |
| url | https://ieeexplore.ieee.org/document/8867930/ |
| work_keys_str_mv | AT mizhang linebasedgeometricconsensusrectificationandcalibrationfromsingledistortedmanhattanimage AT xiangyunhu linebasedgeometricconsensusrectificationandcalibrationfromsingledistortedmanhattanimage AT jianyao linebasedgeometricconsensusrectificationandcalibrationfromsingledistortedmanhattanimage AT likezhao linebasedgeometricconsensusrectificationandcalibrationfromsingledistortedmanhattanimage AT jianchengli linebasedgeometricconsensusrectificationandcalibrationfromsingledistortedmanhattanimage AT jianyagong linebasedgeometricconsensusrectificationandcalibrationfromsingledistortedmanhattanimage |