Accurate Uncalibrated Rectification Using Feature Matching Re-Selection
Rectification is a core programming process that involves multiple views. In this study, we focus on uncalibrated cases that neglect intrinsic and extrinsic camera information. Existing uncalibrated rectification methods use feature-matching techniques to form relationships between different views a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9579422/ |
| _version_ | 1811210607822635008 |
|---|---|
| author | Tai Huu-Phuong Tran Huy-Hung Nguyen Jae Wook Jeon |
| author_facet | Tai Huu-Phuong Tran Huy-Hung Nguyen Jae Wook Jeon |
| author_sort | Tai Huu-Phuong Tran |
| collection | DOAJ |
| description | Rectification is a core programming process that involves multiple views. In this study, we focus on uncalibrated cases that neglect intrinsic and extrinsic camera information. Existing uncalibrated rectification methods use feature-matching techniques to form relationships between different views and use those features to estimate optimized homography matrices. However, outliers are inevitable in feature matching. Using these outliers in a rectification process produces vertical disparity errors and unwanted geometric distortion. To tackle the problem, we propose a novel method that can learn from the rectification results, re-select the matching pairs, and find superior solutions. The proposed method introduces a novel workflow for uncalibrated rectification that incorporates three cores: field of view (FoV) neutralization, rectification, and feature matching re-selection (FMR). While the FoV neutralization module handles FoV differences among views, a combination of the rectification module and FMR module results in the optimal homography matrices. The rectification module takes neutral correspondences and estimates the optimized rectified matrices. Applying the results from the rectification module, the FMR module optimizes the correspondences and return them to the rectification module. For the rectification module, we apply adaptive geometric constraints and our updated optimization strategy to secure satisfied vertical disparity errors while maintaining low distortion levels. Multidisciplinary experiments are performed to analyze the capabilities of the proposed method. We combine existing datasets with extra samples, including various outdoor environments, to gauge the performance better. Compared with existing methods, the proposed method produces fewer rectification errors and keeps the rectified images under low distortion rates. |
| first_indexed | 2024-04-12T04:57:37Z |
| format | Article |
| id | doaj.art-ff0b5b9eb4d24ac3a601d15757cb7ffe |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T04:57:37Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-ff0b5b9eb4d24ac3a601d15757cb7ffe2022-12-22T03:47:04ZengIEEEIEEE Access2169-35362021-01-01914215614216710.1109/ACCESS.2021.31212769579422Accurate Uncalibrated Rectification Using Feature Matching Re-SelectionTai Huu-Phuong Tran0https://orcid.org/0000-0001-9066-4633Huy-Hung Nguyen1https://orcid.org/0000-0001-5394-9381Jae Wook Jeon2https://orcid.org/0000-0003-0037-112XDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South KoreaDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South KoreaDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South KoreaRectification is a core programming process that involves multiple views. In this study, we focus on uncalibrated cases that neglect intrinsic and extrinsic camera information. Existing uncalibrated rectification methods use feature-matching techniques to form relationships between different views and use those features to estimate optimized homography matrices. However, outliers are inevitable in feature matching. Using these outliers in a rectification process produces vertical disparity errors and unwanted geometric distortion. To tackle the problem, we propose a novel method that can learn from the rectification results, re-select the matching pairs, and find superior solutions. The proposed method introduces a novel workflow for uncalibrated rectification that incorporates three cores: field of view (FoV) neutralization, rectification, and feature matching re-selection (FMR). While the FoV neutralization module handles FoV differences among views, a combination of the rectification module and FMR module results in the optimal homography matrices. The rectification module takes neutral correspondences and estimates the optimized rectified matrices. Applying the results from the rectification module, the FMR module optimizes the correspondences and return them to the rectification module. For the rectification module, we apply adaptive geometric constraints and our updated optimization strategy to secure satisfied vertical disparity errors while maintaining low distortion levels. Multidisciplinary experiments are performed to analyze the capabilities of the proposed method. We combine existing datasets with extra samples, including various outdoor environments, to gauge the performance better. Compared with existing methods, the proposed method produces fewer rectification errors and keeps the rectified images under low distortion rates.https://ieeexplore.ieee.org/document/9579422/Different fields of viewfeature matching re-selectionlow distortionmultiple viewsuncalibrated rectification |
| spellingShingle | Tai Huu-Phuong Tran Huy-Hung Nguyen Jae Wook Jeon Accurate Uncalibrated Rectification Using Feature Matching Re-Selection IEEE Access Different fields of view feature matching re-selection low distortion multiple views uncalibrated rectification |
| title | Accurate Uncalibrated Rectification Using Feature Matching Re-Selection |
| title_full | Accurate Uncalibrated Rectification Using Feature Matching Re-Selection |
| title_fullStr | Accurate Uncalibrated Rectification Using Feature Matching Re-Selection |
| title_full_unstemmed | Accurate Uncalibrated Rectification Using Feature Matching Re-Selection |
| title_short | Accurate Uncalibrated Rectification Using Feature Matching Re-Selection |
| title_sort | accurate uncalibrated rectification using feature matching re selection |
| topic | Different fields of view feature matching re-selection low distortion multiple views uncalibrated rectification |
| url | https://ieeexplore.ieee.org/document/9579422/ |
| work_keys_str_mv | AT taihuuphuongtran accurateuncalibratedrectificationusingfeaturematchingreselection AT huyhungnguyen accurateuncalibratedrectificationusingfeaturematchingreselection AT jaewookjeon accurateuncalibratedrectificationusingfeaturematchingreselection |