File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TIM.2023.3280507
- Scopus: eid_2-s2.0-85161044352
- WOS: WOS:001012832900033
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Filtering 2D-3D Outliers by Camera Adjustment for Visual Odometry
Title | Filtering 2D-3D Outliers by Camera Adjustment for Visual Odometry |
---|---|
Authors | |
Keywords | 3-D reconstruction camera pose estimation outlier filtering structure from motion uncertainty measurement visual odometry (VO) visual serving |
Issue Date | 29-May-2023 |
Publisher | Institute of Electrical and Electronics Engineers |
Citation | IEEE Transactions on Instrumentation and Measurement, 2023, v. 72 How to Cite? |
Abstract | We study the problem of the discrepancy between model predictions and image measurements in the form of keypoint locations for perspective cameras. In this process, the prediction is made by projecting given 3-D points using the known pose of a calibrated camera. We test whether some small camera pose adjustment exists for each measurement such that the mentioned discrepancy vanishes. Such adjustment would allow us to quantify the effect of each measurement on the camera pose. In this article, we show for the first time that the pose influence assessment of individual measurements can be used to select a subset of the correspondences for accurate 3-D triangulation from two views. We further demonstrate via several experiments that the obtained 3-D points are well suited to the task of absolute localization. When the 3-D points are provided from an anonymized source, the proposed method also selects a suitable subset of 3-D points for accurate localization around an initial guess. The long-term effectiveness of our filtration method is demonstrated by integrating the method within a typical framework of visual odometry (VO). The proposed method is evaluated on ETH3D and EuRoC benchmarks with real-world data. The results indicate that the proposed method outperforms the state-of-the-art methods in terms of the point uncertainty measure and camera pose estimation accuracy. |
Persistent Identifier | http://hdl.handle.net/10722/337632 |
ISSN | 2023 Impact Factor: 5.6 2023 SCImago Journal Rankings: 1.536 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Duan, Ran | - |
dc.contributor.author | Paudel, Pani Danda | - |
dc.contributor.author | Wen, Chih-Yung | - |
dc.contributor.author | Lu, Peng | - |
dc.date.accessioned | 2024-03-11T10:22:40Z | - |
dc.date.available | 2024-03-11T10:22:40Z | - |
dc.date.issued | 2023-05-29 | - |
dc.identifier.citation | IEEE Transactions on Instrumentation and Measurement, 2023, v. 72 | - |
dc.identifier.issn | 0018-9456 | - |
dc.identifier.uri | http://hdl.handle.net/10722/337632 | - |
dc.description.abstract | <p>We study the problem of the discrepancy between model predictions and image measurements in the form of keypoint locations for perspective cameras. In this process, the prediction is made by projecting given 3-D points using the known pose of a calibrated camera. We test whether some small camera pose adjustment exists for each measurement such that the mentioned discrepancy vanishes. Such adjustment would allow us to quantify the effect of each measurement on the camera pose. In this article, we show for the first time that the pose influence assessment of individual measurements can be used to select a subset of the correspondences for accurate 3-D triangulation from two views. We further demonstrate via several experiments that the obtained 3-D points are well suited to the task of absolute localization. When the 3-D points are provided from an anonymized source, the proposed method also selects a suitable subset of 3-D points for accurate localization around an initial guess. The long-term effectiveness of our filtration method is demonstrated by integrating the method within a typical framework of visual odometry (VO). The proposed method is evaluated on ETH3D and EuRoC benchmarks with real-world data. The results indicate that the proposed method outperforms the state-of-the-art methods in terms of the point uncertainty measure and camera pose estimation accuracy.<br></p> | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers | - |
dc.relation.ispartof | IEEE Transactions on Instrumentation and Measurement | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.subject | 3-D reconstruction | - |
dc.subject | camera pose estimation | - |
dc.subject | outlier filtering | - |
dc.subject | structure from motion | - |
dc.subject | uncertainty measurement | - |
dc.subject | visual odometry (VO) | - |
dc.subject | visual serving | - |
dc.title | Filtering 2D-3D Outliers by Camera Adjustment for Visual Odometry | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/TIM.2023.3280507 | - |
dc.identifier.scopus | eid_2-s2.0-85161044352 | - |
dc.identifier.volume | 72 | - |
dc.identifier.eissn | 1557-9662 | - |
dc.identifier.isi | WOS:001012832900033 | - |
dc.identifier.issnl | 0018-9456 | - |