Feature-based RGB-D camera pose optimization for real-time 3D reconstruction
Abstract In this paper we present a novel feature-based RGB-D camera pose optimization algorithm for real-time 3D reconstruction systems. During camera pose estimation, current methods in online systems suffer from fast-scanned RGB-D data, or generate inaccurate relative transformations between cons...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2017-03-01
|
| Series: | Computational Visual Media |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1007/s41095-016-0072-2 |
| _version_ | 1818425179671363584 |
|---|---|
| author | Chao Wang Xiaohu Guo |
| author_facet | Chao Wang Xiaohu Guo |
| author_sort | Chao Wang |
| collection | DOAJ |
| description | Abstract In this paper we present a novel feature-based RGB-D camera pose optimization algorithm for real-time 3D reconstruction systems. During camera pose estimation, current methods in online systems suffer from fast-scanned RGB-D data, or generate inaccurate relative transformations between consecutive frames. Our approach improves current methods by utilizing matched features across all frames and is robust for RGB-D data with large shifts in consecutive frames. We directly estimate camera pose for each frame by efficiently solving a quadratic minimization problem to maximize the consistency of 3D points in global space across frames corresponding to matched feature points. We have implemented our method within two state-of-the-art online 3D reconstruction platforms. Experimental results testify that our method is efficient and reliable in estimating camera poses for RGB-D data with large shifts. |
| first_indexed | 2024-12-14T14:09:50Z |
| format | Article |
| id | doaj.art-57b2fdb591044b02b3e3ec2f5aca3584 |
| institution | Directory Open Access Journal |
| issn | 2096-0433 2096-0662 |
| language | English |
| last_indexed | 2024-12-14T14:09:50Z |
| publishDate | 2017-03-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Computational Visual Media |
| spelling | doaj.art-57b2fdb591044b02b3e3ec2f5aca35842022-12-21T22:58:21ZengSpringerOpenComputational Visual Media2096-04332096-06622017-03-01329510610.1007/s41095-016-0072-2Feature-based RGB-D camera pose optimization for real-time 3D reconstructionChao Wang0Xiaohu Guo1University of Texas at DallasUniversity of Texas at DallasAbstract In this paper we present a novel feature-based RGB-D camera pose optimization algorithm for real-time 3D reconstruction systems. During camera pose estimation, current methods in online systems suffer from fast-scanned RGB-D data, or generate inaccurate relative transformations between consecutive frames. Our approach improves current methods by utilizing matched features across all frames and is robust for RGB-D data with large shifts in consecutive frames. We directly estimate camera pose for each frame by efficiently solving a quadratic minimization problem to maximize the consistency of 3D points in global space across frames corresponding to matched feature points. We have implemented our method within two state-of-the-art online 3D reconstruction platforms. Experimental results testify that our method is efficient and reliable in estimating camera poses for RGB-D data with large shifts.http://link.springer.com/article/10.1007/s41095-016-0072-2camera pose optimizationfeature matchingreal-time 3D reconstructionfeature correspondence |
| spellingShingle | Chao Wang Xiaohu Guo Feature-based RGB-D camera pose optimization for real-time 3D reconstruction Computational Visual Media camera pose optimization feature matching real-time 3D reconstruction feature correspondence |
| title | Feature-based RGB-D camera pose optimization for real-time 3D reconstruction |
| title_full | Feature-based RGB-D camera pose optimization for real-time 3D reconstruction |
| title_fullStr | Feature-based RGB-D camera pose optimization for real-time 3D reconstruction |
| title_full_unstemmed | Feature-based RGB-D camera pose optimization for real-time 3D reconstruction |
| title_short | Feature-based RGB-D camera pose optimization for real-time 3D reconstruction |
| title_sort | feature based rgb d camera pose optimization for real time 3d reconstruction |
| topic | camera pose optimization feature matching real-time 3D reconstruction feature correspondence |
| url | http://link.springer.com/article/10.1007/s41095-016-0072-2 |
| work_keys_str_mv | AT chaowang featurebasedrgbdcameraposeoptimizationforrealtime3dreconstruction AT xiaohuguo featurebasedrgbdcameraposeoptimizationforrealtime3dreconstruction |