Efficient Ego-Motion Estimation for Multi-Camera Systems With Decoupled Rotation and Translation
In this article, we present novel solutions to estimate the ego-motion of a multi-camera system with a known vertical direction (e.g., from the inertial measurement unit). By assuming small camera motion between successive video frames, we demonstrate that rotation and translation estimation can be...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9172053/ |
| _version_ | 1818736488476573696 |
|---|---|
| author | Miao Tian Banglei Guan Zhibin Xing Friedrich Fraundorfer |
| author_facet | Miao Tian Banglei Guan Zhibin Xing Friedrich Fraundorfer |
| author_sort | Miao Tian |
| collection | DOAJ |
| description | In this article, we present novel solutions to estimate the ego-motion of a multi-camera system with a known vertical direction (e.g., from the inertial measurement unit). By assuming small camera motion between successive video frames, we demonstrate that rotation and translation estimation can be decoupled. This makes our methods require fewer correspondences to estimate the ego-motion and have a good accuracy. Accordingly, we estimate the ego-motion with two steps. First, we propose a 1-point method to estimate rotation with only a single correspondence which produces up to two solutions. Then, we adopt a 3-point linear method and a 2-point sampling method to solve translation which produce a single solution. We compared our algorithms with state-of-the-art algorithms on synthetic and real datasets. The experiments demonstrate that our algorithms are accurate and efficient in road driving scenarios. We also demonstrate that our proposed methods can efficiently find an optimal inlier set using histogram voting or exhaustive search instead of RANSAC. |
| first_indexed | 2024-12-18T00:37:57Z |
| format | Article |
| id | doaj.art-f18ccd167bc34a10ab9cd1a4aa2e1e42 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T00:37:57Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f18ccd167bc34a10ab9cd1a4aa2e1e422022-12-21T21:26:57ZengIEEEIEEE Access2169-35362020-01-01815380415381410.1109/ACCESS.2020.30182259172053Efficient Ego-Motion Estimation for Multi-Camera Systems With Decoupled Rotation and TranslationMiao Tian0https://orcid.org/0000-0001-5265-6050Banglei Guan1https://orcid.org/0000-0003-2123-0182Zhibin Xing2https://orcid.org/0000-0002-0416-4294Friedrich Fraundorfer3https://orcid.org/0000-0002-5805-8892College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, ChinaCollege of Aerospace Science and Engineering, National University of Defense Technology, Changsha, ChinaSchool of Non-Commissioned Officer, Space Engineering University, Beijing, ChinaInstitute of Computer Graphics and Vision, Graz University of Technology, Graz, AustriaIn this article, we present novel solutions to estimate the ego-motion of a multi-camera system with a known vertical direction (e.g., from the inertial measurement unit). By assuming small camera motion between successive video frames, we demonstrate that rotation and translation estimation can be decoupled. This makes our methods require fewer correspondences to estimate the ego-motion and have a good accuracy. Accordingly, we estimate the ego-motion with two steps. First, we propose a 1-point method to estimate rotation with only a single correspondence which produces up to two solutions. Then, we adopt a 3-point linear method and a 2-point sampling method to solve translation which produce a single solution. We compared our algorithms with state-of-the-art algorithms on synthetic and real datasets. The experiments demonstrate that our algorithms are accurate and efficient in road driving scenarios. We also demonstrate that our proposed methods can efficiently find an optimal inlier set using histogram voting or exhaustive search instead of RANSAC.https://ieeexplore.ieee.org/document/9172053/Generalized epipolar constraintmulti-camera systemrelative pose estimation |
| spellingShingle | Miao Tian Banglei Guan Zhibin Xing Friedrich Fraundorfer Efficient Ego-Motion Estimation for Multi-Camera Systems With Decoupled Rotation and Translation IEEE Access Generalized epipolar constraint multi-camera system relative pose estimation |
| title | Efficient Ego-Motion Estimation for Multi-Camera Systems With Decoupled Rotation and Translation |
| title_full | Efficient Ego-Motion Estimation for Multi-Camera Systems With Decoupled Rotation and Translation |
| title_fullStr | Efficient Ego-Motion Estimation for Multi-Camera Systems With Decoupled Rotation and Translation |
| title_full_unstemmed | Efficient Ego-Motion Estimation for Multi-Camera Systems With Decoupled Rotation and Translation |
| title_short | Efficient Ego-Motion Estimation for Multi-Camera Systems With Decoupled Rotation and Translation |
| title_sort | efficient ego motion estimation for multi camera systems with decoupled rotation and translation |
| topic | Generalized epipolar constraint multi-camera system relative pose estimation |
| url | https://ieeexplore.ieee.org/document/9172053/ |
| work_keys_str_mv | AT miaotian efficientegomotionestimationformulticamerasystemswithdecoupledrotationandtranslation AT bangleiguan efficientegomotionestimationformulticamerasystemswithdecoupledrotationandtranslation AT zhibinxing efficientegomotionestimationformulticamerasystemswithdecoupledrotationandtranslation AT friedrichfraundorfer efficientegomotionestimationformulticamerasystemswithdecoupledrotationandtranslation |