SP-VO: RGB-D Visual Odometry Using Static Parts Toward Dynamic Environments
Estimating visual odometry in dynamic environments is a challenging problem, as features of moving objects prevent accurate image matching. Typical approach to deal with dynamic environments is to remove features of moving objects. However, this results in a lot of information loss and makes it impo...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10123925/ |
| _version_ | 1797823462319849472 |
|---|---|
| author | Hyeongjun Jeon Junghyun Oh |
| author_facet | Hyeongjun Jeon Junghyun Oh |
| author_sort | Hyeongjun Jeon |
| collection | DOAJ |
| description | Estimating visual odometry in dynamic environments is a challenging problem, as features of moving objects prevent accurate image matching. Typical approach to deal with dynamic environments is to remove features of moving objects. However, this results in a lot of information loss and makes it impossible to use static parts of moving objects that could be fully utilized for image matching process. To address this issue, we propose a geometrical inference approach that utilizes the static parts of moving objects and background to achieve accurate feature matching. Moreover, we propose the concept of matching confidence that is calculated by comparing the squared residual motion likelihood with the chi-square distribution. For each frame, the geometric model and the semantic model are selected according to the proposed confidence, so that visual odometry could be estimated more accurately. Our algorithm was evaluated on RGB-D datasets, including dynamic environments. The results show better performance than prior algorithms. |
| first_indexed | 2024-03-13T10:24:22Z |
| format | Article |
| id | doaj.art-fab39a0c23834962a104eff95c158a0c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T10:24:22Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-fab39a0c23834962a104eff95c158a0c2023-05-19T23:00:54ZengIEEEIEEE Access2169-35362023-01-0111472024721110.1109/ACCESS.2023.327573910123925SP-VO: RGB-D Visual Odometry Using Static Parts Toward Dynamic EnvironmentsHyeongjun Jeon0https://orcid.org/0000-0001-6091-7951Junghyun Oh1https://orcid.org/0000-0003-0502-7600Department of Robotics, Kwangwoon University, Seoul, South KoreaDepartment of Robotics, Kwangwoon University, Seoul, South KoreaEstimating visual odometry in dynamic environments is a challenging problem, as features of moving objects prevent accurate image matching. Typical approach to deal with dynamic environments is to remove features of moving objects. However, this results in a lot of information loss and makes it impossible to use static parts of moving objects that could be fully utilized for image matching process. To address this issue, we propose a geometrical inference approach that utilizes the static parts of moving objects and background to achieve accurate feature matching. Moreover, we propose the concept of matching confidence that is calculated by comparing the squared residual motion likelihood with the chi-square distribution. For each frame, the geometric model and the semantic model are selected according to the proposed confidence, so that visual odometry could be estimated more accurately. Our algorithm was evaluated on RGB-D datasets, including dynamic environments. The results show better performance than prior algorithms.https://ieeexplore.ieee.org/document/10123925/Visual odometryroboticscomputer visionmobile robotsSLAM |
| spellingShingle | Hyeongjun Jeon Junghyun Oh SP-VO: RGB-D Visual Odometry Using Static Parts Toward Dynamic Environments IEEE Access Visual odometry robotics computer vision mobile robots SLAM |
| title | SP-VO: RGB-D Visual Odometry Using Static Parts Toward Dynamic Environments |
| title_full | SP-VO: RGB-D Visual Odometry Using Static Parts Toward Dynamic Environments |
| title_fullStr | SP-VO: RGB-D Visual Odometry Using Static Parts Toward Dynamic Environments |
| title_full_unstemmed | SP-VO: RGB-D Visual Odometry Using Static Parts Toward Dynamic Environments |
| title_short | SP-VO: RGB-D Visual Odometry Using Static Parts Toward Dynamic Environments |
| title_sort | sp vo rgb d visual odometry using static parts toward dynamic environments |
| topic | Visual odometry robotics computer vision mobile robots SLAM |
| url | https://ieeexplore.ieee.org/document/10123925/ |
| work_keys_str_mv | AT hyeongjunjeon spvorgbdvisualodometryusingstaticpartstowarddynamicenvironments AT junghyunoh spvorgbdvisualodometryusingstaticpartstowarddynamicenvironments |