Simple But Effective Scale Estimation for Monocular Visual Odometry in Road Driving Scenarios
In large-scale environments, scale drift is a crucial problem of monocular visual simultaneous localization and mapping (SLAM). A common solution is to utilize the camera height, which can be obtained using the reconstructed 3D ground points (3DGPs) from two successive frames, as prior knowledge. In...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9205188/ |
| _version_ | 1818431138686828544 |
|---|---|
| author | Ming Fan Seung-Wook Kim Sung-Tae Kim Jee-Young Sun Sung-Jea Ko |
| author_facet | Ming Fan Seung-Wook Kim Sung-Tae Kim Jee-Young Sun Sung-Jea Ko |
| author_sort | Ming Fan |
| collection | DOAJ |
| description | In large-scale environments, scale drift is a crucial problem of monocular visual simultaneous localization and mapping (SLAM). A common solution is to utilize the camera height, which can be obtained using the reconstructed 3D ground points (3DGPs) from two successive frames, as prior knowledge. Increasing the number of 3DGPs by using more proceeding frames can be a natural extension of this solution to estimate a more precise camera height. However, merely employing multiple frames based on conventional methods is hard to be directly applicable in a real-world scenario because the vehicle motion and inaccurate feature matching inevitably cause large uncertainty and noisy 3DGPs. In this study, we propose an elaborate method to collect confident 3DGPs from multiple frames for robust scale estimation. First, we gather 3DGP candidates that can be seen in more than a predefined number of frames. To verify the 3DGP candidates, we filter out the 3D points at the exterior of the road region obtained by the deep-learning-based road segmentation model. In addition, we formulate an optimization problem constrained by a simple but effective geometric assumption that the normal vector of the ground plane lies in the null space of a movement vector of the camera center, and provide a closed-form solution. ORB-SLAM with the proposed scale estimation method achieves the average translation error with 1.19% on the KITTI dataset, which outperforms the state-of-the-art conventional monocular visual SLAM methods in road driving scenarios. |
| first_indexed | 2024-12-14T15:44:33Z |
| format | Article |
| id | doaj.art-86d0ecf4719542c5ac66ff571289890d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T15:44:33Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-86d0ecf4719542c5ac66ff571289890d2022-12-21T22:55:32ZengIEEEIEEE Access2169-35362020-01-01817589117590310.1109/ACCESS.2020.30263479205188Simple But Effective Scale Estimation for Monocular Visual Odometry in Road Driving ScenariosMing Fan0https://orcid.org/0000-0002-0988-9091Seung-Wook Kim1https://orcid.org/0000-0002-6004-4086Sung-Tae Kim2https://orcid.org/0000-0001-6673-6924Jee-Young Sun3Sung-Jea Ko4https://orcid.org/0000-0002-4875-7091Department of Electrical Engineering, Korea University, Seoul, South KoreaDepartment of Electrical Engineering, Korea University, Seoul, South KoreaDepartment of Electrical Engineering, Korea University, Seoul, South KoreaDepartment of Electrical Engineering, Korea University, Seoul, South KoreaDepartment of Electrical Engineering, Korea University, Seoul, South KoreaIn large-scale environments, scale drift is a crucial problem of monocular visual simultaneous localization and mapping (SLAM). A common solution is to utilize the camera height, which can be obtained using the reconstructed 3D ground points (3DGPs) from two successive frames, as prior knowledge. Increasing the number of 3DGPs by using more proceeding frames can be a natural extension of this solution to estimate a more precise camera height. However, merely employing multiple frames based on conventional methods is hard to be directly applicable in a real-world scenario because the vehicle motion and inaccurate feature matching inevitably cause large uncertainty and noisy 3DGPs. In this study, we propose an elaborate method to collect confident 3DGPs from multiple frames for robust scale estimation. First, we gather 3DGP candidates that can be seen in more than a predefined number of frames. To verify the 3DGP candidates, we filter out the 3D points at the exterior of the road region obtained by the deep-learning-based road segmentation model. In addition, we formulate an optimization problem constrained by a simple but effective geometric assumption that the normal vector of the ground plane lies in the null space of a movement vector of the camera center, and provide a closed-form solution. ORB-SLAM with the proposed scale estimation method achieves the average translation error with 1.19% on the KITTI dataset, which outperforms the state-of-the-art conventional monocular visual SLAM methods in road driving scenarios.https://ieeexplore.ieee.org/document/9205188/Monocular SLAMscale estimation3D plane fitting |
| spellingShingle | Ming Fan Seung-Wook Kim Sung-Tae Kim Jee-Young Sun Sung-Jea Ko Simple But Effective Scale Estimation for Monocular Visual Odometry in Road Driving Scenarios IEEE Access Monocular SLAM scale estimation 3D plane fitting |
| title | Simple But Effective Scale Estimation for Monocular Visual Odometry in Road Driving Scenarios |
| title_full | Simple But Effective Scale Estimation for Monocular Visual Odometry in Road Driving Scenarios |
| title_fullStr | Simple But Effective Scale Estimation for Monocular Visual Odometry in Road Driving Scenarios |
| title_full_unstemmed | Simple But Effective Scale Estimation for Monocular Visual Odometry in Road Driving Scenarios |
| title_short | Simple But Effective Scale Estimation for Monocular Visual Odometry in Road Driving Scenarios |
| title_sort | simple but effective scale estimation for monocular visual odometry in road driving scenarios |
| topic | Monocular SLAM scale estimation 3D plane fitting |
| url | https://ieeexplore.ieee.org/document/9205188/ |
| work_keys_str_mv | AT mingfan simplebuteffectivescaleestimationformonocularvisualodometryinroaddrivingscenarios AT seungwookkim simplebuteffectivescaleestimationformonocularvisualodometryinroaddrivingscenarios AT sungtaekim simplebuteffectivescaleestimationformonocularvisualodometryinroaddrivingscenarios AT jeeyoungsun simplebuteffectivescaleestimationformonocularvisualodometryinroaddrivingscenarios AT sungjeako simplebuteffectivescaleestimationformonocularvisualodometryinroaddrivingscenarios |