An improved semi-synthetic approach for creating visual-inertial odometry datasets
Capturing outdoor visual-inertial datasets is a challenging yet vital aspect of developing robust visual-inertial odometry (VIO) algorithms. A significant hurdle is that high-accuracy-ground-truth systems (e.g., motion capture) are not practical for outdoor use. One solution is to use a “semi-synthe...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-04-01
|
| Series: | Graphical Models |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1524070323000036 |
| _version_ | 1797788442376011776 |
|---|---|
| author | Sam Schofield Andrew Bainbridge-Smith Richard Green |
| author_facet | Sam Schofield Andrew Bainbridge-Smith Richard Green |
| author_sort | Sam Schofield |
| collection | DOAJ |
| description | Capturing outdoor visual-inertial datasets is a challenging yet vital aspect of developing robust visual-inertial odometry (VIO) algorithms. A significant hurdle is that high-accuracy-ground-truth systems (e.g., motion capture) are not practical for outdoor use. One solution is to use a “semi-synthetic” approach that combines rendered images with real IMU data. This approach can produce sequences containing challenging imagery and accurate ground truth but with less simulated data than a fully synthetic sequence. Existing methods (used by popular tools/datasets) record IMU measurements from a visual-inertial system while measuring its trajectory using motion capture, then rendering images along that trajectory. This work identifies a major flaw in that approach, specifically that using motion capture alone to estimate the pose of the robot/system results in the generation of inconsistent visual-inertial data that is not suitable for evaluating VIO algorithms. However, we show that it is possible to generate high-quality semi-synthetic data for VIO algorithm evaluation. We do so using an open-source full-batch optimisation tool to incorporate both mocap and IMU measurements when estimating the IMU’s trajectory. We demonstrate that this improved trajectory results in better consistency between the IMU data and rendered images and that the resulting data improves VIO trajectory error by 79% compared to existing methods. Furthermore, we examine the effect of visual-inertial data inconsistency (as a result of trajectory noise) on VIO performance to provide a foundation for future work targeting real-time applications. |
| first_indexed | 2024-03-13T01:36:34Z |
| format | Article |
| id | doaj.art-21837ce3ec834569bfa5261eaba9ae7c |
| institution | Directory Open Access Journal |
| issn | 1524-0703 |
| language | English |
| last_indexed | 2024-03-13T01:36:34Z |
| publishDate | 2023-04-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Graphical Models |
| spelling | doaj.art-21837ce3ec834569bfa5261eaba9ae7c2023-07-04T05:09:40ZengElsevierGraphical Models1524-07032023-04-01126101172An improved semi-synthetic approach for creating visual-inertial odometry datasetsSam Schofield0Andrew Bainbridge-Smith1Richard Green2Correspondence to: Department of Computer Science and Software Engineering, 20 Kirkwood Avenue, Upper Riccarton, Christchurch 8041, New Zealand.; Department of Computer Science and Software Engineering, University of Canterbury, New ZealandDepartment of Computer Science and Software Engineering, University of Canterbury, New ZealandDepartment of Computer Science and Software Engineering, University of Canterbury, New ZealandCapturing outdoor visual-inertial datasets is a challenging yet vital aspect of developing robust visual-inertial odometry (VIO) algorithms. A significant hurdle is that high-accuracy-ground-truth systems (e.g., motion capture) are not practical for outdoor use. One solution is to use a “semi-synthetic” approach that combines rendered images with real IMU data. This approach can produce sequences containing challenging imagery and accurate ground truth but with less simulated data than a fully synthetic sequence. Existing methods (used by popular tools/datasets) record IMU measurements from a visual-inertial system while measuring its trajectory using motion capture, then rendering images along that trajectory. This work identifies a major flaw in that approach, specifically that using motion capture alone to estimate the pose of the robot/system results in the generation of inconsistent visual-inertial data that is not suitable for evaluating VIO algorithms. However, we show that it is possible to generate high-quality semi-synthetic data for VIO algorithm evaluation. We do so using an open-source full-batch optimisation tool to incorporate both mocap and IMU measurements when estimating the IMU’s trajectory. We demonstrate that this improved trajectory results in better consistency between the IMU data and rendered images and that the resulting data improves VIO trajectory error by 79% compared to existing methods. Furthermore, we examine the effect of visual-inertial data inconsistency (as a result of trajectory noise) on VIO performance to provide a foundation for future work targeting real-time applications.http://www.sciencedirect.com/science/article/pii/S1524070323000036Visual inertial odometrySemi-synthetic datasetRobot virtual reality |
| spellingShingle | Sam Schofield Andrew Bainbridge-Smith Richard Green An improved semi-synthetic approach for creating visual-inertial odometry datasets Graphical Models Visual inertial odometry Semi-synthetic dataset Robot virtual reality |
| title | An improved semi-synthetic approach for creating visual-inertial odometry datasets |
| title_full | An improved semi-synthetic approach for creating visual-inertial odometry datasets |
| title_fullStr | An improved semi-synthetic approach for creating visual-inertial odometry datasets |
| title_full_unstemmed | An improved semi-synthetic approach for creating visual-inertial odometry datasets |
| title_short | An improved semi-synthetic approach for creating visual-inertial odometry datasets |
| title_sort | improved semi synthetic approach for creating visual inertial odometry datasets |
| topic | Visual inertial odometry Semi-synthetic dataset Robot virtual reality |
| url | http://www.sciencedirect.com/science/article/pii/S1524070323000036 |
| work_keys_str_mv | AT samschofield animprovedsemisyntheticapproachforcreatingvisualinertialodometrydatasets AT andrewbainbridgesmith animprovedsemisyntheticapproachforcreatingvisualinertialodometrydatasets AT richardgreen animprovedsemisyntheticapproachforcreatingvisualinertialodometrydatasets AT samschofield improvedsemisyntheticapproachforcreatingvisualinertialodometrydatasets AT andrewbainbridgesmith improvedsemisyntheticapproachforcreatingvisualinertialodometrydatasets AT richardgreen improvedsemisyntheticapproachforcreatingvisualinertialodometrydatasets |