Abstract | ||
---|---|---|
Pavement condition is crucial for civil infrastructure maintenance. This task usually requires efficient road damage localization, which can be accomplished by the visual odometry system embedded in unmanned aerial vehicles (UAVs), However, the state-of-the-art visual odometry and mapping methods suffer from large drift under the degeneration of the scene structure. To alleviate this issue, we integrate normal constraints into the visual odometry process, which greatly helps to avoid large drift. By parameterizing the normal vector on the tangential plane, the normal factors are coupled with traditional reprojection factors in the pose optimization procedure. The experimental results demonstrate the effectiveness of the proposed system. The overall absolute trajectory error is improved by approximately 20%, which indicates that the estimated trajectory is much more accurate than that obtained using other state-of-the-art methods. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/IST48021.2019.9010439 | 2019 IEEE International Conference on Imaging Systems and Techniques (IST) |
Keywords | DocType | ISSN |
unmanned aerial vehicles,scene structure,visual odometry process,traditional reprojection factors,robust pavement mapping system,normal-constrained stereo visual odometry,pavement condition,civil infrastructure maintenance,visual odometry system,road damage localization | Conference | 1558-2809 |
ISBN | Citations | PageRank |
978-1-7281-3869-5 | 1 | 0.36 |
References | Authors | |
20 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Huaiyang Huang | 1 | 15 | 5.34 |
Rui Fan | 2 | 258 | 28.91 |
Yilong Zhu | 3 | 6 | 6.16 |
Ming Liu | 4 | 775 | 94.83 |
Ioannis Pitas | 5 | 6478 | 626.09 |