Dataset Open Access

RP-VIO: Robust Plane-based Visual-Inertial Odometry (Dataset)

Ram, Karnik; Kharyal, Chaitanya; Harithas, Sudarshan; Krishna, Madhava

Dataset accompanying our paper on 'RP-VIO: Robust Plane-based Visual-Inertial Odometry for Dynamic Environments'. Data description is available on our project page: https://github.com/karnikram/rp-vio

Paper abstract: Modern visual-inertial navigation systems (VINS) are faced with a critical challenge in real-world deployment: they need to operate reliably and robustly in highly dynamic environments. Current best solutions merely filter dynamic objects as outliers based on the semantics of the object category. Such an approach does not scale as it requires semantic classifiers to encompass all possibly-moving object classes; this is hard to define, let alone deploy. On the other hand, many real-world environments exhibit strong structural regularities in the form of planes such as walls and ground surfaces, which are also crucially static. We present RP-VIO, a monocular visual-inertial odometry system that leverages the simple geometry of these planes for improved robustness and accuracy in challenging dynamic environments. Since existing datasets have a limited number of dynamic elements, we also present a highly-dynamic, photorealistic synthetic dataset for a more effective evaluation of the capabilities of modern VINS systems. We evaluate our approach on this dataset, and three diverse sequences from standard datasets including two real-world dynamic sequences and show a significant improvement in robustness and accuracy over a state-of-the-art monocular visual-inertial odometry system. We also show in simulation an improvement over a simple dynamic-features masking approach. Our code and dataset are publicly available.

Files (3.6 GB)
Name Size
c1.zip
md5:09570e6582c446f60aeb621f9022803f
600.9 MB Download
c2.zip
md5:d8e5e37449ff20152baa977138014f04
598.7 MB Download
c4.zip
md5:07888990eafaba501c74fbdc54cec18b
602.9 MB Download
c6.zip
md5:9d8b2695cc084531e482a52f987794f8
610.8 MB Download
c8.zip
md5:c5f538cb57bf78671e25d996badb9eaf
595.9 MB Download
static.zip
md5:ffe4ba8e21e14d4427e0315be3cb8cc6
594.7 MB Download
110
583
views
downloads
Views 110
Downloads 583
Data volume 349.9 GB
Unique views 95
Unique downloads 86

Share

Cite as