The EuRoC micro aerial vehicle datasets

By Michael Burri, Janosch Nikolic, Pascal Gohl, Thomas Schneider, J. Rehder, Sammy Omari, Markus Achtelik, Roland Yves Siegwart. Int. J. Robotics Res., 2016

2,066 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Geology

View Paper: https://www.semanticscholar.org/paper/8f82018104f6c9f523818007a6e94b63fb2235b6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Geology

Citations in the corpus

BA-Net: Dense Bundle Adjustment Network (2018, methodology): “Due to page limit, we move the ablation studies, evaluation on DeMoN’s dataset, multi-view SfM (up to 5 views), and comparison with CodeSLAM on the EuroC dataset (Burri et al., 2016) to the appendix.”
CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM (2018, background): “ network embeds geometry priors in its weights. These learned priors seem to generalise to real scenes as well: Figure1depicts a two-frame reconstruction with images from the real image EuRoC dataset [2] taken by a drone in an industrial setting. The result corresponds to 50 optimisation steps, each”
Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning (2024, methodology): “To evaluate the generalization ability of our method, we also conduct experiments on an other TUM-VI dataset [27], which is a highly challenging handheld dataset with large-scale scenes, compared with the EuRoC dataset [5].”
DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras (2021, methodology): “Results on EuRoC, TartanAir and ETH-3D (where video can be up to 5000 frames) requires a GPU with 24GB memory.”
Depth From Videos in the Wild: Unsupervised Monocular Depth Learning From Unknown Cameras (2019, methodology): “Frames from EuRoC [5] and the corresponding learned disparity maps.”
Robust Stereo Visual Inertial Odometry for Fast Autonomous Flight (2017, methodology): “Note that compared to the experiments with the EuRoC dataset, the proposed method spends more computational effort on the image processing frontend.”
VINet: Visual-Inertial Odometry as a Sequence-to-Sequence Learning Problem (2017, methodology): “UAV: Challenging Indoor Trajectory We first evaluate our approach on the publicly-available indoor EuRoC micro-aerial-vehicle (MAV) dataset (Burri et al. 2016).”
OpenVSLAM: A Versatile Visual SLAM Framework (2019, methodology): “map information can be reused for any third-party applications in addition to OpenVSLAM. 4 QUANTITATIVE EVALUATION In this section, tracking accuracy of OpenVSLAM is evaluated using EuRoC MAV dataset [2] and KITTI Odomery dataset [5], both of which have ground-truth trajectories. ORB–SLAM2 [11], the”
Visual-Inertial Monocular SLAM With Map Reuse (2016, methodology): “Estimated map and keyframes by our Visual-Inertial ORB-SLAM in V1 02 medium from the EuRoC dataset [14].”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, neutral): “DAR3D LOC MAP RGB RGBD Stereo Front-ends and back-ends in small / medium scale scenarios [293] X X X [319] X X X [233] X X X X X [283] X X X X [141, 239] X [134, 317, 318] X X X [122] X X X X X X X X [39] X X X X X [254] X X X X X Back-ends in small / medium scale scenarios [45, 186] X X Front-ends ”
A General Optimization-based Framework for Local Odometry Estimation with Multiple Sensors (2019, methodology): “We evaluate our proposed system using the EuRoC MAV Visual-Inertial Datasets [27].”
NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields (2022, background): “…estimator [1] to the problem of visual odometry, Droid-SLAM[12] achieves competitive results in a variety of challenging datasets (such as Euroc [13] and TartanAir [14] datasets), Droid-SLAM avoids the dimensionality problem by using downsampled depth maps that are subsequently upsampled using…”
PL-VIO: Tightly-Coupled Monocular Visual–Inertial Odometry Using Point and Line Features (2018, methodology): “The EuRoc micro aerial vehicle (MAV) datasets were collected by an MAV in two indoor scenes, which contain stereo images from a global shutter camera at 20FPS and synchronized IMU measurements at 200 Hz [44].”
ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras (2016, background): “The recent EuRoC dataset [21] contains 11 stereo sequences recorded from a microaerial vehicle (MAV) flying around two different rooms and a large industrial environment.”
TartanAir: A Dataset to Push the Limits of Visual SLAM (2020, background): “Dataset Sensors/Ground Truth Label Conditions Motion Pattern Seq Num Stereo Flow Depth Lidar Pose Light Weather Season DynObj KITTI [12] � � � � � � Car 22 Virtual KITTI [21] � � � � � � Car 50 EuRoC MAV [14] � � � MAV 11 TUM RGB-D [13] � � � Hand 15 ICL-NUM [28] � � Hand 8 SceneNet [20] � � � � Ran”
D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry (2020, methodology): “We evaluate the proposed self-supervised monocular depth estimation network as well as D3VO on both the KITTI [25] and the EuRoC MAV [5] [15].”
Extending Monocular Visual Odometry to Stereo Camera Systems by Scale optimization (2019, methodology): “These include tests on two publicly-available datasets: the KITTI Visual Odometry dataset [19] and the EuRoC MAV dataset [20].”
A Tutorial on Quantitative Trajectory Evaluation for Visual(-Inertial) Odometry (2018, methodology): “We ran VINS-Mono [15], which is a visual-inertial odometry algorithm, on the Machine Hall 01 sequence from the EuRoC dataset [16] and evaluated the estimated trajectory.”
Kimera: From SLAM to spatial perception with 3D dynamic scene graphs (2021, methodology): “We test Kimera in both real and simulated datasets, including the EuRoC dataset (Burri et al., 2016) and the uHumans dataset we released with Rosinol et al.”