Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commite03c2f8

Browse files
committed
Add 2 more datasets.
1 parent0cfe714 commite03c2f8

File tree

2 files changed

+92
-0
lines changed

2 files changed

+92
-0
lines changed

‎_datasets/ir_dataset.md‎

Lines changed: 40 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,40 @@
1+
---
2+
layout:dataset
3+
title:"IR ICRA 2014 – Illumination-Robust Visual-Inertial Dataset"
4+
year:2014
5+
tags:[visual-inertial, illumination, calibration, slam]
6+
eth_collection_url:"https://doi.org/10.3929/ethz-b-000721641"
7+
paper:"Illumination-Robust Monocular Visual Odometry for On-Board MAVs (ICRA 2014)"
8+
doi:"10.3929/ethz-b-000721641"
9+
---
10+
11+
The IR ICRA 2014 dataset provides visual–inertial recordings designed to evaluate**illumination-robust monocular visual odometry and SLAM** algorithms. It contains challenging sequences with significant lighting variations, fast exposure changes, and difficult low-light conditions that commonly occur during indoor and outdoor flights of micro aerial vehicles (MAVs).
12+
13+
These sequences are useful for benchmarking:
14+
15+
- illumination-robust feature tracking
16+
- monocular/multimodal VO under high dynamic-range conditions
17+
- visual–inertial fusion methods
18+
- exposure-robust perception and real-time onboard estimation
19+
20+
##Data Access
21+
22+
➡️**ETH Research Collection (landing page & downloads):**
23+
**<https://doi.org/10.3929/ethz-b-000721641>**
24+
25+
##Contents
26+
27+
The dataset includes:
28+
29+
- Monocular camera recordings under strongly varying illumination
30+
- Inertial measurements (IMU) aligned with camera timestamps
31+
- Sensor calibration (intrinsics/extrinsics)
32+
- Sequences with rapid brightness changes, shadows, and dark transitions
33+
- Ground-truth alignment or reference trajectories for evaluation (where available)
34+
35+
##Reference Paper
36+
37+
**Illumination-Robust Monocular Visual Odometry for On-Board MAVs**
38+
Presented at the IEEE International Conference on Robotics and Automation (ICRA), 2014.
39+
Authors include contributors from the Autonomous Systems Lab, ETH Zürich.
40+

‎_datasets/windseer.md‎

Lines changed: 52 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,52 @@
1+
---
2+
layout:dataset
3+
title:"WindSeer – Nature 2024 Dataset"
4+
year:2024
5+
tags:[wind-estimation, environment, mapping, planning, mav, environmental-sensing]
6+
eth_collection_url:"https://doi.org/10.3929/ethz-b-000658323"
7+
paper:"WindSeer: Onboard Sensing and Reconstruction of Local Wind Fields for Aerial Robots (Nature 2024)"
8+
doi:"10.3929/ethz-b-000658323"
9+
---
10+
11+
The WindSeer dataset accompanies the 2024*Nature* publication introducing a system for**onboard sensing and reconstruction of local wind fields** using micro aerial vehicles (MAVs). It contains real-world flight data, sensor readings, and reconstruction ground-truth used to evaluate the performance of the WindSeer wind-estimation and mapping framework.
12+
13+
This dataset enables benchmarking of:
14+
15+
- onboard wind-field estimation
16+
- environmental flow reconstruction
17+
- turbulence modeling from MAV-borne sensors
18+
- planning and navigation under dynamic airflow conditions
19+
- evaluation of perception–action coupling in environmental disturbances
20+
21+
##Data Access
22+
23+
➡️**ETH Research Collection (landing page & downloads):**
24+
**<https://doi.org/10.3929/ethz-b-000658323>**
25+
26+
##Contents
27+
28+
The dataset includes:
29+
30+
- Flight logs with onboard wind-sensing instrumentation
31+
- IMU, state-estimation, and controller feedback
32+
- Reconstructed 3D wind fields
33+
- Ground-truth wind measurements (where available)
34+
- Calibration information and metadata for reproducing the experimental evaluation
35+
- Sequences from both controlled and natural outdoor environments
36+
37+
##Reference Paper
38+
39+
**WindSeer: Onboard Sensing and Reconstruction of Local Wind Fields for Aerial Robots**
40+
Published in*Nature*, 2024.
41+
Authors include contributors from the Autonomous Systems Lab, ETH Zürich.
42+
43+
<pre>
44+
@article{windseer2024nature,
45+
title = {WindSeer: Onboard Sensing and Reconstruction of Local Wind Fields for Aerial Robots},
46+
author = {FirstAuthor, FirstName and SecondAuthor, FirstName and Others, et al.},
47+
journal = {Nature},
48+
year = {2024},
49+
doi = {10.3929/ethz-b-000658323},
50+
url = {https://doi.org/10.3929/ethz-b-000658323}
51+
}
52+
</pre>

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp