Handheld, Other

TUM-VIE

Event-based visual-inertial perception

Stereo event and grayscale recordings with inertial data, handheld and head-mounted sports sequences, camera calibration, and partially covering motion-capture poses.

Metadata: Complete Metadata needs review

Quick facts

Vehicle type
Handheld, Other
Environment
Indoor, Outdoor
Data origin
Real-world
Sensor count
5
Ground truth
Available
Calibration
Full Raw Calibration Data
Annotations
Not reported

Sensor overview

High-level sensor availability before the detailed sensor records below.

Ground truth

Reference scope, method, rate, coverage, and provenance.

Ground-truth references for TUM-VIE
Scope Method Reference system Count Rate Coverage Reference provenance
External
Measured using equipment independent of the platform’s normal onboard sensor pipeline.
Derived
Computed primarily from the dataset’s own recorded sensors.
Hybrid
Combines independent reference equipment with onboard measurements.
6DoF Motion capture OptiTrack · Flex13 Not reported 120 Hz Partial · Full Trajectories for Seven Mocap-Prefixed Sequences; Beginning and End Segments for Other Sequences. Reference provenance
External
Measured using equipment independent of the platform’s normal onboard sensor pipeline.
Derived
Computed primarily from the dataset’s own recorded sensors.
Hybrid
Combines independent reference equipment with onboard measurements.
External
Reference notes
MoCap timestamps are corrected by matching pose-derived and measured angular velocities. Entry/exit recordings use separate beginning and end alignment estimates; supplied offsets permit custom alignment.

Calibration and synchronization

Reported calibration level, reproducibility signals, and supporting notes.

Level
Full Raw Calibration Data
Processed parameters
Available
Raw calibration data
Available
Calibration targets
AprilTag grid

Reproducible calibration data

Raw calibration data is reported, so users can reproduce or inspect the calibration process.

Notes

Daily joint camera intrinsic/extrinsic calibration uses blinking AprilTags and event time surfaces. Static Aprilgrid supports IMU-camera calibration; calib-vignette recordings provide photometric calibration. IMU bias, axis scaling and misalignment calibration are supplied.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Ground-truth poses cover full mocap sequences but only endpoint portions of longer recordings.

Fast rotations, low light and high dynamic range challenge frame-based tracking.

Cameras

stereo_event

Model
Prophesee GEN4-CD
Setup
Stereo
Count
1
Effective cameras
2
Modality
Event
Resolution
1280 x 720
Rate
Not reported
Shutter
Not Reported
Lens type
Not Reported
HFOV
90 deg
VFOV
65 deg
Notes
Asynchronous events; one giga-event/s is sensor peak capability, not a periodic recording frequency.

stereo_gray

Model
IDS Camera uEye UI-3241LE-M-GL
Setup
Stereo
Count
1
Effective cameras
2
Modality
Grayscale
Resolution
1024 x 1024
Rate
20 Hz
Shutter
Global
Lens type
Not Reported
HFOV
101 deg
VFOV
76 deg
Notes
Image timestamps correspond to mid-exposure; exposure timing is used for clock alignment.

IMUs

Genuino 101 integrated IMU

Model
Bosch BMI160
Count
1
Accel / gyro
200 / 200 Hz

GNSS

Not reported

LiDAR

Not reported

Radar

Not reported

Pitot tube

Not reported

Additional sensors

Not reported

Annotations

Reported annotation availability and task support.

Availability
Not reported
Format
Not reported
Class count
Not reported
Semantic segmentation Not reported
Instance segmentation Not reported
Object detection Not reported
Optical flow Not reported
Depth ground truth Not reported

Citation

Citation key and BibTeX kept at the end of the page for reference.

Citation key
klenk2021tumvie

BibTeX

Not reported

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy