List of Datasets

Automotive

Brno Urban Dataset

Multisensor mapping and localization with thermal imagery

Vehicle recordings combine RGB/thermal cameras, dual LiDAR, inertial/environmental measurements and conditional RTK position/heading.

Metadata: Complete Metadata source documented Released 2019

Primary places to inspect, download, read about, or reproduce the dataset.

Quick facts

Vehicle type
Automotive
Environment
Outdoor
Data origin
Real-world
Sensor count
12
Ground truth
Available
Calibration
Parameters Only
Annotations
Not reported

Sensor overview

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

Cameras

5 reported

IMUs

1 reported

GNSS

2 reported

LiDAR

2 reported

Radar

Not reported

Magnetometers

1 reported

Barometers

1 reported

UWB

Not reported

Ground truth

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

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.
3D position + heading RTK GNSS Trimble BX982 Not reported 20 Hz Partial 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.
Hybrid
Accuracy notes
Paper claims centimetre position where GNSS is available; no numeric corpus accuracy assigned.
Reference notes
Onboard differential receiver with external corrections; only position and heading, not independent full six-degree truth.

Calibration and synchronization

Reported calibration level, reproducibility signals, and supporting notes.

Level
Parameters Only
Processed parameters
Available
Raw calibration data
Not reported
Calibration targets
Not reported

Parameters only

Processed calibration parameters are reported, but raw calibration data is not reported.

Notes

Calibration YAML and a separate parameter repository are distributed. Maintained documentation describes manually estimated alignment; parameter presence is not a guarantee of precise extrinsics or complete raw calibration sessions.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

The paper-era collection reports 67 recordings and 375.7 km; maintained aggregate counts differ. Current full-corpus sequence and distance totals are left unknown rather than mixing editions.

This entry covers the original RGB/thermal/dual-Velodyne/navigation collection. Later Winter Extension Livox, radar and automated YOLO outputs require separate scope review.

Official known bugs include misordered thermal frames in session 1, inverted IMU linear acceleration signs, and a missing row in each LiDAR. Consult release corrections before processing.

RTK position/heading validity depends on reception; numerical independent reference error and achieved synchronization accuracy are not established.

Calibration estimates can be manual. The rig is not fully waterproof, and integrated magnetic/pressure/GNSS outputs share the Xsens device rather than representing additional mounted packages.

Cameras

Camera 1

Model
DFK33-GX174
Setup
Stereo
Count
1
Effective cameras
2
Modality
Rgb
Resolution
1920 x 1200
Rate
10 Hz
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Front stereo pair; approximately 70 cm baseline.

Camera 2

Model
DFK33-GX174
Setup
Mono
Count
2
Effective cameras
2
Modality
Rgb
Resolution
1920 x 1200
Rate
10 Hz
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Lateral cameras.

Camera 3

Model
FLIR Tau 2
Setup
Mono
Count
1
Effective cameras
1
Modality
Thermal
Resolution
640 x 512
Rate
30 Hz
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Official documentation flags thermal frame-order/timing issues; consult release corrections.

IMUs

Xsens integrated navigation IMU

Model
Xsens MTi-G-710
Count
1
Accel / gyro
400 / 400 Hz

GNSS

Trimble BX982

Model or name
Trimble BX982
Count
1
Rate
20 Hz
GNSS type
RTK
Position output
Available
Velocity output
Not reported
Heading output
Available

Xsens MTi-G-710

Model or name
Xsens MTi-G-710
Count
1
Rate
Not reported
GNSS type
UNKNOWN
Position output
Available
Velocity output
Not reported
Heading output
Not reported

LiDAR

Velodyne HDL-32E

Model or name
Velodyne HDL-32E
Count
2
Dimensions
3
Rate
10 Hz
Channels
32
Range
Not reported

Radar

Not reported

Additional sensors

Barometer

Model
Xsens MTi-G-710 integrated pressure sensor
Count
1
Rate
50 Hz
Notes
Pressure output; not a separately mounted package.

Magnetometer

Model
Xsens MTi-G-710 integrated magnetometer
Count
1
Rate
100 Hz
Notes
Part of the same inertial package.

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
ligocki2019brnourban

BibTeX

@misc{ligocki2019brnourban,
  author = {{Adam Ligocki} and {Ales Jelinek} and {Ludek Zalud}},
  title = {Brno Urban Dataset - The New Data for Self-Driving Agents and Mapping Tasks},
  year = {2019},
  eprint = {1909.06897},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1909.06897v1}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy