Automotive

KITTI

Self-driving car

Outdoor automotive dataset with stereo cameras, LiDAR, IMU/GNSS, and GPS/IMU ground truth.

Metadata: Complete Metadata source documented Released 2013

Quick facts

Vehicle type
Automotive
Environment
Outdoor
Data origin
Real-world
Sensor count
7
Ground truth
Available
Calibration
Parameters Only
Annotations
Available

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 KITTI
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 GNSS / INS Not reported Not reported 100 Hz Unknown 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.
Unknown
Accuracy and notes
Reference notes
OXTS RT3003 GNSS/IMU poses. Short communication outages of approximately one second were linearly interpolated and marked in the affected records.

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

Not reported

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

The released raw dataset contains approximately 25% of the overall recordings and excludes sequences used in benchmark test sets.

Short OXTS communication outages of approximately one second were linearly interpolated and marked in the affected records.

Cameras

stereo-rgb

Model
Point Grey Flea2 FL2-14S3C-C
Setup
Stereo
Count
1
Effective cameras
2
Modality
Rgb
Resolution
1392 x 512
Rate
10 Hz
Shutter
Global
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported

stereo-gray

Model
Point Grey Flea2 FL2-14S3M-C
Setup
Stereo
Count
1
Effective cameras
2
Modality
Grayscale
Resolution
1392 x 512
Rate
10 Hz
Shutter
Global
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported

IMUs

OXTS RT3003

Model
OXTS RT3003
Count
1
Accel / gyro
10 / 10 Hz

GNSS

OXTS RT3003

Model or name
OXTS RT3003
Count
1
Rate
10 Hz
GNSS type
RTK
Position output
Available
Velocity output
Available
Heading output
Not reported

LiDAR

Velodyne HDL-64E

Model or name
Velodyne HDL-64E
Count
1
Dimensions
3
Rate
10 Hz
Channels
64
Range
120 m

Additional sensors

Not reported

Annotations

Reported annotation availability and task support.

Availability
Available
Format
3D bounding-box tracklets in XML
Class count
Car, Van, Truck, Pedestrian, Person (sitting), Cyclist, Tram, Misc
Semantic segmentation Not reported
Instance segmentation Not reported
Object detection Available
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
Geiger2013IJRR

BibTeX

@article{Geiger2013IJRR,
  author = {Andreas Geiger and Philip Lenz and Christoph Stiller and Raquel Urtasun},
  title = {Vision meets Robotics: The KITTI Dataset},
  journal = {International Journal of Robotics Research (IJRR)},
  year = {2013},
  month = sep,
  volume = {32},
  number = {11},
  pages = {1231--1237},
  doi = {10.1177/0278364913491297}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy