List of Datasets

UGV

Forklift Multispectral Pedestrian Dataset

Multispectral pedestrian detection and centroid distance estimation

Stereo RGB and thermal warehouse imagery recorded from a moving forklift, with pedestrian, occlusion and centroid distance annotations; available on request for non-profit purposes.

Metadata: Partial Metadata needs review

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

Website

Not reported

Download

Not reported

Code

Not reported

Supplementary

Not reported

Quick facts

Vehicle type
UGV
Environment
Indoor
Data origin
Real-world
Sensor count
4
Ground truth
Available
Calibration
Not reported
Annotations
Available

Sensor overview

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

Cameras

4 reported

IMUs

Not reported

GNSS

Not reported

LiDAR

Not reported

Radar

Not reported

Pitot tube

Not reported

Magnetometers

Not reported

Barometers

Not 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.
Other Other Not reported Not reported Not reported 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.
Derived
Reference notes
Per-pedestrian centroid distances derived from RGB stereo disparity with modified SGM, hole filling, manual outlier removal and local depth averaging. This is not an independent reference trajectory or a verified dense depth release.

Calibration and synchronization

Reported calibration level, reproducibility signals, and supporting notes.

Level
Not reported
Processed parameters
Not reported
Raw calibration data
Not reported
Calibration targets
Heated copper-grid Line-board

Calibration data

Calibration reproducibility details are not reported.

Notes

Stereo multispectral calibration used additional board distances to improve image-edge coverage. RGB stereo disparity is transformed to approximate cross-modal disparity for alignment; supplied calibration files remain unverified.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Use restricted to non-profit purposes; data must be requested from corresponding author.

Frame and pedestrian totals differ between introduction, annotation section and Table 2.

Pedestrians were mostly recorded at 0-10 metres; distance labels are derived from stereo measurements.

Cameras

rgb-stereo

Model
PointGrey Flea3 FL3-GE-13S2C
Setup
Stereo
Count
1
Effective cameras
2
Modality
Rgb
Resolution
Not reported
Rate
Not reported
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Two color cameras; native hardware dimensions 1288 x 964, reported FOV 84.9 H x 68.9 V degrees, Spacecom HF3.5M-2 3.5 mm lenses. Aligned output dimensions are not established; one RGB view supplies manual annotations propagated to aligned views.

thermal-stereo

Model
FLIR A35
Setup
Stereo
Count
1
Effective cameras
2
Modality
Thermal
Resolution
Not reported
Rate
Not reported
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Two thermal cameras; native hardware dimensions 320 x 256, reported FOV 63 H x 50 V degrees, 7.5 mm lenses. Thermal self-master triggers the external-master thermal camera, which triggers both RGB cameras.

IMUs

Not reported

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
Available
Format
Not reported
Class count
3
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
kim2022forklift

BibTeX

@article{kim2022forklift,
  author = {Kim, Hyeongjun and Kim, Taejoo and Jo, Won and Kim, Jiwon and Shin, Jungmin and Han, Daechan and Hwang, Yujin and Choi, Yukyung},
  title = {Multispectral Benchmark Dataset and Baseline for Forklift Collision Avoidance},
  journal = {Sensors},
  year = {2022},
  volume = {22},
  pages = {7953},
  doi = {10.3390/s22207953}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy