List of Datasets

Marine underwater

CADDY Underwater Stereo-Vision Dataset

Underwater human–robot interaction

Rectified underwater stereo imagery for diver gesture recognition and diver-relative heading estimation in sea and pool trials.

Metadata: Complete Metadata needs review

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

Download

Not reported

Supplementary

Not reported

Quick facts

Vehicle type
Marine underwater
Environment
Indoor, Outdoor
Data origin
Real-world
Sensor count
2
Ground truth
Available
Calibration
Parameters Only
Annotations
Available

Sensor overview

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

Cameras

2 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 DiverNet · Pololu MinIMU-9 17 IMUs Not reported Partial · Diver-Heading Subset 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
Reference notes
Diver heading relative to the AUV is computed from torso and lower-back IMUs, projected onto XY, then median-filtered with buffer five and manually bias-corrected. Zero degrees faces the camera; range is -180 to 180 degrees. DiverNet acquisition is 50 Hz, distinct from delivered label cadence.

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

In-air camera calibration files and CamOdCal/Pinax tools are provided; only rectified stereo imagery is released. DiverNet uses T-posture alignment.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Gesture classes and scenarios are imbalanced.

Images exhibit underwater low contrast, color distortion and haze.

Heading scenario labels conflict within the paper.

Cameras

stereo

Model
Point Grey Bumblebee XB3 BBX3-13S2C
Setup
Stereo
Count
1
Effective cameras
2
Modality
Rgb
Resolution
640 x 480
Rate
Not reported
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Camera raw output is reported as 1280 by 960 at 16 Hz; released images are rectified to 640 by 480. Retained pair cadence and total physical camera-instance count are not established.

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
csv
Class count
15
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
Not reported

BibTeX

Not reported

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy