RGB-D dataset

RGB-D indoor dataset

We provide a varied dataset containing RGB-D data with the goal to stablish a benchmark for the evaluation of systems performing NAVI (Navigation Assistance for the Visually Impaired) based on RGB-D devices. The device was carried by a person in order to simulate a realistic situation (see figure). Our dataset contains the color and depth data of an Asus XtionPro Live camera along different indoor scenarios. The data was recorded at 30Hz (full frame rate) with a 640x480 sensor resolution. All scenarios have been recorded in rosbag files. All files contain XYZRGB point-cloud data and most of them have recorded raw images too. The RGB-D device was carried by a person in order to simulate a realistic situation. At the end of this page we provide a calibration file and a set of calibration images of the RGB-D device and more info related with this topic.

AsusUser with asus


Scenario 1 (Ada Byron)
Scenario 1 Long (Ada Byron)
Scenario 2 (I3A)
Scenario 2 Long (I3A)
Scenario 3 (I3A)
Scenario 4 (Ada Byron)
Scenario 5 (Torres Quevedo)
Scenario 6 (Garage)
Calibration
Related publications
Contact

Scenario number 1 (Ada Byron building)

Recorded topics:
/camera/rgb/points
/camera/rgb/image_color
Duration: 2:59
Distance covered: 100 m
Download Rosbag (11.9 GB)
video (23 MB)

Scenario number 1 (Long version) (Ada Byron building)

Recorded topics:
/camera/rgb/points
/camera/rgb/camera_info
/camera/rgb/image_raw
/camera/rgb/image_color
/camera/depth/camera_info
/camera/depth/image
/camera/depth/image_raw
Duration: 7:40
Distance covered: 300 m
Download Rosbag (25.9 GB)
video (58 MB)

Scenario number 2 (I3A building)

Recorded topics:
/camera/rgb/points
/camera/rgb/image_color
Duration: 3:12
Distance covered: 90 m
Download Rosbag (12.7 GB)
video (27 MB)

Scenario number 2 (Long version) (I3A building)

Recorded topics:
/camera/rgb/points
/camera/rgb/camera_info
/camera/rgb/image_raw
/camera/rgb/image_color
/camera/depth/camera_info
/camera/depth/image
/camera/depth/image_raw
Duration: 4:39
Distance covered: 180 m
Download Rosbag (15.3 GB)
video (36 MB)

Scenario number 3 (I3A building)

Recorded topics:
/camera/rgb/points
/camera/rgb/camera_info
/camera/rgb/image_raw
/camera/rgb/image_color
/camera/depth/camera_info
/camera/depth/image
/camera/depth/image_raw
Duration: 1:08
Distance covered: 15 m
Download Rosbag (3.9 GB)
video (6 MB)

Scenario number 4 (Ada Byron building)

Recorded topics:
/camera/rgb/points
/camera/rgb/camera_info
/camera/rgb/image_raw
/camera/rgb/image_color
/camera/depth/camera_info
/camera/depth/image
/camera/depth/image_raw
Duration: 1:10
Distance covered: 15 m
Download Rosbag (3.9 GB)
video (11 MB)

Scenario number 5 (Torres Quevedo building)

Recorded topics:
/camera/rgb/points
/camera/rgb/image_color
Duration: 3:34
Distance covered: 150 m
Download Rosbag (13.8 GB)
video (21 MB)

Scenario number 6 (Garage building)

Recorded topics:
/camera/rgb/camera_info
/camera/rgb/image_raw
/camera/rgb/points
/camera/depth/camera_info
/camera/depth/image_raw
Duration: 3:18
Distance covered: 70 m
Download Rosbag (11.9 GB)
Example image
Example of image

Calibration

We provide a set of 32 calibration images and a calibration report of the RGB-D device. The calibration has been done with the Kinect-stereo-calib software developed by the Mobile Robot Programming Toolkit. The calibration was done with a 8x10 chessboard of 22.8x24.3mm squares.
Links:
Image calibration set (Download zip file)
Calibration report (Download text file)


Related publications

[1] A. Aladrén, G. López-Nicolás, L. Puig, and J. J. Guerrero. Navigation Assistance for the Visually Impaired Using RGB-D Sensor with Range Expansion. IEEE Systems Journal, vol. 10, no. 3, pp. 922-932, Sept. 2016. (video), (pdf)

[2] G. López-Nicolás, A. Aladrén, and J. J. Guerrero. Wearable vision systems for personal guidance and enhanced assistance. Workshop on Robotics Challenges and Vision (RCV2013) in conjuction with Robotics: Science and Systems (RSS), Berlin, Germany, June 27, 2013. (Download paper)

[3] A. Aladrén. Desarrollo de un sistema de navegación utilizando información de visión y rango (Development of Navigation Aid System for the Visually Impaired Based on Vision and Range data). Graduation Project, Universidad de Zaragoza. September, 2013. (Info)


Contact

G. López-Nicolás (gonlopez@unizar.es)
J. J. Guerrero (josechu.guerrero@unizar.es)
Instituto Universitario de Investigación en Ingeniería de Aragón (I3A)
Universidad de Zaragoza.