banners
beforecontenttitle

UMA-SAR Datasets

After content title
Before content body
Chunks
Chunks

SAMPLE VERSION FOR REVIEW 

This is a sample version of the complete dataset webpage, which will be made public in the near future. For review purposes, two representative samples are available from the 2018 and 2019 exercises, respectively. Besides, the full RGB video previews for the complete dataset have been included. This sample version of the website also offers the accompanying software tools and RGB camera calibration images and results.

The UMA-SAR dataset is aimed at the disaster robotics research community. The dataset was recorded from an all-terrain vehicle that was allowed to move through two large-scale realistic search and rescue (SAR) exercises in Málaga (Spain) participated by actual emergency response organizations. The exercises took place in 2018 and 2019. Besides, pre-exercise and  post-exercise sequences were recorded on the empty site for comparison purposes. The vehicle carried an RGB camera, a thermal infrared camera (TIR) and a Velodyne HDL-32 three-dimensional lidar, as well as an inertial measurement unit (IMU) and two global positioning system (GPS) receivers as ground truth. Furthermore, two software tools have been developed for extracting and adapting the data to the users’ preference. The dataset captures unstructured terrain with rubble and a wide range of SAR-related object categories.

Please check the "readme.md" file for further information.

DATASETS

2018 SEQUENCES:

DESCRIPTION PATH DATASET LINKS VIDEO PREVIEW
2018-06-01-12-14-47
  • Exercise
  • Length 469 m (approx).
  • 8m 35s.

 

ZIP FILE (human readable text format and jpeg images):
     2018-06-01-12-14-47.zip (4 GB)  
     SAMPLE: sequence_2018.zip (206 MB) *

ROSBAG:
     2018-06-01-12-14-47.bag  (9 GB)
     SAMPLE: sequence_2018.bag (447 MB) *

* Review samples: from 12-18-32 to 12-18-57.

2018-06-01-12-44-10
  • Exercise
  • Length 934 m (approx).
  • 20m 01s.

ZIP FILE (human readable text format and jpeg images):
     2018-06-01-12-44-10.zip (10 GB) 

ROSBAG:
     2018-06-01-12-44-10.bag (21 GB)

2018-07-25-11-25-10
  • Post-exercise
  • Length 627 m (approx).
  • 4m 54s.

ZIP FILE (human readable text format and jpeg images):
     2018-07-25-11-25-10.zip (2 GB) 

ROSBAG:
     2018-07-25-11-25-10.bag (5 GB)

2018-07-25-11-39-26
  • Post-exercise
  • Length 3320 m (approx).
  • 34m 18s.

ZIP FILE (human readable text format and jpeg images):
     2018-07-25-11-39-26.zip (13 GB) 

ROSBAG:
     2018-07-25-11-39-26.bag (33 GB)

 

2019 SEQUENCES:

DESCRIPTION PATH DATASET LINKS VIDEO PREVIEW
2019-06-05-13-55-16
  • Pre-exercise
  • Length 1029 m (approx).
  • 7m 13s.

ZIP FILE (human readable text format and jpeg images):
     2019-06-05-13-55-16.zip (3 GB) 

ROSBAG:
     2019-06-05-13-55-16.bag (7 GB)

2019-06-06-10-08-55
  • Exercise
  • Length 1843 m (approx).
  • 15m 47s.

ZIP FILE (human readable text format and jpeg images):
     2019-06-06-10-08-55.zip (6 GB) 

ROSBAG:
     2019-06-06-10-08-55.bag (15 GB)

2019-06-06-10-35-12
  • Exercise
  • Length 2000 m (approx).
  • 32m 51s.

 

ZIP FILE (human readable text format and jpeg images):
     2019-06-06-10-35-12.zip (14 GB)    
     SAMPLE: sequence_2019.zip (187 MB) *

ROSBAG:
     2019-06-06-10-35-12.bag (32 GB) 
     SAMPLE: sequence_2019.bag (446 MB) *

* Review samples: from 10-57-22 to 10-57-47.

 

SOFTWARE TOOLS

Sequence extractorhttps://github.com/Robotics-Mechatronics-UMA/dataset_extract_sequence
This tool can be used to extract a sequence from an uncompressed data folder. The user can specify the start and end timestamps for the sequence as well as a subset of sensor modalities.

This tool generates a structure with the bag messages for each sensor.

Enlace a los paquetes ROS empleados para capturar la información.

Modified GPS driver: https://github.com/Robotics-Mechatronics-UMA/novatel_gps_driver_modified 
Modified Novatel driver for use with the JAVAD GPS receivers.

 

RGB CAMERA CALIBRATION

The camera_calibration ROS package was used to obtain the intrinsic parameters of the RGB camera. Images of a 11x7 chessboard (10 cm side) as well as calibration results are provided here: https://drive.google.com/file/d/14RyG3e2d_qKXJkufTK6ixph-cyaFjCQW.

After content body