Geintra

 This page contains links to datasets generated by the GEINTRA research group:

• GOTPD1 & GOTPD2 GEINTRA Overhead ToF People Detection Databases
• GBA Video Dataset for Human Action Recognition
• GEINTRA Multiple Actions Dataset in Cruises (GSMADC)

Open source

In this page we will include software developed in the Group and made available to the community.

SIMITS: Communication simulator in the field of ITS to measure MAC performance

This software is a communications simulator in the field of the Intelligent Transportation Systems (ITS). It is able to simulate and to measure the performance of different medium access control mechanisms (MAC), including Slotted-Aloha, RR-Aloha, and ENCCMA (author's proposal).

The simulation experiments can be performed considering a convoy of autonomous vehicles which follow a trajectory on a limited area. To guarantee the convoy stability, certain messages must be interchanged among the vehicles members of the convoy. In this point, the behaviour of different MAC proposal are measured in terms of throughput as each vehicle must be able to access the shared medium to achieve a successful transmission. To do that, the medium access control mechanism have to cope with collisions among vehicles and with external interferences.

The software is written in C# allows to modify several parameters as the number of vehicles, type of MAC, the way to divide the shared medium in different combinations of TDMA and FDMA, and the presence of interferences.

It also presents the evolution and the results of the experiment in screen and in *.csv files.

The development of this tool is related to the following technical papers, which should be cited in case you use the software:

• "Medium Access Control Based on a Non Cooperative Cognitive Radio for Platooning Communications" Manzano, M.; Espinosa, F.; Bravo, A.M.; Garcia, D.; Gardel, A.; Bravo, I. Intelligent Vehicles Symposium, 2012 IEEE. Pag.: 408 - 413. Doi: 10.1109/IVS.2012.6232172 http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6232172&s...
• Dynamic Cognitive Self-Organized TDMA for Medium Access Control in Real-Time Vehicle to Vehicle Communications” Mario Manzano, Felipe Espinosa, Ángel M. Bravo-Santos, Enrique Santiso, Ignacio Bravo, and David García, Mathematical Problems in Engineering, vol. 2013, Article ID 574528, 13 pages, 2013. doi:10.1155/2013/574528 http://www.hindawi.com/journals/mpe/2013/574528/

Download: From GitHub

License: MIT

Contact: espinosa@depeca.uah.es

GEINTRA Multiple Actions Dataset in Cruises (GSMADC)

The GSMADC is a multimodal images database containing depth and infrared video-sequences, recorded
with an Intel Real Sense D435 camera. The dataset contains a total of 74 videos with an average length
of 40 seconds each. Those videos are equally divided into RGB and Infrared (IR) as the used camera
provides both RGB and IR recordings, which have been taken in different scenarios included in the cruise
ship.

The used camera (Intel Realsense D435) contains a low-power vision processor for real-time depth
sensing. An IR projector and a RGB module are also integrated, which allows the camera to output
the same video recorded in the two different formats (IR and RGB).

Additional information

You can access full details on the dataset in the corresponding document.

To request a copy of the dataset, please contact Marta Marrón Romera at marta.marron@uah.es.

If you make use of this database and/or its related documentation, you are kindly requested to cite the paper:

• Cob-Parro, A. C., Losada-Gutiérrez, C., Marrón-Romera, M., Gardel-Vicente, A., & Bravo-Muñoz, I. (2021). Smart video surveillance system based on edge computing. Sensors, 21(9), 2958.
• Cob-Parro, A. C., Losada-Gutiérrez, C., Marrón-Romera, M., Gardel-Vicente, A., & Bravo-Muñoz, I. (2024). A new framework for deep learning video based Human Action Recognition on the edge. Expert Systems with Applications, 238, 122220.

Licensing

The GEINTRA Multiple Actions Dataset in Cruises (GSMADC) Database (and accompanying files
and documentation) by Carlos Cob-Parro, Cristina Losada-Gutiérrez, Marta Marrón-Romera, Rodrigo
Antonio Vidal Pinto, Ignacio Bravo, Alfredo Gardel is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.