SCENES-DVS Database
Pablo Augusto Negri, Mikel Soto, Teresa Serrano-Gotarredona and Bernabé Linares-Barranco
1. Instituto de Ciencias de la Computación, Universidad de Buenos Aires, ARGENTINA.
2. Instituto de Microelectrónica de Sevilla, IMSE-CNM (CSIC & Univ. of Sevilla), Sevilla, SPAIN.
We present a dataset of urban scenes recorded with a DVS sensor:
SCENES-DVS
The SCENES-DVS database consists of DVS recordings of urban scenes. The dataset was recorded by different people handling a DVS sensor during long hikes in an urban environment. The sequences exceeded 15 minutes long and included indoor and outdoor environments. The records were split in small sequences of 50ms. The sequences were categorized in four classes: `street´, `bridge´, `stairs´ and `corridor´. `street´ and `bridge´ classes correspond to indoor scenes, while `stairs´ and `corridor´ correspond to outdoor ones.
When using the dataset please cite:
P. Negri, M. Soto, B. Linares-Barranco, T. Serrano-Gotarredona "Scene Context Classification with Event-Driven Spiking Deep Neural Networks" , IEEE 25th. International Conference on Circuits and Electronics Circuits (ICECS 2017), Bordeux, 2018. https://ieeexplore.ieee.org/document/8617982/
The recordings have been obtained using the sensitive DVS developed in IMSE
T. Serrano-Gotarredona and B. Linares-Barranco, "A 128x128 1.5% Contrast Sensitivity 0.9% FPN 3us Latency 4mW Asynchronous Frame-Free Dynamic Vision Sensor Using Transimpedance Amplifiers," IEEE J. Solid-State Circuits, vol.48, No. 3, pp. 827-838, March 2013. http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6407468).
Recorded files can be displayed with jAER (available from: http://sourceforge.net/p/jaer/wiki/Home). MatlabTM scripts are provided to transfer files from/to jAER format to matlab.
This database can be downloaded free of charge, provided it is used for non-commercial purposes and the original source is credited in publications and reports.
To download it go to http://imse-cnm.csic.es/caviar/SCENES_DVS.
