Francisco Barranco

Marie-curie Post-Doc Fellow 

computer vision lab, umiacs, university of maryland

computer architecture and technology, ETSIIT CITIc, University of granada (spain)

Previous Research

I have worked developing new methods for low- and mid-level vision operators for their implementation in specific-purpose architectures such as FPGAs. I joined the University of Granada in 2007 to obtain my PhD, where my advisors where Prof. Eduardo Ros and Dr. Javier Diaz. I worked on  the EU project DRIVSCO Learning to emulate perception-action cycles in a driving school scenario from 2007-2010.  In the framework of this project I visited the University of Genoa (2010) under the direction of Prof. Silvio Sabatini. After 2011, I focused on the role that diverse low-level vision engines play in deploying visual attention. The released hardware designs and implementations of all this work can be found at the CERN Open Hardware Repository. I took part of the Telluride Workshop on Neuromorphic Cognition Engineering (Colorado, USA) in 2011. Then, I visited Prof. Kwabena Boahen lab at Stanford University in 2012 designing and developing the final architecture for a visual attention system with top-down modulation. This was the main contribution of my Thesis presented that year. In 2013, I collaborated with the EU project TOMSY Topology based motion synthesis for dextereous manipulation. 

	F. Barranco, C. L. Teo, C. Fermuller, Y. Aloimonos, "Contour detection and characterization for asynchronous event sensors," International Conference on Computer Vision, ICCV ,  2015. [PDF] [BibTex]  [Project page and code]
	F. Barranco, C. Fermuller, Y. Aloimonos, "Contour motion estimation for asynchronous event-driven cameras," Proceedings of the IEEE, 102 (10), 1537-1556, 2014. [PDF] [BibTex]
	F. Barranco, J. Diaz, B. Pino, E. Ros, "Real-time visual saliency architecture for FPGA with top-down attention modulation," IEEE Trans. on Industrial Informatics, 10 (3), 1726-1735, 2014. [PDF] [BibTex] [Code] F. Barranco, "Specific-purpose processing architectures for dynamic artificial vision systems". Granada: Universidad de Granada, 2013. 243 p. [PDF] [BibTex]
	F. Barranco, J. Díaz, A. Gibaldi, S.P. Sabatini, E. Ros, “Vector disparity sensor with vergence control for active vision systems”, Sensors, 12, 1771-1799, 2012. [PDF] [BibTex]
	F. Barranco, M. Tomasi, J. Díaz, E. Ros, “A multi-resolution approach for massively-parallel hardware-friendly optical flow estimation”, Journal of Visual Communication And Image Representation, 23 (8), 1272-1283, 2012. [PDF] [BibTex]
	F. Barranco, M. Tomasi, J. Díaz, E. Ros, "Hierarchical architecture for motion and depth estimations based on color cues'', Journal of Real-Time Image Processing, 1-18, 2012. [PDF] [BibTex] [Code] F. Barranco, M. Tomasi, J. Díaz, M. Vanegas, E. Ros, "Parallel architecture for hierarchical optical flow estimation based on FPGA", IEEE Trans. on VLSI Systems, 20 (6), 1058-1067, 2012. [PDF] [BibTex] [Code] M. Tomasi, M. Vanegas, F. Barranco, J. Díaz and E. Ros, "Massive parallel hardware architecture for multi-scale image structure, stereo, and optical flow computation", IEEE Trans. on CSVT, 22 (2), 282-294, 2012. [PDF] [BibTex] [Code]
	F. Barranco, J. Diaz, E. Ros, B. Pino "Visual system based on artificial retina for motion detection", IEEE Trans. on SMC-Part B, 39 (3), 752-762, 2009. [PDF] [BibTex] [Code]

More publications

Collaborators
- Dr. Matteo Tomasi, Postdoctoral fellow Schepens Eye Research Institute, Harvard Medical School Affiliate, Harvard University (Boston, USA)

- Dr. Mauricio Vanegas, Postdoctoral fellow PSPC-lab, Department of Informatics, Bioengineering, Robotics, and Systems Engineering (DIBRIS) University of Genoa (Genoa, Italy)

- Dr. Jarno Ralli, researcher with Fuel-3D, works in United Kingdom