Affiliation:ISR†† IST

Publications and patents

Projects and students


complete list

Pedro M. Q. Aguiar

The ultimate goal of my research is to make computers extract high level content from images by seeking their simplest interpretation. This lead me to the areas of image processing, computer vision, machine learning, pattern recognition. Other (older) research interests include statistical signal processing, stochastic processes, nonlinear systems, automatic control.

Selected papers:

Shape representation via elementary symmetric polynomials: a complete invariant inspired by the bispectrum
R. Negrinho and P. Aguiar, IEEE Int. Conf. on Image Processing, 2013.

Revisiting complex moments for 2D shape representation and image normalization
J. Crespo and P. Aguiar, IEEE Trans. on Image Processing, 20(10), Oct. 2011.

Globally optimal solution to exploit rigidity when recovering structure from motion under occlusion
P. Aguiar, J. Xavier, and M. Stosic, IEEE Int. Conf. on Image Processing, 2008. DoCoMo USA Labs Innovative Paper Award

Orientation in Manhattan: equiprojective classes and sequential estimation
A. Martins, P. Aguiar, and M. Figueiredo, IEEE Trans. on Pattern Analysis and Machine Intelligence, 27(5), May 2005.††

Acoustic modems for ubiquitous computing
C. Lopes and P. Aguiar, IEEE Pervasive Computing, 2(3), July-Sep. 2003.

Rank 1 weighted factorization for 3D structure recovery
P. Aguiar and J. Moura, IEEE Trans. on Pattern Analysis and Machine Intelligence, 25(9), Sep. 2003.

"invention is, in fact, a cautious dipping into the negation that lies outside system
from a position firmly ensconced in system"

Glenn Gould, royal conservatory of music, Toronto, 1964.