Compressive sensing (CS) and its applications
- Developed Bayesian CS approaches for estimating the original signal based on a set of CS measurements where the sparsity prior belief is enforced by means of heavy-tailed (alpha-stable) multivariate distributions.
- Introduced a Bayesian matching pursuit method for reconstructing a multi-signal ensemble, acquired by the nodes of a sensor network, in a distributed way by exploiting the joint sparsity structure among the signals of the ensemble.
- Introduced and tested a CS-based video compression architecture for remote sensing systems (UAVs and terrestrial-based sensor networks).
Applied the CS methodology to the harmonic part of a sinusoidally-modeled audio signal to encode audio streams with high-quality at low bitrates.
Achieved consistent encoding performance without having to train the encoder, robustness to network errors, and inherent encryption of the data.
Explored the potential of multi-sensor compressed sensing of audio signals, presented a novel scheme to provide improved performance over standard reconstruction algorithms, and designed a new algorithm to perform efficient location tracking in a sensor network.
Addressed the problem of video classification from a set of compressed features. We exploited the properties of linear random projections in the framework of compressive sensing to reduce the task of classifying a given video sequence into a problem of sparse reconstruction.
