Authors:
Damjan Zazula
;
Aleš Holobar
and
Matjaž Divjak
Affiliation:
Faculty of Electrical Engineering and Computer Science, University of Maribor, Slovenia
Keyword(s):
Blind source separation, Convolution kernel compensation, Bioelectrical signal decomposition, Range imaging.
Related
Ontology
Subjects/Areas/Topics:
Multidimensional Signal Processing
;
Multimedia
;
Multimedia Signal Processing
;
Telecommunications
Abstract:
Many practical situations can be modelled with multiple-input multiple-output (MIMO) models. If the input sources are mutually orthogonal, several blind source separation methods can be used to reconstruct the sources and model transfer channels. In this paper, we derive a new approach of this kind, which is based on the compensation of the model convolution kernel. It detects the triggering instants of individual sources, and tolerates their
non-orthogonalities and high amount of additive noise, which qualifies the method in several signal and image analysis applications where other approaches fail.. We explain how to implement the convolution kernel compensation (CKC) method both in 1D and 2D cases. This unified approach made us able to demonstrate its performance in two different experiments. A 1D application was introduced to the decomposition of surface electromyograms (SEMG). Nine healthy males participated in the tests with 5% and 10% maximum voluntary isometric contractions
(MVC) of biceps brachii muscle. We identified 3.4 ± 1.3 (mean ± standard deviation) and 6.2 ± 2.2 motor units (MUs) at 5% and 10% MVC, respectively. At the same time, we applied the 2D version of CKC to range imaging. Dealing with the Middlebury Stereo Vision referential set of images, our method found correct matches of 91.3 ± 12.1% of all pixels, while the obtained RMS disparity difference was 3.4 ± 2.5 pixels. This results are comparable to other ranging approaches, but our solution exhibits better robustness and reliability.
(More)