Authors:
Silvio P. Sabatini
1
;
Giulia Gastaldi
1
;
Fabio Solari
1
;
Karl Pauwels
2
;
Marc van Hulle
2
;
Javier Díaz
3
;
Eduardo Ros
3
;
Nicolas Pugeault
4
and
Norbert Krüger
5
Affiliations:
1
University of Genoa, Italy
;
2
Laboratorium voor Neuro- en Psychofysiologie, K.U.Leuven, Belgium
;
3
University of Granada, Spain
;
4
School of Informatics, University of Edinburgh, United Kingdom
;
5
The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Denmark
Keyword(s):
Phase-based techniques, multidimensional signal processing, filter design, optic flow, stereo vision.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Early Vision and Image Representation
;
Feature Extraction
;
Features Extraction
;
Human-Computer Interaction
;
Image and Video Analysis
;
Image Filtering
;
Image Formation and Preprocessing
;
Informatics in Control, Automation and Robotics
;
Methodologies and Methods
;
Motion and Tracking
;
Motion, Tracking and Stereo Vision
;
Pattern Recognition
;
Physiological Computing Systems
;
Real-Time Vision
;
Signal Processing, Sensors, Systems Modeling and Control
;
Stereo Vision and Structure from Motion
Abstract:
The efficacy of anisotropic versus isotropic filtering is analyzed with respect to general phase-based metrics for early vision attributes. We verified that the spectral information content gathered through oriented frequency channels is characterized by high compactness and flexibility, since a wide range of visual attributes emerge from different hierarchical combinations of the same channels. We observed that it is preferable to construct a multichannel, multiorientation representation, rather than using a more compact representation based on an isotropic generalization of the analytic signal. The complete harmonic content is then combined in the phaseorientation space at the final stage, only, to come up with the ultimate perceptual decisions, thus avoiding an “early condensation” of basic features. The resulting algorithmic solutions reach high performance in real-world situations at an affordable computational cost.