A frequency-domain approach for the extraction of motion patterns

Abstract

In this paper, a new frequency-domain approach to represent motions is proposed. The new scheme is based on a band-pass filtering with a set of logGabor spatio-temporal filters. It is well known that one of the main problems of these approaches is that a filter response varies with the spatial orientation of the underlying signal. To solve this spatial dependency, the proposed model allows to recombine information of motions that has been separated in several filter responses due to its spatial structure. For this purpose, motion patterns are detected as invariance in statistical structure across a range of spatio-temporal frequency bands. This technique is illustrated on real and simulated data sets, including sequences with occlusion and transparencies.

Data-driven synthesis of composite-feature detectors for 3D image analysis

“…Aínda que xa existen investigacións feitas nesta dirección, como por exemplo en (Bovik et al, 1990;Jain et al, 1997;Acharyya et al, 2003) e especialmente en (Rodríguez Sánchez et al, 2000;Chamorro Martínez et al, 2003;Manjunath and Chellappa, 1993), non temos coñemento de que ningunha aproximación deste tipo desenvolvida para datos volumetricos, o cal implica estende-las ideas tomadas das teorías do SHV de 2D a 3D. O SVH non manexa información 3D pura, senón proxeccións estéreo das escenas 3D.…”

“…Although some research has been already done in this direction, like for example in (Bovik et al, 1990;Jain et al, 1997;Acharyya et al, 2003) and especially in (Rodríguez Sánchez et al, 2000;Chamorro Martínez et al, 2003;Manjunath and Chellappa, 1993), we don't have knowledge of any approach of this kind developed for volumetric data, which implies the extension of some ideas extracted for the HVS from 2D to 3D. The HVS does not deal with pure 3D information, but with stereo projections of 3D scenes.…”

Energy Feature Integration for Motion Segmentation

“…To identify relevant composite features in a sequence, it is necessary to define an integration criterion able to relate elementary energy features contributing to the same motion pattern. In previous works Dosil et al, 2005a;Dosil et al, 2005b), we have introduced an integration criterion inspired in biological vision that improves the computational cost and performance of earlier approaches (Rodriguez-Sánchez et al, 1999;Chamorro-Martínez et al, 2003). It is based on the hypothesis of Morrone and Owens (1987) that the Human Visual System (HVS) perceives features at points of locally maximal Phase Congruence (PC).…”

“…The composite feature representation will be applied directly, without estimating motion parameters. Composite energy features have proved to be a powerful tool for the representation of visually independent spatial patterns in 2D data (Rodriguez-Sánchez et al, 1999), volumetric data Dosil et al, 2005b) and video sequences (Chamorro-Martínez et al, 2003). To identify relevant composite features in a sequence, it is necessary to define an integration criterion able to relate elementary energy features contributing to the same motion pattern.…”

Motion Estimation in the 3-D Gabor Domain

“…Frequency domain approaches to motion estimation have been of interest for a number of years [20] [21]. Using the 3-D Fourier transform, the motion information embodied in an image sequence is transferred into certain distribution models of Fourier coefficients [22].…”