Front-End Vision and Multi-Scale Image Analysis: Multi-scale Computer Vision Theory and Applications, written in MathematicaMany approaches have been proposed to solve the problem of finding the optic flow field of an image sequence. Three major classes of optic flow computation techniques can discriminated (see for a good overview Beauchemin and Barron IBeauchemin19951): gradient based (or differential) methods; phase based (or frequency domain) methods; correlation based (or area) methods; feature point (or sparse data) tracking methods; In this chapter we compute the optic flow as a dense optic flow field with a multi scale differential method. The method, originally proposed by Florack and Nielsen [Florack1998a] is known as the Multiscale Optic Flow Constrain Equation (MOFCE). This is a scale space version of the well known computer vision implementation of the optic flow constraint equation, as originally proposed by Horn and Schunck [Horn1981]. This scale space variation, as usual, consists of the introduction of the aperture of the observation in the process. The application to stereo has been described by Maas et al. [Maas 1995a, Maas 1996a]. Of course, difficulties arise when structure emerges or disappears, such as with occlusion, cloud formation etc. Then knowledge is needed about the processes and objects involved. In this chapter we focus on the scale space approach to the local measurement of optic flow, as we may expect the visual front end to do. 17. 2 Motion detection with pairs of receptive fields As a biologically motivated start, we begin with discussing some neurophysiological findings in the visual system with respect to motion detection. |
Contents
1 | |
Foundations of scalespace | 13 |
Gaussian derivatives 53 | 24 |
The Gaussian kernel | 37 |
implementations | 71 |
Differential structure of images 91 | 90 |
Natural limits on observations | 137 |
The frontend visual system the retina | 153 |
The frontend visual system LGN and cortex | 179 |
The frontend visual system cortical columns 197 | 196 |
Deep structure I watershed segmentation | 215 |
Deep structure II catastrophe theory | 241 |
Epilog 393 | 392 |
B The concept of convolution | 413 |
Tips Tricks 423 | 422 |
455 | |
Other editions - View all
Front-End Vision and Multi-Scale Image Analysis: Multi-scale Computer Vision ... Bart M. Haar Romeny No preview available - 2003 |
Front-End Vision and Multi-Scale Image Analysis: Multi-scale Computer Vision ... Bart M. Haar Romeny No preview available - 2003 |
Common terms and phrases
analysis aperture axis blob blurring calculated chapter color computer vision constraint convolution cortical curve deblurring deep structure defined detection detector differential operators diffusion equation dimension direction Display Function Display Together Array edge evolution example extrema Figure filter Florack fold catastrophe Fourier domain Fourier transform front-end ganglion cells gauss Gaussian derivative functions Gaussian derivative kernels Gaussian function Gaussian kernel gradient Hessian matrix ImageSize implementation input intensity invariant Koenderink Laplacian linear List Density Plot ListDensity Plot Mathematica mathematical matrix measurement Module multi-scale noise optic flow order derivative orientation parameter partial derivatives pixels PlotLabel PlotRange polynomial principal curvature receptive fields result retina rotation saddle sampling scale scale-space scale-space theory second order shortnotation Show GraphicsArray Show Import signal Simplify singularities spatial Table Task temporal unitstep vector vectorfield visual system winding number xdim ydim zero