Download:
by Rudolf Mester
In: Proc. IEEE SouthWest Symposium on Image Analysis and Interpretation, Santa Fé (NM), IEEE Computer Society
http://www.uni-frankfurt.de/fb13/iap/cvg/research/../download/SSIAI2002.pdf
Add To MetaCart
Abstract:
The problem of estimating local motion in the presence of noise deserves a thorough system-theoretical analysis. In current textbooks, the predominant procedures are classified into differential (’optical flow’) approaches and matching (or correlation) methods. From a system-theoretical point of view, both classes can be interpreted as a set of linear filters followed by a simple nonlinear operation. However, neither the definition of motion in terms of spatiotemporal gradients nor the minimization of loss functions on two subsequent image patches captures the full essence of what motion means, i.e. the preference direction of a spatiotemporal signal of reduced intrinsic dimensionality embedded in noise. We will discuss the elements that influence the possible precision of local motion estimation methods,
Citations
|
191
|
Signal Processing for Computer Vision
– Granlund, Knutsson
- 1995
|
|
105
|
Prolate spheroidal wave functions, fourier analysis and uncertainty
– Slepian, Pollak
- 1961
|
|
87
|
Optimal orientation detection of linear symmetry
– Bigun, Granlund
- 1987
|
|
61
|
Design of multi-dimensional derivatives filters
– Simoncelli
- 1994
|
|
59
|
Digital image processing
– Jähne
- 2002
|
|
38
|
Computing optical flow with physical models of brightness variation
– Haußecker, Fleet
- 2001
|
|
35
|
The role of total least squares in motion analysis
– Muhlich, Mester
- 1998
|
|
24
|
Optical flow estimation and the interaction between measurement errors at adjacent pixel positions
– Nagel
- 1995
|
|
22
|
Likelihood functions and confidence bounds for total-least-squares problems
– Nestares, Fleet, et al.
- 2000
|
|
18
|
Optimal filters for gradient-based motion estimation
– Elad, Teo, et al.
- 1999
|
|
14
|
Subspace methods and equilibration in computer vision
– Mühlich, Mester
- 1999
|
|
11
|
Removal of translation bias when using subspace methods
– MacLean
- 1999
|
|
8
|
Anisotropic spectral magnitude estimation filters for noise reduction and image enhancement
– Aach, Kunz
- 1996
|
|
6
|
On texture analysis: Local energy transforms versus quadrature filters
– Aach, Kaup, et al.
- 1995
|
|
4
|
M.: Equivalence of subpixel motion estimators based on optical flow and block matching
– Davis, Karu, et al.
- 1995
|
|
2
|
Orientation estimation: conventional techniques and a new approach
– Mester
- 2000
|
|
1
|
Bias introduced by mean orientation estimation methods
– Costa, Germain, et al.
- 2000
|
|
1
|
Improving the accuracy of differential-based optical flow algorithms
– Manduchi
- 1994
|
