Abstract. Retinal image motion and optical flow as its approximation are fundamental concepts in the field of vision, perceptual and computational. However, the computation of optical flow remains a challenging problem as image motion includes discontinuities and multiple values mostly due to scene geometry, surface translucency and various photometric effects such as reflectance. In this contribution, we analyze image motion in the frequency space with respect to motion discontinuities and translucence. We derive, under models of constant and linear optical flow, the frequency structure of motion discontinuities due to occlusion and we demonstrate its various geometrical properties. The aperture problem is investigated and we show that the information content of an occlusion almost always disambiguates the velocity of an occluding signal suffering from the aperture problem. In addition, the theoretical framework can describe the exact frequency structure of Non-Fourier motion and bridges the gap between Non-Fourier visual phenomena and their understanding in the frequency domain.
|
686
|
Performance of optical flow techniques
– Barron, Fleet, et al.
- 1994
|
|
482
|
A computer algorithm for reconstructing a scene from two projections," Nature 293
– Longuet-Higgins
|
|
248
|
Uniqueness and estimation of threedimensional motion parameters of rigid objects with curved surfaces
– Tsai, Huang
- 1984
|
|
239
|
Computation of component image velocity from local phase information
– Fleet, Jepson
- 1990
|
|
211
|
Determining three-dimensional motion and structure from optical flow generated by several moving objects
– Adiv
- 1985
|
|
199
|
The interpretation of moving retinal image
– Longuet-Higgins, Prazdny
- 1980
|
|
129
|
Mixture models for optical flow computation
– Jepson, Black
- 1993
|
|
122
|
Scene segmentation from visual motion using global optimization
– Murray, Buxton
- 1987
|
|
111
|
Motion segmentation and qualitative dynamic scene analysis from an image sequence
– Bouthemy, Francois
- 1993
|
|
92
|
Disparity analysis of images
– Barnard, Thompson
- 1980
|
|
74
|
Measurement of Image Velocity
– Fleet
- 1992
|
|
66
|
Directional selectivity and its use in early visual processing
– Man', Ullman
- 1979
|
|
59
|
Recovery of ego-motion using image stabilization
– Irani, Rousso, et al.
- 1994
|
|
48
|
The sampling and reconstruction of time-varying imagery with application in video systems
– Dubois
- 1985
|
|
48
|
Motion recovery from image sequences using only first order optical flow information
– Negahdaripour, Lee
- 1992
|
|
47
|
Obstacle detection by evaluation of optical flow fields
– Enkelmann
- 1990
|
|
45
|
Automatic Feature Point Extraction and Tracking in Image Sequences for Arbitrary Camera Motion
– Zheng, Chellappa
- 1995
|
|
44
|
Motion estimation from tagged MR image sequences
– Prince, McVeigh
- 1992
|
|
40
|
Three-dimensional motion computation and object segmentation in a long sequence of stereo frames
– Zhang, Faugeras
- 1992
|
|
32
|
Tsotsos. Techniques for disparity measurement
– Jenkin, Jepson, et al.
- 1991
|
|
26
|
Computational analysis of non-Fourier motion
– Fleet, Langley
- 1994
|
|
26
|
The accuracy of the computation of optical flow and of the recovery of motion parameters
– Micheli, Torre, et al.
- 1993
|
|
25
|
Direct computation of the focus of expansion
– Jain
- 1983
|
|
24
|
An iterative image-registration technique with an application to stereo vision
– Lucas, Kanade
- 1981
|
|
23
|
Vertical and horizontal disparities from phase
– Langley, Atherton, et al.
- 1990
|
|
21
|
Edge detection and motion detection
– Spacek
- 1986
|
|
20
|
A model for the detection of motion over time
– Black, Anandan
- 1990
|
|
20
|
Segmentation of frame sequences obtained by a moving observer
– Jain
- 1984
|
|
19
|
On the Detection of Motion and the Computation of Optical Flow
– Duncan, Chou
- 1992
|
|
19
|
Optical motions and space perception: An extension of gibson's analysis
– Hay
- 1966
|
|
18
|
Motion compensated television coding: Part 1
– Netravali, Robbins
- 1979
|
|
17
|
The feasibility of motion and structure from noisy time-varying image velocity information
– Jepson, Barron, et al.
- 1990
|
|
15
|
A split-merge parallel block-matching algorithm for video displacement estimation
– Carpentieri, Storer
- 1992
|
|
15
|
Bounds on Time-to-Collision and Rotational Component from First-Order Derivatives of Image Flow
– Subbarao
- 1990
|
|
14
|
How do we avoid confounding the direction we are looking and the direction we are moving
– Regan, Beverley
- 1982
|
|
14
|
Identifying Multiple Motions from Optical Flow
– Rognone, Campani, et al.
- 1992
|
|
13
|
A Fast Obstacle Detection Method based on Optical Flow
– Ancona
- 1992
|
|
13
|
The use of optical flow for the autonomous navigation
– Campani, Straforini, et al.
- 1992
|
|
13
|
Motion and Structure from Optical Flow
– Prazdny
- 1979
|
|
12
|
Optic flow to measure minute increments in plant growth
– Barron, Liptay
- 1994
|
|
11
|
Time-to-x: Analysis of motion through temporal parameters
– Burlina, Chellappa
- 1994
|
|
11
|
Subspace methods for recovering rigid motion 2: Algorithm and implementation
– Heeger, Jepson
- 1992
|
|
11
|
An error-weighted regularization algorithm for image motion-field estimation
– Zheng, Blostein
- 1993
|
|
9
|
Gradient-based flow segmentation and location of the focus of expansion
– Overington
- 1987
|
|
9
|
A fast method to estimate sensor translation
– Sundareswaran
- 1992
|
|
9
|
Theta motion: A paradoxical stimulus to explore higher-order motion extraction
– Zanker
- 1993
|
|
8
|
A video encoding system using conditional picture-element replenishment
– Mounts
- 1969
|
|
8
|
Motion-detection model with two stages: Spatiotemporal filtering and feature matching
– Ogata, Sato
- 1992
|
|
8
|
Movement detectors of the correlation type provide sufficient information for local computation of 2d velocity fields
– Reichardt, Schlogl, et al.
- 1988
|
|
7
|
Stereo correspondence from optical flow
– Cornilleau-Peres, Droulez
- 1990
|
|
