We show how to automatically acquire a Euclidean shape representations of objects from noisy image sequences under weak perspective. The proposed method is linear and incremental, requiring no more than pseudo-inverse. A nonlinear but numerically sound preprocessing stage is added to improve the accuracy of the results even further. Experiments show that attention to noise and computational techniques improve the shape results substantially with respect to previous methods proposed for ideal images. Keywords--- Structure from motion, linear reconstruction, factorization method, affine shape, Euclidean shape, weak perspective, Gramian, affine coordinates. 1
|
639
|
Shape and motion from image streams under ortography: a factorization approach
– Tomasi, Kanade
- 1992
|
|
482
|
A computer algorithm for reconstructing a scene from two projections," Nature 293
– Longuet-Higgins
|
|
476
|
What can be seen in three dimensions with an uncalibrated stereo rig
– Faugeras
- 1992
|
|
372
|
Closed-form solution of absolute orientation using orthonormal matrices
– Horn, Hilden, et al.
- 1988
|
|
366
|
Recognition by Linear Combinations of Models
– Ullman, Basri
- 1991
|
|
297
|
The Interpretation of Visual Motion
– Ullman
- 1984
|
|
248
|
Affine Structure from Motion
– Koenderink, Doorn
- 1991
|
|
247
|
Uniqueness and estimation of threedimensional motion parameters of rigid objects with curved surfaces
– Tsai, Huang
|
|
169
|
Epipolar-plane image analysis: An approach to determining structure from motion
– Bolles, Baker, et al.
- 1987
|
|
163
|
Kalman filterbased algorithms for estimating depth from image sequences
– Matthies, Kanade, et al.
- 1989
|
|
160
|
Stochastic models, estimation and control
– Maybeck
- 1979
|
|
139
|
Shape and Motion from Image Streams: A Factorization Method Part 3 - Detection and Tracking of Point Features
– Tomasi, Kanade
- 1991
|
|
106
|
Relative orientation
– Horn
- 1990
|
|
99
|
Affine invariant model-based object recognition
– Lamdan, Schwartz, et al.
- 1990
|
|
97
|
Relative 3D reconstruction using multiple uncalibrated images
– Mohr, Quan, et al.
- 1992
|
|
72
|
Recursive 3-D motion estimation from a monocular sequence
– Broida, Chandrashekhar, et al.
- 1990
|
|
52
|
A study of affine matching with bounded sensor error
– Grimson, Huttenlocher, et al.
- 1994
|
|
52
|
Maximizing rigidity: The incremental recovery of 3-d structure from rigid and rubbery motion
– Ullman
- 1984
|
|
37
|
Model-based invariants for 3-D vision
– Weinshall
- 1993
|
|
36
|
Perspective approximations
– Aloimonos
- 1990
|
|
27
|
Visual Tracking with Deformation Models
– Rehg, Witkin
- 1991
|
|
25
|
Direct computation of the focus of expansion
– Jain
- 1983
|
|
23
|
Optimal motion estimation
– Spetsakis, Aloimonos
- 1989
|
|
20
|
Description and reconstruction from image trajectories of rotational motion
– Sawhney, Oliensis, et al.
- 1990
|
|
19
|
Computer tracking of objects moving in space
– Roach, Aggarwal
- 1979
|
|
18
|
Sensitivity of the Pose Refinement Problem to Accurate Estimation of Camera Parameters
– Kumar, Hanson
- 1990
|
|
18
|
Processing translational motion sequences
– Lawton
- 1983
|
|
18
|
A rational algebraic formulation of the problem of relative orientation
– Thompson
|
|
15
|
Visual perception of three-dimensional motion
– Heeger, Jepson
- 1989
|
|
13
|
Motion displacement estimation using an affine model for image matching
– Fuh, Maragos
- 1991
|
|
9
|
Psychophysical support for a 2D interpolation theory of object recognition
– Bulthoff, Edelman
- 1990
|
|
5
|
A direct data approximation based motion estimation algorithm
– Debrunner, Ahuja
- 1990
|
|
2
|
and incremental acquisition of invariant shape models from image sequences. RC 18549 (81133), IBM
– Linear
- 1992
|
|
1
|
On rank-revealing QR factorizations. Research report YALEU/DCS/RR-880
– Chandrasekaran, Ipsen
- 1991
|
|
