Correspondenceless stereo and motion: planar surfaces

Aloimonos, John; Herve, J.-Y.

doi:10.1109/34.55111

Cited by 37 publications

(7 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For a short baseline, we calculate the change of the above derivatives caused by the camera's movement by differentiating with respect to x',: (6) where 6, is the Kronecker delta, and the indexes i, j can take either of the two values x ory. We can multiply equations (l), (5) and (6) by z, to obtain the linear system of equations:…”

Section: Lambertian Suflacesmentioning

confidence: 99%

Active vision

Aloimonos¹,

Weiss²,

Bandyopadhyay³

1988

Int J Comput Vision

885

436

View full text Add to dashboard Cite

We investigate several basic problems in vision under the assumption that the observer is active. An observer is called active when engaged in some kind of activity whose purpose is to control the geometric parameters of the sensory apparatus. The purpose of the activity is to manipulate the constraints underlying the observed phenomena in order to improve the quality of the perceptual results. For example a monocular observer that moves with a known or unknown motion or a binocular observer that can rotate his eyes and track environmental objects are just two examples of an observer that we call active. We prove that an active observer can solve basic vision problems in a much more efficient way than a passive one. Problems that are ill-posed and nonlinear for a passive observer become well-posed and linear for an active observer. In particular, the problems of shape from shading and depth computation, shape from contour, shape from texture, and structure from motion are shown to be much easier for an active observer than for a passive one. It has to be emphasized that correspondence is not used in our approach, i.e., active vision is not correspondence of features from multiple viewpoints. Finally, active vision here does not mean active sensing, and this paper introduces a general methodology, a general framework in which we believe low-level vision problems should be addressed.

show abstract

Section: Lambertian Suflacesmentioning

confidence: 99%

Active vision

Aloimonos¹,

Weiss²,

Bandyopadhyay³

1988

Int J Comput Vision

885

436

View full text Add to dashboard Cite

show abstract

“…Gaussian mask is a low-pass filter which can get rid of the high frequency error of the curve during imaging, quantlization and preprocessing. The Gaussian mask they take is g(t,cY) g(t,a) = e'/22 (2) cysJ:…”

Section: Detection Of Zero Curvature Points and Corner Pointsmentioning

confidence: 99%

<title>Quadric-matching-based reconstruction of space curve</title>

Ding¹,

Yan

1998

International Symposium on Multispectral Image Processing (ISMIP'98)

View full text Add to dashboard Cite

A fast 3-D reconstruction of space curve based on quadric segment and matching in trinocular vision is proposed in this paper. First by using the perspective invariance of zero curvature and corner points in curves, curves can be segmented into different quadric curves. Then match these segments among three images and reconstruct them respectively. Finally combine all reconstructed segments together to form continuous curves. The experiments illustrated that the reconstruction speed is higher than those which take points or lines as primitives and duality and a uniqueness solution can be ensured.

show abstract

“…Others used controlled camera motions to assist the process of recovering 3D structures from the scene [7,20]. Waxman and Duncan [21], Jenkin and Tsotsos [13], and Aloimonos and Nerve [1] attempt to unify stereo and motion cues to overcome these shortcomings, but these approaches have their own limitations, such as a planarity assumption and extensive computational searching. Another approach is to remove the ambiguity that the motion cue recovers about the world information, only up to a scale factor in the case of an unknown motion.…”

Section: Introductionmentioning

confidence: 99%