Automatic model construction, pose estimation, and object recognition from photographs using triangular splines

Sullivan, Steve; Ponce, Jean

doi:10.1109/iccv.1998.710765

Cited by 43 publications

(23 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This information has been put to very good effect by researchers, such as Sullivan et al (1994), Vaillant and Faugeras (1992), Sullivan and Ponce (1998), Cross and Zisserman (2000), Szeliski and Weiss (1998), Boyer and Berger (1997), Davis and Bobick (1998), Cipolla and Blake (1992), Terzopoulos and Metaxas (1991), among many others. In most of these works, the technique used to actually extract the occluding contours is relatively straightforward.…”

Section: Related Workmentioning

confidence: 99%

Implicit Meshes for Effective Silhouette Handling

Ilić

Salzmann

Fua

2006

Int J Comput Vision

View full text Add to dashboard Cite

Abstract. Using silhouettes in uncontrolled environments typically requires handling occlusions as well as changing or cluttered backgrounds, which limits the applicability of most silhouette based methods. For the purpose of 3-D shape modeling, we show that representing generic 3-D surfaces as implicit surfaces lets us effectively address these issues.This desirable behavior is completely independent from the way the surface deformations are parametrized. To show this, we demonstrate our technique in three very different cases: Modeling the deformations of a piece of paper represented by an ordinary triangulated mesh; reconstruction and tracking a person's shoulders whose deformations are expressed in terms of Dirichlet Free Form Deformations; reconstructing the shape of a human face parametrized in terms of a Principal Component Analysis model.

show abstract

Section: Related Workmentioning

confidence: 99%

Implicit Meshes for Effective Silhouette Handling

Ilić

Salzmann

Fua

2006

Int J Comput Vision

View full text Add to dashboard Cite

show abstract

“…An octree data structure was proposed to speed up the construction of the visual hull model (Potmesil 1987). A method using splines instead of polygonal meshes was proposed to improve the shape of the model (Sullivan & Ponce 1998). Another method for constructing the visual hull models using voxels was proposed, but the processing was done off-line (Moezzi et al 1996).…”

Section: Previous Workmentioning

confidence: 99%

O fly, where art thou?

Grover

Tower

Tavaré

2008

J. R. Soc. Interface.

View full text Add to dashboard Cite

In this paper, the design of a real-time image acquisition system for tracking the movement of Drosophila in three-dimensional space is presented. The system uses three calibrated and synchronized cameras to detect multiple flies and integrates the detected fly silhouettes to construct the three-dimensional visual hull models of each fly. We used an extended Kalman filter to estimate the state of each fly, given past positions from the reconstructed fly visual hulls. The results show that our approach constructs the three-dimensional visual hull of each fly from the detected image silhouettes and robustly tracks them at real-time rates. The system is suitable for a more detailed analysis of fly behaviour.

show abstract

“…Instead, an outer approximation of the observed solid-dubbed the visual hull in [21]-is computed as the intersection of the viewing cones associated with all input cameras. Several variants of Baumgart's original algorithm have been proposed over the years, including [1,8,25,29], and the method recently proposed by…”

Section: Introductionmentioning

confidence: 99%

Robust structure and motion from outlines of smooth curved surfaces

Furukawa

Sethi

Ponce

et al. 2006

IEEE Trans. Pattern Anal. Machine Intell.

Self Cite

View full text Add to dashboard Cite

This article addresses the problem of estimating the motion of a camera as it observes the outline (or apparent contour) of a solid bounded by a smooth surface in successive image frames. In this context, the surface points that project onto the outline of an object depend on the viewpoint, and the only true correspondences between two outlines of the same object are the projections of frontier points where the viewing rays intersect in the tangent plane of the surface. In turn, the epipolar geometry is easily estimated once these correspondences have been identified. Given the apparent contours detected in an image sequence, a robust procedure based on RANSAC and a voting strategy is proposed to simultaneously estimate the camera configurations and a consistent set of frontier point projections by enforcing the redundancy of multi-view epipolar geometry. The proposed approach is, in principle, applicable to orthographic, weak-perspective and affine projection models. Experiments with nine real image sequences are presented for the orthographic projection case, including a quantitative comparison with the ground-truth data for the six datasets for which the latter information is available. Sample visual hulls have been computed from all image sequences for qualitative evaluation.

show abstract

Automatic model construction, pose estimation, and object recognition from photographs using triangular splines

Cited by 43 publications

References 27 publications

Implicit Meshes for Effective Silhouette Handling

Implicit Meshes for Effective Silhouette Handling

O fly, where art thou?

Robust structure and motion from outlines of smooth curved surfaces

Contact Info

Product

Resources

About