Yasuyuki Sugaya

Geometric Structure of Degeneracy for Multi-body Motion Segmentation

Many techniques have been proposed for segmenting feature point trajectories tracked through a video sequence into independent motions. It has been found, however, that methods that perform very well in simulations perform very poorly for real video sequences. This paper resolves this mystery by analyzing the geometric structure of the degeneracy of the motion model. This leads to a new segmentation algorithm: a multi-stage unsupervised learning scheme first using the degenerate motion model and then using the general 3-D motion model. We demonstrate by simulated and real video experiments that our method is superior to all existing methods in practical situations.

Extending Interrupted Feature Point Tracking for 3-D Affine Reconstruction

Feature point tracking over a video sequence fails when the points go out of the field of view or behind other objects. In this paper, we extend such interrupted tracking by imposing the constraint that under the affine camera model all feature trajectories should be in an affine space. Our method consists of iterations for optimally extending the trajectories and for optimally estimating the affine space, coupled with an outlier removal process. Using real video images, we demonstrate that our method can restore a sufficient number of trajectories for detailed 3-D reconstruction.

Stabilizing the Focal Length Computation for 3-D Reconstruction from Two Uncalibrated Views

In order to reconstruct 3-D shape from two uncalibrated views, one needs to resolve two problems: (i) the computed focal lengths can be imaginary; (ii) the computation fails for fixated images. We present a practical remedy for these by subsampling feature points and fixing the focal length. We first summarize theoretical backgrounds and then do simulations, which reveal a rather surprising fact that when the focal length is actually fixed, not using that knowledge yields better results for non-fixated images. We give an explanation to this seeming paradox and derive a hybrid method switching the computation by judging whether or not the images are fixated. Doing simulations and real image experiments, we demonstrate the effectiveness of our method.

Optimizing a Triangular Mesh for Shape Reconstruction from Images

In reconstructing 3-D from images based on feature points, one usually defines a triangular mesh that has these feature points as vertices and displays the scene as a polyhedron. If the scene itself is a polyhedron, however, some of the displayed edges may be inconsistent with the true shape. This paper presents a new technique for automatically eliminating such inconsistencies by using a special template. We also present a technique for removing spurious occluding edges. All the procedures do not require any thresholds to be adjusted. Using real images, we demonstrate that our method has high capability to correct inconsistencies.

Statistical Optimization for 3-D Reconstruction from a Single View

We analyze the noise sensitivity of the focal length computation, the principal point estimation, and the orthogonality enforcement for single-view 3-D reconstruction based on vanishing points and orthogonality. We point out that due to the nonlinearity of the problem the standard statistical optimization is not very effective. We present a practical compromise for avoiding the computational failure and preserving high accuracy, allowing a consistent 3-D shape in the presence of however large noise.

LATEST ALGORITHMS FOR 3-D RECONSTRUCTION FROM TWO VIEWS

This paper presents a new algorithm for reconstructing the 3-D shape of the scene from point correspondences over two views. The basic principle is well known, but we incorporate into it the latest results of the authors’ studies of statistical optimization techniques. As a result, not only the accuracy increases but also the organization of the program becomes simpler, allowing this system to be used in a wider range of practical application. Also, our system take into consideration the degenerate situation where the camera is in a fixating configuration. This makes our system very practical, since this is the situation most frequently encountered in practice. Finally, we demonstrate the performance of our system using real images.

Mesh optimization using an inconsistency detection template

We propose a new technique for optimizing a triangular mesh for polyhedral representation of the scene in a video stream. We introduce a specially designed template that can effectively detect color and texture discontinuities. Using real images, we demonstrate that our method is superior to existing methods