Search For:

Displaying 1-11 out of 11 total
Hyper Least Squares and Its Applications
Found in: Pattern Recognition, International Conference on
By Prasanna Rangarajan, Kenichi Kanatani, Hirotaka Niitsuma, Yasuyuki Sugaya
Issue Date:August 2010
pp. 5-8
We present a new form of least squares (LS), called ``hyper LS'', for geometric problems that frequently appear in computer vision applications. Doing rigorous error analysis, we maximize the accuracy by introducing a normalization that eliminates statisti...
 
Mesh Optimization Using an Inconsistency Detection Template
Found in: Computer Vision, IEEE International Conference on
By Atsutada Nakatuji, Yasuyuki Sugaya, Kenichi Kanatani
Issue Date:October 2005
pp. 1148-1153
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 demons...
 
Further Improving Geometric Fitting
Found in: 3D Digital Imaging and Modeling, International Conference on
By Kenichi Kanatani
Issue Date:June 2005
pp. 2-13
We give a formal definition of geometric fitting in a way that suits computer vision applications. We point out that the performance of geometric fitting should be evaluated in the limit of small noise rather than in the limit of a large number of data as ...
 
Uncertainty Modeling and Model Selection for Geometric Inference
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kenichi Kanatani
Issue Date:October 2004
pp. 1307-1319
We first investigate the meaning of
 
Gauge Fixing for Accurate 3D Estimation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Daniel D. Morris, Kenichi Kanatani, Takeo Kanade
Issue Date:December 2001
pp. 343
Computer vision techniques can estimate 3D shape from images, but usually only up to a scale factor. The scale factor must be obtained by a physical measurement of the scene or the camera motion. Using gauge theory, we show that how this scale factor is de...
 
Do we really have to consider covariance matrices for image features?
Found in: Computer Vision, IEEE International Conference on
By Yasushi Kanazawa, Kenichi Kanatani
Issue Date:July 2001
pp. 301
Many studies have been made in the past for optimization using covariance matrices of feature points. We first describe how to compute the covariance matrix of a feature point from the gray levels by integrating existing methods. Then, we experimentally ex...
 
Comments on
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kenichi Kanatani
Issue Date:December 1997
pp. 1391-1392
<p><b>Abstract</b>—I point out the existence of a theoretical difficulty that underlies the curve segmentation problem studied by Rosin and West and present a possible solution to it.</p>
 
Comments on
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kenichi Kanatani
Issue Date:March 1997
pp. 246-247
<p><b>Abstract</b>—We point out the existence of a theoretical difficulty that underlies the symmetry detection studied by Zabrodsky et al. [<ref rid=
 
Motion Segmentation by Subspace Separation and Model Selection
Found in: Computer Vision, IEEE International Conference on
By Kenichi Kanatani
Issue Date:July 2001
pp. 586
Reformulating the Costeira-Kanade algorithm as a pure mathematical theorem independent of the Tomasi-Kanade factorization, we present a robust segmentation algorithm by incorporating such techniques as dimension correction, model selection using the geomet...
 
Gauge-Based Reliability Analysis of 3-D Reconstruction from Two Uncalibrated Perspective Views
Found in: Pattern Recognition, International Conference on
By Kenichi Kanatani
Issue Date:September 2000
pp. 1076
We evaluate the reliability of the 3-D (Euclidean) shape reconstructed from two uncalibrated perspective views. Introducing a statistical model of image noise, we optimally compute the fundamental matrix and evaluate its uncertainty in quantitative terms. ...
 
Accuracy Bounds and Optimal Computation of Homography for Image Mosaicing Applications
Found in: Computer Vision, IEEE International Conference on
By Kenichi Kanatani, Naoya Ohta
Issue Date:September 1999
pp. 73
We describe a theoretically optimal algorithm for computing the homography between two images in relation to image mosaicing applications. First, we derive a theoretical accuracy bound based on a mathematical model of image noise and do simulation to confi...
 
 1