Search For:

Displaying 1-25 out of 25 total
Efficient algorithm for low-rank matrix factorization with missing components and performance comparison of latest algorithms
Found in: Computer Vision, IEEE International Conference on
By Takayuki Okatani,Takahiro Yoshida,Koichiro Deguchi
Issue Date:November 2011
pp. 842-849
This paper examines numerical algorithms for factorization of a low-rank matrix with missing components. We first propose a new method that incorporates a damping factor into the Wiberg method to solve the problem. The new method is characterized by the wa...
 
Accurate and robust planar tracking based on a model of image sampling and reconstruction process
Found in: Mixed and Augmented Reality, IEEE / ACM International Symposium on
By Eisuke Ito,Takayuki Okatani,Koichiro Deguchi
Issue Date:October 2011
pp. 1-8
It is one of the central issues in augmented reality and computer vision to track a planar object moving relatively to a camera in an accurate and robust manner. In previous studies, it was pointed out that there are several factors making the tracking dif...
 
Estimating Scale of a Scene from a Single Image Based on Defocus Blur and Scene Geometry
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Takayuki Okatani, Koichiro Deguchi
Issue Date:June 2007
pp. 1-8
Using an imaging system in which the image plane can be tilted with respect to the optical axis of the lens, the image of a large-scale scene that appears to be a miniature to human eyes can be captured. This phenomenon suggests that the image contains inf...
 
Variational Bayes Based Approach to Robust Subspace Learning
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Takayuki Okatani, Koichiro Deguchi
Issue Date:June 2007
pp. 1-8
This paper presents a new algorithm for the problem of robust subspace learning (RSL), i.e., the estimation of linear subspace parameters from a set of data points in the presence of outliers (and missing data). The algorithm is derived on the basis of the...
 
Autocalibration of an Ad Hoc Construction of Multi-Projector Displays
Found in: Computer Vision and Pattern Recognition Workshop
By Takayuki Okatani, Koichiro Deguchi
Issue Date:June 2006
pp. 4
In this paper, we present a method for geometric calibration of a multi-projector display system. It enables easy calibration of the system such that the user needs only to take a picture of the projected images on the planar screen with a hand-held camera...
 
Autocalibration of a Projector-Camera System
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Takayuki Okatani, Koichiro Deguchi
Issue Date:December 2005
pp. 1845-1855
This paper presents a method for calibrating a projector-camera system that consists of multiple projectors (or multiple poses of a single projector), a camera, and a planar screen. We consider the problem of estimating the homography between the screen an...
 
A Color-based Tracking by Kalman Particle Filter
Found in: Pattern Recognition, International Conference on
By Yoshinori Satoh, Takayuki Okatani, Koichiro Deguchi
Issue Date:August 2004
pp. 502-505
In this paper, a method for real-time tracking of moving objects is proposed. We applied Kalman particle filter (KPF) to color-based tracking. This KPF is a particle filter including the principle of Kalman filter, and it was adopted to the object contour ...
 
Object Tracking by the Mean-Shift of Regional Color Distribution Combined with the Particle-Filter Algorithm
Found in: Pattern Recognition, International Conference on
By Koichiro Deguchi, Oki Kawanaka, Takayuki Okatani
Issue Date:August 2004
pp. 506-509
This paper presents a method for tracking a person in a video sequence in real time. In this method the profile of color distribution characterises target's feature. It is invariant for rotation and scale changes. It's also robust to non-rigidity and parti...
 
3D Models Coding and Morphing for Efficient Video Compression
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Franck Galpin, Raphaèle Balter, Luce Morin, Koichiro Deguchi
Issue Date:July 2004
pp. 334-341
This paper presents new results in the field of video coding and compression using 3D information. Contrary to prior art in 3D model-based coding where 3D models have to be known, the 3D models are here automatically computed from the original video sequen...
 
Autocalibration of a Projector-Screen-Camera System: Theory and Algorithm for Screen-to-Camera Homography Estimation
Found in: Computer Vision, IEEE International Conference on
By Takayuki Okatani, Koichiro Deguchi
Issue Date:October 2003
pp. 774
This paper deals with the autocalibration of a system that consists of a planar screen, multiple projectors, and a camera. In the system, either multiple projectors or a single moving projector projects patterns on a screen while a stationary camera placed...
 
Toward a Statistically Optimal Method for Estimating Geometric Relations from Noisy Data: Cases of Linear Relations
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Takayuki Okatani, Koichiro Deguchi
Issue Date:June 2003
pp. 432
In many problems of computer vision we have to estimate parameters in the presence of nuisance parameters increasing with the amount of data. It is known that unlike in the cases without nuisance parameters, maximum likelihood estimation (MLE) is not optim...
 
Robust Estimation of Camera Translation Between Two Images Using a Camera With a 3D Orientation Sensor
Found in: Pattern Recognition, International Conference on
By Takayuki Okatani, Koichiro Deguchi
Issue Date:August 2002
pp. 10275
It is still a difficult problem to establish correspondences of feature points and to estimate view relations for multiple images of a static scene, if the images have large disparities. In this paper we explore the possibility of applying a cheap and gene...
 
On Photometric Aspects of Catadioptric Cameras
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Takayuki Okatani, Koichiro Deguchi
Issue Date:December 2001
pp. 1106
Several imaging systems called catadioptric cameras have been developed that use a combination of lenses and mirrors to obtain wide fields of view. Geometric aspects of them have been well studied so far. This paper focuses on photometric aspects of the ca...
 
Primitive Curve Generation Based on Multiscale Contour Figure Approximation
Found in: Pattern Recognition, International Conference on
By Hidekata Hontani, Koichiro Deguchi
Issue Date:September 2000
pp. 2887
We propose a method to generate primitive curves from a set of given contour figures. The primitive curve is a partial shape, which is commonly seen in given contours, and describes total characteristic shape of them. The proposed method, first, approximat...
 
Estimation of Illumination Distribution Using a Specular Sphere
Found in: Pattern Recognition, International Conference on
By Takayuki Okatani, Koichiro Deguchi
Issue Date:September 2000
pp. 3596
A method has been proposed for acquiring an omnidirectional image of a scene using a specular sphere (namely a mirror ball). The method takes the reflected image on the specular sphere located at a desired position in a scene by an ordinary camera. This pa...
 
A Method for Fine Registration of Multiple View Range Images Considering the Measurement Error Properties
Found in: Pattern Recognition, International Conference on
By Ikuko Shimizu Okatani, Koichiro Deguchi
Issue Date:September 2000
pp. 1280
This paper presents a new method for fine registration of two range images from different viewpoints that have been roughly registered. Our method takes into account the properties of the measurement error of the range images. The error distribution is dif...
 
Multi-Scale Image Analysis for Detection of Characteristic Component Figure Shapes and Sizes
Found in: Pattern Recognition, International Conference on
By Hidekata Hontani, Koichiro Deguchi
Issue Date:August 1998
pp. 1470
No summary available.
 
On Identification of Singular Points Using Photometric Invariants for Global Shape from Shading Problem
Found in: Pattern Recognition, International Conference on
By Takayuki Okatani, Koichiro Deguchi
Issue Date:August 1998
pp. 1787
No summary available.
 
Precise Shape Reconstruction by Active Pattern in Total-Internal-Reflection-Based Tactile Sensor
Found in: IEEE Transactions on Haptics
By Satoshi Saga,Ryosuke Taira,Koichiro Deguchi
Issue Date:January 2014
pp. 67-77
We are developing a total-internal-reflection-based tactile sensor in which the shape is reconstructed using an optical reflection. This sensor consists of silicone rubber, an image pattern, and a camera. It reconstructs the shape of the sensor surface fro...
 
Detecting Changes in 3D Structure of a Scene from Multi-view Images Captured by a Vehicle-Mounted Camera
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Ken Sakurada,Takayuki Okatani,Koichiro Deguchi
Issue Date:June 2013
pp. 137-144
This paper proposes a method for detecting temporal changes of the three-dimensional structure of an outdoor scene from its multi-view images captured at two separate times. For the images, we consider those captured by a camera mounted on a vehicle runnin...
 
Discrete MRF Inference of Marginal Densities for Non-uniformly Discretized Variable Space
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Masaki Saito,Takayuki Okatani,Koichiro Deguchi
Issue Date:June 2013
pp. 57-64
This paper is concerned with the inference of marginal densities based on MRF models. The optimization algorithms for continuous variables are only applicable to a limited number of problems, whereas those for discrete variables are versatile. Thus, it is ...
 
3D Fundus Pattern Reconstruction and Display from Multiple Fundus Images
Found in: Pattern Recognition, International Conference on
By Koichiro Deguchi, Junko Noami, Hidekata Hontani
Issue Date:September 2000
pp. 4094
This paper proposes a method to reconstruct and display 3D fundus (inner bottom of eyeball) pattern from a set of multiple partial images of fundus. They were taken from several different view angles by shifting fundus camera. Because they are distorted by...
 
Recognition of Indoor Images Employing Qualitative Model Fitting and Supporting Relation between Objects
Found in: Pattern Recognition, International Conference on
By Keiji Yanai, Koichiro Deguchi
Issue Date:September 2000
pp. 1964
In this paper, we describe a new design of a recognition system for a single image of indoor scene including complex occlusions. In our system, first, the system estimates 3D structure of an object by fitting a 3D structure model to the image qualitatively...
 
An Architecture of Object Recognition System for Various Images Based on Multi-Agent
Found in: Pattern Recognition, International Conference on
By Keiji Yanai, Koichiro Deguchi
Issue Date:August 1998
pp. 278
No summary available.
 
An Information Theoretic Approach for Active and Effective Object Recognitions
Found in: Pattern Recognition, International Conference on
By Koichiro DEGUCHI, Hiromi OHTSU
Issue Date:August 2006
pp. 622
This paper describes the strategy of optimal action selection for recognition of the observed object among those registered in the image data base from an information theoretic point of view. The goal is to reduce the number and effort of the recognition s...
 
 1