scispace - formally typeset
Search or ask a question
Author

Hong-Jae Kim

Bio: Hong-Jae Kim is an academic researcher from Samsung. The author has contributed to research in topics: Image plane & Real image. The author has an hindex of 1, co-authored 1 publications receiving 5 citations.

Papers
More filters
Proceedings ArticleDOI
Hong-Jae Kim1, Bum-Jae You1, Gregory D. Hager1, Sang-Rok Oh1, Chong Won Lee1 
17 Oct 1999
TL;DR: A simple and fast stereo matching algorithm for real-time robotic applications and an improved scheme for feature matching using three-dimensional information by adopting backprojection as a feedback element measuring the degree of feature matching.
Abstract: There has been much interests on three-dimensional pose estimation of an object since there are a lot of robotic applications such as intelligent robotic assembly and/or vision-guided control of a humanoid or human-friendly robot. In this paper, there are proposed a simple and fast stereo matching algorithm for real-time robotic applications and an improved scheme for feature matching using three-dimensional information by adopting backprojection as a feedback element measuring the degree of feature matching. The degree of feature matching is determined by checking existence ratio of each feature point in real images after back-projecting an object model into image plane. The proposed pose determination algorithm is applied for a humanoid robot in KIST, whose name is CENTAUR, successfully and determine the pose of several polyhedral objects using 3D information of vertexes on the outline of an object in image plane.

5 citations


Cited by
More filters
Proceedings ArticleDOI
17 Dec 2010
TL;DR: In this article, several kinds of multi-CMOS station mode are introduced, and fundamental principles and classification of station mode directly affect on measurement parameters of the system, no matter what mode is designed, the ultimate goal is to extend Effective Viewing Field (EVF), increase capture ratio of objects and increase measurement precision.
Abstract: A key problem of attitude determination system is how to locate CMOS cameras and deal with relations among them. In this paper, several kinds of multi-CMOS station mode are introduced. Fundamental principles and classification of station mode directly affect on measurement parameters of system. No matter what mode is designed, the ultimate goal is to extend Effective Viewing Field (EVF), increase capture ratio of objects and increase measurement precision. Station mode introduced in this paper is made of CMOS cameras, because of low cost, high speed frame frequency and low power consumption, CMOS cameras were putted near from object tested. So sequences of image are legible, which are convenient for analysis of three dimensional(3D) attitude.

1 citations

Proceedings ArticleDOI
10 Dec 2010
TL;DR: In this paper, a multi-CMOS station mode is designed, multiple CMOS videos were placed on two parallel sides in measurement system, every two CMOS form an intersection viewing field, multiple viewing field join to cover shooting range, which can augment Effective Viewing Field(EVF), increase capture ratio of objects with high speed and measurement precision of small objects.
Abstract: A key problem of attitude measurement of small- multi-target with high speed is how to decide the optimum of the CMOS stations. A multi-CMOS station mode is designed in this paper, multiple CMOS videos were placed on two parallel sides in measurement system, every two CMOS form an intersection viewing field, multiple viewing field join to cover shooting range, which can augment Effective Viewing Field(EVF) , increase capture ratio of objects with high speed and measurement precision of small objects. When an object passes through the joint area, it will be imaged separately on each CMOS focal plane. Multiple CMOS videos were triggered synchronously, a sequence of image information was extracted, the target attitude was confirmed by digital image processing technology. The merit of station mode is low cost, large measurement scope, extending freely and so on.

1 citations

01 Jan 2010
TL;DR: In this paper, an intersecting system based on multiple high-speed CMOS cameras was introduced to measure attitude of small, dim and high speed targets in a shooting range, where cameras were laid near from objects for small size.
Abstract: In order to measure attitude of small, dim and high-speed targets in shooting range, intersecting system based on multiple high-speed CMOS cameras was introduced in this paper. CMOS cameras were laid near from objects for small size, using multiple CMOS cameras to compose intersecting system for big number of targets tested, and selecting CMOS camera between CMOS and CCD for low cost and considering damage to measurement equipment of objects tested. Pitch angle and yaw angle were measured by extracting axle wire through image processing, image sequences were obtained from cameras laying on two sides. Velocity of objects was calculated by least square curve-fitting, acquiring coordinate of centroid on image received by CMOS camera laying below effective viewing field. One CMOS camera was laid on right ahead for measuring roll angle. Station mode introduced in this paper has virtue of low cost and free extending.

1 citations

Proceedings ArticleDOI
01 Dec 2010
TL;DR: In order to measure attitude of small, dim and high-speed targets in shooting range, intersecting system based on multiple high- speed CMOS cameras was introduced in this paper.
Abstract: In order to measure attitude of small, dim and high-speed targets in shooting range, intersecting system based on multiple high-speed CMOS cameras was introduced in this paper. CMOS cameras were laid near from objects for small size, using multiple CMOS cameras to compose intersecting system for big number of targets tested, and selecting CMOS camera between CMOS and CCD for low cost and considering damage to measurement equipment of objects tested. Pitch angle and yaw angle were measured by extracting axle wire through image processing, image sequences were obtained from cameras laying on two sides. Velocity of objects was calculated by least square curve-fitting, acquiring coordinate of centroid on image received by CMOS camera laying below effective viewing field. One CMOS camera was laid on right ahead for measuring roll angle. Station mode introduced in this paper has virtue of low cost and free extending.