Multiple points' 3D localization using a single camera

Title
Multiple points' 3D localization using a single camera
Authors
이득희박세형
Keywords
컴퓨터 비전; 물체 추적; 3D pose estimation; Image moments; Circle marker; Single camera
Issue Date
2010-01
Publisher
HCI2010 Proceedings
Abstract
Stereoscopic 3D images which could be seen at only special movie theaters have been popular in these days due to 3D TVs and 120Hz monitors. In this reason, The demand for the interaction between user and a virtual object in stereoscopic 3D images is increasing. In this paper, 3D input method of multiple points without an expensive device like a data glove is proposed. This method uses a planar homography, which consists of two parts: the physical transformation and camera intrinsics matrix. When we take pictures of a planar object with a calibrated camera, we can find out the physical transformation such as rotation matrix and translation vector with the feature points of the planar object and the corresponding positions in the image. For robust implementation, we use circular markers. The method of detecting the corresponding points in images is explained.
URI
http://pubs.kist.re.kr/handle/201004/37118
Appears in Collections:
KIST Publication > Conference Paper
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE