3D Object pose estimation from binarized images

Shingo Kagami; Masaru Morita; Koichi Hashimoto

3D Object pose estimation from binarized images

Shingo Kagami, Masaru Morita, Koichi Hashimoto

INF - System Information Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper discusses a 3D object pose estimation problem in which binarized images are used. Assuming that a CAD model of the object of interest is available, minimization of the difference between the captured and rendered images is considered. To make this minimization feasible in the situation where only binarized images are available, we propose to render a higher-resolution image at first and then resize it to the original size with help of an anti-alias filter. The simulated results show that the proposed method performs well as long as the given image offers sufficient clues.

Original language	English
Title of host publication	2012 Proceedings of SICE Annual Conference, SICE 2012
Publisher	Society of Instrument and Control Engineers (SICE)
Pages	759-761
Number of pages	3
ISBN (Print)	9781467322591
Publication status	Published - 2012 Jan 1
Event	2012 51st Annual Conference on of the Society of Instrument and Control Engineers of Japan, SICE 2012 - Akita, Japan Duration: 2012 Aug 20 → 2012 Aug 23

Publication series

Name	Proceedings of the SICE Annual Conference

Other

Other	2012 51st Annual Conference on of the Society of Instrument and Control Engineers of Japan, SICE 2012
Country	Japan
City	Akita
Period	12/8/20 → 12/8/23

Keywords

Levenberg-Marquardt method
appearance-based pose estimation
least square

ASJC Scopus subject areas

Control and Systems Engineering
Computer Science Applications
Electrical and Electronic Engineering

Access to Document

Fingerprint Dive into the research topics of '3D Object pose estimation from binarized images'. Together they form a unique fingerprint.

Cite this

Kagami, S, Morita, M & Hashimoto, K 2012, 3D Object pose estimation from binarized images. in 2012 Proceedings of SICE Annual Conference, SICE 2012., 6318540, Proceedings of the SICE Annual Conference, Society of Instrument and Control Engineers (SICE), pp. 759-761, 2012 51st Annual Conference on of the Society of Instrument and Control Engineers of Japan, SICE 2012, Akita, Japan, 12/8/20.

@inproceedings{fb76c04ee0e54d858b1191ec1f043722,

title = "3D Object pose estimation from binarized images",

abstract = "This paper discusses a 3D object pose estimation problem in which binarized images are used. Assuming that a CAD model of the object of interest is available, minimization of the difference between the captured and rendered images is considered. To make this minimization feasible in the situation where only binarized images are available, we propose to render a higher-resolution image at first and then resize it to the original size with help of an anti-alias filter. The simulated results show that the proposed method performs well as long as the given image offers sufficient clues.",

keywords = "Levenberg-Marquardt method, appearance-based pose estimation, least square",

author = "Shingo Kagami and Masaru Morita and Koichi Hashimoto",

year = "2012",

month = jan,

day = "1",

language = "English",

isbn = "9781467322591",

series = "Proceedings of the SICE Annual Conference",

publisher = "Society of Instrument and Control Engineers (SICE)",

pages = "759--761",

booktitle = "2012 Proceedings of SICE Annual Conference, SICE 2012",

note = "2012 51st Annual Conference on of the Society of Instrument and Control Engineers of Japan, SICE 2012 ; Conference date: 20-08-2012 Through 23-08-2012",

}

TY - GEN

T1 - 3D Object pose estimation from binarized images

AU - Kagami, Shingo

AU - Morita, Masaru

AU - Hashimoto, Koichi

PY - 2012/1/1

Y1 - 2012/1/1

N2 - This paper discusses a 3D object pose estimation problem in which binarized images are used. Assuming that a CAD model of the object of interest is available, minimization of the difference between the captured and rendered images is considered. To make this minimization feasible in the situation where only binarized images are available, we propose to render a higher-resolution image at first and then resize it to the original size with help of an anti-alias filter. The simulated results show that the proposed method performs well as long as the given image offers sufficient clues.

AB - This paper discusses a 3D object pose estimation problem in which binarized images are used. Assuming that a CAD model of the object of interest is available, minimization of the difference between the captured and rendered images is considered. To make this minimization feasible in the situation where only binarized images are available, we propose to render a higher-resolution image at first and then resize it to the original size with help of an anti-alias filter. The simulated results show that the proposed method performs well as long as the given image offers sufficient clues.

KW - Levenberg-Marquardt method

KW - appearance-based pose estimation

KW - least square

UR - http://www.scopus.com/inward/record.url?scp=84869387694&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84869387694&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84869387694

SN - 9781467322591

T3 - Proceedings of the SICE Annual Conference

SP - 759

EP - 761

BT - 2012 Proceedings of SICE Annual Conference, SICE 2012

PB - Society of Instrument and Control Engineers (SICE)

T2 - 2012 51st Annual Conference on of the Society of Instrument and Control Engineers of Japan, SICE 2012

Y2 - 20 August 2012 through 23 August 2012

ER -