A camera based location estimation using point clouds

Masafumi Nakagawa; Daisuke Kato; Hirotaka Endo; Kenta Ochiai; Anna Nakanishi

A camera based location estimation using point clouds

Masafumi Nakagawa, Daisuke Kato, Hirotaka Endo, Kenta Ochiai, Anna Nakanishi

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

Abstract

When facility information is geocoded onto maps, higher accuracy and higher spatial resolution are required to assist AR interface. In this paper, we focus on the potential of a camera to act as a location sensor, assisting other location sensors to improve positioning accuracy. However, for a camera to be used as a location sensor, reliable maps will be required. We therefore focus on massive point-cloud data for use in reliable maps. We then develop a location-matching methodology based on image matching using an image taken from a camera and panoramic images generated from a massive colored point cloud. Finally, we present experimental results that confirm the validity of our approach.

Original language	English
Title of host publication	33rd Asian Conference on Remote Sensing 2012, ACRS 2012
Pages	43-50
Number of pages	8
Publication status	Published - 2012 Dec 1
Event	33rd Asian Conference on Remote Sensing 2012, ACRS 2012 - Pattaya, Thailand Duration: 2012 Nov 26 → 2012 Nov 30

Publication series

Name	33rd Asian Conference on Remote Sensing 2012, ACRS 2012
Volume	1

Conference

Conference	33rd Asian Conference on Remote Sensing 2012, ACRS 2012
Country/Territory	Thailand
City	Pattaya
Period	12/11/26 → 12/11/30

Keywords

Camera calibration
Image matching
Location estimation
Panorama image
Point cloud

ASJC Scopus subject areas

Information Systems

Cite this

@inproceedings{f1cfe2a294dc4e0a9c6468d734fba621,

title = "A camera based location estimation using point clouds",

abstract = "When facility information is geocoded onto maps, higher accuracy and higher spatial resolution are required to assist AR interface. In this paper, we focus on the potential of a camera to act as a location sensor, assisting other location sensors to improve positioning accuracy. However, for a camera to be used as a location sensor, reliable maps will be required. We therefore focus on massive point-cloud data for use in reliable maps. We then develop a location-matching methodology based on image matching using an image taken from a camera and panoramic images generated from a massive colored point cloud. Finally, we present experimental results that confirm the validity of our approach.",

keywords = "Camera calibration, Image matching, Location estimation, Panorama image, Point cloud",

author = "Masafumi Nakagawa and Daisuke Kato and Hirotaka Endo and Kenta Ochiai and Anna Nakanishi",

year = "2012",

month = dec,

day = "1",

language = "English",

isbn = "9781622769742",

series = "33rd Asian Conference on Remote Sensing 2012, ACRS 2012",

pages = "43--50",

booktitle = "33rd Asian Conference on Remote Sensing 2012, ACRS 2012",

note = "33rd Asian Conference on Remote Sensing 2012, ACRS 2012 ; Conference date: 26-11-2012 Through 30-11-2012",

}

TY - GEN

T1 - A camera based location estimation using point clouds

AU - Nakagawa, Masafumi

AU - Kato, Daisuke

AU - Endo, Hirotaka

AU - Ochiai, Kenta

AU - Nakanishi, Anna

PY - 2012/12/1

Y1 - 2012/12/1

N2 - When facility information is geocoded onto maps, higher accuracy and higher spatial resolution are required to assist AR interface. In this paper, we focus on the potential of a camera to act as a location sensor, assisting other location sensors to improve positioning accuracy. However, for a camera to be used as a location sensor, reliable maps will be required. We therefore focus on massive point-cloud data for use in reliable maps. We then develop a location-matching methodology based on image matching using an image taken from a camera and panoramic images generated from a massive colored point cloud. Finally, we present experimental results that confirm the validity of our approach.

AB - When facility information is geocoded onto maps, higher accuracy and higher spatial resolution are required to assist AR interface. In this paper, we focus on the potential of a camera to act as a location sensor, assisting other location sensors to improve positioning accuracy. However, for a camera to be used as a location sensor, reliable maps will be required. We therefore focus on massive point-cloud data for use in reliable maps. We then develop a location-matching methodology based on image matching using an image taken from a camera and panoramic images generated from a massive colored point cloud. Finally, we present experimental results that confirm the validity of our approach.

KW - Camera calibration

KW - Image matching

KW - Location estimation

KW - Panorama image

KW - Point cloud

UR - http://www.scopus.com/inward/record.url?scp=84880030785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880030785&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84880030785

SN - 9781622769742

T3 - 33rd Asian Conference on Remote Sensing 2012, ACRS 2012

SP - 43

EP - 50

BT - 33rd Asian Conference on Remote Sensing 2012, ACRS 2012

T2 - 33rd Asian Conference on Remote Sensing 2012, ACRS 2012

Y2 - 26 November 2012 through 30 November 2012

ER -

A camera based location estimation using point clouds

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this