Geolocation for printed maps using line segment-based SIFT-like feature matching

Gautier Minster; Guillaume Moreau; Hideo Saito

doi:10.1109/ISMARW.2015.24

Geolocation for printed maps using line segment-based SIFT-like feature matching

Gautier Minster, Guillaume Moreau, Hideo Saito

Department of Information and Computer Science

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

2 Citations (Scopus)

Abstract

This paper presents a method for the geolocation of printed maps. It enables the registration of unprepared maps with a Geographical Information System (GIS) database, and can for example be used as a first step to augment an unknown map. We define and match local road pattern descriptors, which are similar to SIFT descriptors [6], but adapted to the case of simple textureless line segments. Using a processing pipeline commonly encountered in the feature-point based matching of texture images - composed of offline description and indexing, followed by an online description, matching and robust transformation estimation - we show that local descriptors can successfully register unprepared maps using only geographic features and no texture information. Our method is scale and rotation invariant, and circumvents the two hurdles that are the level-of-detail, and the changing colormaps and textures, allowing the processing of large classes of printed maps.

Original language	English
Title of host publication	Proceedings of the 2015 IEEE International Symposium on Mixed and Augmented Reality Workshops, ISMARW 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	88-93
Number of pages	6
ISBN (Print)	9781467384711
DOIs	https://doi.org/10.1109/ISMARW.2015.24
Publication status	Published - 2015 Dec 2
Event	14th IEEE International Symposium on Mixed and Augmented Reality Workshops, ISMARW 2015 - Fukuoka, Japan Duration: 2015 Sep 29 → 2015 Oct 3

Other

Other	14th IEEE International Symposium on Mixed and Augmented Reality Workshops, ISMARW 2015
Country	Japan
City	Fukuoka
Period	15/9/29 → 15/10/3

Keywords

Geolocation
GIS
Local descriptor
Map registration
Printed map

ASJC Scopus subject areas

Computer Science Applications
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ISMARW.2015.24

Fingerprint Dive into the research topics of 'Geolocation for printed maps using line segment-based SIFT-like feature matching'. Together they form a unique fingerprint.

Cite this

Geolocation for printed maps using line segment-based SIFT-like feature matching. / Minster, Gautier; Moreau, Guillaume; Saito, Hideo.

Proceedings of the 2015 IEEE International Symposium on Mixed and Augmented Reality Workshops, ISMARW 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 88-93 7344764.

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

Minster, G, Moreau, G & Saito, H 2015, Geolocation for printed maps using line segment-based SIFT-like feature matching. in Proceedings of the 2015 IEEE International Symposium on Mixed and Augmented Reality Workshops, ISMARW 2015., 7344764, Institute of Electrical and Electronics Engineers Inc., pp. 88-93, 14th IEEE International Symposium on Mixed and Augmented Reality Workshops, ISMARW 2015, Fukuoka, Japan, 15/9/29. https://doi.org/10.1109/ISMARW.2015.24

@inproceedings{6ea19f2e21414e5fb848549478babb34,

title = "Geolocation for printed maps using line segment-based SIFT-like feature matching",

abstract = "This paper presents a method for the geolocation of printed maps. It enables the registration of unprepared maps with a Geographical Information System (GIS) database, and can for example be used as a first step to augment an unknown map. We define and match local road pattern descriptors, which are similar to SIFT descriptors [6], but adapted to the case of simple textureless line segments. Using a processing pipeline commonly encountered in the feature-point based matching of texture images - composed of offline description and indexing, followed by an online description, matching and robust transformation estimation - we show that local descriptors can successfully register unprepared maps using only geographic features and no texture information. Our method is scale and rotation invariant, and circumvents the two hurdles that are the level-of-detail, and the changing colormaps and textures, allowing the processing of large classes of printed maps.",

keywords = "Geolocation, GIS, Local descriptor, Map registration, Printed map",

author = "Gautier Minster and Guillaume Moreau and Hideo Saito",

year = "2015",

month = dec,

day = "2",

doi = "10.1109/ISMARW.2015.24",

language = "English",

isbn = "9781467384711",

pages = "88--93",

booktitle = "Proceedings of the 2015 IEEE International Symposium on Mixed and Augmented Reality Workshops, ISMARW 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "14th IEEE International Symposium on Mixed and Augmented Reality Workshops, ISMARW 2015 ; Conference date: 29-09-2015 Through 03-10-2015",

}

TY - GEN

T1 - Geolocation for printed maps using line segment-based SIFT-like feature matching

AU - Minster, Gautier

AU - Moreau, Guillaume

AU - Saito, Hideo

PY - 2015/12/2

Y1 - 2015/12/2

N2 - This paper presents a method for the geolocation of printed maps. It enables the registration of unprepared maps with a Geographical Information System (GIS) database, and can for example be used as a first step to augment an unknown map. We define and match local road pattern descriptors, which are similar to SIFT descriptors [6], but adapted to the case of simple textureless line segments. Using a processing pipeline commonly encountered in the feature-point based matching of texture images - composed of offline description and indexing, followed by an online description, matching and robust transformation estimation - we show that local descriptors can successfully register unprepared maps using only geographic features and no texture information. Our method is scale and rotation invariant, and circumvents the two hurdles that are the level-of-detail, and the changing colormaps and textures, allowing the processing of large classes of printed maps.

AB - This paper presents a method for the geolocation of printed maps. It enables the registration of unprepared maps with a Geographical Information System (GIS) database, and can for example be used as a first step to augment an unknown map. We define and match local road pattern descriptors, which are similar to SIFT descriptors [6], but adapted to the case of simple textureless line segments. Using a processing pipeline commonly encountered in the feature-point based matching of texture images - composed of offline description and indexing, followed by an online description, matching and robust transformation estimation - we show that local descriptors can successfully register unprepared maps using only geographic features and no texture information. Our method is scale and rotation invariant, and circumvents the two hurdles that are the level-of-detail, and the changing colormaps and textures, allowing the processing of large classes of printed maps.

KW - Geolocation

KW - GIS

KW - Local descriptor

KW - Map registration

KW - Printed map

UR - http://www.scopus.com/inward/record.url?scp=84960399266&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960399266&partnerID=8YFLogxK

U2 - 10.1109/ISMARW.2015.24

DO - 10.1109/ISMARW.2015.24

M3 - Conference contribution

AN - SCOPUS:84960399266

SN - 9781467384711

SP - 88

EP - 93

BT - Proceedings of the 2015 IEEE International Symposium on Mixed and Augmented Reality Workshops, ISMARW 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th IEEE International Symposium on Mixed and Augmented Reality Workshops, ISMARW 2015

Y2 - 29 September 2015 through 3 October 2015

ER -