Geolocation based landmark detection and annotation-towards clickable real world-

Atsushi Shimada, Vincent Charvillat, Hajime Nagahara, Rin-Ichiro Taniguchi

研究成果: ジャーナルへの寄稿記事

抄録

Clickable Real World is a new framework to realize an intuitive information search with a mobile terminal. To achieve the goal, we tackle two challenging tasks. One is landmark detection from an observing scene. Our approach detects a landmark based on an image prior. The prior is not given manually. Instead, it is generated automatically from the training samples collected from photo sharing website. Another challenging task is image annotation assisted by geolocation. We use the location of a user who uses a mobile terminal, and geolocation where the training sample images were taken. Two probabilistic models are generated to achieve image annotation. One is image-based labeling which utilizes the co-occurrence between image features and label features. The other is label-based localization which uses the consensus about the label given around the geolocation among photographers. We combine two probabilistic approaches to improve the accuracy of image annotation. We demonstrate this approach for 87 scenes in the world.

元の言語英語
ページ(範囲)142-149
ページ数8
ジャーナルIEEJ Transactions on Electronics, Information and Systems
133
発行部数1
DOI
出版物ステータス出版済み - 1 1 2013

Fingerprint

Labels
Labeling
Websites
Statistical Models

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

これを引用

Geolocation based landmark detection and annotation-towards clickable real world-. / Shimada, Atsushi; Charvillat, Vincent; Nagahara, Hajime; Taniguchi, Rin-Ichiro.

:: IEEJ Transactions on Electronics, Information and Systems, 巻 133, 番号 1, 01.01.2013, p. 142-149.

研究成果: ジャーナルへの寄稿記事

@article{890b2497320e44718a93906bb3672caf,
title = "Geolocation based landmark detection and annotation-towards clickable real world-",
abstract = "Clickable Real World is a new framework to realize an intuitive information search with a mobile terminal. To achieve the goal, we tackle two challenging tasks. One is landmark detection from an observing scene. Our approach detects a landmark based on an image prior. The prior is not given manually. Instead, it is generated automatically from the training samples collected from photo sharing website. Another challenging task is image annotation assisted by geolocation. We use the location of a user who uses a mobile terminal, and geolocation where the training sample images were taken. Two probabilistic models are generated to achieve image annotation. One is image-based labeling which utilizes the co-occurrence between image features and label features. The other is label-based localization which uses the consensus about the label given around the geolocation among photographers. We combine two probabilistic approaches to improve the accuracy of image annotation. We demonstrate this approach for 87 scenes in the world.",
author = "Atsushi Shimada and Vincent Charvillat and Hajime Nagahara and Rin-Ichiro Taniguchi",
year = "2013",
month = "1",
day = "1",
doi = "10.1541/ieejeiss.133.142",
language = "English",
volume = "133",
pages = "142--149",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "1",

}

TY - JOUR

T1 - Geolocation based landmark detection and annotation-towards clickable real world-

AU - Shimada, Atsushi

AU - Charvillat, Vincent

AU - Nagahara, Hajime

AU - Taniguchi, Rin-Ichiro

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Clickable Real World is a new framework to realize an intuitive information search with a mobile terminal. To achieve the goal, we tackle two challenging tasks. One is landmark detection from an observing scene. Our approach detects a landmark based on an image prior. The prior is not given manually. Instead, it is generated automatically from the training samples collected from photo sharing website. Another challenging task is image annotation assisted by geolocation. We use the location of a user who uses a mobile terminal, and geolocation where the training sample images were taken. Two probabilistic models are generated to achieve image annotation. One is image-based labeling which utilizes the co-occurrence between image features and label features. The other is label-based localization which uses the consensus about the label given around the geolocation among photographers. We combine two probabilistic approaches to improve the accuracy of image annotation. We demonstrate this approach for 87 scenes in the world.

AB - Clickable Real World is a new framework to realize an intuitive information search with a mobile terminal. To achieve the goal, we tackle two challenging tasks. One is landmark detection from an observing scene. Our approach detects a landmark based on an image prior. The prior is not given manually. Instead, it is generated automatically from the training samples collected from photo sharing website. Another challenging task is image annotation assisted by geolocation. We use the location of a user who uses a mobile terminal, and geolocation where the training sample images were taken. Two probabilistic models are generated to achieve image annotation. One is image-based labeling which utilizes the co-occurrence between image features and label features. The other is label-based localization which uses the consensus about the label given around the geolocation among photographers. We combine two probabilistic approaches to improve the accuracy of image annotation. We demonstrate this approach for 87 scenes in the world.

UR - http://www.scopus.com/inward/record.url?scp=84873802102&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873802102&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.133.142

DO - 10.1541/ieejeiss.133.142

M3 - Article

VL - 133

SP - 142

EP - 149

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 1

ER -