The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Cet article propose une méthode de détection de changement pour les bâtiments basée sur des réseaux de neurones convolutifs. La méthode proposée détecte les changements dans les bâtiments à partir de paires d'images aériennes optiques et d'informations cartographiques antérieures concernant les bâtiments. En utilisant de manière transparente une paire d'images haute résolution et des informations cartographiques antérieures, la méthode proposée peut capturer les zones de construction plus précisément par rapport à une méthode conventionnelle. Nos résultats expérimentaux montrent que la méthode proposée surpasse la méthode conventionnelle de détection des changements qui utilise des images aériennes optiques pour détecter les changements dans les bâtiments.
Motohiro TAKAGI
NTT Corporation
Kazuya HAYASE
Nippon Telegraph and Telephone Corporation
Masaki KITAHARA
NTT Corporation
Jun SHIMAMURA
NTT Corporation
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Motohiro TAKAGI, Kazuya HAYASE, Masaki KITAHARA, Jun SHIMAMURA, "Building Change Detection by Using Past Map Information and Optical Aerial Images" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 6, pp. 897-900, June 2021, doi: 10.1587/transinf.2020EDL8129.
Abstract: This paper proposes a change detection method for buildings based on convolutional neural networks. The proposed method detects building changes from pairs of optical aerial images and past map information concerning buildings. Using high-resolution image pair and past map information seamlessly, the proposed method can capture the building areas more precisely compared to a conventional method. Our experimental results show that the proposed method outperforms the conventional change detection method that uses optical aerial images to detect building changes.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDL8129/_p
Copier
@ARTICLE{e104-d_6_897,
author={Motohiro TAKAGI, Kazuya HAYASE, Masaki KITAHARA, Jun SHIMAMURA, },
journal={IEICE TRANSACTIONS on Information},
title={Building Change Detection by Using Past Map Information and Optical Aerial Images},
year={2021},
volume={E104-D},
number={6},
pages={897-900},
abstract={This paper proposes a change detection method for buildings based on convolutional neural networks. The proposed method detects building changes from pairs of optical aerial images and past map information concerning buildings. Using high-resolution image pair and past map information seamlessly, the proposed method can capture the building areas more precisely compared to a conventional method. Our experimental results show that the proposed method outperforms the conventional change detection method that uses optical aerial images to detect building changes.},
keywords={},
doi={10.1587/transinf.2020EDL8129},
ISSN={1745-1361},
month={June},}
Copier
TY - JOUR
TI - Building Change Detection by Using Past Map Information and Optical Aerial Images
T2 - IEICE TRANSACTIONS on Information
SP - 897
EP - 900
AU - Motohiro TAKAGI
AU - Kazuya HAYASE
AU - Masaki KITAHARA
AU - Jun SHIMAMURA
PY - 2021
DO - 10.1587/transinf.2020EDL8129
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2021
AB - This paper proposes a change detection method for buildings based on convolutional neural networks. The proposed method detects building changes from pairs of optical aerial images and past map information concerning buildings. Using high-resolution image pair and past map information seamlessly, the proposed method can capture the building areas more precisely compared to a conventional method. Our experimental results show that the proposed method outperforms the conventional change detection method that uses optical aerial images to detect building changes.
ER -