Presentation 2022-03-10
Automatic flood estimation using aerial images by CNN
Soichiro Yanagihara, Tomoki Honma, Yuukou Horita,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When a wide-area disaster occurs, from the viewpoint of initial response, it is becoming more important to quickly grasp the damaged area. So, in this report, for investigating the possibility of determining the presence or absence of a disaster using machine learning, as a preliminary step, we focus on the "floods" that have occurred frequently in Japan in recent years. We use data for learning using flood images and non-flood images extracted from the LADI (Low Altitude Disaster Imagery) dataset, create a classifier for determining the presence or absence of flood occurrence using CNN (Convolutional Neural Network), and its accuracy was verified. In addition, we also analyze the features of the images classified using Grad-CAM (Gradient-weighted Class Activation Mapping).
Keyword(in Japanese) (See Japanese page)
Keyword(in English) LADI / CNN / Grad-CAM
Paper # IMQ2021-40,IE2021-102,MVE2021-69
Date of Issue 2022-03-02 (IMQ, IE, MVE)

Conference Information
Committee CQ / IMQ / MVE / IE
Conference Date 2022/3/9(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Online (Zoom)
Topics (in Japanese) (See Japanese page)
Topics (in English) Media of five senses, Multimedia, Media experience, Picture codinge, Image media quality, Network,quality and reliability, etc
Chair Jun Okamoto(NTT) / Kenya Uomori(Osaka Univ.) / Masayuki Ihara(RIKEN) / Kazuya Kodama(NII)
Vice Chair Takefumi Hiraguri(Nippon Inst. of Tech.) / Gou Hasegawa(Tohoku Univ.) / Mitsuru Maeda(Canon) / Kiyoshi Kiyokawa(NAIST) / Hiroyuki Bandoh(NTT) / Toshihiko Yamazaki(Univ. of Tokyo)
Secretary Takefumi Hiraguri(NTT) / Gou Hasegawa(Ritsumeikan Univ.) / Mitsuru Maeda(Nagoya Univ.) / Kiyoshi Kiyokawa(NTT) / Hiroyuki Bandoh(Oosaka Inst. of Tech.) / Toshihiko Yamazaki(NTT)
Assistant Yoshiaki Nishikawa(NEC) / Ryoichi Kataoka(KDDI Research) / Kimiko Kawashima(NTT) / Masato Tsukada(NEC) / Takashi Yamazoe(Seikei Univ.) / Naoya Isoyama(NAIST) / Takenori Hara(DNP) / Mitsuhiro Goto(NTT) / Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT)

Paper Information
Registration To Technical Committee on Communication Quality / Technical Committee on Image Media Quality / Technical Committee on Media Experience and Virtual Environment / Technical Committee on Image Engineering
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Automatic flood estimation using aerial images by CNN
Sub Title (in English)
Keyword(1) LADI
Keyword(2) CNN
Keyword(3) Grad-CAM
1st Author's Name Soichiro Yanagihara
1st Author's Affiliation University of Toyama(Univ.of Toyama)
2nd Author's Name Tomoki Honma
2nd Author's Affiliation University of Toyama(Univ.of Toyama)
3rd Author's Name Yuukou Horita
3rd Author's Affiliation University of Toyama(Univ.of Toyama)
Date 2022-03-10
Paper # IMQ2021-40,IE2021-102,MVE2021-69
Volume (vol) vol.121
Number (no) IMQ-420,IE-422,MVE-423
Page pp.pp.159-162(IMQ), pp.159-162(IE), pp.159-162(MVE),
#Pages 4
Date of Issue 2022-03-02 (IMQ, IE, MVE)