Presentation | 2019-11-01 Sea Fog Classification from GOCI Images using CNN Transfer Learning Models Ho-Kun Jeon, Jonathan Edwin, Seungryong Kim, Chan-Su Yang, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This study provides an approaching method of classifying sea fog from Geostationary Ocean Color Image, an optical satellite of South Korea. Convolution Neural Network Transfer Learning (CNN-TL) model is used because of a higher classification ability than a single CNN. The CNN-TL model is combined with dataset VGG19 and ResNet50 which have high performance but less layer than other datasets. In classification with 3-bands training images, the CNN-TL shows 96.7% and 93.0% in VGG19 and ResNet50, respectively. On the other hand, only CNN with identical training images shows the accuracy of 85.3% in VGG19 and 52% in VGG19 and ResNet 50. The result can be used to automate local sea fog detection and prediction. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Sea Fog / CNN / Classification / Transfer learning / Ocean color |
Paper # | SANE2019-65 |
Date of Issue | 2019-10-24 (SANE) |
Conference Information | |
Committee | SANE |
---|---|
Conference Date | 2019/10/31(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | KOREA (Jeju) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | ICSANE2019 |
Chair | Akitsugu Nadai(NICT) |
Vice Chair | Hiroyoshi Yamada(Niigata Univ.) / Makoto Tanaka(Tokai Univ.) |
Secretary | Hiroyoshi Yamada(Univ. of Electro-Comm.) / Makoto Tanaka(Mitsubishi Electric) |
Assistant | Ryo Natsuaki(Univ. of Tokyo) / Masato Yamanashi(Mitsubishi Space Software) / Shunichi Futatsumori(ENRI) |
Paper Information | |
Registration To | Technical Committee on Space, Aeronautical and Navigational Electronics |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Sea Fog Classification from GOCI Images using CNN Transfer Learning Models |
Sub Title (in English) | |
Keyword(1) | Sea Fog |
Keyword(2) | CNN |
Keyword(3) | Classification |
Keyword(4) | Transfer learning |
Keyword(5) | Ocean color |
1st Author's Name | Ho-Kun Jeon |
1st Author's Affiliation | Korea Institute of Ocean Science & Technology(KIOST) |
2nd Author's Name | Jonathan Edwin |
2nd Author's Affiliation | Korea Institute of Ocean Science & Technology(KIOST) |
3rd Author's Name | Seungryong Kim |
3rd Author's Affiliation | Korea Institute of Ocean Science & Technology(KIOST) |
4th Author's Name | Chan-Su Yang |
4th Author's Affiliation | Korea Institute of Ocean Science & Technology(KIOST) |
Date | 2019-11-01 |
Paper # | SANE2019-65 |
Volume (vol) | vol.119 |
Number (no) | SANE-255 |
Page | pp.pp.87-90(SANE), |
#Pages | 4 |
Date of Issue | 2019-10-24 (SANE) |