Presentation | 2019-10-31 Estimation of Ship Velocity from Multispectral Satellite Image Tae-Ho Kim, JeongJu Bae, Chan-Su Yang, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this study, we present the estimation results of ship velocity using a multispectral satellite image. In the case of moving ship, its position in a satellite image varies at each band due to the time offsets of multiple bands. We have proposed an algorithm for estimating the ship velocity using these characteristics. The red and blue band data of the Sentinel-2 satellites used, and the reference point for distance calculation was set using the template matching method with the highest cross-correlation. As a result of estimating the velocity of the same ship, the satellite-based method showed a velocity of 15.91 m/s, and the AIS was 19.86 m/s. In this paper, we compared the estimated speeds for only one ship. In satellite imagery, the reflection from ships may be affected by ship size, speed, direction, and maritime conditions. Therefore, verification of the speed estimation result under various states should be performed. The results of this study are expected to be able to determine the information of multiple ships using a single satellite. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Ship velocity / Sentinel-2 image / Multispectral satellite image / Deep learning |
Paper # | SANE2019-54 |
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) | Estimation of Ship Velocity from Multispectral Satellite Image |
Sub Title (in English) | |
Keyword(1) | Ship velocity |
Keyword(2) | Sentinel-2 image |
Keyword(3) | Multispectral satellite image |
Keyword(4) | Deep learning |
1st Author's Name | Tae-Ho Kim |
1st Author's Affiliation | Korea Institute of Ocean Science & Technology(KIOST) |
2nd Author's Name | JeongJu Bae |
2nd Author's Affiliation | Korea Institute of Ocean Science & Technology(KIOST) |
3rd Author's Name | Chan-Su Yang |
3rd Author's Affiliation | Korea Institute of Ocean Science & Technology(KIOST) |
Date | 2019-10-31 |
Paper # | SANE2019-54 |
Volume (vol) | vol.119 |
Number (no) | SANE-255 |
Page | pp.pp.37-40(SANE), |
#Pages | 4 |
Date of Issue | 2019-10-24 (SANE) |