Presentation 2018-08-27
機械学習を用いた海岸漂着ごみ定量化手法の構築
Shin'ichiro Kako, Ayato Udo, Shohei Morita, Tetusya Taneda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This study attempts to construct a new image processing method for detecting the pixels of colored marine debris on the beach photographs. This method involves generating a learning data using HSV (Hue, Saturation, Value) color space to perform a machine learning. The image processing method with machine learning constructed in this study is well capable of detecting the marine debris pixels of various colors accurately and objectively compared with the previous method which used color references constructed in the uniform colors space. The image processing method in this study allows us to estimate the marine debris abundance from the photographs regardless of their lightness values.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Marine debris / image processing method / machine learning / objectivity / versatility
Paper # AI2018-22
Date of Issue 2018-08-20 (AI)

Conference Information
Committee AI
Conference Date 2018/8/27(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Tsunenori Mine(Kyushu Univ.)
Vice Chair Daisuke Katagami(Tokyo Polytechnic Univ.) / Naoki Fukuta(Shizuoka Univ.)
Secretary Daisuke Katagami(Ritsumeikan Univ.) / Naoki Fukuta(Univ. of Electro-Comm.)
Assistant Yuko Sakurai(AIST)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN-ONLY
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English)
Sub Title (in English)
Keyword(1) Marine debris
Keyword(2) image processing method
Keyword(3) machine learning
Keyword(4) objectivity
Keyword(5) versatility
Keyword(6)
1st Author's Name Shin'ichiro Kako
1st Author's Affiliation Kagoshima University(Kagoshima Univ.)
2nd Author's Name Ayato Udo
2nd Author's Affiliation Kagoshima University(Kagoshima Univ.)
3rd Author's Name Shohei Morita
3rd Author's Affiliation Kagoshima University(Kagoshima Univ.)
4th Author's Name Tetusya Taneda
4th Author's Affiliation Kagoshima University(Kagoshima Univ.)
Date 2018-08-27
Paper # AI2018-22
Volume (vol) vol.118
Number (no) AI-197
Page pp.pp.51-54(AI),
#Pages 4
Date of Issue 2018-08-20 (AI)