講演名 | 2019-10-10 Segnet and U-Net Implementations for Water Hyacinth Semantic Segmentation in Thailand Supatta Viriyavisuthisakul(PIM), Parinya Sanguansat(PIM), Toshihiko Yamasaki(東大), |
---|---|
PDFダウンロードページ | PDFダウンロードページへ |
抄録(和) | Water Hyacinth is an aquatic weed that can spread very quickly. Normally, it can be found in a dam or river. Water Hyacinth is one of the main problems in irrigation management, water transportation, and agriculture. That makes it is one of the national problems, especially Thailand. To plan the solution for this problem, quantitative measurement of Water Hyacinth in many areas is required. Semantic segmentation with deep learning is very accurate now, and it can be used in this task. In this paper, the semantic segmentation is applied to segment the Water Hyacinth in the images. Segnet and U-Net were compared. Both of them use convolutional layers but in different architectures. With our limited resources, we found that U-Net is more suitable in this task than Segnet in both computational time and performance. |
抄録(英) | Water Hyacinth is an aquatic weed that can spread very quickly. Normally, it can be found in a dam or river. Water Hyacinth is one of the main problems in irrigation management, water transportation, and agriculture. That makes it is one of the national problems, especially Thailand. To plan the solution for this problem, quantitative measurement of Water Hyacinth in many areas is required. Semantic segmentation with deep learning is very accurate now, and it can be used in this task. In this paper, the semantic segmentation is applied to segment the Water Hyacinth in the images. Segnet and U-Net were compared. Both of them use convolutional layers but in different architectures. With our limited resources, we found that U-Net is more suitable in this task than Segnet in both computational time and performance. |
キーワード(和) | Water Hyacinth / Semantic Segmentation / Segnet / U-Net |
キーワード(英) | Water Hyacinth / Semantic Segmentation / Segnet / U-Net |
資料番号 | MVE2019-25 |
発行日 | 2019-10-03 (MVE) |
研究会情報 | |
研究会 | MVE |
---|---|
開催期間 | 2019/10/10(から2日開催) |
開催地(和) | 北海道 斜里町 ウトロ漁村センター |
開催地(英) | |
テーマ(和) | 新しいエクスペリエンスを目指すモノづくり・コトづくり・社会展開および一般(VR学会SIG‐CS,SIG‐MR,HI学会SIG-DeMO連催) |
テーマ(英) | |
委員長氏名(和) | 間瀬 健二(名大) |
委員長氏名(英) | Kenji Mase(Nagoya Univ.) |
副委員長氏名(和) | 井原 雅行(NTT) |
副委員長氏名(英) | Masayuki Ihara(NTT) |
幹事氏名(和) | 平山 高嗣(名大) / 青木 良輔(NTT) |
幹事氏名(英) | Takatsugu Hirayama(Nagoya Univ.) / Ryosuke Aoki(NTT) |
幹事補佐氏名(和) | 西口 敏司(阪工大) / 横山 正典(NTT) / 福嶋 政期(東大) |
幹事補佐氏名(英) | Satoshi Nishiguchi(Oosaka Inst. of Tech.) / Masanori Yokoyama(NTT) / Shogo Fukushima(Univ. of ToKyo) |
講演論文情報詳細 | |
申込み研究会 | Technical Committee on Media Experience and Virtual Environment |
---|---|
本文の言語 | ENG |
タイトル(和) | |
サブタイトル(和) | |
タイトル(英) | Segnet and U-Net Implementations for Water Hyacinth Semantic Segmentation in Thailand |
サブタイトル(和) | |
キーワード(1)(和/英) | Water Hyacinth / Water Hyacinth |
キーワード(2)(和/英) | Semantic Segmentation / Semantic Segmentation |
キーワード(3)(和/英) | Segnet / Segnet |
キーワード(4)(和/英) | U-Net / U-Net |
第 1 著者 氏名(和/英) | Supatta Viriyavisuthisakul / Supatta Viriyavisuthisakul |
第 1 著者 所属(和/英) | Panyapiwat Institute of Management(略称:PIM) Panyapiwat Institute of Management(略称:PIM) |
第 2 著者 氏名(和/英) | Parinya Sanguansat / Parinya Sanguansat |
第 2 著者 所属(和/英) | Panyapiwat Institute of Management(略称:PIM) Panyapiwat Institute of Management(略称:PIM) |
第 3 著者 氏名(和/英) | Toshihiko Yamasaki / Toshihiko Yamasaki |
第 3 著者 所属(和/英) | The University of Tokyo(略称:東大) The University of Tokyo(略称:UTokyo) |
発表年月日 | 2019-10-10 |
資料番号 | MVE2019-25 |
巻番号(vol) | vol.119 |
号番号(no) | MVE-222 |
ページ範囲 | pp.9-12(MVE), |
ページ数 | 4 |
発行日 | 2019-10-03 (MVE) |