WEKO3
アイテム
養殖魚給餌システムのための軌跡マッピングに基づく追跡とCNNに基づくテクスチャー特徴抽出
https://doi.org/10.18997/00008660
https://doi.org/10.18997/000086601f1afc8d-7497-4f3c-83bc-fbe29e3a5585
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
sei_k_421.pdf (18.7 MB)
|
|
| Item type | 学位論文 = Thesis or Dissertation(1) | |||||||
|---|---|---|---|---|---|---|---|---|
| 公開日 | 2021-12-20 | |||||||
| 資源タイプ | ||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_db06 | |||||||
| 資源タイプ | doctoral thesis | |||||||
| タイトル | ||||||||
| タイトル | Trajectory Mapping Based-Object Tracking and CNN Based-Textural Feature Extraction for Application to Aquaculture | |||||||
| 言語 | en | |||||||
| タイトル | ||||||||
| タイトル | 養殖魚給餌システムのための軌跡マッピングに基づく追跡とCNNに基づくテクスチャー特徴抽出 | |||||||
| 言語 | ja | |||||||
| 言語 | ||||||||
| 言語 | eng | |||||||
| 著者 |
Muhamad Hilmil Muchtar Aditya Pradana
× Muhamad Hilmil Muchtar Aditya Pradana
|
|||||||
| 抄録 | ||||||||
| 内容記述タイプ | Abstract | |||||||
| 内容記述 | Based on global aquaculture production statistic database, the proportion of aquatic animals farm is significantly increasing to 27.1 million tonnes in one decade. This trend indicates that aquaculture industry has to create a new technique to enlarge economic scale with reducing production cost and increasing production efficiency. Optimizing fish feeding process is the most influential aspect because the process itself takes up to 40 percent of total production cost. Automatic controlling fish feeding in real environment is still challenging problem and active research in aquaculture field because experienced fishermen can adequately control fish feeding machine based on assumption of ripple behavior and duration of fish feeding process. To build robust method which is reasonable application, we propose automatic controlling fish feeding machine based on computer vision using combination of two feature extractions which counts number of nutriments and estimates ripple behavior using regression and textural feature, respectively. To count number of nutriments, we apply object detection and tracking methods to acknowledge the nutriments moving to sea surface. Recently, object tracking is active research and challenging problem in applications of computer vision. Unfortunately, the robust tracking method for multiple small objects with dense and complex relationship is still challenging problem in aquaculture field with more appearance creatures. Assuming that degree of hunger can be represented by behavior of ripple area, estimation of ripple behavior is defined by human assumption of which the size and number of ripple can be used to adjust the activity level of ripple. Based on the number of nutriments fed and ripple behavior, we can control fish feeding machine which consistently performs well in real environment datasets. In evaluation, the proposed method presents the agreement for automatic controlling fish feeding by the activation graphs of regression and textural feature of ripple behavior results. Our tracking method can precisely track the nutriments in next frame comparing with other methods. Based on computational time, proposed method reaches 3.86 fps while other methods spend lower than 1.93 fps. Quantitative evaluation can give promising that the proposed method is valuable for aquaculture fish farm with widely applied to real environment datasets. | |||||||
| 目次 | ||||||||
| 内容記述タイプ | TableOfContents | |||||||
| 内容記述 | 1 Introduction||2 Literature Review||3 Trajectory Mapping||4 Regression||5 Variance of VGG Texture||6 Image Quality Assessment||7 Conclusion | |||||||
| 備考 | ||||||||
| 内容記述タイプ | Other | |||||||
| 内容記述 | 九州工業大学博士学位論文 学位記番号：生工博甲第421号 学位授与年月日：令和3年9月24日 | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | Production Efficiency | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | Fish Feeding | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | Ripple Behavior | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | Textural Feature | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | Tracking | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | Multiple Small Objects | |||||||
| アドバイザー | ||||||||
| 堀尾, 恵一 | ||||||||
| 学位授与番号 | ||||||||
| 学位授与番号 | 甲第421号 | |||||||
| 学位名 | ||||||||
| 学位名 | 博士（工学） | |||||||
| 学位授与年月日 | ||||||||
| 学位授与年月日 | 2021-09-24 | |||||||
| 学位授与機関 | ||||||||
| 学位授与機関識別子Scheme | kakenhi | |||||||
| 学位授与機関識別子 | 17104 | |||||||
| 学位授与機関名 | 九州工業大学 | |||||||
| 学位授与年度 | ||||||||
| 内容記述タイプ | Other | |||||||
| 内容記述 | 令和3年度 | |||||||
| 出版タイプ | ||||||||
| 出版タイプ | VoR | |||||||
| 出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||
| アクセス権 | ||||||||
| アクセス権 | open access | |||||||
| アクセス権URI | http://purl.org/coar/access_right/c_abf2 | |||||||
| ID登録 | ||||||||
| ID登録 | 10.18997/00008660 | |||||||
| ID登録タイプ | JaLC | |||||||
