WEKO3
アイテム
単画像多矩形物体検出のための特徴抽出
https://doi.org/10.19000/0002000405
https://doi.org/10.19000/00020004059cb1a426-0ceb-4f9b-bd7c-90cd4e9ac5d8
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
Doctoral Thesis_TUERSUNJIANG YIMAMU-1 .pdf (1.9 MB)
|
|
| Item type | 学位論文 / Thesis or Dissertation(1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2023-04-03 | |||||||||
| タイトル | ||||||||||
| タイトル | Feature Extraction for Single Shot Multibox Object Detector | |||||||||
| 言語 | en | |||||||||
| タイトル | ||||||||||
| タイトル | 単画像多矩形物体検出のための特徴抽出 | |||||||||
| 言語 | ja | |||||||||
| 言語 | ||||||||||
| 言語 | eng | |||||||||
| 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 | |||||||||
| ID登録 | ||||||||||
| ID登録 | 10.19000/0002000405 | |||||||||
| ID登録タイプ | JaLC | |||||||||
| 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 | |||||||||
| 著者 |
TUERSUNJIANG YIMAMU
× TUERSUNJIANG YIMAMU
× トルスンジャン・イマム
|
|||||||||
| 抄録 | ||||||||||
| 内容記述タイプ | Abstract | |||||||||
| 内容記述 | Recently, object detection based on deep convolutional neural networks (CNNs) have achieved remarkable result and successfully applied many real-world applications. However, scale variation problem in multiscale object detection still is challenging problem, especially for small objects. Concerning the above problem, we proposed a new detection network with an efficient feature fusion module based on SSD using VGG-16 as backbone called Multi-path Feature Fusion Single Shot Multibox Detector (MF-SSD). The proposed feature fusion module consists of two newly designed modules with dilated convolution, which fuses features from shallow layers (mainly contain boundary information) to highRecently, object detection based on deep convolutional neural networks (CNNs) have achieved remarkable result and successfully applied many real-world applications. However, scale variation problem in multiscale object detection still is challenging problem, especially for small objects. Concerning the above problem, we proposed a new detection network with an efficient feature fusion module based on SSD using VGG-16 as backbone called Multi-path Feature Fusion Single Shot Multibox Detector (MF-SSD). The proposed feature fusion module consists of two newly designed modules with dilated convolution, which fuses features from shallow layers (mainly contain boundary information) to higher level features (mainly contain semantic reach information) without reducing the original resolution of the feature map. We have conducted experiments on three datasets to explicate the efficacy of our proposed detector. The proposed MF-SSD with input size 512×512 achieved 81.5% mAP and 34.1 % mAP on PASCAL VOC test set and MS COCO test-dev, respectively. Experimental results show the proposed feature fusion module can improve both semantic and boundary information for object detectioner level features (mainly contain semantic reach information) without reducing the original resolution of the feature map. We have conducted experiments on three datasets to explicate the efficacy of our proposed detector. The proposed MF-SSD with input size 512×512 achieved 81.5% mAP and 34.1 % mAP on PASCAL VOC test set and MS COCO test-dev, respectively. Experimental results show the proposed feature fusion module can improve both semantic and boundary information for object detection. |
|||||||||
| 言語 | en | |||||||||
| 書誌情報 |
発行日 2023-03 |
|||||||||
| 著者版フラグ | ||||||||||
| 言語 | en | |||||||||
| 値 | ETD | |||||||||
| 学位名 | ||||||||||
| 言語 | ja | |||||||||
| 学位名 | 博士（工学） | |||||||||
| 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 | 10106 | |||||||||
| 言語 | ja | |||||||||
| 学位授与機関名 | 北見工業大学 | |||||||||
| 学位授与番号 | ||||||||||
| 学位授与番号 | 甲第208号 | |||||||||
| 研究科・専攻名 | ||||||||||
| 言語 | ja | |||||||||
| 値 | 生産基盤工学専攻 | |||||||||
| 学位授与年月日 | ||||||||||
| 学位授与年月日 | 2023-03-17 | |||||||||
