Feature Extraction for Single Shot Multibox Object Detector

TUERSUNJIANG YIMAMU

WEKO3

lat lon distance

[[sub_check.contents]]

[[sub_radio.contents]]

Field does not validate

[[sub_attr.contents]]　

インデックスツリー

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

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

Feature Extraction for Single Shot Multibox Object Detector

言語

タイトル

単画像多矩形物体検出のための特徴抽出

言語

eng

資源タイプ

資源

http://purl.org/coar/resource_type/c_db06

タイプ

doctoral thesis

ID登録

10.19000/0002000405

ID登録タイプ

JaLC

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

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

bibliographic_information

p. 1, 発行日 2023-03

学位名

言語

学位名

博士（工学）

item_7_degree_grantor_61

学位授与機関識別子Scheme

kakenhi

学位授与機関識別子

10106

言語

学位授与機関名

北見工業大学

dissertation_number

学位授与番号

甲第208号

item_7_text_66

言語

研究科・専攻名

生産基盤工学専攻

学位授与年月日

2023-03-17

戻る

views

See details

	Views

Versions

Ver.1

2023-04-03 04:34:32.699226

Show All versions

Cite as

エクスポート

OAI-PMH

JPCOAR 2.0
JPCOAR 1.0
DublinCore
DDI

Other Formats

JSON
BIBTEX

インデックスリンク

インデックスツリー

アイテム

単画像多矩形物体検出のための特徴抽出

× TUERSUNJIANG YIMAMU

Versions

Share

Cite as

エクスポート