東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Object Recognition in 3D Data Using ...

Ahmad, Ayesha.

FindBook

Google Book

Amazon

博客來

Object Recognition in 3D Data Using Capsules.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Object Recognition in 3D Data Using Capsules./
作者:	Ahmad, Ayesha.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2018,
面頁冊數:	84 p.
附註:	Source: Masters Abstracts International, Volume: 57-06.
Contained By:	Masters Abstracts International57-06(E).
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10817027
ISBN:	9780438103078

Object Recognition in 3D Data Using Capsules.
Ahmad, Ayesha.

Object Recognition in 3D Data Using Capsules. - Ann Arbor : ProQuest Dissertations & Theses, 2018 - 84 p.

Source: Masters Abstracts International, Volume: 57-06.

Thesis (M.S.)--Syracuse University, 2018.

The proliferation of 3D sensors induced 3D computer vision research for many application areas including virtual reality, autonomous navigation and surveillance. Recently, dierent methods have been proposed for 3D object classication. Many of the existing 2D and 3D classication methods rely on convolutional neural networks (CNNs), which are very successful in extracting features from the data. However, CNNs cannot address the spatial relationship between features due to the max-pooling layers, and they require vast amount of data for training. In this work, we propose a model architecture for 3D object classication, which is an extension of Capsule Networks (CapsNets) to 3D data. Our proposed architecture called 3D CapsNet, takes advantage of the fact that a CapsNet preserves the orientation and spatial relationship of the extracted features, and thus requires less data to train the network. We use ModelNet database, a comprehensive clean collection of 3D CAD models for objects, to train and test the 3D CapsNet model. We then compare our approach with ShapeNet, a deep belief network for object classication based on CNNs, and show that our method provides performance improvement especially when training data size gets smaller.

ISBN: 9780438103078Subjects--Topical Terms:

523869
Computer science.

Object Recognition in 3D Data Using Capsules.
LDR:02107nmm a2200289 4500 001 2205001
005 20190718114218.5
008 201008s2018 ||||||||||||||||| ||eng d
020 $a 9780438103078
035 $a (MiAaPQ)AAI10817027
035 $a (MiAaPQ)syr:11883
035 $a AAI10817027
040 $a MiAaPQ $c MiAaPQ
100 1 $a Ahmad, Ayesha. $3 1952502
245 1 0 $a Object Recognition in 3D Data Using Capsules.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2018
300 $a 84 p.
500 $a Source: Masters Abstracts International, Volume: 57-06.
500 $a Adviser: Senem Velipasalar.
502 $a Thesis (M.S.)--Syracuse University, 2018.
520 $a The proliferation of 3D sensors induced 3D computer vision research for many application areas including virtual reality, autonomous navigation and surveillance. Recently, dierent methods have been proposed for 3D object classication. Many of the existing 2D and 3D classication methods rely on convolutional neural networks (CNNs), which are very successful in extracting features from the data. However, CNNs cannot address the spatial relationship between features due to the max-pooling layers, and they require vast amount of data for training. In this work, we propose a model architecture for 3D object classication, which is an extension of Capsule Networks (CapsNets) to 3D data. Our proposed architecture called 3D CapsNet, takes advantage of the fact that a CapsNet preserves the orientation and spatial relationship of the extracted features, and thus requires less data to train the network. We use ModelNet database, a comprehensive clean collection of 3D CAD models for objects, to train and test the 3D CapsNet model. We then compare our approach with ShapeNet, a deep belief network for object classication based on CNNs, and show that our method provides performance improvement especially when training data size gets smaller.
590 $a School code: 0659.
650 4 $a Computer science. $3 523869
690 $a 0984
710 2 $a Syracuse University. $b Electrical Engineering and Computer Science. $3 3169988
773 0 $t Masters Abstracts International $g 57-06(E).
790 $a 0659
791 $a M.S.
792 $a 2018
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10817027