南開科技大學圖書館 |

Language: 繁體中文

ヘルプ

南開科技大學

圖書館首頁

編目中圖書申請

ログイン

ホームページ

スイッチ: ラベル | MARC形式 | 国際標準書誌記述(ISBD)

Neural network modeling of three-dim...

Cretu, Ana-Maria.

Neural network modeling of three-dimensional objects for virtualized reality applications.

レコード種別:	コンピュータ・メディア : 単行資料
タイトル / 著者:	Neural network modeling of three-dimensional objects for virtualized reality applications./
著者:	Cretu, Ana-Maria.
記述:	151 p.
注記:	Source: Masters Abstracts International, Volume: 42-06, page: 2284.
含まれています:	Masters Abstracts International42-06.
主題:	Engineering, Electronics and Electrical. -
電子資源:	Download fulltext (下載全文)
国際標準図書番号 (ISBN):	0612900525

Neural network modeling of three-dimensional objects for virtualized reality applications.
Cretu, Ana-Maria.

Neural network modeling of three-dimensional objects for virtualized reality applications. - 151 p.

Source: Masters Abstracts International, Volume: 42-06, page: 2284.

Thesis (M.A.Sc.)--University of Ottawa (Canada), 2003.

This thesis presents a critical comparison between three neural architectures for 3D object representation in terms of purpose, computational cost, complexity, conformance and convenience, ease of manipulation and potential uses in the context of virtualized reality. Starting from a pointcloud that embeds the shape of the object to be modeled, a volumetric representation is obtained using a multilayered feedforward neural network or a surface representation using either the self-organizing map or the neural gas network. The representation provided by the neural networks is simple, compact and accurate. The models can be easily transformed in size, position (affine transformations) and shape (deformation). Some potential uses of the presented architectures in the context of virtualized reality are for the modeling of set operations and object morphing, for the detection of objects collision and for object recognition, object motion estimation and segmentation.

ISBN: 0612900525Subjects--Topical Terms:

170927
Engineering, Electronics and Electrical.

Neural network modeling of three-dimensional objects for virtualized reality applications.
LDR:01978nmm 2200301 4500 001 1000004352
005 20051102155249.5
008 141201s2003 eng d
020 $a 0612900525
035 $a (UnM)AAIMQ90052
035 $a AAIMQ90052
040 $a UnM $c UnM{me_controlnum}
100 1 $a Cretu, Ana-Maria. $3 1000005717
245 1 0 $a Neural network modeling of three-dimensional objects for virtualized reality applications.
300 $a 151 p.
500 $a Source: Masters Abstracts International, Volume: 42-06, page: 2284.
500 $a Advisers: Emil Petriu; Gilles Patry.
502 $a Thesis (M.A.Sc.)--University of Ottawa (Canada), 2003.
520 $a This thesis presents a critical comparison between three neural architectures for 3D object representation in terms of purpose, computational cost, complexity, conformance and convenience, ease of manipulation and potential uses in the context of virtualized reality. Starting from a pointcloud that embeds the shape of the object to be modeled, a volumetric representation is obtained using a multilayered feedforward neural network or a surface representation using either the self-organizing map or the neural gas network. The representation provided by the neural networks is simple, compact and accurate. The models can be easily transformed in size, position (affine transformations) and shape (deformation). Some potential uses of the presented architectures in the context of virtualized reality are for the modeling of set operations and object morphing, for the detection of objects collision and for object recognition, object motion estimation and segmentation.
590 $a School code: 0918.
650 4 $a Engineering, Electronics and Electrical. $3 170927
650 4 $a Computer Science. $3 1000005419
650 4 $a Artificial Intelligence. $3 165300
690 $a 0544
690 $a 0984
690 $a 0800
710 2 0 $a University of Ottawa (Canada). $3 1000005489
773 0 $t Masters Abstracts International $g 42-06.
790 1 0 $a Petriu, Emil, $e advisor
790 1 0 $a Patry, Gilles, $e advisor
790 $a 0918
791 $a M.A.Sc.
792 $a 2003
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MQ90052 $z Download fulltext (下載全文)