東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Neural network modeling of three-dim...

Cretu, Ana-Maria.

Linked to FindBook

Google Book

Amazon

博客來

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

Record Type:	Electronic resources : Monograph/item
Title/Author:	Neural network modeling of three-dimensional objects for virtualized reality applications./
Author:	Cretu, Ana-Maria.
Description:	151 p.
Notes:	Source: Masters Abstracts International, Volume: 42-06, page: 2284.
Contained By:	Masters Abstracts International42-06.
Subject:	Engineering, Electronics and Electrical. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MQ90052
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:

626636
Engineering, Electronics and Electrical.

Neural network modeling of three-dimensional objects for virtualized reality applications.
LDR:01929nmm 2200301 4500 001 1848285
005 20051102155249.5
008 130614s2003 eng d
020 $a 0612900525
035 $a (UnM)AAIMQ90052
035 $a AAIMQ90052
040 $a UnM $c UnM
100 1 $a Cretu, Ana-Maria. $3 1936299
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 626636
650 4 $a Computer Science. $3 626642
650 4 $a Artificial Intelligence. $3 769149
690 $a 0544
690 $a 0984
690 $a 0800
710 2 0 $a University of Ottawa (Canada). $3 1017488
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