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

Distributed multi-modal human activi...

Chen, Cheng-Yao.

Linked to FindBook

Google Book

Amazon

博客來

Distributed multi-modal human activity analysis: From algorithms to systems.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Distributed multi-modal human activity analysis: From algorithms to systems./
Author:	Chen, Cheng-Yao.
Description:	232 p.
Notes:	Source: Dissertation Abstracts International, Volume: 68-10, Section: B, page: .
Contained By:	Dissertation Abstracts International68-10B.
Subject:	Engineering, Electronics and Electrical. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3286109
ISBN:	9780549285144

Distributed multi-modal human activity analysis: From algorithms to systems.
Chen, Cheng-Yao.

Distributed multi-modal human activity analysis: From algorithms to systems. - 232 p.

Source: Dissertation Abstracts International, Volume: 68-10, Section: B, page: .

Thesis (Ph.D.)--Princeton University, 2007.

Human activity analysis is one of the most important and challenging research fields of information technology. It has a significant impact on applications such as semantic multimedia indexing, human-machine interaction, and homeland security. This dissertation discusses the search for the most effective and efficient architecture for human activity analysis from both an algorithm and system perspective. The discussion starts from the most fundamental system setup that of single uni-modal sensor processing. Afterwards, to enhance the performance from single uni-modal sensor processing, two architectures are discussed, distributed uni-modal sensor processing and single multi-modal sensor processing. Distributed uni-modal sensor processing applies multiple uni-modal sensors in a network to increase the range of the sensing views, and to decrease the sensitivity to environmental changes. On the other hand, applying a single multi-modal sensor extends the scope of analysis by having more sensing modalities. Combining these two directions, a distributed multi-modal human activity analysis system is proposed. This architecture demonstrates a significant advantage in its effectiveness of human activity analysis. However, managing such a complicated system is challenging, so a dedicated monitoring framework is proposed at the end of this dissertation to resolve this system design issue. With the promising system proposed by this dissertation, human activity analysis can further advance to another level.

ISBN: 9780549285144Subjects--Topical Terms:

626636
Engineering, Electronics and Electrical.

Distributed multi-modal human activity analysis: From algorithms to systems.
LDR:02288nam 2200241 a 45 001 942896
005 20110520
008 110520s2007 eng d
020 $a 9780549285144
035 $a (UMI)AAI3286109
035 $a AAI3286109
040 $a UMI $c UMI
100 1 $a Chen, Cheng-Yao. $3 1266928
245 1 0 $a Distributed multi-modal human activity analysis: From algorithms to systems.
300 $a 232 p.
500 $a Source: Dissertation Abstracts International, Volume: 68-10, Section: B, page: .
502 $a Thesis (Ph.D.)--Princeton University, 2007.
520 $a Human activity analysis is one of the most important and challenging research fields of information technology. It has a significant impact on applications such as semantic multimedia indexing, human-machine interaction, and homeland security. This dissertation discusses the search for the most effective and efficient architecture for human activity analysis from both an algorithm and system perspective. The discussion starts from the most fundamental system setup that of single uni-modal sensor processing. Afterwards, to enhance the performance from single uni-modal sensor processing, two architectures are discussed, distributed uni-modal sensor processing and single multi-modal sensor processing. Distributed uni-modal sensor processing applies multiple uni-modal sensors in a network to increase the range of the sensing views, and to decrease the sensitivity to environmental changes. On the other hand, applying a single multi-modal sensor extends the scope of analysis by having more sensing modalities. Combining these two directions, a distributed multi-modal human activity analysis system is proposed. This architecture demonstrates a significant advantage in its effectiveness of human activity analysis. However, managing such a complicated system is challenging, so a dedicated monitoring framework is proposed at the end of this dissertation to resolve this system design issue. With the promising system proposed by this dissertation, human activity analysis can further advance to another level.
590 $a School code: 0181.
650 4 $a Engineering, Electronics and Electrical. $3 626636
690 $a 0544
710 2 0 $a Princeton University. $3 645579
773 0 $t Dissertation Abstracts International $g 68-10B.
790 $a 0181
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3286109