English  |  正體中文  |  简体中文  |  Items with full text/Total items : 2737/2828
Visitors : 341788      Online Users : 28
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ir.lib.stu.edu.tw:80/ir/handle/310903100/1257

Title: 基於UPnP技術之數位家庭保全服務研究
The study of Security Service in Digital Home based on UPnP Technology.
Authors: 張博超
Bo-Chao Chang
Contributors: Mong-Fong Horng
資訊工程學系
Keywords: 家庭保全;通用型隨插即用技術;影像處理;動作預估;完全搜尋演算法;三步搜尋演算法
Home Security;UPnP(Universal Plug and Play);Image Processing;Motion Estimation;ESA;TSSA
Date: 2008
Issue Date: 2011-05-24 15:12:02 (UTC+8)
Publisher: 高雄市:[樹德科技大學資訊工程學系]
Abstract: 本論文目的是利用通用型隨插即用(UPnP, Universal Plug and Play)與影像處理技術開發可以支援數位家庭保全服務。在此一系統中,主要元件有家用伺服器與手持式裝置。透過UPnP軟體的設計與植入,家用伺服器可以監測來自固定式攝影機的影像,並偵測、識別、鎖定可疑的入侵物體。在將關鍵影像(key frame)存檔後,可以在使用者進入家用網路服務範圍時,主動識別、驗證使用者的身份,並推送(push)關鍵影像至使用者的手持式裝置或者預設傳送到遠端主機中。在入侵物偵測方面,同時實作兩種不同的影像比對方式(1)完全搜尋演算法(Exhaustive Search Algorithm, ESA)與(2)三步搜尋演算法(Three Step Search Algorithm, TSSA)。並透過實驗分析兩者的效能在辨識度與執行時間的差異。實驗結果顯示,在單純背景環境中,完全搜尋演算法的入侵偵測準確度可達100%,而三步搜尋演算法的準確度為90%;在時間效能上,完全搜尋演算法搜尋入侵物的平均時間為14.9秒,而三步搜尋演算法的平均時間為1.9秒。可以得知在完全搜尋入侵物時,準確度比三步搜尋高10%,相對所需執行時間比三步搜尋高出7.84倍的時間。此外,藉由UPnP技術的導入可以提供更加友善的操作介面,讓使用者可以感受到數位家庭的便利,並達成數位家庭保全服務之目的。
In this paper, a study of UPnP-based security service for digital home users is presented. The prototype platform supporting intrusion detection and automatic alerting services are developed on the combination of UPnP and image processing. In this system, the main components include cameras, monitor servers and handheld devices. Monitor servers through cameras capture the image sequence of the monitored area. Then the developed software modules offer the functionalities of detecting, identifying, tracking the suspicious invaders. Once the invader as been detected, the key frame of the invaders is analyzed, extracted and pushed to the handheld devices of specific users To effectively and efficiently identify the suspicious invaders, various techniques of motion estimations are evaluated, including (1) Exhaustive Search Algorithm(ESA) and (2) Three Step Search Algorithm(TSSA). Afterward, a new hybrid-model search algorithm called as HMSA is proposed. HMSA benefits the reduction of the execution time of the ESA and enhancing the accuracy of the TSSA. Experimental results demonstrate that execution time of the HMSA is faster than ESA by 3.51 times, and accuracy of the HMSA is better than TSSA by 10%. Besides, the friendly user interface is also an important feature considered in this presented system. The alerting system based on UPnP technology provides an automation of home networking, service discovery, and content delivery. Through the presented system, users experience a convenient and secure digital living.
Appears in Collections:[資訊工程系(所) ] 博碩士論文

Files in This Item:

File Description SizeFormat
基於UPnP技術之數位家庭保全服務研究__臺灣博碩士論文知識加值系統.htm國圖104KbHTML379View/Open
基於UPnP技術之數位家庭保全服務研究.pdf11822KbAdobe PDF665View/Open


All items in STUAIR are protected by copyright, with all rights reserved.

 


無標題文件

著作權政策宣告:

1.

本網站之數位內容為樹德科技大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,惟仍請適度,合理使用本網站之內容,以尊重著作權人之權益。商業上之利用,則請先取得著作權人之授權。
 
2. 本網站之製作,已盡力防止侵害著作權人之權益,如仍發現本網站之數位內容有侵害著作權人權益情事者,請權利人通知本校護人員(clairhsu@stu.edu.tw),維護人員將立即採取移除該數位著作等補救措施。
 
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback