English  |  正體中文  |  简体中文  |  Items with full text/Total items : 27308/39152
Visitors : 2448490      Online Users : 119
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://ntour.ntou.edu.tw:8080/ir/handle/987654321/30627

Title: 人、車計數與相關異常事件分析
Counting and Analyzing Abnornal Events on Vehicles and Crowd
Authors: 謝君偉
Contributors: NTOU:Department of Computer Science and Engineering
國立臺灣海洋大學:資訊工程學系
Date: 2011-08
Issue Date: 2012-04-13T01:13:36Z
Publisher: 行政院國家科學委員會
Abstract: 人、車計數與相關異常事件分析是一個困難的工作,因為在陰影、遮蔽、天氣多變及背景擾動的 情況下,要分辨出的人車個別物件是非常困難的,此技術可以應用於許多方面,例如對人的計數,我 們可以應用在百貨公司或車站裡,藉由這項統計資訊控制進出口人數;也可根據在館人數進行某特定 區域的燈光及空調強弱,進行最佳化節能省碳的工作;對於戶外廣告,可利用此人數計數技術搭配性 別辨識系統,進而調整即時行銷策略調整;對於交通方面的計數,我們可利用人車的即時統計資訊, 調節交通號誌時間,進而解決交通阻塞;更可以藉由此技術即時偵測車輛擁塞情況,讓駕駛者更改行 車路線早日到達目的地;也可藉由車輛顏色判別,可讓警方來對車輛作追蹤與搜尋。為達上述目地, 我們提出這三年計畫,來發展「人、車計數與相關異常事件分析」相關技術,此計畫共分成三個部分, 分別在三年中完成,他們分別是(1) 人群計數與分析研究;(2) 車輛計數與車輛顏色標記研究;(3) 人 群與道路異常事件分析與系統整合。期望在這三年計畫中,深入探討完成視訊處理技術應用於人車計 數之系統,並分析群眾、車輛與車之間所可能發生的相關異常事件,以方便未來各個領域的應用,並 希望此計畫所研究的成果,可以提供台灣企業在相關產業更多機會及潛在的市場競爭實力。 關鍵字:視訊監控、遮蔽、人群辨識、車輛計數、異常事件分析
It is very challenging to count and analyze abnornal events on vehicles and crowd due to the changes of lighting changes, occlusions, shadows, backgrounds, and weather conditions. There are many potential applications using this technologies. For example, we can apply it to department stores or parking slots for people flow controlling. It can also be used for power controls on air-conditionings or ligtings for balancing the numbers of customers entering shoping malls. In intelligent transportation systems, we also can use it for detecting traffic jams and vehicle accidents. In addition, through the task of vehicle color classification, polices can use it for tracking suspicious vehicles on roads for crime prevention. Thus, we propose this three-year project to develop the technology of counting and analyzing abnornal events on vehicles and crowd directly from videos. This project can be divided into three parts: (1) people couting under occlusions; (2) vehicle couting and vehicle color classification; (3) abnormal event analysis on crowd and vehicles. In addition, an embedded system will be developed for integrating all the above techniques for vaious video surveillance applications. It is sincerely expected that all relevant developed techniques can explore more potential markets and offer more smart solutions for the enterprises in Taiwan and abroad as well.
Relation: NSC99-2221-E019-035-MY3
URI: http://ntour.ntou.edu.tw/handle/987654321/30627
Appears in Collections:[資訊工程學系] 研究計畫

Files in This Item:

There are no files associated with this item.



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

 


著作權政策宣告: 本網站之內容為國立臺灣海洋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,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback