淡江大學機構典藏:Item 987654321/35703
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62797/95867 (66%)
Visitors : 3744885      Online Users : 509
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/35703


    Title: 以對稱小波轉換演算法應用於移動物件偵測與追蹤之研究
    Other Titles: A study on moving objects detection and tracking using symmetric wavelet transform scheme
    Authors: 黃丁威;Huang, Ding-wei
    Contributors: 淡江大學電機工程學系碩士班
    江正雄;Chiang, Jen-shiun
    Keywords: 監視器系統;對稱遮罩小波轉換架構;偽移動量;移動物件偵測與追蹤;Visual surveillance system;Symmetric Mask-Based Scheme;Fake motion;Moving object detection and tracking
    Date: 2009
    Issue Date: 2010-01-11 07:02:20 (UTC+8)
    Abstract: 近年來為了安全上的需求,監視系統已經被快速的發展,越來越多學者專家開始發展智慧型監視系統取代傳統的被動式監視系統。智慧型監視系統第一步是要先偵測移動物件,接下來將會把焦點擺在所偵測的區域做各種的影像後處理,例如物件分類、物件追蹤、以及行為描述的處理。在每個監視應用中偵測移動物件是最基本也是最重要的工作,正確的移動物件區域不僅是使後處理提供一個較佳的資訊,也能減少多餘計算量的處理。然而,要在現實生活環境中正確偵測出移動物件並非容易,因為在背景中有許多像是亮度的改變、偽移動量、高斯雜訊等問題將會導致電腦視覺偵測到非正確的移動物件。

    傳統中有三種典型的偵測移動物件方法︰背景先減法、連續畫面差異以及光流法,但這三種移動物件偵測法普遍地對亮度變化、雜訊、樹上移動葉子的偽移動非常的敏感。近幾年有許多物件偵測與追蹤方法相繼的被提出,例如使用離散小波轉換或由平均方式產生的低維度影像等當作移動物件偵測與追蹤系統之前處理。但是,基於傳統離散小波轉換,原始影像經由二維方向(行和列)計算而產生的低低頻影像會造成大量計算負擔。而低維度影像又比離散小波轉換產生的低頻影像更模糊,這樣會降低後處理的精準度(像是物件追蹤和物件辨識)。

    所以為了克服上述提及的問題,我們提出了一個方式,對稱式遮罩演算架構,藉由使用對稱式遮罩離散小波轉換偵測及追蹤物件以減少資料量。在對稱式遮罩演算架構中,只有對稱式遮罩離散小波轉換中的低低頻(5×5)遮罩矩陣會被使用,不像傳統離散小波分開處理行和列各自經由低通濾波器和取樣方式,此對稱式遮罩離散小波低低頻遮罩直接地計算低低頻影像資訊。我們提出的方式能減少影像轉換的計算量也能夠移除不屬於真實移動物件的偽移動量,並且可以維持住物體較慢移動量,以提供有效的完整移動物件範圍。
    In recent years, visual surveillance systems for the purpose of security have been rapidly developed. More and more people try to develop intelligent visual surveillance systems to replace the traditional passive video surveillance systems. The intelligent visual surveillance system can detect moving objects in the initial stage and subsequently process the functions such as object classification, object tracking, and object behaviors description. Detecting moving object is a basic and significant task in every surveillance application. The accurate location of the moving object does not only provide a focus of attention for post-processing but also can reduce the redundant computation for the incorrect motion of the moving object. The successful moving object detection in a real surrounding environment is a difficult task, since there are many kinds of problems such as illumination changes, fake motion, and Gaussian noise in the background that may lead to detect incorrect motion of the moving object.

    There are three typical approaches for motion detection: background subtraction, frame difference, and optical flow. Generally, the above three moving object detection methods are all sensitive to illumination changes, noises, and fake motion such as moving leaves of trees. In past years, several approaches for object detecting and tracking for pre-processing were proposed, such as the discrete wavelet transform(DWT) and the low resolution image generated by replacing each pixel value of the original image with the average value of its neighbors and itself. But the LL band image produced by the original image size via two dimensions (row and column) calculation on the conventional DWT may cause high computing cost. These low resolution images become fuzzier than the LL band image generated by using DWT. It may reduce the preciseness of post-processing (such as object tracking and object identification).

    To overcome the above-mentioned problems, we propose a method, symmetric mask-based scheme (SMBS), for detecting and tracking moving objects by using symmetric mask-based discrete wavelet transform (SMDWT). In the SMBS, only the LL (5×5) mask band of SMDWT is used. Unlike the traditional DWT method to process row and column dimensions separately by low-pass filter and down sampling, the LL mask band of SMDWT is used to directly calculate the LL band image. Our proposed method can reduce the image transfer computing cost and remove fake motion that is not belonged to the real moving object. Furthermore, we can retain a better slow motion of the object than that of the low resolution method and provide effective and complete moving object regions.
    Appears in Collections:[Graduate Institute & Department of Electrical Engineering] Thesis

    Files in This Item:

    File SizeFormat
    0KbUnknown402View/Open

    All items in 機構典藏 are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback