English  |  正體中文  |  简体中文  |  Items with full text/Total items : 79372/79372 (100%)
Visitors : 40065037      Online Users : 850
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU 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: http://ir.lib.ncu.edu.tw/handle/987654321/538


    Title: 多時期衛星影像之自動化監督性分類;Automatic Supervised Classification of Multi-temporal Satellite Images
    Authors: 李岳壇;Yueh-Tan Li
    Contributors: 土木工程研究所
    Keywords: 監督性模糊分類;多時期衛星影像;supervised fuzzy classification;multi-temporal satellite images
    Date: 2000-07-17
    Issue Date: 2009-09-18 17:07:19 (UTC+8)
    Publisher: 國立中央大學圖書館
    Abstract: 在衛星遙測技術的發達及取得衛星影像方便的情況下,獲取衛星影像是件容易的事,但困難的卻是在處理衛星影像的技術上。如何能對衛星影像進行精確及方便的分類,是為重要的課題之一。本研究即是以監督性模糊分類的方法,以自動化萃取訓練區方式,對多時期但同地區的衛星影像進行分類。 在監督性的分類方法中,通常需要圈選訓練資料。但如有連續不同時段同地區所拍攝的數張衛星影像,作監督性分類時,以人工方式對每張衛星影像圈選訓練區是件費時且費工的動作。本研究即發展出僅需對第一時期衛星影像選取訓練區並分類,爾後同地區的衛星影像即不需再以人工方式圈選訓練區,而改以自動化方式取得各時期衛星影像所需訓練區的資料,然後進行分類。 利用前時期的分類影像對後時期的衛星影像進行分類時,自動化的選取訓練區,會因後時期衛星影像類別位置、個數及內容的變化而造成訓練區資料的不足或混雜,因此本研究將針對此種變化情況,進行探討及謀求解決的方法。 解決的重點在於如何利用各訓練區的協方差矩陣和平均值來判斷後時期衛星影像是否有增多或減少的類別,進而利用模糊訓練區的特性,達到分類的目的。本研究以模擬資料及實際的SPOT影像作測試,結果得到相當好的分類成果,預期可對多時期衛星影像的自動化分類,提供一具實際應用的方法。 In process of remote sensing images, accurate and convenient methods of classification are very important. Therefore, this study aims at supervised fuzzy classification of multi-temporal images in the same area, choosing training set automatically. Training data are necessary for supervised classification. But it is manpower- and time-consuming to choose training data manually, especially in multi-temporal images in the same area. For this reason, a concept is proposed: choosing training set and finishing classification in first-period images, then following period images would be proceeded automatically. But the positions, number and contents of class changes in following-period images would influence results of classification. This problem is studied and solutions are researched in this paper. The key-point is "how to judge with covariance matrix and fuzzy mean if the classes of following-period images change or not". Simulated data and real SPOT images are tested, and results are obtained, so a practical method for automatic classification of multi-temporal images is expected.
    Appears in Collections:[土木工程研究所] 博碩士論文

    Files in This Item:

    File SizeFormat


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

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明