English  |  正體中文  |  简体中文  |  Items with full text/Total items : 26988/38789
Visitors : 2345300      Online Users : 36
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/987654321/11173

Title: 水下感測元件及系統之研發與應用於水下作業---子計畫三:水下超音波影像處理(II)
Developments of Techniques for Underwater Ultrasonic Image Processing (II)
Authors: 王榮華
Contributors: NTOU:Department of Electrical Engineering
國立臺灣海洋大學:電機工程學系
Date: 2004
Issue Date: 2011-06-28T08:08:34Z
Publisher: 行政院國家科學委員會
Abstract: 本報告係三年期「水下感測元件及系統之研發與應用於水下作業」整合型計劃中之子計畫「水下超音波影像處理技術研發」的第二年成果說明。本計畫延續第一年之成果,學習神經網路應用於水下超音波影像處理之能力。本計劃將藉由改變一高階網路架構,達成更快速有效地消除水下超音波影像之斑點雜訊。再者,根據輸入影像雜訊特性及考慮水下特殊環境條件,提出一適應性邊緣偵測器,能快速有效地擷取目標物之輪廓,並達到物件定位以利機械臂進行水下施工及物件之打撈動作。本計畫研發之相關技術結果已發表於 IEEE 國際會議[1,12]。
This midterm report describes the results obtained from fulfilling a three-year project, a subpart of a joint project granted by NSC. The name of the joint project is Development of underwater sensory devices and system of an underwater operating system under grant number of NSC 93-2611-E-019-007. This report presents techniques developed to enhance underwater ultrasonic images, and to detect and locate the object of interested. Based on characterizing Higher Order Neural Network, we have implemented SGF Using Higher-Order Neural Networks to reduce speckle noise for achieving better image quality with less computation time. On the other hand, by incorporating the characteristics of underwater ultrasonic images, we have proposed an Adaptive Likelihood Ratio Edge Detector to obtain the contour of interested object. The results show that the proposed filters can achieve speckle noise reduction effectively and object orientation accurately for ultrasonic images taken during the underwater operations.
Relation: NSC93-2611-E019-007
URI: http://ntour.ntou.edu.tw/ir/handle/987654321/11173
Appears in Collections:[電機工程學系] 研究計畫

Files in This Item:

File Description SizeFormat
index.html0KbHTML55View/Open


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