English  |  正體中文  |  简体中文  |  Items with full text/Total items : 26988/38789
Visitors : 2352098      Online Users : 32
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/987654321/28701

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(3/3)
Authors: 王榮華
Contributors: NTOU:Department of Electrical Engineering
國立臺灣海洋大學:電機工程學系
Keywords: ultrasonic image;Improved Snake Model;image recognition;Kovesi Detector;FPGA;超音波影像;改良式蛇型輪廓模型;影像辨識
Date: 2006
Issue Date: 2011-10-21T02:39:23Z
Publisher: 國科會專題研究計畫成果報告
Abstract: Abstract:This final report describes the results from fulfilling a sub-project of a three-year joint research granted by NSC, namely, development of underwater sensory devices and system of an underwater operating system. This report presents techniques developed to enhance underwater ultrasonic images, and to detect and locate the object of interest. We describe a procedure capable of achieving the rotational invariance, an attribute normaly not seen in conventional methods dealing with underwater images. First, we have developed an Improved Snake Model (ISM) [1]. The result of ISM is then incorporated with a filter [2] that employs Kovesi Detector and Laplacian of Gaussians(LOG) to extract invariant features. Following that, we use Normailzed Cross-Correlation (NCC) to find the corresponding features. Finally, Hardware Description Language and FPGA are used to implement in hardware so as to further enhance object positioning ability essential for underwater operations by robots.
摘要:本論文係三年期「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」第三年的成果報告。本計畫延續第二年水下超音波影像辨識及實現影像處理演算法於FPGA上,且針對水下特殊環境條件,發展一適用於水下影像之影像分割演算法名為改良式蛇型輪廓模型 (Improved Snake Model)[1] 以期能擁有更有效的物件分割之能力,並將先前所提出之影像濾波方法[2]應用於實際超音波影像上,針對先前所提出之 Harris Detector 以及Laplacian of Gaussians(LOG)擷取特徵值之方法進行進一步的改進,係藉由 Kovesi Detector 結合 LOG 克服了習知超音波影像辨識在物件旋轉後辨識效果不佳之缺點,並且運用 Normailzed Cross-Correlation (NCC) 作為對應點匹配之方法,再者透過硬體描述語言 VHDL 將所提出之影像辨識演算法應用 FPGA 硬體電路進行實現,達到更有效之物件定位,以利於機械臂進行水下施工及打撈作業。
URI: http://ntour.ntou.edu.tw/handle/987654321/28701
Appears in Collections:[電機工程學系] 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