English  |  正體中文  |  简体中文  |  Items with full text/Total items : 27287/39131
Visitors : 2443944      Online Users : 36
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/18425

Title: 結合影像處理及類神經網路之船舶避碰系統探討
On the Integration of Image Processing Technique and Neural Network to the Study of a Ship Collision Avoidance System
Authors: Guo-Kuei Tang
Contributors: NTOU:Department of Communications Navigation and Control Engineering
Keywords: 影像處理;CCD攝影機;疊標導航;類神經網路;自航器;船舶避碰
Image Processing;CCD Camera;Leading Line Guidance;Neural Network;Autopilot;Collision Avoidance
Date: 2010
Issue Date: 2011-07-04
Abstract: 本文主旨在於以影像處理方法結合類神經網路自航器,建立以電腦視覺為迴授機制之船舶自動進港及避碰系統。實驗之進行係透過架設於船艏之CCD攝影機擷取影像,透過影像處理技術過濾出置於障礙物之上下識別物,進而計算本船與障礙物之相對方位及距離資訊,提供給類神經網路自航器執行避碰作業。當本船完成避碰作業後,藉由CCD旋轉台之旋轉機制,搜尋並鎖定岸壁上下疊標,進而計算本船進港導引資訊,提供給類神經網路自航器完成進港作業。於影像處理方面則採用HSV色彩模型,經由適當選取影像成份中H[色調(Hue)]、S[飽和度(Saturation)]及V[色深度(Value)]的篩選值Hmax、Smax、Vmax與Hmin、Smin、Vmin值達到目標物鎖定之目的。本文之實驗軟體使用MATLAB/ Simulink xPC Target環境,並整合實驗載具(小型FRP船)、電力模組、影像擷取模組、控制模組、舵機模組等次系統硬體架構。總結,本研究達成以影像處理技術結合類神經網路自航器,於海洋大學小艇碼頭水域以小型船舶完成避讓固定障礙物之避碰測試,並藉由CCD旋轉台之旋轉機制,改善CCD因水平視角侷限造成之疊標出鏡問題,以保持影像資訊之連續性與準確性。
This work is on the development of a ship collision avoidance system basing on the integration of image processing technique and ANN (artificial neural network). A CCD camera mounted on the bow of a small boat is used in capturing images of a set of targets placed on a stationary obstacle ship and the computed orientation and distance information is fed into an ANN autopilot to steer the boat clear of the obstacle ship. Afterwards, the small boat is able to resume its original track defined by two leading marks for the approaching maneuver. The HSV (Hue, Saturation and Value) color model has been adopted in the image processing technique, and proper threshold values (maximum and minimum) for the H, S and V components are selected to result in successful locking of the targets. Specifically, use of a rotating stand solves the limited view angle problem associated a fixed CCD camera; hence, significantly improves the performance of the system. In summary, this work adopts the MATLAB/Simulink framework and integrates image processing technique and ANN in realizing a ship collision avoidance system. A small boat_based collision avoidance maneuvers conduced in the waterways of the NTOU small boat harbour demonstrates feasibility of the proposed system.
URI: http://ethesys.lib.ntou.edu.tw/cdrfb3/record/#G0M97670018
Appears in Collections:[通訊與導航工程學系] 博碩士論文

Files in This Item:

File Description SizeFormat

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