Please use this identifier to cite or link to this item: https://www.um.edu.mt/library/oar/handle/123456789/94179
Title: Marine navigational lights recognition
Authors: Borg, Peter (2009)
Keywords: Ships
Navigation
Global Positioning System
Computer vision
Issue Date: 2009
Citation: Borg, P. (2009). Marine navigational lights recognition (Bachelor's dissertation).
Abstract: The amount of research relating to intelligent marine vessel systems is little compared to that related to computer vision based vehicles. Leisure vessels are equipped with autopilot systems and GPS tracking devices which are commonly used to promote marine safety. The basic form of a marine anti-collision device is the radar application which signals possible danger zones to the mariner, however, this does not identify the source, nor does it suggest any alternative maneuvers to overcome these dangers. In order to provide marine safety at night, every vessel is required to display a set of navigational lights which are used to raise awareness of the vessel's nature and action to neighbouring vessels. It is in this way that other vessels are able to be cautioned of any possible dangers which lie within their vicinity. The set of lights are distinguished by a trained mariner who possesses the knowledge of navigational light representation. The trained mariner is able to maneuver the vessel according to established marine navigational rules in order to avoid collision with other vessels. Besides being on the look out for other vessels which might place the mariner in danger, one must also be aware of fixed buoy markers which are used to signal danger zones. They also suggest trajectories and safe water navigational paths. These buoys can be distinguished by the continuous strobing pattern and the colour of light which they emit. In this dissertation, we explore the field of marine based computer vision and we introduce the evolvement of marine navigational lights recognition by developing an application which is able to recognize simulated vessel lighting systems and buoy marker detections. Through the use of a simulated onboard imaging device, the system will be able to capture a video feed which with the use of image processing techniques and template objects, will be capable of detecting and recognizing marine objects. Based on the recognition of the vessels and buoys, the application will suggest the required maneuver according to the highest ranked alert in order to avoid collisions with other vessels and to keep away from danger zones.
Description: B.Sc. IT (Hons)(Melit.)
URI: https://www.um.edu.mt/library/oar/handle/123456789/94179
Appears in Collections:Dissertations - FacICT - 1999-2009
Dissertations - FacICTCS - 2009

Files in This Item:
File Description SizeFormat 
BSC(HONS)IT_Borg, Peter_2009.PDF
  Restricted Access
7.06 MBAdobe PDFView/Open Request a copy


Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.