Improved maritime target tracker using colour fusion

Searching for humans lost in vast stretches of ocean has always been a difficult task. This paper investigates a machine vision system that addresses this problem by exploiting the useful properties of alternate colour spaces. In particular, the paper investigates the fusion of colour information fr...

Full description

Saved in:
Bibliographic Details
Published in2009 International Conference on High Performance Computing and Simulation pp. 230 - 236
Main Authors Westall, P., O'Shea, P., Ford, J.J., Hrabar, S.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2009
Subjects
Australia
Cameras
Colour Fusion
Hidden Markov models
Humans
Machine vision
Maritime Search and Rescue
Mathematical Morphology
Object detection
Oceans
Sea surface
Surface morphology
Target tracking
Online AccessGet full text
ISBN1424449065
9781424449064
DOI10.1109/HPCSIM.2009.5192545

Cover

More Information
Summary:Searching for humans lost in vast stretches of ocean has always been a difficult task. This paper investigates a machine vision system that addresses this problem by exploiting the useful properties of alternate colour spaces. In particular, the paper investigates the fusion of colour information from the HSV, RGB, YCbCr and YIQ colour spaces within the emission matrix of a Hidden Markov Model tracker to enhance video based maritime target detection. The system has shown promising results. The paper also identifies challenges still needing to be met.
ISBN:1424449065
9781424449064
DOI:10.1109/HPCSIM.2009.5192545