Improved maritime target tracker using colour fusion

Author

Westall, Paul ; O´Shea, Peter ; Ford, Jason J. ; Hrabar, Stefan

Author_Institution

Sch. of Eng. Syst., Queensland Univ. of Technol., Brisbane, QLD, Australia

fYear

2009

fDate

21-24 June 2009

Firstpage

230

Lastpage

236

Abstract

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.

Keywords

Markov processes; image colour analysis; image enhancement; image fusion; object detection; target tracking; video signal processing; HSV colour spaces; RGB spaces; YCbCr colour spaces; YIQ colour spaces; colour fusion; colour information; emission matrix; hidden Markov model tracker; maritime target detection; maritime target tracker; video enhancement; Australia; Cameras; Hidden Markov models; Humans; Machine vision; Object detection; Oceans; Sea surface; Surface morphology; Target tracking; Colour Fusion; Hidden Markov Models; Maritime Search and Rescue; Mathematical Morphology;

fLanguage

English

Publisher

ieee

Conference_Titel

High Performance Computing & Simulation, 2009. HPCS '09. International Conference on

Conference_Location

Leipzig

Print_ISBN

978-1-4244-4906-4

Electronic_ISBN

978-1-4244-4907-1

Type

conf

DOI

10.1109/HPCSIM.2009.5192545

Filename

5192545