Detection of sea targets from thermal images


Yaslan Y., Gunsel B.

IEEE 12th Signal Processing and Communications Applications Conference, Kusadasi, Turkey, 28 - 30 April 2004, pp.672-675 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/siu.2004.1338620
  • City: Kusadasi
  • Country: Turkey
  • Page Numbers: pp.672-675
  • Istanbul Technical University Affiliated: No

Abstract

In this paper, sea targets detection problem from thermal (IR) images is solved by using statistical classification methods. Background modelling is achieved via principle component analysis (PCA) followed by a two-class Bayes classification step, i.e., target or sea. A wavelet-denoising block is added to the system resulting in a significant increase in the detection performance. K-means clustering is also implemented to explore the target detection accuracy without training. It is concluded that the PCA training provides high detection accuracy while the K-means clustering mostly fails to classify the sea targets.