Extended Object Tracking and Shape Classification


Tuncer B., Kumru M., Alatan A. A. , Özkan E.

21st International Conference on Information Fusion (FUSION), Cambridge, Canada, 10 - 13 July 2018, pp.267-274 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.23919/icif.2018.8455464
  • City: Cambridge
  • Country: Canada
  • Page Numbers: pp.267-274
  • Keywords: Extended Target Tracking, Contour representation, Shape-based Classification, Gaussian Process, Bayesian, Classification, Learning, TARGET TRACKING, FOURIER, RECOGNITION

Abstract

Recent extended target tracking algorithms provide reliable shape estimates while tracking objects. The estimated extent of the objects can also be used for online classification. In this work, we propose to use a Bayesian classifier to identify different objects based on their contour estimates during tracking. The proposed method uses the uncertainty information provided by the estimation covariance of the tracker.