Genetic tracker with adaptive neuro-fuzzy inference system for multiple target tracking

TÜRKMEN I., Guney K.

EXPERT SYSTEMS WITH APPLICATIONS, vol.35, no.4, pp.1657-1667, 2008 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 35 Issue: 4
  • Publication Date: 2008
  • Doi Number: 10.1016/j.eswa.2007.08.065
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.1657-1667
  • Erciyes University Affiliated: Yes


In this paper, a genetic tracker with adaptive neuro-fuzzy inference system (GT-ANFIS) is presented for multiple target tracking (MTT). First, the data association problem, formulated its an N-dimensional assignment problem, is solved using the genetic algorithm (GA), and then the inaccuracies in the estimation are corrected by the adaptive neuro-fuzzy inference system (ANFIS). The performances of the GT-ANFIS, the joint probabilistic data association filter (JPDAF), the genetic tracker (GT), and the genetic tracker with neural network (GT-NN) are compared with each other for six different tracking scenarios. It was shown that the tracks estimated by using proposed GT-ANFIS agree better with the true tracks than the tracks predicted by the JPDAF, the GT, and the GT-NN. (C) 2007 Elsevier Ltd. All rights reserved.