Polynomial segment model for radar target recognition using Gibbs sampling approach

Hadavi, M ; Sharif University of Technology | 2017

462 Viewed
  1. Type of Document: Article
  2. DOI: 10.1049/iet-spr.2014.0455
  3. Publisher: Institution of Engineering and Technology , 2017
  4. Abstract:
  5. High resolution range profile (HRRP) is a widely noted tool in radar target recognition. However, its high sensitivity to the target's aspect angle makes it necessary to seek solutions for this problem. One alternative is to assume consecutive samples of HRRP identically and independently distributed in small frames of aspect angles, an assumption which is not true in reality. Based on this simplifying assumption, some models, such as the hidden Markov model, have been developed to characterise the sequential information contained in multi-aspect radar echoes. As a result, these models consider only the short dependency between consecutive samples. Considering such issues, in this study, the authors propose an alternative polynomial segment model. In addition, using a Markov chain Monte-Carlo based Gibbs sampler as an iterative approach to estimate the parameters of the segment model, the authors will show that the results are quite satisfactory. © The Institution of Engineering and Technology
  6. Keywords:
  7. Hidden Markov models ; Markov processes ; Radar ; Radar signal processing ; High resolution range profiles ; High sensitivity ; Iterative approach ; Markov Chain Monte-Carlo ; Polynomial segments ; Segment modeling ; Sequential information ; Simplifying assumptions ; Radar target recognition
  8. Source: IET Signal Processing ; Volume 11, Issue 3 , 2017 , Pages 285-294 ; 17519675 (ISSN)
  9. URL: http://digital-library.theiet.org/content/journals/10.1049/iet-spr.2014.0455