Loading...

Using the Echo of Rotating Parts to Recognize a Radar Target

Johari, Mohammad Mahdi | 2016

748 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 48821 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Nayebi, Mohammad Mahdi
  7. Abstract:
  8. Target recognition techniques based on micro Doppler phenomenon are popular because they are applicable even on low resolution radars, in contrast to other techniques such as High Resolution Range Profile (HRRP) which need high resolution in range or angle. Usually, main purpose of such techniques is generating robust features against target initial state, velocity, aspect angle, etc. rather than features which exactly identify a target. Main approaches in the literature are based on time-frequency transforms (TFT) such as spectrogram in order to generate features to classify targets, but in this thesis, we propose a totally different method using Recurrence Plot for generating features based on micro Doppler effect. Recurrence Plot is a two-dimensional binary plot which both axes are Time (in contrast to spectrogram which is continuous time-frequency plot) and visualize relation of system states at different time samples. Statistical measurements from Recurrence plot can be used as discriminant features for target classification.
    Extracted features have been scored using joint mutual information (JMI) method, which is a classifier independent and information-theory-based feature selection method, and high score features are selected and presented to the classifier. The proposed method is tested on simulated data of three different targets (one jet aircraft, one propeller aircraft and one helicopter) using multiclass support vector machine and classification rate of about 97% is achieved. Also, effect of noise and coherent processing time (CPT) on classification rate is investigated
  9. Keywords:
  10. Target Recognition ; Feature Extraction ; Mutual Information ; Time Frequency Transform ; Radar Target Recognition ; Support Vector Machine (SVM)Classifier ; Recurrence Plot ; Micro Doppler

 Digital Object List

 Bookmark

No TOC