DESIGN OF AN AUTOMATIC TARGET RECOGNATION ALGORITHM


Aldemir E., YILDIZ N., Tavsanoglu V.

21st Signal Processing and Communications Applications Conference (SIU), CYPRUS, 24 - 26 April 2013 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/siu.2013.6531498
  • Country: CYPRUS
  • Keywords: Image processing, automated target recognition/tracking, Freeman chain coding, image classification, RECOGNITION
  • Dokuz Eylül University Affiliated: No

Abstract

In this study, first, an Automated Target Recognition/Tracking (ATR, ATT) system is analyzed, developed and simulated on Matlab environment. Second, a new edge detection method is proposed which is obtained by combining two common edge detection algorithms. Finally, it is shown that Freeman chain codding can be used in feature extraction stage of an ATR system. The system is tested for many different image databases, except for its classification and decision making part, which is still under development, and the results are verified by human eye. Note that, with the development of the classification part, the results will be able to verified with an objective criteria. On the other hand, the designed ATR system is planed to be optimized for an hardware and implemented on an FPGA device in a future work.