Design of Automatic Target Recognition system based on multistatic passive RADAR
Session
Computer Science and Communication Engineering
Description
Nowadays, a great number of researchers are concerned about aerial targets since they are involved in many aspects of everyday life, such as military issues, including aircrafts and missiles, or Unmanned Aerial Vehicles (UAVs) flying over city centers or airport areas. The design of an efficient Automatic Target Recognition (ATR) system has been an attractive problem and for this reason many researchers rely on experiments to extract the necessary data for the ATR system. In this paper, a new method for extracting the radar cross-section (RCS) data has been proposed, which uses the Boundary Element Method (BEM) to efficiently compute the RCS values of different objects at any point of the coordinate system in a short period of time, without need of any experiment. Multiple RCS values in the presence of noise are used for the training and the evaluation of two ATR systems, based on the nearest neighbor classification rule or a multilayer Neural Network.
Keywords:
Automatic target recognition (ATR), bistatic radar, radar cross- section (RCS), classification, machine learning, neural networks
Session Chair
Bertan Karahoda
Session Co-Chair
Krenare Pireva
Proceedings Editor
Edmond Hajrizi
ISBN
978-9951-437-69-1
Location
Pristina, Kosovo
Start Date
27-10-2018 10:45 AM
End Date
27-10-2018 12:15 PM
DOI
10.33107/ubt-ic.2018.89
Recommended Citation
Polyzos, Konstantinos and Dermatas, Evangelos, "Design of Automatic Target Recognition system based on multistatic passive RADAR" (2018). UBT International Conference. 89.
https://knowledgecenter.ubt-uni.net/conference/2018/all-events/89
Design of Automatic Target Recognition system based on multistatic passive RADAR
Pristina, Kosovo
Nowadays, a great number of researchers are concerned about aerial targets since they are involved in many aspects of everyday life, such as military issues, including aircrafts and missiles, or Unmanned Aerial Vehicles (UAVs) flying over city centers or airport areas. The design of an efficient Automatic Target Recognition (ATR) system has been an attractive problem and for this reason many researchers rely on experiments to extract the necessary data for the ATR system. In this paper, a new method for extracting the radar cross-section (RCS) data has been proposed, which uses the Boundary Element Method (BEM) to efficiently compute the RCS values of different objects at any point of the coordinate system in a short period of time, without need of any experiment. Multiple RCS values in the presence of noise are used for the training and the evaluation of two ATR systems, based on the nearest neighbor classification rule or a multilayer Neural Network.