Target Localization in Multi-static Passive Radar Systems with Artificial Neural Networks

We propose an artificial neural network (ANN)-based target localization method for a multi-static passive radar system consisting of multiple illuminators, a radar receiver, and a single target. Assuming a multi-frequency network, the time difference-of-arrival (TDOA) of signals coming from each illuminator via the target and direct paths is estimated from the cross-ambiguity function. The training data consists of the estimated TDOAs corresponding to all illuminators and the target locations in the training set. The performance of the ANN is then evaluated with the test data, where 10% of the total data is randomly chosen as the test data. Simulation results show that the performance of the proposed ANN-based method decreases with the increasing estimation error in TDOA. Moreover, the results show that the mean square error (MSE) performance achieved with a set of 1, 000 data points is close to that achieved with the perfect case even the signal-to-noise-ratio in the surveillance channel is − 23 dB.

[1]  Braham Himed,et al.  Target position localization in a passive radar system through convex optimization , 2013, Defense, Security, and Sensing.

[2]  Gang Wang,et al.  Efficient Convex Relaxation Methods for Robust Target Localization by a Sensor Network Using Time Differences of Arrivals , 2009, IEEE Transactions on Signal Processing.

[3]  K. C. Ho,et al.  An accurate algebraic solution for moving source location using TDOA and FDOA measurements , 2004, IEEE Transactions on Signal Processing.

[4]  Hao Ling,et al.  Tracking a moving target with multiple doppler sensors using an artificial neural network , 2007, 2007 IEEE Antennas and Propagation Society International Symposium.

[5]  Baris Fidan,et al.  Localization Algorithms and Strategies for Wireless Sensor Networks: Monitoring and Surveillance Techniques for Target Tracking , 2009 .

[6]  Chris Baker,et al.  Passive coherent location radar systems. Part 2: waveform properties , 2005 .

[7]  Wenyan He,et al.  A novel method for chirp signal detection based on fractional Fourier transform , 2008, International Symposium on Instrumentation and Control Technology.

[8]  Nirwan Ansari,et al.  A Semidefinite Relaxation Method for Source Localization Using TDOA and FDOA Measurements , 2013, IEEE Transactions on Vehicular Technology.

[9]  Guoqiang Mao,et al.  LOCALIZATION PROBLEM IN SENSOR NETWORKS : THE MACHINE LEARNING APPROACH , 2008 .

[10]  Zhi Ding,et al.  Source Localization in Wireless Sensor Networks From Signal Time-of-Arrival Measurements , 2011, IEEE Transactions on Signal Processing.

[11]  H. Griffiths,et al.  Television-based bistatic radar , 1986 .

[12]  H. Griffiths,et al.  Passive coherent location radar systems. Part 1: performance prediction , 2005 .

[13]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[14]  Jian Li,et al.  Exact and Approximate Solutions of Source Localization Problems , 2008, IEEE Transactions on Signal Processing.

[15]  Yimin Zhang,et al.  Localization of Inanimate Moving Targets Using Dual-Frequency Synthetic Aperture Radar and Time-Frequency Analysis , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[16]  Braham Himed,et al.  Target localization in a multi-static passive radar system through convex optimization , 2014, Signal Process..

[17]  Wing-Kin Ma,et al.  Accurate approximation algorithm for TOA-based maximum likelihood mobile location using semidefinite programming , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[18]  Jacob Benesty,et al.  Real-time passive source localization: a practical linear-correction least-squares approach , 2001, IEEE Trans. Speech Audio Process..

[19]  V. Koch,et al.  New approach to a multistatic passive radar sensor for air/space defense , 1995 .