Direction of Arrival Estimation of Humans with a Small Sensor Array Using an Artificial Neural Network

An array processing algorithm based on artiflcial neural networks (ANNs) is proposed to estimate the directions of arrival (DOAs) of moving humans using a small sensor array. In the approach, software beamforming is flrst performed on the received signals from the sensor elements to form a number of overlapping beams. The received signals from all the beams produce a unique \signature" in accordance with the target locations as well as the number of targets. The target tracking procedure is handled by two separate ANNs in sequence. The flrst ANN determines the number of targets, and the second ANN estimates their respective DOAs. The ANNs are trained using simulation data generated based on a point scatterer model in free space. The proposed approach is tested using measurement data from two loudspeakers and two walking humans in line-of-sight and through-wall environments.

[1]  Samuel M. Sherman,et al.  Monopulse Principles and Techniques , 1984 .

[2]  Hao Ling,et al.  Through-Wall Tracking of Human Movers Using Joint Doppler and Array Processing , 2008, IEEE Geoscience and Remote Sensing Letters.

[3]  Yimin Zhang,et al.  Three-Dimensional Wideband Beamforming for Imaging Through a Single Wall , 2008, IEEE Geoscience and Remote Sensing Letters.

[4]  B. D. Steinberg,et al.  Reduction of sidelobe and speckle artifacts in microwave imaging: the CLEAN technique , 1988 .

[5]  Thomas Kailath,et al.  ESPRIT-A subspace rotation approach to estimation of parameters of cisoids in noise , 1986, IEEE Trans. Acoust. Speech Signal Process..

[6]  Andrea Massa,et al.  KERNELS EVALUATION OF SVM-BASED ESTIMATORS FOR INVERSE SCATTERING PROBLEMS , 2005 .

[7]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[8]  C. Burrus,et al.  Array Signal Processing , 1989 .

[9]  Hao Ling,et al.  Doppler and direction-of-arrival (DDOA) radar for multiple-mover sensing , 2007, IEEE Transactions on Aerospace and Electronic Systems.

[10]  Mark A. Barnes,et al.  Ultrawideband through-wall radar for detecting the motion of people in real time , 2002, SPIE Defense + Commercial Sensing.

[11]  Y. Rahmat-Samii,et al.  Particle swarm optimization in electromagnetics , 2004, IEEE Transactions on Antennas and Propagation.

[12]  Michael Georgiopoulos,et al.  A neural network-based smart antenna for multiple source tracking , 2000 .

[13]  W. Chen,et al.  Improved Blind 2D-Direction of Arrival Estimation with L-Shaped Array Using Shift Invariance Property , 2009 .

[14]  J. Litva,et al.  Radial basis function neural network for direction-of-arrivals estimation , 1994, IEEE Signal Processing Letters.

[15]  R. O. Schmidt,et al.  Multiple emitter location and signal Parameter estimation , 1986 .

[16]  P. Saratchandran,et al.  Direction of Arrival (DoA) Estimation Under Array Sensor Failures Using a Minimal Resource Allocation Neural Network , 2007, IEEE Transactions on Antennas and Propagation.

[17]  Guisheng Liao,et al.  A Method for DOA Estimation in the Presence of Unknown Nonuniform Noise , 2008 .

[18]  Youngwook Kim,et al.  Through-wall human monitoring using data-driven models with Doppler information , 2008 .

[19]  Jian Li,et al.  Efficient mixed-spectrum estimation with applications to target feature extraction , 1995, Conference Record of The Twenty-Ninth Asilomar Conference on Signals, Systems and Computers.

[20]  Harry L. Van Trees,et al.  Optimum Array Processing , 2002 .