Title :
Mine detection using scattering parameters
Author :
Plett, Gregory L. ; Doi, Takeshi ; Torrieri, Don
Author_Institution :
Dept. of Electr. Eng., Stanford Univ., CA, USA
fDate :
11/1/1997 12:00:00 AM
Abstract :
The detection and disposal of antipersonnel land mines is one of the most difficult and intractable problems faced in ground conflict. This paper presents detection methods which use a separated-aperture microwave sensor and an artificial neural network pattern classifier. Several data-specific preprocessing methods are developed to enhance neural network learning. In addition, a generalized Karhunen-Loeve transform and the eigenspace separation transform are used to perform data reduction and reduce network complexity. Highly favorable results have been obtained using the above methods in conjunction with a feedforward neural network
Keywords :
eigenvalues and eigenfunctions; feature extraction; feedforward neural nets; microwave detectors; object detection; pattern classification; transforms; weapons; antipersonnel land mines; artificial neural network pattern classifier; data-specific preprocessing methods; eigenspace separation transform; feedforward neural network; generalized Karhunen-Loeve transform; ground conflict; mine detection; neural network learning; scattering parameters; separated-aperture microwave sensor; Apertures; Artificial neural networks; Costs; Detectors; Face detection; Landmine detection; Microwave sensors; Scattering parameters; Sensor phenomena and characterization; Testing;
Journal_Title :
Neural Networks, IEEE Transactions on
