Identification of multiaspect radar signals based on the feature space trajectory concept
Authors:
- Ho-Ryung JeongHJHo-Ryung Jeong
- 7 November 2005
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 53 (11) , 3811-3821
Abstract
Identification of radar targets has often been based on information gathered from only a single relative aspect between the radar and target. However, identification performances can be significantly improved, provided that radar signals at multiple aspects are simultaneously used to identify radar targets. In this paper, we investigate performances of various approaches to identification using multiaspect radar signals. In addition, some novel techniques based on the feature space trajectory concept are introduced to further enhance the identification performance of the conventional methods. All of these approaches are demonstrated using radar cross section (RCS) data of various aircraft models measured at compact range. Results show that the proposed methods via the FST concept can provide the most promising identification accuracy.Keywords
This publication has 16 references indexed in Scilit:
- Sum versus vote fusion in multiple classifier systemsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Efficient radar target recognition using the MUSIC algorithm and invariant featuresIEEE Transactions on Antennas and Propagation, 2002
- One-dimension range profile identification of radar targets based on a linear interpolation neural networkSignal Processing, 2001
- Target identification with wave-based matched pursuits and hidden Markov modelsIEEE Transactions on Antennas and Propagation, 1999
- On combining classifiersIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Neural network approach for high-resolution target classification1995
- Classifier and shift-invariant automatic target recognition neural networksNeural Networks, 1995
- Feature space trajectory (FST) classifier neural network1994
- Recurrent neural networks for radar target identication1993
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989