Abstract
The work presented here introduces a procedure for the automatic recognition of ground-based targets from high range resolution (HRR) profile sequences that may be obtained from a synthetic aperture radar (SAR) platform. The procedure incorporates an adaptive target mask and uses a superresolution algorithm to identify the cross-range positions of target scattering centers. These are used to generate a pseudoimage of the target whose low-order discrete cosine transform coefficients form the recognizer feature vector. Within the recognizer, the states of a hidden Markov model (HMM) are used to represent the target orientation and a Gaussian mixture model is used for the feature vector distribution. In a closed-set identification experiment, the misclassification rate for ten MSTAR targets was 2.8%. Also presented are results from open-set experiments and investigates the effect on recognizer performance of variations in feature vector dimension, azimuth aperture, and target variants.
| Original language | English |
|---|---|
| Article number | 5310314 |
| Pages (from-to) | 1512 |
| Number of pages | 1 |
| Journal | IEEE Transactions on Aerospace and Electronic Systems |
| Volume | 45 |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - Oct 2009 |
Bibliographical note
Funding Information:This work was supported by the UK Ministry of Defence through work funded by the Defence Technology Center for Data and Information Fusion.
Funding Information:
The MSTAR data set was collected by the Sandia National Laboratory (SNL) SAR sensor platform [32]. The collection was jointly sponsored by US Defence Advanced Research Projects Agency (DARPA) and Air Force Research Laboratory as part of the Moving and Stationary Target Acquisition and Recognition (MSTAR) program. SNL used an X-band SAR sensor in 0:3 m resolution spotlight mode. The MSTAR public-release dataset consists of 10 target classes