Multiclass SAR feature space trajectory (FST) neural network class and pose estimation results

Rajesh Shenoy; David P. Casasent

doi:10.1117/12.281549

Translator Disclaimer

28 July 1997 Multiclass SAR feature space trajectory (FST) neural network class and pose estimation results

Rajesh Shenoy; David P. Casasent

Author Affiliations +

Proceedings Volume 3070, Algorithms for Synthetic Aperture Radar Imagery IV; (1997) https://doi.org/10.1117/12.281549
Event: AeroSense '97, 1997, Orlando, FL, United States

Abstract

The feature space trajectory representation and neural network is used for classification and pose estimation of distorted objects in SAR data. New feature spaces and techniques to extend the concept to multiple classes are emphasized with initial four class results. On 4 class data, we obtain P_c equals 98.3 percent and clutter P_FA equals 0.026/km².

Citation Download Citation

Rajesh Shenoy and David P. Casasent "Multiclass SAR feature space trajectory (FST) neural network class and pose estimation results", Proc. SPIE 3070, Algorithms for Synthetic Aperture Radar Imagery IV, (28 July 1997); https://doi.org/10.1117/12.281549

ACCESS THE FULL ARTICLE