27 August 2001 Increasing the discrimination of SAR recognition models
Author Affiliations +
The focus of this paper is optimizing recognition models for Synthetic Aperture Radar signatures of vehicles to improve the performance of a recognition algorithm under the extended operating conditions of target articulation, occlusion and configuration variants. The recognition models are based on quasi-invariant local features, scattering center locations and magnitudes. The approach determines the similarities and differences among the various vehicle models. Methods to penalize similar features or reward dissimilar features are used to increase the distinguishability of the recognition model instances. Extensive experimental recognition results are presented in terms of confusion matrices and receiver operating characteristic curves to show the improvements in recognition performance for MSTAR vehicle targets with articulation, configuration variants and occlusion.
© (2001) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Bir Bhanu, Bir Bhanu, Grinnell Jones, Grinnell Jones, } "Increasing the discrimination of SAR recognition models", Proc. SPIE 4382, Algorithms for Synthetic Aperture Radar Imagery VIII, (27 August 2001); doi: 10.1117/12.438223; https://doi.org/10.1117/12.438223


Recognizing occluded MSTAR targets
Proceedings of SPIE (August 23 2000)
Composite class models for SAR recognition
Proceedings of SPIE (September 11 2003)
Performance modeling of vote-based object recognition
Proceedings of SPIE (August 19 2003)

Back to Top