28 July 1997 Enhancements of pose-tagged partial evidence fusion SAR ATR
Author Affiliations +
Abstract
This paper discusses enhancements of a recently developed system for robust, obscured object recognition by means of partial evidence reconstruction from object restricted measures (PERFORM). PERFORM employs a partial evidence accrual approach to form both an object identity metric and an object pose estimate. Recent enhancements of PERFORM resulted in significant performance improvements over those reported in our previous publications. Partial evidence information is obtained by applying several instances of the authors' linear signal decomposition/direction of arrival (LSD/DOA) pose estimation technique. The LSD/DOA ATR system avoids search techniques and is capable of detection and classification of possibly articulated, multiple objects with many degrees of freedom. Development of PERFORM was motivated by the fact that pose estimation in the LSD/DOA method is primarily degraded in practice by the presence of background clutter in the pose estimation filter's region of support. The use of several independent pose estimators based upon LSD/DOA's reciprocal basis set filters constructed for overlapping sub-regions of the object, allow for clutter independent pose estimation, and robust detection of obscured targets. Recent enhancements of the partial evidence fusion have been focused on introducing subhypothesis decisions related to the occupancy of the various subregions by target or clutter and fusion of information for target occupied regions. Presented results include receiver operating characteristic curves for SAR targets embedded in clutter with and without partial obscuration.
© (1997) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Witold R. Jachimczyk, Witold R. Jachimczyk, David Cyganski, David Cyganski, } "Enhancements of pose-tagged partial evidence fusion SAR ATR", Proc. SPIE 3070, Algorithms for Synthetic Aperture Radar Imagery IV, (28 July 1997); doi: 10.1117/12.281570; https://doi.org/10.1117/12.281570
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT

Adaptive aircraft detection in high-resolution SAR images
Proceedings of SPIE (October 25 2013)
Very fast SAR detection
Proceedings of SPIE (June 13 1996)
Adaptive recognition of previously seen vehicles
Proceedings of SPIE (September 01 2004)
Adaptive target recognition
Proceedings of SPIE (June 09 1997)

Back to Top