Share Email Print

Proceedings Paper

Assessment of a novel decision and reject method for multi-class problems in a target classification framework for SAR scenarios
Author(s): Wolfgang Middelmann; Alfons Ebert; Ulrich Thoennessen
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The enhancement and improvement of classifiers for SAR signatures are a permanent challenge. The focus of this paper is the development of an integrated decision-and-reject method suitable for a kernel-machine-based target classification framework for SAR scenarios. The proposed processing chain consists of a screening process identifying ROIs with target cues, a pre-processing, and a high-performance classifier. A feasible screening method has to provide a maximum of detections namely object hypotheses while the false alarm rate is of lower interest. Therefore the quality of the following classification step significantly depends on the capability of reducing the false alarms. In complex scenarios standard approaches may classify clutter objects incorrectly as targets. To overcome this problem a novel classification scheme was developed. Class discriminating information is computed in a pre-classification step by a family of two-class kernel machines. Thus, a feature vector for an additional classification stage is provided. A comparative assessment was done using a SAR data set provided by QinetiQ. First results are given in terms of ROC curves.

Paper Details

Date Published: 17 May 2006
PDF: 9 pages
Proc. SPIE 6237, Algorithms for Synthetic Aperture Radar Imagery XIII, 62370P (17 May 2006); doi: 10.1117/12.664919
Show Author Affiliations
Wolfgang Middelmann, FGAN-FOM (Germany)
Alfons Ebert, FGAN-FOM (Germany)
Ulrich Thoennessen, FGAN-FOM (Germany)

Published in SPIE Proceedings Vol. 6237:
Algorithms for Synthetic Aperture Radar Imagery XIII
Edmund G. Zelnio; Frederick D. Garber, Editor(s)

© SPIE. Terms of Use
Back to Top