Abstract
The use of topographic features has been proposed for classifying targets in Synthetic Aperture Radar (SAR) images. These features are based upon the curvature properties of a surface model that is used to estimate the underlying image intensity. The stability of these features with respect to aspect and sensor noise is investigated. Attention is given to ensure appropriate registration of SAR images and to the modeling of noise in the SAR imaging process. Sensitivity and stability of features are quantitatively and qualitatively analyzed based on each pixel's label, and on the relative groupings of features respectively in the corresponding images. Stability results are presented for simulated XPATCH images as well as the MSTAR Target Dataset.
| Original language | English (US) |
|---|---|
| Pages | 464-467 |
| Number of pages | 4 |
| State | Published - 1997 |
| Externally published | Yes |
| Event | Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3) - Santa Barbara, CA, USA Duration: Oct 26 1997 → Oct 29 1997 |
Other
| Other | Proceedings of the 1997 International Conference on Image Processing. Part 2 (of 3) |
|---|---|
| City | Santa Barbara, CA, USA |
| Period | 10/26/97 → 10/29/97 |
ASJC Scopus subject areas
- Hardware and Architecture
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering