Abstract

With continuing growth in sensor capabilities and database complexity, the analysis and understanding of large data sets becomes increasingly important. Numerous researchers have recently explored the geometry and topology of high contrast patches in natural images in an attempt to understand the underlying manifold of the data. The results show that the majority of natural image patches are best represented by corners and edges, as one would expect from visual inspection. In this paper, we extend this analysis to log-magnitude SAR images from the MSTAR database. Our results show that the most representative high contrast patches in SAR images lie among the clutter however methods extracting target patches only show results more similar to that obtained for natural imagery. Contrary to their natural image counterparts however, high contrast patches in SAR imagery lack a significant geometric structure.

Original languageEnglish (US)
Title of host publicationIEEE National Radar Conference - Proceedings
Pages905-909
Number of pages5
DOIs
StatePublished - 2010
EventIEEE International Radar Conference 2010, RADAR 2010 - Washington DC, United States
Duration: May 10 2010May 14 2010

Other

OtherIEEE International Radar Conference 2010, RADAR 2010
CountryUnited States
CityWashington DC
Period5/10/105/14/10

Fingerprint

Topology
Inspection
Geometry
Sensors

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Knee, P., Berisha, V., Spanias, A., & Taylor, T. (2010). Topology of high-contrast patches in SAR images. In IEEE National Radar Conference - Proceedings (pp. 905-909). [5494491] https://doi.org/10.1109/RADAR.2010.5494491

Topology of high-contrast patches in SAR images. / Knee, Peter; Berisha, Visar; Spanias, Andreas; Taylor, Thomas.

IEEE National Radar Conference - Proceedings. 2010. p. 905-909 5494491.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Knee, P, Berisha, V, Spanias, A & Taylor, T 2010, Topology of high-contrast patches in SAR images. in IEEE National Radar Conference - Proceedings., 5494491, pp. 905-909, IEEE International Radar Conference 2010, RADAR 2010, Washington DC, United States, 5/10/10. https://doi.org/10.1109/RADAR.2010.5494491
Knee P, Berisha V, Spanias A, Taylor T. Topology of high-contrast patches in SAR images. In IEEE National Radar Conference - Proceedings. 2010. p. 905-909. 5494491 https://doi.org/10.1109/RADAR.2010.5494491
Knee, Peter ; Berisha, Visar ; Spanias, Andreas ; Taylor, Thomas. / Topology of high-contrast patches in SAR images. IEEE National Radar Conference - Proceedings. 2010. pp. 905-909
@inproceedings{f00aca01ac834fc0a72fb176ca99cb0d,
title = "Topology of high-contrast patches in SAR images",
abstract = "With continuing growth in sensor capabilities and database complexity, the analysis and understanding of large data sets becomes increasingly important. Numerous researchers have recently explored the geometry and topology of high contrast patches in natural images in an attempt to understand the underlying manifold of the data. The results show that the majority of natural image patches are best represented by corners and edges, as one would expect from visual inspection. In this paper, we extend this analysis to log-magnitude SAR images from the MSTAR database. Our results show that the most representative high contrast patches in SAR images lie among the clutter however methods extracting target patches only show results more similar to that obtained for natural imagery. Contrary to their natural image counterparts however, high contrast patches in SAR imagery lack a significant geometric structure.",
author = "Peter Knee and Visar Berisha and Andreas Spanias and Thomas Taylor",
year = "2010",
doi = "10.1109/RADAR.2010.5494491",
language = "English (US)",
isbn = "9781424458127",
pages = "905--909",
booktitle = "IEEE National Radar Conference - Proceedings",

}

TY - GEN

T1 - Topology of high-contrast patches in SAR images

AU - Knee, Peter

AU - Berisha, Visar

AU - Spanias, Andreas

AU - Taylor, Thomas

PY - 2010

Y1 - 2010

N2 - With continuing growth in sensor capabilities and database complexity, the analysis and understanding of large data sets becomes increasingly important. Numerous researchers have recently explored the geometry and topology of high contrast patches in natural images in an attempt to understand the underlying manifold of the data. The results show that the majority of natural image patches are best represented by corners and edges, as one would expect from visual inspection. In this paper, we extend this analysis to log-magnitude SAR images from the MSTAR database. Our results show that the most representative high contrast patches in SAR images lie among the clutter however methods extracting target patches only show results more similar to that obtained for natural imagery. Contrary to their natural image counterparts however, high contrast patches in SAR imagery lack a significant geometric structure.

AB - With continuing growth in sensor capabilities and database complexity, the analysis and understanding of large data sets becomes increasingly important. Numerous researchers have recently explored the geometry and topology of high contrast patches in natural images in an attempt to understand the underlying manifold of the data. The results show that the majority of natural image patches are best represented by corners and edges, as one would expect from visual inspection. In this paper, we extend this analysis to log-magnitude SAR images from the MSTAR database. Our results show that the most representative high contrast patches in SAR images lie among the clutter however methods extracting target patches only show results more similar to that obtained for natural imagery. Contrary to their natural image counterparts however, high contrast patches in SAR imagery lack a significant geometric structure.

UR - http://www.scopus.com/inward/record.url?scp=77954944983&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954944983&partnerID=8YFLogxK

U2 - 10.1109/RADAR.2010.5494491

DO - 10.1109/RADAR.2010.5494491

M3 - Conference contribution

SN - 9781424458127

SP - 905

EP - 909

BT - IEEE National Radar Conference - Proceedings

ER -