Invariant rules for multi-polarization SAR change detection

Vincenzo Carotenuto, Antonio De Maio, Carmine Clemente, John J. Soraghan

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

This paper deals with coherent (in the sense that both amplitudes and relative phases of the polarimetric returns are used to construct the decision statistic), multi-polarization SAR change detection assuming the availability of reference and test images collected from N multiple polarimetric channels. At the design stage, the change detection problem is formulated as a binary hypothesis testing problem and the principle of invariance is used to come up with decision rules sharing the Constant False Alarm Rate (CFAR) property. The maximal invariant statistic and the maximal invariant in the parameter space are obtained. Hence, the optimum invariant test is devised proving that a Uniformly Most Powerful Invariant (UMPI) detector does not exist. Based on this, the class of sub-optimum invariant receivers, which also includes the Generalized Likelihood Ratio Test (GLRT), is considered. At the analysis stage, the performance of some tests, belonging to the aforementioned class, is assessed and compared with the optimum clairvoyant invariant detector. Finally, detection maps on real high resolution SAR data are computed showing the effectiveness of the considered invariant decision structures.
LanguageEnglish
Pages3294-3311
Number of pages18
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume53
Issue number6
Early online date23 Dec 2014
DOIs
Publication statusPublished - Jun 2015

Fingerprint

synthetic aperture radar
polarization
Statistics
Polarization
Detectors
Invariance
Availability
hypothesis testing
Testing
test
detection
decision
statistics
detector

Keywords

  • invariant rules
  • linear matrix inequalities
  • multipolarization
  • coherent change detection
  • maximal invariant

Cite this

@article{1ba58deeafd845e480d6321606810413,
title = "Invariant rules for multi-polarization SAR change detection",
abstract = "This paper deals with coherent (in the sense that both amplitudes and relative phases of the polarimetric returns are used to construct the decision statistic), multi-polarization SAR change detection assuming the availability of reference and test images collected from N multiple polarimetric channels. At the design stage, the change detection problem is formulated as a binary hypothesis testing problem and the principle of invariance is used to come up with decision rules sharing the Constant False Alarm Rate (CFAR) property. The maximal invariant statistic and the maximal invariant in the parameter space are obtained. Hence, the optimum invariant test is devised proving that a Uniformly Most Powerful Invariant (UMPI) detector does not exist. Based on this, the class of sub-optimum invariant receivers, which also includes the Generalized Likelihood Ratio Test (GLRT), is considered. At the analysis stage, the performance of some tests, belonging to the aforementioned class, is assessed and compared with the optimum clairvoyant invariant detector. Finally, detection maps on real high resolution SAR data are computed showing the effectiveness of the considered invariant decision structures.",
keywords = "invariant rules, linear matrix inequalities, multipolarization, coherent change detection, maximal invariant",
author = "Vincenzo Carotenuto and {De Maio}, Antonio and Carmine Clemente and Soraghan, {John J.}",
year = "2015",
month = "6",
doi = "10.1109/TGRS.2014.2372900",
language = "English",
volume = "53",
pages = "3294--3311",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "IEEE",
number = "6",

}

Invariant rules for multi-polarization SAR change detection. / Carotenuto, Vincenzo; De Maio, Antonio; Clemente, Carmine; Soraghan, John J.

In: IEEE Transactions on Geoscience and Remote Sensing, Vol. 53, No. 6, 06.2015, p. 3294-3311 .

Research output: Contribution to journalArticle

TY - JOUR

T1 - Invariant rules for multi-polarization SAR change detection

AU - Carotenuto, Vincenzo

AU - De Maio, Antonio

AU - Clemente, Carmine

AU - Soraghan, John J.

PY - 2015/6

Y1 - 2015/6

N2 - This paper deals with coherent (in the sense that both amplitudes and relative phases of the polarimetric returns are used to construct the decision statistic), multi-polarization SAR change detection assuming the availability of reference and test images collected from N multiple polarimetric channels. At the design stage, the change detection problem is formulated as a binary hypothesis testing problem and the principle of invariance is used to come up with decision rules sharing the Constant False Alarm Rate (CFAR) property. The maximal invariant statistic and the maximal invariant in the parameter space are obtained. Hence, the optimum invariant test is devised proving that a Uniformly Most Powerful Invariant (UMPI) detector does not exist. Based on this, the class of sub-optimum invariant receivers, which also includes the Generalized Likelihood Ratio Test (GLRT), is considered. At the analysis stage, the performance of some tests, belonging to the aforementioned class, is assessed and compared with the optimum clairvoyant invariant detector. Finally, detection maps on real high resolution SAR data are computed showing the effectiveness of the considered invariant decision structures.

AB - This paper deals with coherent (in the sense that both amplitudes and relative phases of the polarimetric returns are used to construct the decision statistic), multi-polarization SAR change detection assuming the availability of reference and test images collected from N multiple polarimetric channels. At the design stage, the change detection problem is formulated as a binary hypothesis testing problem and the principle of invariance is used to come up with decision rules sharing the Constant False Alarm Rate (CFAR) property. The maximal invariant statistic and the maximal invariant in the parameter space are obtained. Hence, the optimum invariant test is devised proving that a Uniformly Most Powerful Invariant (UMPI) detector does not exist. Based on this, the class of sub-optimum invariant receivers, which also includes the Generalized Likelihood Ratio Test (GLRT), is considered. At the analysis stage, the performance of some tests, belonging to the aforementioned class, is assessed and compared with the optimum clairvoyant invariant detector. Finally, detection maps on real high resolution SAR data are computed showing the effectiveness of the considered invariant decision structures.

KW - invariant rules

KW - linear matrix inequalities

KW - multipolarization

KW - coherent change detection

KW - maximal invariant

UR - http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=36

U2 - 10.1109/TGRS.2014.2372900

DO - 10.1109/TGRS.2014.2372900

M3 - Article

VL - 53

SP - 3294

EP - 3311

JO - IEEE Transactions on Geoscience and Remote Sensing

T2 - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

IS - 6

ER -