Abstract

The extraction of objects from advanced geospatial intelligence (AGI) products based on synthetic aperture radar (SAR) imagery is complicated by a number of factors. For example, accurate detection of temporal changes represented in two-color multiview (2CMV) AGI products can be challenging because of speckle noise susceptibility and false positives that result from small orientation differences between objects imaged at different times. These cases of apparent motion can result in 2CMV detection, but they obviously differ greatly in terms of significance. In investigating the state-of-the-art in SAR image processing, we have found that differentiating between these two general cases is a problem that has not been well addressed. We propose a framework of methods to address these problems. For the detection of the temporal changes while reducing the number of false positives, we propose using adaptive object intensity and area thresholding in conjunction with relaxed brightness optical flow algorithms that track the motion of objects across time in small regions of interest. The proposed framework for distinguishing between actual motion and misregistration can lead to more accurate and meaningful change detection and improve object extraction from a SAR AGI product. Results demonstrate the ability of our techniques to reduce false positives up to 60%.

Original languageEnglish (US)
Title of host publicationAlgorithms for Synthetic Aperture Radar Imagery XXIV
PublisherSPIE
Volume10201
ISBN (Electronic)9781510609037
DOIs
StatePublished - 2017
EventAlgorithms for Synthetic Aperture Radar Imagery XXIV 2017 - Anaheim, United States
Duration: Apr 13 2017 → …

Other

OtherAlgorithms for Synthetic Aperture Radar Imagery XXIV 2017
CountryUnited States
CityAnaheim
Period4/13/17 → …

Fingerprint

radar imagery
intelligence
Synthetic Aperture
synthetic aperture radar
Synthetic aperture radar
Radar
False Positive
products
change detection
Optical flows
Motion
Speckle
image processing
Luminance
brightness
Image processing
Speckle Noise
Change Detection
Color
Optical Flow

Keywords

  • 2CMV
  • Change detection
  • Optical flow
  • SAR
  • Synthetic aperture radar

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Kanberoglu, B., & Frakes, D. (2017). Extraction of advanced geospatial intelligence (AGI) from commercial synthetic aperture radar imagery. In Algorithms for Synthetic Aperture Radar Imagery XXIV (Vol. 10201). [1020106] SPIE. https://doi.org/10.1117/12.2262359

Extraction of advanced geospatial intelligence (AGI) from commercial synthetic aperture radar imagery. / Kanberoglu, Berkay; Frakes, David.

Algorithms for Synthetic Aperture Radar Imagery XXIV. Vol. 10201 SPIE, 2017. 1020106.

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

Kanberoglu, B & Frakes, D 2017, Extraction of advanced geospatial intelligence (AGI) from commercial synthetic aperture radar imagery. in Algorithms for Synthetic Aperture Radar Imagery XXIV. vol. 10201, 1020106, SPIE, Algorithms for Synthetic Aperture Radar Imagery XXIV 2017, Anaheim, United States, 4/13/17. https://doi.org/10.1117/12.2262359
Kanberoglu B, Frakes D. Extraction of advanced geospatial intelligence (AGI) from commercial synthetic aperture radar imagery. In Algorithms for Synthetic Aperture Radar Imagery XXIV. Vol. 10201. SPIE. 2017. 1020106 https://doi.org/10.1117/12.2262359
Kanberoglu, Berkay ; Frakes, David. / Extraction of advanced geospatial intelligence (AGI) from commercial synthetic aperture radar imagery. Algorithms for Synthetic Aperture Radar Imagery XXIV. Vol. 10201 SPIE, 2017.
@inproceedings{b7d288791a1b4c4eae3dda309b62145e,
title = "Extraction of advanced geospatial intelligence (AGI) from commercial synthetic aperture radar imagery",
abstract = "The extraction of objects from advanced geospatial intelligence (AGI) products based on synthetic aperture radar (SAR) imagery is complicated by a number of factors. For example, accurate detection of temporal changes represented in two-color multiview (2CMV) AGI products can be challenging because of speckle noise susceptibility and false positives that result from small orientation differences between objects imaged at different times. These cases of apparent motion can result in 2CMV detection, but they obviously differ greatly in terms of significance. In investigating the state-of-the-art in SAR image processing, we have found that differentiating between these two general cases is a problem that has not been well addressed. We propose a framework of methods to address these problems. For the detection of the temporal changes while reducing the number of false positives, we propose using adaptive object intensity and area thresholding in conjunction with relaxed brightness optical flow algorithms that track the motion of objects across time in small regions of interest. The proposed framework for distinguishing between actual motion and misregistration can lead to more accurate and meaningful change detection and improve object extraction from a SAR AGI product. Results demonstrate the ability of our techniques to reduce false positives up to 60{\%}.",
keywords = "2CMV, Change detection, Optical flow, SAR, Synthetic aperture radar",
author = "Berkay Kanberoglu and David Frakes",
year = "2017",
doi = "10.1117/12.2262359",
language = "English (US)",
volume = "10201",
booktitle = "Algorithms for Synthetic Aperture Radar Imagery XXIV",
publisher = "SPIE",
address = "United States",

}

TY - GEN

T1 - Extraction of advanced geospatial intelligence (AGI) from commercial synthetic aperture radar imagery

AU - Kanberoglu, Berkay

AU - Frakes, David

PY - 2017

Y1 - 2017

N2 - The extraction of objects from advanced geospatial intelligence (AGI) products based on synthetic aperture radar (SAR) imagery is complicated by a number of factors. For example, accurate detection of temporal changes represented in two-color multiview (2CMV) AGI products can be challenging because of speckle noise susceptibility and false positives that result from small orientation differences between objects imaged at different times. These cases of apparent motion can result in 2CMV detection, but they obviously differ greatly in terms of significance. In investigating the state-of-the-art in SAR image processing, we have found that differentiating between these two general cases is a problem that has not been well addressed. We propose a framework of methods to address these problems. For the detection of the temporal changes while reducing the number of false positives, we propose using adaptive object intensity and area thresholding in conjunction with relaxed brightness optical flow algorithms that track the motion of objects across time in small regions of interest. The proposed framework for distinguishing between actual motion and misregistration can lead to more accurate and meaningful change detection and improve object extraction from a SAR AGI product. Results demonstrate the ability of our techniques to reduce false positives up to 60%.

AB - The extraction of objects from advanced geospatial intelligence (AGI) products based on synthetic aperture radar (SAR) imagery is complicated by a number of factors. For example, accurate detection of temporal changes represented in two-color multiview (2CMV) AGI products can be challenging because of speckle noise susceptibility and false positives that result from small orientation differences between objects imaged at different times. These cases of apparent motion can result in 2CMV detection, but they obviously differ greatly in terms of significance. In investigating the state-of-the-art in SAR image processing, we have found that differentiating between these two general cases is a problem that has not been well addressed. We propose a framework of methods to address these problems. For the detection of the temporal changes while reducing the number of false positives, we propose using adaptive object intensity and area thresholding in conjunction with relaxed brightness optical flow algorithms that track the motion of objects across time in small regions of interest. The proposed framework for distinguishing between actual motion and misregistration can lead to more accurate and meaningful change detection and improve object extraction from a SAR AGI product. Results demonstrate the ability of our techniques to reduce false positives up to 60%.

KW - 2CMV

KW - Change detection

KW - Optical flow

KW - SAR

KW - Synthetic aperture radar

UR - http://www.scopus.com/inward/record.url?scp=85021808367&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021808367&partnerID=8YFLogxK

U2 - 10.1117/12.2262359

DO - 10.1117/12.2262359

M3 - Conference contribution

AN - SCOPUS:85021808367

VL - 10201

BT - Algorithms for Synthetic Aperture Radar Imagery XXIV

PB - SPIE

ER -