Abstract

Data fusion from disparate sensors significantly improves automated man-made target detection performance compared to that of just an individual sensor. In particular, it can solve hyperspectral imagery (HSI) detection problems pertaining to low-radiance man-made objects and objects in shadows. We present an algorithm that fuses HSI and LIDAR data for automated detection of man-made objects. LIDAR is used to define a set of potential targets based on physical dimensions, and HSI is then used to discriminate between man-made and natural objects. The discrimination technique is a novel HSI detection concept that uses an HSI detection score localization metric capable of distinguishing between wide-area score distributions inherent to natural objects and highly localized score distributions indicative of man-made targets. A typical man-made localization score was found to be around 0.5 compared to natural background typical localization scores being less than 0.1.

© 2011 OSA

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. I. S. Reed and X. Yu, “Adaptive Multiple-Band CFAR Detection of an Optical Pattern with Unknown Spectral Distribution,” IEEE Trans. Acoust. Speech Signal Process. 38, 10 (1992).
  2. D. W. J. Stein, S. C. Beaven, L. E. Hoff, E. W. Winter, A. P. Schaum, and A. D. Stocker, “Anomaly detection from hyperspectral imagery,” IEEE Signal Process. Mag. 19(1), 58–69 (2002).
    [CrossRef]
  3. D. Manolakis, “Taxonomy of detection algorithms for hyperspectral imaging applications,” Opt. Eng. 44(6), 066403 (2005).
    [CrossRef]
  4. A. V. Kanaev and J. Murray-Krezan, “Spectral anomaly detection in deep shadows,” Appl. Opt. 49(9), 1614–1622 (2010).
    [CrossRef] [PubMed]
  5. M. A. Kolodner, “Automated target detection system for hyperspectral imaging sensors,” Appl. Opt. 47(28), F61–F70 (2008).
    [CrossRef] [PubMed]
  6. M. S. Foster, J. R. Schott, D. W. Messinger, and R. Raqueno, “Use of Lidar data to geometrically-constrain radiance spaces for physics-based target detection,” Proc. SPIE 6661, 66610J (2007).
    [CrossRef]
  7. D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
    [CrossRef]
  8. M. Dalponte, L. Bruzzone, and D. Gianelle, “Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas,” IEEE Trans. Geosci. Rem. Sens. 46(5), 1416–1427 (2008).
    [CrossRef]
  9. D. Borghys, M. Shimoni, and C. Perneel, “Change detection in urban scenes by fusion of SAR and hyperspectral data,” Proc. SPIE 6749, 67490R (2007).
    [CrossRef]
  10. S. Kraut, L. Scharf, and L. T. McWhorter, “Adaptive sub-space detectors,” IEEE Trans. Signal Process. 49(1), 1–16 (2001).
    [CrossRef]
  11. A. P. Schaum and A. D. Stocker, “Hyperspectral change detection and supervised matched filtering based on Covariance Equalization,” Proc. SPIE 5425, 77–90 (2004).
    [CrossRef]
  12. G. A. F. Seber, Multivariate Observations (John Wiley & Sons Inc., 1984).
  13. MATLAB version R2011a. Natick, MA The MathWorks Inc., 2011.
  14. F. Maes, A. Collignon, D. Vandermeulen, G. Marchal, and P. Suetens, “Multimodality image registration by maximization of mutual information,” IEEE Trans. Med. Imaging 16(2), 187–198 (1997).
    [CrossRef] [PubMed]

2010

A. V. Kanaev and J. Murray-Krezan, “Spectral anomaly detection in deep shadows,” Appl. Opt. 49(9), 1614–1622 (2010).
[CrossRef] [PubMed]

D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
[CrossRef]

2008

M. Dalponte, L. Bruzzone, and D. Gianelle, “Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas,” IEEE Trans. Geosci. Rem. Sens. 46(5), 1416–1427 (2008).
[CrossRef]

M. A. Kolodner, “Automated target detection system for hyperspectral imaging sensors,” Appl. Opt. 47(28), F61–F70 (2008).
[CrossRef] [PubMed]

2007

M. S. Foster, J. R. Schott, D. W. Messinger, and R. Raqueno, “Use of Lidar data to geometrically-constrain radiance spaces for physics-based target detection,” Proc. SPIE 6661, 66610J (2007).
[CrossRef]

D. Borghys, M. Shimoni, and C. Perneel, “Change detection in urban scenes by fusion of SAR and hyperspectral data,” Proc. SPIE 6749, 67490R (2007).
[CrossRef]

2005

D. Manolakis, “Taxonomy of detection algorithms for hyperspectral imaging applications,” Opt. Eng. 44(6), 066403 (2005).
[CrossRef]

2004

A. P. Schaum and A. D. Stocker, “Hyperspectral change detection and supervised matched filtering based on Covariance Equalization,” Proc. SPIE 5425, 77–90 (2004).
[CrossRef]

2002

D. W. J. Stein, S. C. Beaven, L. E. Hoff, E. W. Winter, A. P. Schaum, and A. D. Stocker, “Anomaly detection from hyperspectral imagery,” IEEE Signal Process. Mag. 19(1), 58–69 (2002).
[CrossRef]

2001

S. Kraut, L. Scharf, and L. T. McWhorter, “Adaptive sub-space detectors,” IEEE Trans. Signal Process. 49(1), 1–16 (2001).
[CrossRef]

1997

F. Maes, A. Collignon, D. Vandermeulen, G. Marchal, and P. Suetens, “Multimodality image registration by maximization of mutual information,” IEEE Trans. Med. Imaging 16(2), 187–198 (1997).
[CrossRef] [PubMed]

1992

I. S. Reed and X. Yu, “Adaptive Multiple-Band CFAR Detection of an Optical Pattern with Unknown Spectral Distribution,” IEEE Trans. Acoust. Speech Signal Process. 38, 10 (1992).

Abramovitz, Y.

D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
[CrossRef]

Adar, R.

D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
[CrossRef]

Bar, D. E.

D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
[CrossRef]

Beaven, S. C.

D. W. J. Stein, S. C. Beaven, L. E. Hoff, E. W. Winter, A. P. Schaum, and A. D. Stocker, “Anomaly detection from hyperspectral imagery,” IEEE Signal Process. Mag. 19(1), 58–69 (2002).
[CrossRef]

Ben-Dov, A.

D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
[CrossRef]

Borghys, D.

D. Borghys, M. Shimoni, and C. Perneel, “Change detection in urban scenes by fusion of SAR and hyperspectral data,” Proc. SPIE 6749, 67490R (2007).
[CrossRef]

Bruzzone, L.

M. Dalponte, L. Bruzzone, and D. Gianelle, “Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas,” IEEE Trans. Geosci. Rem. Sens. 46(5), 1416–1427 (2008).
[CrossRef]

Collignon, A.

F. Maes, A. Collignon, D. Vandermeulen, G. Marchal, and P. Suetens, “Multimodality image registration by maximization of mutual information,” IEEE Trans. Med. Imaging 16(2), 187–198 (1997).
[CrossRef] [PubMed]

Dalponte, M.

M. Dalponte, L. Bruzzone, and D. Gianelle, “Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas,” IEEE Trans. Geosci. Rem. Sens. 46(5), 1416–1427 (2008).
[CrossRef]

Figov, Z.

D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
[CrossRef]

Foster, M. S.

M. S. Foster, J. R. Schott, D. W. Messinger, and R. Raqueno, “Use of Lidar data to geometrically-constrain radiance spaces for physics-based target detection,” Proc. SPIE 6661, 66610J (2007).
[CrossRef]

Gianelle, D.

M. Dalponte, L. Bruzzone, and D. Gianelle, “Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas,” IEEE Trans. Geosci. Rem. Sens. 46(5), 1416–1427 (2008).
[CrossRef]

Hoff, L. E.

D. W. J. Stein, S. C. Beaven, L. E. Hoff, E. W. Winter, A. P. Schaum, and A. D. Stocker, “Anomaly detection from hyperspectral imagery,” IEEE Signal Process. Mag. 19(1), 58–69 (2002).
[CrossRef]

Kanaev, A. V.

Kolodner, M. A.

Kraut, S.

S. Kraut, L. Scharf, and L. T. McWhorter, “Adaptive sub-space detectors,” IEEE Trans. Signal Process. 49(1), 1–16 (2001).
[CrossRef]

Maes, F.

F. Maes, A. Collignon, D. Vandermeulen, G. Marchal, and P. Suetens, “Multimodality image registration by maximization of mutual information,” IEEE Trans. Med. Imaging 16(2), 187–198 (1997).
[CrossRef] [PubMed]

Manolakis, D.

D. Manolakis, “Taxonomy of detection algorithms for hyperspectral imaging applications,” Opt. Eng. 44(6), 066403 (2005).
[CrossRef]

Marchal, G.

F. Maes, A. Collignon, D. Vandermeulen, G. Marchal, and P. Suetens, “Multimodality image registration by maximization of mutual information,” IEEE Trans. Med. Imaging 16(2), 187–198 (1997).
[CrossRef] [PubMed]

McWhorter, L. T.

S. Kraut, L. Scharf, and L. T. McWhorter, “Adaptive sub-space detectors,” IEEE Trans. Signal Process. 49(1), 1–16 (2001).
[CrossRef]

Messinger, D. W.

M. S. Foster, J. R. Schott, D. W. Messinger, and R. Raqueno, “Use of Lidar data to geometrically-constrain radiance spaces for physics-based target detection,” Proc. SPIE 6661, 66610J (2007).
[CrossRef]

Michaeli, A.

D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
[CrossRef]

Murray-Krezan, J.

Perneel, C.

D. Borghys, M. Shimoni, and C. Perneel, “Change detection in urban scenes by fusion of SAR and hyperspectral data,” Proc. SPIE 6749, 67490R (2007).
[CrossRef]

Raqueno, R.

M. S. Foster, J. R. Schott, D. W. Messinger, and R. Raqueno, “Use of Lidar data to geometrically-constrain radiance spaces for physics-based target detection,” Proc. SPIE 6661, 66610J (2007).
[CrossRef]

Reed, I. S.

I. S. Reed and X. Yu, “Adaptive Multiple-Band CFAR Detection of an Optical Pattern with Unknown Spectral Distribution,” IEEE Trans. Acoust. Speech Signal Process. 38, 10 (1992).

Scharf, L.

S. Kraut, L. Scharf, and L. T. McWhorter, “Adaptive sub-space detectors,” IEEE Trans. Signal Process. 49(1), 1–16 (2001).
[CrossRef]

Schaum, A. P.

A. P. Schaum and A. D. Stocker, “Hyperspectral change detection and supervised matched filtering based on Covariance Equalization,” Proc. SPIE 5425, 77–90 (2004).
[CrossRef]

D. W. J. Stein, S. C. Beaven, L. E. Hoff, E. W. Winter, A. P. Schaum, and A. D. Stocker, “Anomaly detection from hyperspectral imagery,” IEEE Signal Process. Mag. 19(1), 58–69 (2002).
[CrossRef]

Schott, J. R.

M. S. Foster, J. R. Schott, D. W. Messinger, and R. Raqueno, “Use of Lidar data to geometrically-constrain radiance spaces for physics-based target detection,” Proc. SPIE 6661, 66610J (2007).
[CrossRef]

Shimoni, M.

D. Borghys, M. Shimoni, and C. Perneel, “Change detection in urban scenes by fusion of SAR and hyperspectral data,” Proc. SPIE 6749, 67490R (2007).
[CrossRef]

Stein, D. W. J.

D. W. J. Stein, S. C. Beaven, L. E. Hoff, E. W. Winter, A. P. Schaum, and A. D. Stocker, “Anomaly detection from hyperspectral imagery,” IEEE Signal Process. Mag. 19(1), 58–69 (2002).
[CrossRef]

Stocker, A. D.

A. P. Schaum and A. D. Stocker, “Hyperspectral change detection and supervised matched filtering based on Covariance Equalization,” Proc. SPIE 5425, 77–90 (2004).
[CrossRef]

D. W. J. Stein, S. C. Beaven, L. E. Hoff, E. W. Winter, A. P. Schaum, and A. D. Stocker, “Anomaly detection from hyperspectral imagery,” IEEE Signal Process. Mag. 19(1), 58–69 (2002).
[CrossRef]

Suetens, P.

F. Maes, A. Collignon, D. Vandermeulen, G. Marchal, and P. Suetens, “Multimodality image registration by maximization of mutual information,” IEEE Trans. Med. Imaging 16(2), 187–198 (1997).
[CrossRef] [PubMed]

Swirski, Y.

D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
[CrossRef]

Vandermeulen, D.

F. Maes, A. Collignon, D. Vandermeulen, G. Marchal, and P. Suetens, “Multimodality image registration by maximization of mutual information,” IEEE Trans. Med. Imaging 16(2), 187–198 (1997).
[CrossRef] [PubMed]

Vaynzof, Y.

D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
[CrossRef]

Weizman, L.

D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
[CrossRef]

Winter, E. W.

D. W. J. Stein, S. C. Beaven, L. E. Hoff, E. W. Winter, A. P. Schaum, and A. D. Stocker, “Anomaly detection from hyperspectral imagery,” IEEE Signal Process. Mag. 19(1), 58–69 (2002).
[CrossRef]

Wolowelsky, K.

D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
[CrossRef]

Yaron, O.

D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
[CrossRef]

Yu, X.

I. S. Reed and X. Yu, “Adaptive Multiple-Band CFAR Detection of an Optical Pattern with Unknown Spectral Distribution,” IEEE Trans. Acoust. Speech Signal Process. 38, 10 (1992).

Appl. Opt.

IEEE Sens. J.

D. E. Bar, K. Wolowelsky, Y. Swirski, Z. Figov, A. Michaeli, Y. Vaynzof, Y. Abramovitz, A. Ben-Dov, O. Yaron, L. Weizman, and R. Adar, “Target Detection and Verification via Airborne Hyperspectral and High-Resolution Imagery Processing and Fusion,” IEEE Sens. J. 10(3), 707–711 (2010).
[CrossRef]

IEEE Signal Process. Mag.

D. W. J. Stein, S. C. Beaven, L. E. Hoff, E. W. Winter, A. P. Schaum, and A. D. Stocker, “Anomaly detection from hyperspectral imagery,” IEEE Signal Process. Mag. 19(1), 58–69 (2002).
[CrossRef]

IEEE Trans. Acoust. Speech Signal Process.

I. S. Reed and X. Yu, “Adaptive Multiple-Band CFAR Detection of an Optical Pattern with Unknown Spectral Distribution,” IEEE Trans. Acoust. Speech Signal Process. 38, 10 (1992).

IEEE Trans. Geosci. Rem. Sens.

M. Dalponte, L. Bruzzone, and D. Gianelle, “Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas,” IEEE Trans. Geosci. Rem. Sens. 46(5), 1416–1427 (2008).
[CrossRef]

IEEE Trans. Med. Imaging

F. Maes, A. Collignon, D. Vandermeulen, G. Marchal, and P. Suetens, “Multimodality image registration by maximization of mutual information,” IEEE Trans. Med. Imaging 16(2), 187–198 (1997).
[CrossRef] [PubMed]

IEEE Trans. Signal Process.

S. Kraut, L. Scharf, and L. T. McWhorter, “Adaptive sub-space detectors,” IEEE Trans. Signal Process. 49(1), 1–16 (2001).
[CrossRef]

Opt. Eng.

D. Manolakis, “Taxonomy of detection algorithms for hyperspectral imaging applications,” Opt. Eng. 44(6), 066403 (2005).
[CrossRef]

Proc. SPIE

M. S. Foster, J. R. Schott, D. W. Messinger, and R. Raqueno, “Use of Lidar data to geometrically-constrain radiance spaces for physics-based target detection,” Proc. SPIE 6661, 66610J (2007).
[CrossRef]

A. P. Schaum and A. D. Stocker, “Hyperspectral change detection and supervised matched filtering based on Covariance Equalization,” Proc. SPIE 5425, 77–90 (2004).
[CrossRef]

D. Borghys, M. Shimoni, and C. Perneel, “Change detection in urban scenes by fusion of SAR and hyperspectral data,” Proc. SPIE 6749, 67490R (2007).
[CrossRef]

Other

G. A. F. Seber, Multivariate Observations (John Wiley & Sons Inc., 1984).

MATLAB version R2011a. Natick, MA The MathWorks Inc., 2011.

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (11)

Fig. 1
Fig. 1

Flow chart of HSI_LIDAR fusion algorithm.

Fig. 2
Fig. 2

Georegistered false color RGB representation (red - 1032 nm, green - 1220 nm, and blue - 1570 nm) of HSI cube containing 83 bands (a); georegistered DEM of the same area generated from first return LIDAR data (b).

Fig. 3
Fig. 3

Co-registered HSI cube and DEM.

Fig. 4
Fig. 4

SSRX score with three missed (1-3) and three detected targets (4-6). Three zoomed target areas emphasize missed detections. Glint (white spot) from the second target is not considered as detection.

Fig. 5
Fig. 5

Binary segmented DEM obtained by k-means clustering of entropy filtered images. Twelve objects which satisfy possible physical target dimensions are detected.

Fig. 6
Fig. 6

Example scores obtained by using signatures of two DEM detected objects: a) background elevation signature used in ACE b) target signature used in ACE c) background elevation signature used in MF d) target signature used in MF.

Fig. 7
Fig. 7

ACE and MF score localization values for twelve objects in the scene. 1-6 denote targets and 7-12 denote background elevations.

Fig. 8
Fig. 8

Co-registered HSI cube and DEM. Dark target is outlined by ellipse.

Fig. 9
Fig. 9

SSRX score with a zoomed area showing missed detection of a dark target.

Fig. 10
Fig. 10

Two scores obtained by using signatures of DEM detected objects: a) background elevation signature used in ACE b) dark target signature used in ACE.

Fig. 11
Fig. 11

Score localization values for ten objects in the scene using MF and ACE. 1 - denotes dark target, 2-10 - denote background objects.

Equations (9)

Equations on this page are rendered with MathJax. Learn more.

H 1 :X=Tt+n H 0 :X=Bb.
p B (x)= (2π) J/2 ||C| | 1/2 exp( 1 2 (xμ ) C 1 (xμ) ).
μ= 1 M i=1 M x i C= 1 M i=1 M ( x i μ)( x i μ ) .
Max p T ( x:{t} ) {t} p B (x) > < k ,
(xμ ) C 1 (xμ) > < k .
s(x)=(tμ ) C 1 (xμ) > < k .
s(x)= [(tμ ) C 1 (xμ)] 2 (tμ ) C 1 (tμ)(xμ ) C 1 (xμ) > < k .
I j = kΩ I k log 2 I k ,
L= Ω OBJECT s(x) d 2 x Ω IMAGE s(x) d 2 x ,

Metrics