Abstract

An automatic target detection system that uses hyperspectral (HS) imagery is proposed. HS images contain both spatial and spectral response information that provides detailed descriptions of an object. These new, to our knowledge, sensor data are useful in automatic target recognition applications. To provide discrimination information from the HS images and to select features that generalize well, we describe a new, to our knowledge, high-dimensional generalized discriminant feature-extraction algorithm and compare its performance with that of other feature-reduction methods for two HS target detection applications (mine and vehicle detection) by using a nearest-neighbor classifier. We also advance an approach to simultaneously optimize both spatial and spectral responses.

© 2004 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. B. Yu, L. Hoff, I. Reed, A. Chen, L. Stotts, “Automatic target detection and recognition in multiband imagery: a unified ML detection and estimation approach,” IEEE Trans. Image Process. 6, 143–156 (1997).
    [CrossRef] [PubMed]
  2. L. Hoff, A. Chen, X. Yu, E. Winter, “Enhanced classification performance from multiband infrared imagery,” in Proceedings of the IEEE Twenty-Ninth Conference on Signals, Systems and Computers (Institute of Electrical and Electronics Engineers, New York, 1995), pp. 837–841.
  3. L. Hoff, J. Zeidler, C. Yerkes, “Adaptive multispectral image processing for the detection of small targets in terrain clutter,” in Signal and Data Processing of Small Targets 1992, O. E. Drummond, ed., Proc. SPIE1698, 100–114 (1992).
    [CrossRef]
  4. A. Jain, R. Ruin, J. Mao, “Statistical pattern recognition: a review,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 4–37 (2000).
    [CrossRef]
  5. E. Baum, D. Haussler, “What size net gives valid generalization?” Neural Comput. 1, 151–160 (1989).
    [CrossRef]
  6. D. Archibald, C. Thai, F. Dowell, “Development of short-wavelength near-infrared spectral imaging for grain color,” in Precision Agriculture and Biological Quality, G. E. Meyer, J. A. DeShazer, eds., Proc. SPIE3543, 189–198 (1999).
    [CrossRef]
  7. F. Dowell, M. Ram, L. Seitz, “Predicting scab, vomitoxin, and ergosterol in single wheat kernels using near-infrared spectroscopy,” Cereal Chem. 76, 573–576 (1999).
    [CrossRef]
  8. F. Dowell, “Detecting vitreous and non-vitreous durum wheat kernels using near-infrared spectroscopy,” in 1999 ASAE Annual International Meeting (American Society of Agricultural Engineers, Toronto, 1999), paper 993082.
  9. A. Adams, D. Herden, “Spectral reflectance of rice seedings,” in Precision Agriculture and Biological Quality, G. E. Meyer, J. A. DeShazer, eds., Proc. SPIE3543, 259–264 (1999).
    [CrossRef]
  10. M. J. Muasher, D. A. Landgrebe, “The K-L expansion as an effective feature ordering techniques for limited training sample size,” IEEE Trans. Geosci. Remote Sens. GE-21, 438–441 (1983).
    [CrossRef]
  11. P. N. Belhumeur, J. P. Hespanha, D. J. Kriegman, “Eigenfaces vs. Fisherfaces: recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 711–720 (1997).
    [CrossRef]
  12. K. Etemad, R. Chellappa, “Discriminant analysis for recognition of human face images,” J. Opt. Soc. Am. A 14, 1724–1733 (1997).
    [CrossRef]
  13. T. Pearson, “Spectral properties and effect of drying temperature on almonds with concealed damage,” Lebensm.-Wiss. Technol. 32, 67–72 (1999).
    [CrossRef]
  14. X. Miao, M. Azimi-Sadjadi, B. Tian, A. Dubey, N. Witherspoon, “Detection of mines and minelike targets using principal component and neural-network methods,” IEEE Trans. Neural Netw. 9, 454–463 (1998).
    [CrossRef]
  15. H. Kwon, S. Der, N. Nasrabadi, H. Moon, “Use of hyperspectral imagery for material classification in outdoor scenes,” in Algorithms, Devices, and Systems for Optical Information Processing III, B. Javidi, D. Psaltis, eds., Proc. SPIE3804, 104–115 (1999).
    [CrossRef]
  16. M. Shirvaikar, M. Trivedi, “A neural network filter to detect small targets in high clutter backgrounds,” IEEE Trans. Neural Netw. 6, 252–257 (1995).
    [CrossRef] [PubMed]
  17. M. Azimi-Sadjadi, X. Miao, “Mine target detection using principal component and neural networks method,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 675–686 (1995).
    [CrossRef]
  18. G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, “Multispectral image feature selection for land mine detection,” IEEE Trans. Geosci. Remote Sens. 38, 304–311 (2000).
    [CrossRef]
  19. G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, D. Fields, R. Sherwood, P. Schaich, “Multispectral image fusion for detecting land mines,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 850–864 (1995).
    [CrossRef]
  20. J. Serra, Images Analysis and Mathematical Morphology (Academic, New York, 1982).
  21. R. Duda, P. Hart, Pattern Classification and Scene Analysis (Wiley, New York, 1973), pp. 115–118.
  22. D. Ballard, C. Brown, Computer Vision (Prentice-Hall, Englewood Cliffs, N.J., 1982), p. 151.
  23. D. P. Casasent, X.-W. Chen, “Feature reduction methods for hyperspectral data,” in Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision, D. P. Casasent, E. L. Hall, eds., Proc. SPIE4572, 1–11 (2001).
    [CrossRef]

2000

A. Jain, R. Ruin, J. Mao, “Statistical pattern recognition: a review,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 4–37 (2000).
[CrossRef]

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, “Multispectral image feature selection for land mine detection,” IEEE Trans. Geosci. Remote Sens. 38, 304–311 (2000).
[CrossRef]

1999

F. Dowell, M. Ram, L. Seitz, “Predicting scab, vomitoxin, and ergosterol in single wheat kernels using near-infrared spectroscopy,” Cereal Chem. 76, 573–576 (1999).
[CrossRef]

T. Pearson, “Spectral properties and effect of drying temperature on almonds with concealed damage,” Lebensm.-Wiss. Technol. 32, 67–72 (1999).
[CrossRef]

1998

X. Miao, M. Azimi-Sadjadi, B. Tian, A. Dubey, N. Witherspoon, “Detection of mines and minelike targets using principal component and neural-network methods,” IEEE Trans. Neural Netw. 9, 454–463 (1998).
[CrossRef]

1997

B. Yu, L. Hoff, I. Reed, A. Chen, L. Stotts, “Automatic target detection and recognition in multiband imagery: a unified ML detection and estimation approach,” IEEE Trans. Image Process. 6, 143–156 (1997).
[CrossRef] [PubMed]

P. N. Belhumeur, J. P. Hespanha, D. J. Kriegman, “Eigenfaces vs. Fisherfaces: recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 711–720 (1997).
[CrossRef]

K. Etemad, R. Chellappa, “Discriminant analysis for recognition of human face images,” J. Opt. Soc. Am. A 14, 1724–1733 (1997).
[CrossRef]

1995

M. Shirvaikar, M. Trivedi, “A neural network filter to detect small targets in high clutter backgrounds,” IEEE Trans. Neural Netw. 6, 252–257 (1995).
[CrossRef] [PubMed]

1989

E. Baum, D. Haussler, “What size net gives valid generalization?” Neural Comput. 1, 151–160 (1989).
[CrossRef]

1983

M. J. Muasher, D. A. Landgrebe, “The K-L expansion as an effective feature ordering techniques for limited training sample size,” IEEE Trans. Geosci. Remote Sens. GE-21, 438–441 (1983).
[CrossRef]

Adams, A.

A. Adams, D. Herden, “Spectral reflectance of rice seedings,” in Precision Agriculture and Biological Quality, G. E. Meyer, J. A. DeShazer, eds., Proc. SPIE3543, 259–264 (1999).
[CrossRef]

Aimonetti, W.

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, “Multispectral image feature selection for land mine detection,” IEEE Trans. Geosci. Remote Sens. 38, 304–311 (2000).
[CrossRef]

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, D. Fields, R. Sherwood, P. Schaich, “Multispectral image fusion for detecting land mines,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 850–864 (1995).
[CrossRef]

Archibald, D.

D. Archibald, C. Thai, F. Dowell, “Development of short-wavelength near-infrared spectral imaging for grain color,” in Precision Agriculture and Biological Quality, G. E. Meyer, J. A. DeShazer, eds., Proc. SPIE3543, 189–198 (1999).
[CrossRef]

Azimi-Sadjadi, M.

X. Miao, M. Azimi-Sadjadi, B. Tian, A. Dubey, N. Witherspoon, “Detection of mines and minelike targets using principal component and neural-network methods,” IEEE Trans. Neural Netw. 9, 454–463 (1998).
[CrossRef]

M. Azimi-Sadjadi, X. Miao, “Mine target detection using principal component and neural networks method,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 675–686 (1995).
[CrossRef]

Ballard, D.

D. Ballard, C. Brown, Computer Vision (Prentice-Hall, Englewood Cliffs, N.J., 1982), p. 151.

Baum, E.

E. Baum, D. Haussler, “What size net gives valid generalization?” Neural Comput. 1, 151–160 (1989).
[CrossRef]

Belhumeur, P. N.

P. N. Belhumeur, J. P. Hespanha, D. J. Kriegman, “Eigenfaces vs. Fisherfaces: recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 711–720 (1997).
[CrossRef]

Brown, C.

D. Ballard, C. Brown, Computer Vision (Prentice-Hall, Englewood Cliffs, N.J., 1982), p. 151.

Casasent, D. P.

D. P. Casasent, X.-W. Chen, “Feature reduction methods for hyperspectral data,” in Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision, D. P. Casasent, E. L. Hall, eds., Proc. SPIE4572, 1–11 (2001).
[CrossRef]

Chellappa, R.

Chen, A.

B. Yu, L. Hoff, I. Reed, A. Chen, L. Stotts, “Automatic target detection and recognition in multiband imagery: a unified ML detection and estimation approach,” IEEE Trans. Image Process. 6, 143–156 (1997).
[CrossRef] [PubMed]

L. Hoff, A. Chen, X. Yu, E. Winter, “Enhanced classification performance from multiband infrared imagery,” in Proceedings of the IEEE Twenty-Ninth Conference on Signals, Systems and Computers (Institute of Electrical and Electronics Engineers, New York, 1995), pp. 837–841.

Chen, X.-W.

D. P. Casasent, X.-W. Chen, “Feature reduction methods for hyperspectral data,” in Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision, D. P. Casasent, E. L. Hall, eds., Proc. SPIE4572, 1–11 (2001).
[CrossRef]

Clark, G.

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, “Multispectral image feature selection for land mine detection,” IEEE Trans. Geosci. Remote Sens. 38, 304–311 (2000).
[CrossRef]

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, D. Fields, R. Sherwood, P. Schaich, “Multispectral image fusion for detecting land mines,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 850–864 (1995).
[CrossRef]

Der, S.

H. Kwon, S. Der, N. Nasrabadi, H. Moon, “Use of hyperspectral imagery for material classification in outdoor scenes,” in Algorithms, Devices, and Systems for Optical Information Processing III, B. Javidi, D. Psaltis, eds., Proc. SPIE3804, 104–115 (1999).
[CrossRef]

Donetti, J.

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, “Multispectral image feature selection for land mine detection,” IEEE Trans. Geosci. Remote Sens. 38, 304–311 (2000).
[CrossRef]

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, D. Fields, R. Sherwood, P. Schaich, “Multispectral image fusion for detecting land mines,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 850–864 (1995).
[CrossRef]

Dowell, F.

F. Dowell, M. Ram, L. Seitz, “Predicting scab, vomitoxin, and ergosterol in single wheat kernels using near-infrared spectroscopy,” Cereal Chem. 76, 573–576 (1999).
[CrossRef]

F. Dowell, “Detecting vitreous and non-vitreous durum wheat kernels using near-infrared spectroscopy,” in 1999 ASAE Annual International Meeting (American Society of Agricultural Engineers, Toronto, 1999), paper 993082.

D. Archibald, C. Thai, F. Dowell, “Development of short-wavelength near-infrared spectral imaging for grain color,” in Precision Agriculture and Biological Quality, G. E. Meyer, J. A. DeShazer, eds., Proc. SPIE3543, 189–198 (1999).
[CrossRef]

Dubey, A.

X. Miao, M. Azimi-Sadjadi, B. Tian, A. Dubey, N. Witherspoon, “Detection of mines and minelike targets using principal component and neural-network methods,” IEEE Trans. Neural Netw. 9, 454–463 (1998).
[CrossRef]

Duda, R.

R. Duda, P. Hart, Pattern Classification and Scene Analysis (Wiley, New York, 1973), pp. 115–118.

Etemad, K.

Fields, D.

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, D. Fields, R. Sherwood, P. Schaich, “Multispectral image fusion for detecting land mines,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 850–864 (1995).
[CrossRef]

Hart, P.

R. Duda, P. Hart, Pattern Classification and Scene Analysis (Wiley, New York, 1973), pp. 115–118.

Haussler, D.

E. Baum, D. Haussler, “What size net gives valid generalization?” Neural Comput. 1, 151–160 (1989).
[CrossRef]

Herden, D.

A. Adams, D. Herden, “Spectral reflectance of rice seedings,” in Precision Agriculture and Biological Quality, G. E. Meyer, J. A. DeShazer, eds., Proc. SPIE3543, 259–264 (1999).
[CrossRef]

Hespanha, J. P.

P. N. Belhumeur, J. P. Hespanha, D. J. Kriegman, “Eigenfaces vs. Fisherfaces: recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 711–720 (1997).
[CrossRef]

Hoff, L.

B. Yu, L. Hoff, I. Reed, A. Chen, L. Stotts, “Automatic target detection and recognition in multiband imagery: a unified ML detection and estimation approach,” IEEE Trans. Image Process. 6, 143–156 (1997).
[CrossRef] [PubMed]

L. Hoff, J. Zeidler, C. Yerkes, “Adaptive multispectral image processing for the detection of small targets in terrain clutter,” in Signal and Data Processing of Small Targets 1992, O. E. Drummond, ed., Proc. SPIE1698, 100–114 (1992).
[CrossRef]

L. Hoff, A. Chen, X. Yu, E. Winter, “Enhanced classification performance from multiband infrared imagery,” in Proceedings of the IEEE Twenty-Ninth Conference on Signals, Systems and Computers (Institute of Electrical and Electronics Engineers, New York, 1995), pp. 837–841.

Jain, A.

A. Jain, R. Ruin, J. Mao, “Statistical pattern recognition: a review,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 4–37 (2000).
[CrossRef]

Kriegman, D. J.

P. N. Belhumeur, J. P. Hespanha, D. J. Kriegman, “Eigenfaces vs. Fisherfaces: recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 711–720 (1997).
[CrossRef]

Kwon, H.

H. Kwon, S. Der, N. Nasrabadi, H. Moon, “Use of hyperspectral imagery for material classification in outdoor scenes,” in Algorithms, Devices, and Systems for Optical Information Processing III, B. Javidi, D. Psaltis, eds., Proc. SPIE3804, 104–115 (1999).
[CrossRef]

Landgrebe, D. A.

M. J. Muasher, D. A. Landgrebe, “The K-L expansion as an effective feature ordering techniques for limited training sample size,” IEEE Trans. Geosci. Remote Sens. GE-21, 438–441 (1983).
[CrossRef]

Mao, J.

A. Jain, R. Ruin, J. Mao, “Statistical pattern recognition: a review,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 4–37 (2000).
[CrossRef]

Miao, X.

X. Miao, M. Azimi-Sadjadi, B. Tian, A. Dubey, N. Witherspoon, “Detection of mines and minelike targets using principal component and neural-network methods,” IEEE Trans. Neural Netw. 9, 454–463 (1998).
[CrossRef]

M. Azimi-Sadjadi, X. Miao, “Mine target detection using principal component and neural networks method,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 675–686 (1995).
[CrossRef]

Moon, H.

H. Kwon, S. Der, N. Nasrabadi, H. Moon, “Use of hyperspectral imagery for material classification in outdoor scenes,” in Algorithms, Devices, and Systems for Optical Information Processing III, B. Javidi, D. Psaltis, eds., Proc. SPIE3804, 104–115 (1999).
[CrossRef]

Muasher, M. J.

M. J. Muasher, D. A. Landgrebe, “The K-L expansion as an effective feature ordering techniques for limited training sample size,” IEEE Trans. Geosci. Remote Sens. GE-21, 438–441 (1983).
[CrossRef]

Nasrabadi, N.

H. Kwon, S. Der, N. Nasrabadi, H. Moon, “Use of hyperspectral imagery for material classification in outdoor scenes,” in Algorithms, Devices, and Systems for Optical Information Processing III, B. Javidi, D. Psaltis, eds., Proc. SPIE3804, 104–115 (1999).
[CrossRef]

Pearson, T.

T. Pearson, “Spectral properties and effect of drying temperature on almonds with concealed damage,” Lebensm.-Wiss. Technol. 32, 67–72 (1999).
[CrossRef]

Ram, M.

F. Dowell, M. Ram, L. Seitz, “Predicting scab, vomitoxin, and ergosterol in single wheat kernels using near-infrared spectroscopy,” Cereal Chem. 76, 573–576 (1999).
[CrossRef]

Reed, I.

B. Yu, L. Hoff, I. Reed, A. Chen, L. Stotts, “Automatic target detection and recognition in multiband imagery: a unified ML detection and estimation approach,” IEEE Trans. Image Process. 6, 143–156 (1997).
[CrossRef] [PubMed]

Roeske, F.

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, “Multispectral image feature selection for land mine detection,” IEEE Trans. Geosci. Remote Sens. 38, 304–311 (2000).
[CrossRef]

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, D. Fields, R. Sherwood, P. Schaich, “Multispectral image fusion for detecting land mines,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 850–864 (1995).
[CrossRef]

Ruin, R.

A. Jain, R. Ruin, J. Mao, “Statistical pattern recognition: a review,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 4–37 (2000).
[CrossRef]

Schaich, P.

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, D. Fields, R. Sherwood, P. Schaich, “Multispectral image fusion for detecting land mines,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 850–864 (1995).
[CrossRef]

Seitz, L.

F. Dowell, M. Ram, L. Seitz, “Predicting scab, vomitoxin, and ergosterol in single wheat kernels using near-infrared spectroscopy,” Cereal Chem. 76, 573–576 (1999).
[CrossRef]

Sengupta, S.

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, “Multispectral image feature selection for land mine detection,” IEEE Trans. Geosci. Remote Sens. 38, 304–311 (2000).
[CrossRef]

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, D. Fields, R. Sherwood, P. Schaich, “Multispectral image fusion for detecting land mines,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 850–864 (1995).
[CrossRef]

Serra, J.

J. Serra, Images Analysis and Mathematical Morphology (Academic, New York, 1982).

Sherwood, R.

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, D. Fields, R. Sherwood, P. Schaich, “Multispectral image fusion for detecting land mines,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 850–864 (1995).
[CrossRef]

Shirvaikar, M.

M. Shirvaikar, M. Trivedi, “A neural network filter to detect small targets in high clutter backgrounds,” IEEE Trans. Neural Netw. 6, 252–257 (1995).
[CrossRef] [PubMed]

Stotts, L.

B. Yu, L. Hoff, I. Reed, A. Chen, L. Stotts, “Automatic target detection and recognition in multiband imagery: a unified ML detection and estimation approach,” IEEE Trans. Image Process. 6, 143–156 (1997).
[CrossRef] [PubMed]

Thai, C.

D. Archibald, C. Thai, F. Dowell, “Development of short-wavelength near-infrared spectral imaging for grain color,” in Precision Agriculture and Biological Quality, G. E. Meyer, J. A. DeShazer, eds., Proc. SPIE3543, 189–198 (1999).
[CrossRef]

Tian, B.

X. Miao, M. Azimi-Sadjadi, B. Tian, A. Dubey, N. Witherspoon, “Detection of mines and minelike targets using principal component and neural-network methods,” IEEE Trans. Neural Netw. 9, 454–463 (1998).
[CrossRef]

Trivedi, M.

M. Shirvaikar, M. Trivedi, “A neural network filter to detect small targets in high clutter backgrounds,” IEEE Trans. Neural Netw. 6, 252–257 (1995).
[CrossRef] [PubMed]

Winter, E.

L. Hoff, A. Chen, X. Yu, E. Winter, “Enhanced classification performance from multiband infrared imagery,” in Proceedings of the IEEE Twenty-Ninth Conference on Signals, Systems and Computers (Institute of Electrical and Electronics Engineers, New York, 1995), pp. 837–841.

Witherspoon, N.

X. Miao, M. Azimi-Sadjadi, B. Tian, A. Dubey, N. Witherspoon, “Detection of mines and minelike targets using principal component and neural-network methods,” IEEE Trans. Neural Netw. 9, 454–463 (1998).
[CrossRef]

Yerkes, C.

L. Hoff, J. Zeidler, C. Yerkes, “Adaptive multispectral image processing for the detection of small targets in terrain clutter,” in Signal and Data Processing of Small Targets 1992, O. E. Drummond, ed., Proc. SPIE1698, 100–114 (1992).
[CrossRef]

Yu, B.

B. Yu, L. Hoff, I. Reed, A. Chen, L. Stotts, “Automatic target detection and recognition in multiband imagery: a unified ML detection and estimation approach,” IEEE Trans. Image Process. 6, 143–156 (1997).
[CrossRef] [PubMed]

Yu, X.

L. Hoff, A. Chen, X. Yu, E. Winter, “Enhanced classification performance from multiband infrared imagery,” in Proceedings of the IEEE Twenty-Ninth Conference on Signals, Systems and Computers (Institute of Electrical and Electronics Engineers, New York, 1995), pp. 837–841.

Zeidler, J.

L. Hoff, J. Zeidler, C. Yerkes, “Adaptive multispectral image processing for the detection of small targets in terrain clutter,” in Signal and Data Processing of Small Targets 1992, O. E. Drummond, ed., Proc. SPIE1698, 100–114 (1992).
[CrossRef]

Cereal Chem.

F. Dowell, M. Ram, L. Seitz, “Predicting scab, vomitoxin, and ergosterol in single wheat kernels using near-infrared spectroscopy,” Cereal Chem. 76, 573–576 (1999).
[CrossRef]

IEEE Trans. Geosci. Remote Sens.

M. J. Muasher, D. A. Landgrebe, “The K-L expansion as an effective feature ordering techniques for limited training sample size,” IEEE Trans. Geosci. Remote Sens. GE-21, 438–441 (1983).
[CrossRef]

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, “Multispectral image feature selection for land mine detection,” IEEE Trans. Geosci. Remote Sens. 38, 304–311 (2000).
[CrossRef]

IEEE Trans. Image Process.

B. Yu, L. Hoff, I. Reed, A. Chen, L. Stotts, “Automatic target detection and recognition in multiband imagery: a unified ML detection and estimation approach,” IEEE Trans. Image Process. 6, 143–156 (1997).
[CrossRef] [PubMed]

IEEE Trans. Neural Netw.

X. Miao, M. Azimi-Sadjadi, B. Tian, A. Dubey, N. Witherspoon, “Detection of mines and minelike targets using principal component and neural-network methods,” IEEE Trans. Neural Netw. 9, 454–463 (1998).
[CrossRef]

M. Shirvaikar, M. Trivedi, “A neural network filter to detect small targets in high clutter backgrounds,” IEEE Trans. Neural Netw. 6, 252–257 (1995).
[CrossRef] [PubMed]

IEEE Trans. Pattern Anal. Mach. Intell.

A. Jain, R. Ruin, J. Mao, “Statistical pattern recognition: a review,” IEEE Trans. Pattern Anal. Mach. Intell. 22, 4–37 (2000).
[CrossRef]

P. N. Belhumeur, J. P. Hespanha, D. J. Kriegman, “Eigenfaces vs. Fisherfaces: recognition using class specific linear projection,” IEEE Trans. Pattern Anal. Mach. Intell. 19, 711–720 (1997).
[CrossRef]

J. Opt. Soc. Am. A

Lebensm.-Wiss. Technol.

T. Pearson, “Spectral properties and effect of drying temperature on almonds with concealed damage,” Lebensm.-Wiss. Technol. 32, 67–72 (1999).
[CrossRef]

Neural Comput.

E. Baum, D. Haussler, “What size net gives valid generalization?” Neural Comput. 1, 151–160 (1989).
[CrossRef]

Other

D. Archibald, C. Thai, F. Dowell, “Development of short-wavelength near-infrared spectral imaging for grain color,” in Precision Agriculture and Biological Quality, G. E. Meyer, J. A. DeShazer, eds., Proc. SPIE3543, 189–198 (1999).
[CrossRef]

L. Hoff, A. Chen, X. Yu, E. Winter, “Enhanced classification performance from multiband infrared imagery,” in Proceedings of the IEEE Twenty-Ninth Conference on Signals, Systems and Computers (Institute of Electrical and Electronics Engineers, New York, 1995), pp. 837–841.

L. Hoff, J. Zeidler, C. Yerkes, “Adaptive multispectral image processing for the detection of small targets in terrain clutter,” in Signal and Data Processing of Small Targets 1992, O. E. Drummond, ed., Proc. SPIE1698, 100–114 (1992).
[CrossRef]

F. Dowell, “Detecting vitreous and non-vitreous durum wheat kernels using near-infrared spectroscopy,” in 1999 ASAE Annual International Meeting (American Society of Agricultural Engineers, Toronto, 1999), paper 993082.

A. Adams, D. Herden, “Spectral reflectance of rice seedings,” in Precision Agriculture and Biological Quality, G. E. Meyer, J. A. DeShazer, eds., Proc. SPIE3543, 259–264 (1999).
[CrossRef]

M. Azimi-Sadjadi, X. Miao, “Mine target detection using principal component and neural networks method,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 675–686 (1995).
[CrossRef]

H. Kwon, S. Der, N. Nasrabadi, H. Moon, “Use of hyperspectral imagery for material classification in outdoor scenes,” in Algorithms, Devices, and Systems for Optical Information Processing III, B. Javidi, D. Psaltis, eds., Proc. SPIE3804, 104–115 (1999).
[CrossRef]

G. Clark, S. Sengupta, W. Aimonetti, F. Roeske, J. Donetti, D. Fields, R. Sherwood, P. Schaich, “Multispectral image fusion for detecting land mines,” in Detection Technologies for Mines and Minelike Targets, A. C. Dubey, I. Cindrich, J. M. Ralston, K. A. Rigano, eds., Proc. SPIE2496, 850–864 (1995).
[CrossRef]

J. Serra, Images Analysis and Mathematical Morphology (Academic, New York, 1982).

R. Duda, P. Hart, Pattern Classification and Scene Analysis (Wiley, New York, 1973), pp. 115–118.

D. Ballard, C. Brown, Computer Vision (Prentice-Hall, Englewood Cliffs, N.J., 1982), p. 151.

D. P. Casasent, X.-W. Chen, “Feature reduction methods for hyperspectral data,” in Intelligent Robots and Computer Vision XX: Algorithms, Techniques, and Active Vision, D. P. Casasent, E. L. Hall, eds., Proc. SPIE4572, 1–11 (2001).
[CrossRef]

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 (14)

Fig. 1
Fig. 1

Block diagram of the automatic target detection system for HS images.

Fig. 2
Fig. 2

Representative training-set images of the HMMWV at (a) 620 nm and (b) 740 nm.

Fig. 3
Fig. 3

Cross-validation results for the PCA algorithm to select the number of PCA features to use for the vehicle database.

Fig. 4
Fig. 4

Cross-validation results for the PCA-LDA algorithm to select the number of PCA features to use for the vehicle database.

Fig. 5
Fig. 5

Cross-validation results for the HDGD algorithm to select the number of HDGD features to use for the vehicle database.

Fig. 6
Fig. 6

Classification result for the HMMWV training scene by use of HDGD features: (a) before postprocessing and (b) final classification outputs.

Fig. 7
Fig. 7

Final classification output on the first APC test scene by use of (a) six PCA features and (b) four HDGD features.

Fig. 8
Fig. 8

Pixel-classification output on the first APC test scene by use of (a) the LDA feature and (b) three PCA features in PCA-LDA.

Fig. 9
Fig. 9

(a) Test scene and (b) its binary pixel-classification output by use of six HDGD features.

Fig. 10
Fig. 10

Images of (a) small clutter, (b) a small mine, (c) a large mine, and (d) large clutter.

Fig. 11
Fig. 11

Binary output by use of one LDA feature: (a) after pixel classification and (b) after blob-colored HMT.

Fig. 12
Fig. 12

Binary output by use of eight PCA features: (a) after pixel classification and (b) after blob-colored HMT.

Fig. 13
Fig. 13

Binary output by use of six PCA-LDA features: (a) after pixel classification and (b) after blob-colored HMT.

Fig. 14
Fig. 14

Binary output by use of six HDGD features: (a) after pixel classification and (b) after blob-colored HMT.

Tables (3)

Tables Icon

Table 1 Pixel Test Results by Use of the LDA, PCA, PCA-LDA, and HDGD Feature-Extraction Algorithms for the Vehicle Database

Tables Icon

Table 2 Test Results for the PCA, LDA, PCA-LDA, and HDGD Feature-Extraction Algorithms on the Mine Test-Set Chips

Tables Icon

Table 3 Results for the PCA, LDA, PCA-LDA, and HDGD Feature-Extraction Algorithms (with Postprocessing) on the Mine Database Training and Test Scenes with 40 Mines in Each Set

Equations (7)

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

J=difference of means of projectionssum of scatter of projections=ϕTRϕϕTCwϕ,
Rϕ=λCwϕ.
ϕ=Cw-1μ1-μ2.
ϕ=i=1nviviTλiμ1-μ2=i=1nviTμ1-μ2λivi.
Ji=|viTμ1-μ2|2/λi+|Δλi|/λi.
A  B=AB Θ B.
AB=A Θ CAc Θ D.

Metrics