Abstract

Quadratic correlation filters (QCFs) have been used successfully to detect and recognize targets embedded in background clutter. Recently, a QCF called the Rayleigh quotient quadratic correlation filter (RQQCF) was formulated for automatic target recognition (ATR) in IR imagery. Using training images from target and clutter classes, the RQQCF explicitly maximized a class separation metric. What we believe to be a novel approach is presented for ATR that synthesizes the RQQCF using compressed images. The proposed approach considerably reduces the computational complexity and storage requirements while retaining the high recognition accuracy of the original RQQCF technique. The advantages of the proposed scheme are illustrated using sample results obtained from experiments on IR imagery.

© 2007 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |

  1. C. F. Olson and D. P. Huttenlocher, "Automatic target recognition by matching oriented edge pixels," IEEE Trans. Image Process. 6, 103-113 (1997).
    [CrossRef] [PubMed]
  2. C. E. Daniell, D. H. Kemsley, W. P. Lincoln, W. A. Tackett, and G. A. Baraghimian, "Artificial neural networks for automatic target recognition," Opt. Eng. 31, 2521-2531 (1992).
    [CrossRef]
  3. J. A. O'Sullivan, M. D. DeVore, V. Kedia, and M. I. Miller, "SAR ATR performance using a conditionally Gaussian model," IEEE Trans. Aerosp. Electron. Syst. 37, 91-108 (2001).
    [CrossRef]
  4. S. G. Sun, D. M. Kwak, W. B. Jang, and D. J. Kim, "Small target detection using center-surround difference with locally adaptive threshold," in Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, ISPA 2005, September 2005, pp. 402-407.
    [CrossRef] [PubMed]
  5. C. F. Olson, D. P. Huttenlocher, and D. M. Doria, "Recognition by matching with edge location and orientation," in Proceedings of the ARPA Image Understanding Workshop, 1996, pp. 1167-1174.
  6. F. Sadjadi, "Object recognition using coding schemes," Opt. Eng. 31, 2580-2583 (1992).
    [CrossRef]
  7. J. G. Verly, R. L. Delanoy, and D. E. Dudgeon, "Model-based system for automatic target recognition from forward-looking laser-radar imagery," Opt. Eng. 31, 2540-2552 (1992).
    [CrossRef]
  8. B. Bhanu and J. Ahn, "A system for model-based recognition of articulated objects," in Proceedings of the Fourteenth International Conference on Pattern Recognition (IEEE, 1998), Vol. 2, pp. 1812-1815.
    [CrossRef]
  9. S. Z. Der, Q. Zheng, R. Chellappa, B. Redman, and H. Mahmoud, "View based recognition of military vehicles in LADAR imagery using CAD model matching," in Image Recognition and Classification, Algorithms, Systems and Applications, B.Javidi, ed. (Dekker, 2002), pp. 151-187.
  10. J. Starch, R. Sharma, and S. Shaw, "A unified approach to feature extraction for model based ATR," Proc. SPIE 2757, 294-305 (1997).
    [CrossRef]
  11. D. Casasent and R. Shenoy, "Feature space trajectory for distorted object classification and pose estimation in SAR," Opt. Eng. 36, 2719-2728 (1997).
    [CrossRef]
  12. D. P. Kottke, J. Fwu, and K. Brown, "Hidden Markov modelling for automatic target recognition," presented at The Conference Record of the Thirty-First Asilomar Conference on Signals, Systems, and Computers, 2-5 Nov. 1997 Vol. 1, pp. 859-863.
  13. S. A. Rizvi and N. M. Nasrabadi, "Automatic target recognition of cluttered FLIR imagery using multistage feature extraction and feature repair," Proc. SPIE 5015, 1-10 (2003).
    [CrossRef]
  14. L. A. Chan, S. Z. Der, and N. M. Nasrabadi, "Neural based target detectors for multi-band infrared imagery," in Image Recognition and Classification, Algorithms, Systems and Applications, B.Javidi, ed. (Dekker, 2002), pp. 1-36.
  15. D. Torreiri, "A linear transform that simplifies and improves neural network classifiers," in Proceedings of International Conference on Neural Networks, 1996, Vol. 3, pp. 1738-1743.
  16. J. H. Friedman, "Greedy function approximation: a gradient boosting machine," Ann. Stat. 29, 1189-1232 (2001).
  17. H. Drucker, C. J. C. Burges, L. Kaufman, A. Smola, and V. Vapnik, "Support vector regression machines," Adv. Neural Inf. Process. Syst. 9, 155-161 (1997).
  18. H. C. Chiang, R. L. Moses, and W. W. Irving, "Performance estimation of model-based automatic target recognition using attributed scattering center features," in Proceedings of the International Conference on Image Analysis and Processing (IEEE, 1999), pp. 303-308.
    [CrossRef]
  19. S. A. Rizvi and N. M. Nasrabadi, "Fusion techniques for automatic target recognition," Presented at The 32nd Applied Imagery Pattern Recognition Workshop (AIPR'03), 2003, pp. 27-32.
  20. D. Casasent and Y. C. Wang, "Automatic target recognition using new support vector machine," in Proceedings of the 2005 IEEE International Joint Conference on Neural Networks (IJCNN, 2005), Vol. 1, pp. 84-89.
    [CrossRef]
  21. R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2nd ed. (Wiley-Interscience, 2000).
  22. B. V. K. Vijaya Kumar, "Tutorial survey of composite filter designs for optical correlators," Appl. Opt. 31, 4773-4801 (1992).
    [CrossRef] [PubMed]
  23. A. Mahalanobis, B. V. K. Vijaya Kumar, S. R. F. Sims, and J. Epperson, "Unconstrained correlation filters," Appl. Opt. 33, 3751-3759 (1994).
    [CrossRef] [PubMed]
  24. X. Huo, M. Elad, A. G. Flesia, R. R. Muise, S. R. Stanfill, J. Friedman, B. Popescu, J. Chen, A. Mahalanobis, and D. L. Donoho, "Optimal reduced-rank quadratic classifiers using the Fukunaga-Koontz transform with applications to automated target recognition," Proc. SPIE 5094, 59-72 (2003).
    [CrossRef]
  25. S. R. F. Sims and A. Mahalanobis, "Performance evaluation of quadratic correlation filters for target detection and discrimination in infrared imagery," Opt. Eng. 43, 1705-1711 (2004).
    [CrossRef]
  26. A. Mahalanobis, R. R. Muise, and S. R. Stanfill, "Quadratic correlation filter design methodology for target detection and surveillance applications," Appl. Opt. 43, 5198-5205 (2004).
    [CrossRef] [PubMed]
  27. R. Muise, A. Mahalanobis, R. Mohapatra, X. Li, D. Han, and W. Mikhael, "Constrained quadratic correlation filters for target detection," Appl. Opt. 43, 304-314 (2004).
    [CrossRef] [PubMed]
  28. K. R. Rao and P. Yip, Discrete Cosine Transform: Algorithms, Advantages, Applications (Academic, 1990).
  29. E. Feig and S. Winograd, "On the multiplicative complexity of discrete cosine transforms," IEEE Trans. Inf. Theory 38, 1387-1391 (1992).
    [CrossRef]
  30. H. R. Wu and Z. Man, "Comments on fast algorithms and implementation of 2D discrete cosine transform," IEEE Trans. Circuits Syst. Video Technol. 8, 128-129 (1998).
    [CrossRef]
  31. C. Chen, B. Liu, and J. Yang, "Direct recursive structures for computing radix-r two-dimensional DCT/IDCT/DST/IDST," IEEE Trans. Circuits Syst. 51, 2017-2030 (2004).
    [CrossRef]

2004 (4)

S. R. F. Sims and A. Mahalanobis, "Performance evaluation of quadratic correlation filters for target detection and discrimination in infrared imagery," Opt. Eng. 43, 1705-1711 (2004).
[CrossRef]

C. Chen, B. Liu, and J. Yang, "Direct recursive structures for computing radix-r two-dimensional DCT/IDCT/DST/IDST," IEEE Trans. Circuits Syst. 51, 2017-2030 (2004).
[CrossRef]

R. Muise, A. Mahalanobis, R. Mohapatra, X. Li, D. Han, and W. Mikhael, "Constrained quadratic correlation filters for target detection," Appl. Opt. 43, 304-314 (2004).
[CrossRef] [PubMed]

A. Mahalanobis, R. R. Muise, and S. R. Stanfill, "Quadratic correlation filter design methodology for target detection and surveillance applications," Appl. Opt. 43, 5198-5205 (2004).
[CrossRef] [PubMed]

2003 (2)

X. Huo, M. Elad, A. G. Flesia, R. R. Muise, S. R. Stanfill, J. Friedman, B. Popescu, J. Chen, A. Mahalanobis, and D. L. Donoho, "Optimal reduced-rank quadratic classifiers using the Fukunaga-Koontz transform with applications to automated target recognition," Proc. SPIE 5094, 59-72 (2003).
[CrossRef]

S. A. Rizvi and N. M. Nasrabadi, "Automatic target recognition of cluttered FLIR imagery using multistage feature extraction and feature repair," Proc. SPIE 5015, 1-10 (2003).
[CrossRef]

2001 (1)

J. A. O'Sullivan, M. D. DeVore, V. Kedia, and M. I. Miller, "SAR ATR performance using a conditionally Gaussian model," IEEE Trans. Aerosp. Electron. Syst. 37, 91-108 (2001).
[CrossRef]

1998 (1)

H. R. Wu and Z. Man, "Comments on fast algorithms and implementation of 2D discrete cosine transform," IEEE Trans. Circuits Syst. Video Technol. 8, 128-129 (1998).
[CrossRef]

1997 (4)

C. F. Olson and D. P. Huttenlocher, "Automatic target recognition by matching oriented edge pixels," IEEE Trans. Image Process. 6, 103-113 (1997).
[CrossRef] [PubMed]

H. Drucker, C. J. C. Burges, L. Kaufman, A. Smola, and V. Vapnik, "Support vector regression machines," Adv. Neural Inf. Process. Syst. 9, 155-161 (1997).

J. Starch, R. Sharma, and S. Shaw, "A unified approach to feature extraction for model based ATR," Proc. SPIE 2757, 294-305 (1997).
[CrossRef]

D. Casasent and R. Shenoy, "Feature space trajectory for distorted object classification and pose estimation in SAR," Opt. Eng. 36, 2719-2728 (1997).
[CrossRef]

1994 (1)

1992 (5)

C. E. Daniell, D. H. Kemsley, W. P. Lincoln, W. A. Tackett, and G. A. Baraghimian, "Artificial neural networks for automatic target recognition," Opt. Eng. 31, 2521-2531 (1992).
[CrossRef]

F. Sadjadi, "Object recognition using coding schemes," Opt. Eng. 31, 2580-2583 (1992).
[CrossRef]

J. G. Verly, R. L. Delanoy, and D. E. Dudgeon, "Model-based system for automatic target recognition from forward-looking laser-radar imagery," Opt. Eng. 31, 2540-2552 (1992).
[CrossRef]

E. Feig and S. Winograd, "On the multiplicative complexity of discrete cosine transforms," IEEE Trans. Inf. Theory 38, 1387-1391 (1992).
[CrossRef]

B. V. K. Vijaya Kumar, "Tutorial survey of composite filter designs for optical correlators," Appl. Opt. 31, 4773-4801 (1992).
[CrossRef] [PubMed]

Adv. Neural Inf. Process. Syst. (1)

H. Drucker, C. J. C. Burges, L. Kaufman, A. Smola, and V. Vapnik, "Support vector regression machines," Adv. Neural Inf. Process. Syst. 9, 155-161 (1997).

Ann. Stat. (1)

J. H. Friedman, "Greedy function approximation: a gradient boosting machine," Ann. Stat. 29, 1189-1232 (2001).

Appl. Opt. (4)

IEEE Trans. Aerosp. Electron. Syst. (1)

J. A. O'Sullivan, M. D. DeVore, V. Kedia, and M. I. Miller, "SAR ATR performance using a conditionally Gaussian model," IEEE Trans. Aerosp. Electron. Syst. 37, 91-108 (2001).
[CrossRef]

IEEE Trans. Circuits Syst. (1)

C. Chen, B. Liu, and J. Yang, "Direct recursive structures for computing radix-r two-dimensional DCT/IDCT/DST/IDST," IEEE Trans. Circuits Syst. 51, 2017-2030 (2004).
[CrossRef]

IEEE Trans. Circuits Syst. Video Technol. (1)

H. R. Wu and Z. Man, "Comments on fast algorithms and implementation of 2D discrete cosine transform," IEEE Trans. Circuits Syst. Video Technol. 8, 128-129 (1998).
[CrossRef]

IEEE Trans. Image Process. (1)

C. F. Olson and D. P. Huttenlocher, "Automatic target recognition by matching oriented edge pixels," IEEE Trans. Image Process. 6, 103-113 (1997).
[CrossRef] [PubMed]

IEEE Trans. Inf. Theory (1)

E. Feig and S. Winograd, "On the multiplicative complexity of discrete cosine transforms," IEEE Trans. Inf. Theory 38, 1387-1391 (1992).
[CrossRef]

Opt. Eng. (5)

S. R. F. Sims and A. Mahalanobis, "Performance evaluation of quadratic correlation filters for target detection and discrimination in infrared imagery," Opt. Eng. 43, 1705-1711 (2004).
[CrossRef]

C. E. Daniell, D. H. Kemsley, W. P. Lincoln, W. A. Tackett, and G. A. Baraghimian, "Artificial neural networks for automatic target recognition," Opt. Eng. 31, 2521-2531 (1992).
[CrossRef]

F. Sadjadi, "Object recognition using coding schemes," Opt. Eng. 31, 2580-2583 (1992).
[CrossRef]

J. G. Verly, R. L. Delanoy, and D. E. Dudgeon, "Model-based system for automatic target recognition from forward-looking laser-radar imagery," Opt. Eng. 31, 2540-2552 (1992).
[CrossRef]

D. Casasent and R. Shenoy, "Feature space trajectory for distorted object classification and pose estimation in SAR," Opt. Eng. 36, 2719-2728 (1997).
[CrossRef]

Proc. SPIE (3)

S. A. Rizvi and N. M. Nasrabadi, "Automatic target recognition of cluttered FLIR imagery using multistage feature extraction and feature repair," Proc. SPIE 5015, 1-10 (2003).
[CrossRef]

X. Huo, M. Elad, A. G. Flesia, R. R. Muise, S. R. Stanfill, J. Friedman, B. Popescu, J. Chen, A. Mahalanobis, and D. L. Donoho, "Optimal reduced-rank quadratic classifiers using the Fukunaga-Koontz transform with applications to automated target recognition," Proc. SPIE 5094, 59-72 (2003).
[CrossRef]

J. Starch, R. Sharma, and S. Shaw, "A unified approach to feature extraction for model based ATR," Proc. SPIE 2757, 294-305 (1997).
[CrossRef]

Other (12)

L. A. Chan, S. Z. Der, and N. M. Nasrabadi, "Neural based target detectors for multi-band infrared imagery," in Image Recognition and Classification, Algorithms, Systems and Applications, B.Javidi, ed. (Dekker, 2002), pp. 1-36.

D. Torreiri, "A linear transform that simplifies and improves neural network classifiers," in Proceedings of International Conference on Neural Networks, 1996, Vol. 3, pp. 1738-1743.

D. P. Kottke, J. Fwu, and K. Brown, "Hidden Markov modelling for automatic target recognition," presented at The Conference Record of the Thirty-First Asilomar Conference on Signals, Systems, and Computers, 2-5 Nov. 1997 Vol. 1, pp. 859-863.

H. C. Chiang, R. L. Moses, and W. W. Irving, "Performance estimation of model-based automatic target recognition using attributed scattering center features," in Proceedings of the International Conference on Image Analysis and Processing (IEEE, 1999), pp. 303-308.
[CrossRef]

S. A. Rizvi and N. M. Nasrabadi, "Fusion techniques for automatic target recognition," Presented at The 32nd Applied Imagery Pattern Recognition Workshop (AIPR'03), 2003, pp. 27-32.

D. Casasent and Y. C. Wang, "Automatic target recognition using new support vector machine," in Proceedings of the 2005 IEEE International Joint Conference on Neural Networks (IJCNN, 2005), Vol. 1, pp. 84-89.
[CrossRef]

R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2nd ed. (Wiley-Interscience, 2000).

K. R. Rao and P. Yip, Discrete Cosine Transform: Algorithms, Advantages, Applications (Academic, 1990).

B. Bhanu and J. Ahn, "A system for model-based recognition of articulated objects," in Proceedings of the Fourteenth International Conference on Pattern Recognition (IEEE, 1998), Vol. 2, pp. 1812-1815.
[CrossRef]

S. Z. Der, Q. Zheng, R. Chellappa, B. Redman, and H. Mahmoud, "View based recognition of military vehicles in LADAR imagery using CAD model matching," in Image Recognition and Classification, Algorithms, Systems and Applications, B.Javidi, ed. (Dekker, 2002), pp. 151-187.

S. G. Sun, D. M. Kwak, W. B. Jang, and D. J. Kim, "Small target detection using center-surround difference with locally adaptive threshold," in Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, ISPA 2005, September 2005, pp. 402-407.
[CrossRef] [PubMed]

C. F. Olson, D. P. Huttenlocher, and D. M. Doria, "Recognition by matching with edge location and orientation," in Proceedings of the ARPA Image Understanding Workshop, 1996, pp. 1167-1174.

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

Sample frames from (a) Video 1, (b) Video 2, (c) Video 3, and (d) Video 4.

Fig. 2
Fig. 2

VIDEO 1. (a) DCT coefficients obtained by converting a 2D target chip into a 1D vector before applying the 1D DCT, (b) DCT coefficients obtained by first transforming the chip using the 2D DCT and then converting it to a 1D vector.

Fig. 3
Fig. 3

VIDEO 1. (a) DCT coefficients obtained by converting a 2D clutter chip into a 1D vector before applying the 1D DCT, (b) DCT coefficients obtained by first transforming the chip using the 2D DCT and then converting to a 1D vector.

Fig. 4
Fig. 4

Distribution of eigenvalues in (a) spatial domain RQQCF method, (b) TDRQQCF method for chips compressed to 8 × 8 .

Fig. 5
Fig. 5

VIDEO 1. Response of (a) representative target vector and (b) representative clutter vector, versus the index of the dominant eigenvectors (spatial domain).

Fig. 6
Fig. 6

VIDEO 1. Response of (a) representative target vector and (b) representative clutter vector, versus the index of the dominant eigenvectors derived from the truncated chips ( 8 × 8 ) in the DCT domain.

Fig. 7
Fig. 7

VIDEO 2. Response of (a) representative target vector and (b) representative clutter vector, versus the index of the dominant eigenvectors (spatial domain).

Fig. 8
Fig. 8

VIDEO 2. Response of (a) representative target vector, and (b) representative clutter vector, versus the index of the dominant eigenvectors derived from the truncated chips ( 8 × 8 ) in the DCT domain.

Fig. 9
Fig. 9

VIDEO 3. Response of (a) representative target vector and (b) representative clutter vector, versus the index of the dominant eigenvectors (spatial domain).

Fig. 10
Fig. 10

VIDEO 3. Response of (a) representative target vector and (b) representative clutter vector, versus the index of the dominant eigenvectors derived from the truncated chips ( 8 × 8 ) in the DCT domain.

Fig. 11
Fig. 11

VIDEO 4. Response of (a) representative target vector and (b) representative clutter vector, versus the index of the dominant eigenvectors (spatial domain).

Fig. 12
Fig. 12

VIDEO 4. Response of (a) representative target vector and (b) representative clutter vector, versus the index of the dominant eigenvectors derived from the truncated chips ( 8 × 8 ) in the DCT domain.

Fig. 13
Fig. 13

Misclassified target chip form VIDEO 4.

Fig. 14
Fig. 14

Sample representative target chip form VIDEO 4.

Tables (7)

Tables Icon

Table 1 Number of Frames and Number of Target and Clutter Chips, M , for Each Video

Tables Icon

Table 2 VIDEO 1: Average Energy in Different Transformed and Truncated Matrices of the Target and Clutter Sets

Tables Icon

Table 3 VIDEO 2: Average Energy in Different Transformed and Truncated Matrices of the Target and Clutter Sets

Tables Icon

Table 4 VIDEO 3: Average Energy in Different Transformed and Truncated Matrices of the Target and Clutter Sets

Tables Icon

Table 5 VIDEO 4: Average Energy in Different Transformed and Truncated Matrices of the Target and Clutter Sets

Tables Icon

Table 6 Recognition Accuracy of the Spatial Domain RQQCF and the TDRQQCF for All Four Videos

Tables Icon

Table 7 Storage and Computational Complexity of the Spatial Domain RQQCF Versus that for the TDRQQCF a

Equations (7)

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

T = i = 1 n w i w i T ¯ ,
φ = u ¯ T T u ¯ .
J ( w ¯ ) = E 1 { φ } E 2 { φ } E 1 { φ } + E 2 { φ } = i = 1 n w i ¯ ( R x R y ) w i T ¯ i = 1 n w i ¯ ( R x + R y ) w i T ¯ ,
( R x + R y ) 1 ( R x R y ) w i ¯ = λ i w i ¯ .
A = ( R x + R y ) 1 ( R x R y ) ,
B p q = α p α q m = 0 M 1 n = 0 N 1 A m n cos π ( 2 m + 1 ) p 2 M cos π ( 2 n + 1 ) q 2 N ,
0 p M 1 , 0 q N 1 ,

Metrics