Abstract

An infrared target tracking framework is presented that consists of three main parts: mean shift tracking, its tracking performance evaluation, and position correction. The mean shift tracking algorithm, which is a widely used kernel-based method, has been developed for the initial tracking for its efficiency and effectiveness. A performance evaluation module is applied for the online evaluation of its tracking performance with a kernel- based metric to unify the tracking and performance metric within a kernel-based tracking framework. Then the tracking performance evaluation result is input into a controller in which a decision is made whether to trigger a position correction process. The position correction module employs a matching method with a new eigenvalue-based similarity measure computed from a local complexity degree weighted covariance matrix. Experimental results on real-life infrared image sequences are presented to demonstrate the efficacy of the proposed method.

© 2007 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. M. S. Alam, J. Khan, and A. Bal, "Heteroassociative multiple-target tracking by fringe- adjusted joint transform correlation," Appl. Opt. 43, 358-365 (2004).
    [CrossRef] [PubMed]
  2. A. Yilmaz, K. Shafique, and M. Shah, "Target tracking in airborne forward looking infrared imagery," Image Vision Comput. 21, 623-635 (2003).
    [CrossRef]
  3. J. S. Shaik and K. M. Iftekharuddin, "Detection and tracking of rotated and scaled targets by use of Hilbert-wavelet transform," Appl. Opt. 42, 4718-4735 (2003).
    [CrossRef] [PubMed]
  4. A. Bal and M. S. Alam, "Automatic target tracking in FLIR image sequences using intensity variation function and template modeling," IEEE Trans. Instrum. Meas. 54, 1846-1852 (2005).
    [CrossRef]
  5. A. Bal and M. S. Alam, "Automatic target tracking in FLIR image sequences," in Automatic Target Recognition XIV, F. A. Sadjadi eds., Proc. SPIE 5426, 30-36 (2004).
    [CrossRef]
  6. C. Loo and M. S. Alam, "Invariant object tracking using fringe-adjusted joint transform correlator," Opt. Eng. 43, 2175-2183 (2004).
    [CrossRef]
  7. C. Loo and M. S. Alam, "Invariant fringe-adjusted joint transform correlation-based target tracking in FLIR sequences," in Optical Pattern Recognition XV, D. P. Casasent and T. H. Chao, eds., Proc. SPIE 5437, 38-50 (2004).
    [CrossRef]
  8. M. G. S. Bruno, "Mixed-state particle filters for multiaspect target tracking in image sequences," in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing-Proceedings (IEEE, 2003), pp. 165-168.
  9. A. Dawoud, M. S. Alam, A. Bal, and C. Loo, "Target tracking in infrared imagery using weighted composite reference function-based decision fusion," IEEE Trans. Image Process. 15, 404-410 (2006).
    [CrossRef] [PubMed]
  10. A. Bal and M. S. Alam, "Dynamic target tracking with fringe-adjusted joint transform correlation and template matching," Appl. Opt. 43, 4874-4881 (2004).
    [CrossRef] [PubMed]
  11. D. Comaniciu, V. Ramesh, and P. Meer, "Kernel-based object tracking," IEEE Trans. Pattern Anal. Mach. Intell. 25, 564-577 (2003).
    [CrossRef]
  12. D. Comaniciu, V. Ramesh, and P. Meer, "Real-time tracking of non-rigid objects using mean shift," in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE, 2000), pp. 142-149.
  13. R. T. Collins, "Mean-shift blob tracking through scale space," in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE, 2003), pp. 234-240.
  14. D. Comaniciu and P. Meer, "Mean shift: A robust approach toward feature space analysis," IEEE Trans. Pattern Anal. Mach. Intell. 24, 603-619 (2002).
    [CrossRef]
  15. J. G. Ling, E. Q. Liu, H. Y. Liang, and J. Yang, "Kernel-based metric for performance evaluation of video infrared target tracking," Opt. Eng. 45, 0605051-0605053 (2006).
    [CrossRef]
  16. A. Yilmaz, X. Li, and M. Shah, "Contour-based object tracking with occlusion handling in video acquired using mobile cameras," IEEE Trans. Pattern Anal. Mach. Intell. 26, 1531-1536 (2004).
    [CrossRef] [PubMed]
  17. R. Missaoui, M. Sarifuddin, and J. Vaillancourt, "Similarity measures for efficient content-based image retrieval," IEE Proc. Vision Image Signal Process. 152, 875-887 (2005).
    [CrossRef]
  18. Y. K. Lee and W. T. Rhodes, "Invariant pattern recognition using angular signature functions," Appl. Opt. 32, 4372-4377 (1993).
    [CrossRef] [PubMed]
  19. D. M. Tsai and R. H. Yang, "An eigenvalue-based similarity measure and its application in defect detection," Image Vision Comput. 23, 1094-1101 (2005).
    [CrossRef]
  20. K. Briechle and U. D. Hanebeck, "Template matching using fast normalized cross correlation," in Optical Pattern Recognition XII, D. P. Casasent and T. H. Chao, eds., Proc. SPIE 4387, 95-102 (2001).
    [CrossRef]
  21. W. Jie and G. Izidor, "Discrimination, tracking, and recognition of small and fast moving objects," in Automatic Target Recognition XII, F. A. Sadjadi, ed., Proc. SPIE 4726, 253-266 (2002).
  22. E. Polat, M. Yeasin, and R. Sharma, "A 2D/3D model-based object tracking framework," Pattern Recogn. 36, 2127-2141 (2003).
    [CrossRef]

2006 (2)

A. Dawoud, M. S. Alam, A. Bal, and C. Loo, "Target tracking in infrared imagery using weighted composite reference function-based decision fusion," IEEE Trans. Image Process. 15, 404-410 (2006).
[CrossRef] [PubMed]

J. G. Ling, E. Q. Liu, H. Y. Liang, and J. Yang, "Kernel-based metric for performance evaluation of video infrared target tracking," Opt. Eng. 45, 0605051-0605053 (2006).
[CrossRef]

2005 (3)

R. Missaoui, M. Sarifuddin, and J. Vaillancourt, "Similarity measures for efficient content-based image retrieval," IEE Proc. Vision Image Signal Process. 152, 875-887 (2005).
[CrossRef]

D. M. Tsai and R. H. Yang, "An eigenvalue-based similarity measure and its application in defect detection," Image Vision Comput. 23, 1094-1101 (2005).
[CrossRef]

A. Bal and M. S. Alam, "Automatic target tracking in FLIR image sequences using intensity variation function and template modeling," IEEE Trans. Instrum. Meas. 54, 1846-1852 (2005).
[CrossRef]

2004 (6)

A. Bal and M. S. Alam, "Automatic target tracking in FLIR image sequences," in Automatic Target Recognition XIV, F. A. Sadjadi eds., Proc. SPIE 5426, 30-36 (2004).
[CrossRef]

C. Loo and M. S. Alam, "Invariant object tracking using fringe-adjusted joint transform correlator," Opt. Eng. 43, 2175-2183 (2004).
[CrossRef]

C. Loo and M. S. Alam, "Invariant fringe-adjusted joint transform correlation-based target tracking in FLIR sequences," in Optical Pattern Recognition XV, D. P. Casasent and T. H. Chao, eds., Proc. SPIE 5437, 38-50 (2004).
[CrossRef]

A. Bal and M. S. Alam, "Dynamic target tracking with fringe-adjusted joint transform correlation and template matching," Appl. Opt. 43, 4874-4881 (2004).
[CrossRef] [PubMed]

A. Yilmaz, X. Li, and M. Shah, "Contour-based object tracking with occlusion handling in video acquired using mobile cameras," IEEE Trans. Pattern Anal. Mach. Intell. 26, 1531-1536 (2004).
[CrossRef] [PubMed]

M. S. Alam, J. Khan, and A. Bal, "Heteroassociative multiple-target tracking by fringe- adjusted joint transform correlation," Appl. Opt. 43, 358-365 (2004).
[CrossRef] [PubMed]

2003 (4)

A. Yilmaz, K. Shafique, and M. Shah, "Target tracking in airborne forward looking infrared imagery," Image Vision Comput. 21, 623-635 (2003).
[CrossRef]

J. S. Shaik and K. M. Iftekharuddin, "Detection and tracking of rotated and scaled targets by use of Hilbert-wavelet transform," Appl. Opt. 42, 4718-4735 (2003).
[CrossRef] [PubMed]

D. Comaniciu, V. Ramesh, and P. Meer, "Kernel-based object tracking," IEEE Trans. Pattern Anal. Mach. Intell. 25, 564-577 (2003).
[CrossRef]

E. Polat, M. Yeasin, and R. Sharma, "A 2D/3D model-based object tracking framework," Pattern Recogn. 36, 2127-2141 (2003).
[CrossRef]

2002 (2)

W. Jie and G. Izidor, "Discrimination, tracking, and recognition of small and fast moving objects," in Automatic Target Recognition XII, F. A. Sadjadi, ed., Proc. SPIE 4726, 253-266 (2002).

D. Comaniciu and P. Meer, "Mean shift: A robust approach toward feature space analysis," IEEE Trans. Pattern Anal. Mach. Intell. 24, 603-619 (2002).
[CrossRef]

2001 (1)

K. Briechle and U. D. Hanebeck, "Template matching using fast normalized cross correlation," in Optical Pattern Recognition XII, D. P. Casasent and T. H. Chao, eds., Proc. SPIE 4387, 95-102 (2001).
[CrossRef]

1993 (1)

Alam, M. S.

A. Dawoud, M. S. Alam, A. Bal, and C. Loo, "Target tracking in infrared imagery using weighted composite reference function-based decision fusion," IEEE Trans. Image Process. 15, 404-410 (2006).
[CrossRef] [PubMed]

A. Bal and M. S. Alam, "Automatic target tracking in FLIR image sequences using intensity variation function and template modeling," IEEE Trans. Instrum. Meas. 54, 1846-1852 (2005).
[CrossRef]

A. Bal and M. S. Alam, "Automatic target tracking in FLIR image sequences," in Automatic Target Recognition XIV, F. A. Sadjadi eds., Proc. SPIE 5426, 30-36 (2004).
[CrossRef]

C. Loo and M. S. Alam, "Invariant object tracking using fringe-adjusted joint transform correlator," Opt. Eng. 43, 2175-2183 (2004).
[CrossRef]

C. Loo and M. S. Alam, "Invariant fringe-adjusted joint transform correlation-based target tracking in FLIR sequences," in Optical Pattern Recognition XV, D. P. Casasent and T. H. Chao, eds., Proc. SPIE 5437, 38-50 (2004).
[CrossRef]

M. S. Alam, J. Khan, and A. Bal, "Heteroassociative multiple-target tracking by fringe- adjusted joint transform correlation," Appl. Opt. 43, 358-365 (2004).
[CrossRef] [PubMed]

A. Bal and M. S. Alam, "Dynamic target tracking with fringe-adjusted joint transform correlation and template matching," Appl. Opt. 43, 4874-4881 (2004).
[CrossRef] [PubMed]

Bal, A.

A. Dawoud, M. S. Alam, A. Bal, and C. Loo, "Target tracking in infrared imagery using weighted composite reference function-based decision fusion," IEEE Trans. Image Process. 15, 404-410 (2006).
[CrossRef] [PubMed]

A. Bal and M. S. Alam, "Automatic target tracking in FLIR image sequences using intensity variation function and template modeling," IEEE Trans. Instrum. Meas. 54, 1846-1852 (2005).
[CrossRef]

M. S. Alam, J. Khan, and A. Bal, "Heteroassociative multiple-target tracking by fringe- adjusted joint transform correlation," Appl. Opt. 43, 358-365 (2004).
[CrossRef] [PubMed]

A. Bal and M. S. Alam, "Automatic target tracking in FLIR image sequences," in Automatic Target Recognition XIV, F. A. Sadjadi eds., Proc. SPIE 5426, 30-36 (2004).
[CrossRef]

A. Bal and M. S. Alam, "Dynamic target tracking with fringe-adjusted joint transform correlation and template matching," Appl. Opt. 43, 4874-4881 (2004).
[CrossRef] [PubMed]

Briechle, K.

K. Briechle and U. D. Hanebeck, "Template matching using fast normalized cross correlation," in Optical Pattern Recognition XII, D. P. Casasent and T. H. Chao, eds., Proc. SPIE 4387, 95-102 (2001).
[CrossRef]

Bruno, M. G. S.

M. G. S. Bruno, "Mixed-state particle filters for multiaspect target tracking in image sequences," in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing-Proceedings (IEEE, 2003), pp. 165-168.

Collins, R. T.

R. T. Collins, "Mean-shift blob tracking through scale space," in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE, 2003), pp. 234-240.

Comaniciu, D.

D. Comaniciu, V. Ramesh, and P. Meer, "Kernel-based object tracking," IEEE Trans. Pattern Anal. Mach. Intell. 25, 564-577 (2003).
[CrossRef]

D. Comaniciu and P. Meer, "Mean shift: A robust approach toward feature space analysis," IEEE Trans. Pattern Anal. Mach. Intell. 24, 603-619 (2002).
[CrossRef]

D. Comaniciu, V. Ramesh, and P. Meer, "Real-time tracking of non-rigid objects using mean shift," in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE, 2000), pp. 142-149.

Dawoud, A.

A. Dawoud, M. S. Alam, A. Bal, and C. Loo, "Target tracking in infrared imagery using weighted composite reference function-based decision fusion," IEEE Trans. Image Process. 15, 404-410 (2006).
[CrossRef] [PubMed]

Hanebeck, U. D.

K. Briechle and U. D. Hanebeck, "Template matching using fast normalized cross correlation," in Optical Pattern Recognition XII, D. P. Casasent and T. H. Chao, eds., Proc. SPIE 4387, 95-102 (2001).
[CrossRef]

Iftekharuddin, K. M.

Izidor, G.

W. Jie and G. Izidor, "Discrimination, tracking, and recognition of small and fast moving objects," in Automatic Target Recognition XII, F. A. Sadjadi, ed., Proc. SPIE 4726, 253-266 (2002).

Jie, W.

W. Jie and G. Izidor, "Discrimination, tracking, and recognition of small and fast moving objects," in Automatic Target Recognition XII, F. A. Sadjadi, ed., Proc. SPIE 4726, 253-266 (2002).

Khan, J.

Lee, Y. K.

Li, X.

A. Yilmaz, X. Li, and M. Shah, "Contour-based object tracking with occlusion handling in video acquired using mobile cameras," IEEE Trans. Pattern Anal. Mach. Intell. 26, 1531-1536 (2004).
[CrossRef] [PubMed]

Liang, H. Y.

J. G. Ling, E. Q. Liu, H. Y. Liang, and J. Yang, "Kernel-based metric for performance evaluation of video infrared target tracking," Opt. Eng. 45, 0605051-0605053 (2006).
[CrossRef]

Ling, J. G.

J. G. Ling, E. Q. Liu, H. Y. Liang, and J. Yang, "Kernel-based metric for performance evaluation of video infrared target tracking," Opt. Eng. 45, 0605051-0605053 (2006).
[CrossRef]

Liu, E. Q.

J. G. Ling, E. Q. Liu, H. Y. Liang, and J. Yang, "Kernel-based metric for performance evaluation of video infrared target tracking," Opt. Eng. 45, 0605051-0605053 (2006).
[CrossRef]

Loo, C.

A. Dawoud, M. S. Alam, A. Bal, and C. Loo, "Target tracking in infrared imagery using weighted composite reference function-based decision fusion," IEEE Trans. Image Process. 15, 404-410 (2006).
[CrossRef] [PubMed]

C. Loo and M. S. Alam, "Invariant fringe-adjusted joint transform correlation-based target tracking in FLIR sequences," in Optical Pattern Recognition XV, D. P. Casasent and T. H. Chao, eds., Proc. SPIE 5437, 38-50 (2004).
[CrossRef]

C. Loo and M. S. Alam, "Invariant object tracking using fringe-adjusted joint transform correlator," Opt. Eng. 43, 2175-2183 (2004).
[CrossRef]

Meer, P.

D. Comaniciu, V. Ramesh, and P. Meer, "Kernel-based object tracking," IEEE Trans. Pattern Anal. Mach. Intell. 25, 564-577 (2003).
[CrossRef]

D. Comaniciu and P. Meer, "Mean shift: A robust approach toward feature space analysis," IEEE Trans. Pattern Anal. Mach. Intell. 24, 603-619 (2002).
[CrossRef]

D. Comaniciu, V. Ramesh, and P. Meer, "Real-time tracking of non-rigid objects using mean shift," in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE, 2000), pp. 142-149.

Missaoui, R.

R. Missaoui, M. Sarifuddin, and J. Vaillancourt, "Similarity measures for efficient content-based image retrieval," IEE Proc. Vision Image Signal Process. 152, 875-887 (2005).
[CrossRef]

Polat, E.

E. Polat, M. Yeasin, and R. Sharma, "A 2D/3D model-based object tracking framework," Pattern Recogn. 36, 2127-2141 (2003).
[CrossRef]

Ramesh, V.

D. Comaniciu, V. Ramesh, and P. Meer, "Kernel-based object tracking," IEEE Trans. Pattern Anal. Mach. Intell. 25, 564-577 (2003).
[CrossRef]

D. Comaniciu, V. Ramesh, and P. Meer, "Real-time tracking of non-rigid objects using mean shift," in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE, 2000), pp. 142-149.

Rhodes, W. T.

Sarifuddin, M.

R. Missaoui, M. Sarifuddin, and J. Vaillancourt, "Similarity measures for efficient content-based image retrieval," IEE Proc. Vision Image Signal Process. 152, 875-887 (2005).
[CrossRef]

Shafique, K.

A. Yilmaz, K. Shafique, and M. Shah, "Target tracking in airborne forward looking infrared imagery," Image Vision Comput. 21, 623-635 (2003).
[CrossRef]

Shah, M.

A. Yilmaz, X. Li, and M. Shah, "Contour-based object tracking with occlusion handling in video acquired using mobile cameras," IEEE Trans. Pattern Anal. Mach. Intell. 26, 1531-1536 (2004).
[CrossRef] [PubMed]

A. Yilmaz, K. Shafique, and M. Shah, "Target tracking in airborne forward looking infrared imagery," Image Vision Comput. 21, 623-635 (2003).
[CrossRef]

Shaik, J. S.

Sharma, R.

E. Polat, M. Yeasin, and R. Sharma, "A 2D/3D model-based object tracking framework," Pattern Recogn. 36, 2127-2141 (2003).
[CrossRef]

Tsai, D. M.

D. M. Tsai and R. H. Yang, "An eigenvalue-based similarity measure and its application in defect detection," Image Vision Comput. 23, 1094-1101 (2005).
[CrossRef]

Vaillancourt, J.

R. Missaoui, M. Sarifuddin, and J. Vaillancourt, "Similarity measures for efficient content-based image retrieval," IEE Proc. Vision Image Signal Process. 152, 875-887 (2005).
[CrossRef]

Yang, J.

J. G. Ling, E. Q. Liu, H. Y. Liang, and J. Yang, "Kernel-based metric for performance evaluation of video infrared target tracking," Opt. Eng. 45, 0605051-0605053 (2006).
[CrossRef]

Yang, R. H.

D. M. Tsai and R. H. Yang, "An eigenvalue-based similarity measure and its application in defect detection," Image Vision Comput. 23, 1094-1101 (2005).
[CrossRef]

Yeasin, M.

E. Polat, M. Yeasin, and R. Sharma, "A 2D/3D model-based object tracking framework," Pattern Recogn. 36, 2127-2141 (2003).
[CrossRef]

Yilmaz, A.

A. Yilmaz, X. Li, and M. Shah, "Contour-based object tracking with occlusion handling in video acquired using mobile cameras," IEEE Trans. Pattern Anal. Mach. Intell. 26, 1531-1536 (2004).
[CrossRef] [PubMed]

A. Yilmaz, K. Shafique, and M. Shah, "Target tracking in airborne forward looking infrared imagery," Image Vision Comput. 21, 623-635 (2003).
[CrossRef]

Appl. Opt. (4)

IEE Proc. Vision Image Signal Process. (1)

R. Missaoui, M. Sarifuddin, and J. Vaillancourt, "Similarity measures for efficient content-based image retrieval," IEE Proc. Vision Image Signal Process. 152, 875-887 (2005).
[CrossRef]

IEEE Trans. Image Process. (1)

A. Dawoud, M. S. Alam, A. Bal, and C. Loo, "Target tracking in infrared imagery using weighted composite reference function-based decision fusion," IEEE Trans. Image Process. 15, 404-410 (2006).
[CrossRef] [PubMed]

IEEE Trans. Instrum. Meas. (1)

A. Bal and M. S. Alam, "Automatic target tracking in FLIR image sequences using intensity variation function and template modeling," IEEE Trans. Instrum. Meas. 54, 1846-1852 (2005).
[CrossRef]

IEEE Trans. Pattern Anal. Mach. Intell. (3)

D. Comaniciu, V. Ramesh, and P. Meer, "Kernel-based object tracking," IEEE Trans. Pattern Anal. Mach. Intell. 25, 564-577 (2003).
[CrossRef]

D. Comaniciu and P. Meer, "Mean shift: A robust approach toward feature space analysis," IEEE Trans. Pattern Anal. Mach. Intell. 24, 603-619 (2002).
[CrossRef]

A. Yilmaz, X. Li, and M. Shah, "Contour-based object tracking with occlusion handling in video acquired using mobile cameras," IEEE Trans. Pattern Anal. Mach. Intell. 26, 1531-1536 (2004).
[CrossRef] [PubMed]

Image Vision Comput. (2)

D. M. Tsai and R. H. Yang, "An eigenvalue-based similarity measure and its application in defect detection," Image Vision Comput. 23, 1094-1101 (2005).
[CrossRef]

A. Yilmaz, K. Shafique, and M. Shah, "Target tracking in airborne forward looking infrared imagery," Image Vision Comput. 21, 623-635 (2003).
[CrossRef]

Opt. Eng. (2)

J. G. Ling, E. Q. Liu, H. Y. Liang, and J. Yang, "Kernel-based metric for performance evaluation of video infrared target tracking," Opt. Eng. 45, 0605051-0605053 (2006).
[CrossRef]

C. Loo and M. S. Alam, "Invariant object tracking using fringe-adjusted joint transform correlator," Opt. Eng. 43, 2175-2183 (2004).
[CrossRef]

Pattern Recogn. (1)

E. Polat, M. Yeasin, and R. Sharma, "A 2D/3D model-based object tracking framework," Pattern Recogn. 36, 2127-2141 (2003).
[CrossRef]

Proc. SPIE (3)

C. Loo and M. S. Alam, "Invariant fringe-adjusted joint transform correlation-based target tracking in FLIR sequences," in Optical Pattern Recognition XV, D. P. Casasent and T. H. Chao, eds., Proc. SPIE 5437, 38-50 (2004).
[CrossRef]

K. Briechle and U. D. Hanebeck, "Template matching using fast normalized cross correlation," in Optical Pattern Recognition XII, D. P. Casasent and T. H. Chao, eds., Proc. SPIE 4387, 95-102 (2001).
[CrossRef]

A. Bal and M. S. Alam, "Automatic target tracking in FLIR image sequences," in Automatic Target Recognition XIV, F. A. Sadjadi eds., Proc. SPIE 5426, 30-36 (2004).
[CrossRef]

Other (4)

D. Comaniciu, V. Ramesh, and P. Meer, "Real-time tracking of non-rigid objects using mean shift," in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE, 2000), pp. 142-149.

R. T. Collins, "Mean-shift blob tracking through scale space," in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE, 2003), pp. 234-240.

W. Jie and G. Izidor, "Discrimination, tracking, and recognition of small and fast moving objects," in Automatic Target Recognition XII, F. A. Sadjadi, ed., Proc. SPIE 4726, 253-266 (2002).

M. G. S. Bruno, "Mixed-state particle filters for multiaspect target tracking in image sequences," in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing-Proceedings (IEEE, 2003), pp. 165-168.

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 (13)

Fig. 1
Fig. 1

Target tracking algorithm block diagram.

Fig. 2
Fig. 2

Example of the position correction process in which the rectangle shown in the infrared image indicates the located target region or predefined search region: (a) Reference image (target region is 20 × 12 pixels). (b) Target region obtained with mean shift tracking algorithm ( E k = 0.648 ). (c) Predefined search region of the position correction module (the size is 30 × 22 pixels, and the center obtained with mean shift tracking algorithm is indicated by a white cross). (d) Final output of the tracking framework. (e) Correction output plane.

Fig. 3
Fig. 3

Plane-1 sequence and its different located target regions: (a) correct location, E k = 1 ; (b) frame 15, E k = 0.587 ; (c) frame 45, E k = 0.667 ; (d) frame 78, E k = 0.602 .

Fig. 4
Fig. 4

Plane-2 sequence and its different located target regions: (a) frame 1, E k = 0.955 ; (b) frame 15, E k = 0.477 ; (c) frame 45, E k = 0.640 ; (d) frame 56, E k = 0.936 ; (e) frame 75, E k = 0.620 ; (f) frame 81, E k = 0.929 .

Fig. 5
Fig. 5

(Color online) Values of kernel-based metric and cost functions against frame number for Plane-1 sequence.

Fig. 6
Fig. 6

(Color online) Kernel-based metric for the analysis of tracking performance for Plane-2 sequence: (a) values of metric and cost functions against frame number and (b) metric and tracking accuracy as a function of frame number.

Fig. 7
Fig. 7

(Color online) Comparison of tracking accuracy for two plane sequences: (a) Plane-1 sequence and (b) Plane-2 sequence.

Fig. 8
Fig. 8

(Color online) ROC curve analysis for two plane sequences: (a) Plane-1 sequence and (b) Plane-2 sequence.

Fig. 9
Fig. 9

Ship-1 sequence and the tracking results: (a) frame 1, (b) frame 15, (c) frame 35, (d) frame 50, (e) frame 66, (f) frame 80.

Fig. 10
Fig. 10

Ship-2 sequence and the tracking results: (a) frame 5, (b) frame 35, (c) frame 65, (d) frame 95, (e) frame 125, (f) frame 155, (g) frame 185, (h) frame 200.

Fig. 11
Fig. 11

Ship-3 sequence and the tracking results: (a) frame 50, (b) frame 110, (c) frame 150, (d) frame 170, (e) frame 210, (f) frame 230, (g) frame 270, (h) frame 350, (i) frame 400.

Fig. 12
Fig. 12

Ship-4 sequence and the tracking results: (a) frame 1, (b) frame 45, (c) frame 85, (d) frame 125, (e) frame 165, (f) frame 190.

Fig. 13
Fig. 13

Ship-5 sequence and the tracking results: (a) frame 5, (b) frame 25, (c) frame 45, (d) frame 65, (e) frame 85, (f) frame 100.

Equations (35)

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

q u = C i = 1 n k ( | | x i l h | | 2 ) δ [ b ( x i ) u ] ,
K h s , h r ( x ) = C h s 2 h r p k s ( | | x s h s | | 2 ) k r ( | | x r h r | | 2 ) ,
q u = C 1 h s 2 h r p i = 1 n k s ( | | x i l 1 h s | | 2 ) k r ( | | I Q ( x i ) l 2 h r | | 2 ) × δ [ b ( x i ) u ] ,
q = { q u } u = 1 m u = 1 m q u = 1 .
p u = C 2 h s 2 h r p i = 1 n k s ( | | x i l 1 h s | | 2 ) k r ( | | I Q ( x i ) l 2 h r | | 2 ) × δ [ b ( x i ) u ] ,
p = { p u } u = 1 m u = 1 m p u = 1 .
q u > o u exp ( τ ) u = 1 , , m ,
S k = { N N k N if   N N k 0 else ,
p ( u ) = q u , p ( v ) = q v ,
p ( u , v ) = C i = 1 n j = 1 n k s ( | | x i l 1 h s | | 2 ) k s ( | | x i l 1 h s | | 2 ) × k r ( | | I Q ( x i ) l 2 h r | | 2 ) k r ( | | I Q ( x i ) l 2 h r | | 2 ) × δ [ b ( x i ) u ] δ [ b ( x i ) v ] ,
I ( U , V ) = u = 1 m v = 1 m p ( u , v ) log p ( u , v ) p ( u ) p ( v ) .
M k = I ( U , V ) max ( H 1 , H 2 ) ,
H 1 = u = 1 m p ( u ) log p ( u ) , H 2 = v = 1 m p ( v ) log p ( v ) ,
0 M k 1.
E k = c 1 ( α S k + M k + c 2 ) ,
0 E k 1.
E k < ε ,
L ( x , y ) = 1 P W ( I ( x , y ) = I ( x , y ) ) ( x , y ) ( x , y ) | W | 1 ,
( x , y ) W ,
L = 1 X × Y x = 1 X y = 1 Y L ( x , y ) ,
G = ( g 11 g 12 g 21 g 22 ) ,
g 11 = 1 X × Y x = 1 X y = 1 Y L R 2 ( x , y ) R 2 ( x , y ) ( R ¯ ) 2
g 22 = 1 X × Y x = 1 X y = 1 Y L S 2 ( x , y ) S 2 ( x , y ) ( S ¯ ) 2
g 12 = g 21 = 1 X × Y x = 1 X y = 1 Y L R ( x , y ) R ( x , y ) × L S ( x , y ) S ( x , y ) ( R ¯ S ¯ ) ,
R ¯ = 1 X × Y x = 1 X y = 1 Y L R ( x , y ) R ( x , y )
S ¯ = 1 X × Y x = 1 X y = 1 Y L S ( x , y ) S ( x , y ) .
C v ( x , y ) = exp [ a λ ( x , y ) ] ,
C m s n h ( C a + C s + C d ) ,
C p c 3 [ n h ( C a + C m ) + n h C a ] + n h C L n h C a ,
C p c 5 n h C a + 3 n h C m + n h C L .
F = exp { ξ · ( 1 ρ [ q k 1 , p k 1 ] ) } ,
q u , k = A · [ ( 1 F ) q u , k 1 + F · p u , k 1 ] u = 1 , , m ,
TR = T P T P + F N , FAR = F P T P + F P .
L ( u ) = log max ( q u , ζ ) max ( o u , ζ ) u = 1 m ,
f ^ ( i , j ) = { 255 L [ b ( i , j ) ] > υ 0 L [ b ( i , j ) ] υ ,

Metrics