Abstract

We introduce a method for change detection under nonuniform changes of intensity using an improved least-squares method. A locally adaptive normalizing window is correlated with the two images, and a morphological postprocessing is then applied to isolate objects that have been added or removed from the scene. We use a modification of the least-squares solution to get rid of clutter caused by intensity changes that do not satisfy the model assumed for the least-squares solution.

© 2007 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |

  1. M. Xu, R. Niu, and P. K. Varshney, in International Conference on Image Processing (ICIP '04) (IEEE, 2004), Vol. 4, p. 2595.
  2. C. C. Chang, T. L. Chia, and C. K. Yang, Opt. Eng. 44, 027001 (2005).
    [CrossRef]
  3. E. Durucan and T. Ebrahimi, in European Signal Processing Conference EUSIPCO, 2000 (EUSIPCO-2000), p. 1141.
  4. E. Durucan and T. Ebrahimi, Proc. IEEE 89, 1368 (2001).
    [CrossRef]
  5. P. Rosin, in Sixth International Conference on Computer Vision (IEEE, 1998), p. 274.
  6. L. Li and M. K. H. Leung, IEEE Trans. Image Process. 11, 105 (2002).
  7. D. Toth, T. Aoch, and V. Melzter, in European Signal Processing Conference EUSIPCO, 2000 (EUSIPCO-2000), p. 2081.
  8. T. Aach, A. Kaup, and R. Mester, Signal Process. 31, 165 (1993).
  9. H. H. Arsenault, A. Gherabi, and Pascuala García-Martínez, Proc. SPIE 6312, 1 (2006).
  10. S. Satoh, Y. Idehara, H. Mo, and T. Hamada, in Proceedings of the 2001 Internation Conference on Images Processing (IEEE, 2001), Vol. 2, p. 725.
  11. D. Lefebvre, H. H. Arsenault, P. García-Martínez, and C. Ferreira, Appl. Opt. 41, 6135 (2002).
    [CrossRef] [PubMed]

2006

H. H. Arsenault, A. Gherabi, and Pascuala García-Martínez, Proc. SPIE 6312, 1 (2006).

2005

C. C. Chang, T. L. Chia, and C. K. Yang, Opt. Eng. 44, 027001 (2005).
[CrossRef]

2002

2001

E. Durucan and T. Ebrahimi, Proc. IEEE 89, 1368 (2001).
[CrossRef]

1993

T. Aach, A. Kaup, and R. Mester, Signal Process. 31, 165 (1993).

Appl. Opt.

IEEE Trans. Image Process.

L. Li and M. K. H. Leung, IEEE Trans. Image Process. 11, 105 (2002).

Opt. Eng.

C. C. Chang, T. L. Chia, and C. K. Yang, Opt. Eng. 44, 027001 (2005).
[CrossRef]

Proc. IEEE

E. Durucan and T. Ebrahimi, Proc. IEEE 89, 1368 (2001).
[CrossRef]

Proc. SPIE

H. H. Arsenault, A. Gherabi, and Pascuala García-Martínez, Proc. SPIE 6312, 1 (2006).

Signal Process.

T. Aach, A. Kaup, and R. Mester, Signal Process. 31, 165 (1993).

Other

M. Xu, R. Niu, and P. K. Varshney, in International Conference on Image Processing (ICIP '04) (IEEE, 2004), Vol. 4, p. 2595.

D. Toth, T. Aoch, and V. Melzter, in European Signal Processing Conference EUSIPCO, 2000 (EUSIPCO-2000), p. 2081.

P. Rosin, in Sixth International Conference on Computer Vision (IEEE, 1998), p. 274.

E. Durucan and T. Ebrahimi, in European Signal Processing Conference EUSIPCO, 2000 (EUSIPCO-2000), p. 1141.

S. Satoh, Y. Idehara, H. Mo, and T. Hamada, in Proceedings of the 2001 Internation Conference on Images Processing (IEEE, 2001), Vol. 2, p. 725.

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 (1)

Fig. 1
Fig. 1

Change detection results: (a) initial scene, (b) illuminated scene with a moving object (chair), (c) least-squares method result, and (d) our method after a morphological processing and a thresholding of 0.6.

Equations (5)

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

S 2 ( x , y ) = a S 1 ( x , y ) + b .
σ 2 = σ a 1 = a σ 1 ,
S 1 ( x , y ) σ 1 S 2 ( x , y ) σ 2 = S 1 ( x , y ) σ 1 a S 1 ( x , y ) a σ 1 = 0.
σ 2 ( x , y ) = ( S 2 2 ( x , y ) ( x , y ) ) N ( S 2 ( x , y ) ( x , y ) ) 2 N 2 ,
S ( x , y ) = ( S 1 ( x , y ) σ S 1 σ S 2 S 2 ( x , y ) ) + ( S 2 ( x , y ) σ S 2 σ S 1 S 1 ( x , y ) ) = ( S 1 ( x , y ) σ S 1 σ S 2 S 2 ( x , y ) ) ( 1 σ S 2 σ S 1 ) ,

Metrics