Abstract

Visual correspondence has been a major research topic in the fields of image registration, 3D reconstruction, and object tracking for some decades. However, due to the radiometric variations of images, conventional approaches fail to produce robust matching results. The traditional method of intensity-based mutual information performs very good for global variations between images, however, its performance degrades in the case of local radiometric variations. Monogenic curvature phase information, as an important local feature of the image, has the advantage of being robust against brightness variation. Hence, in this Letter, we propose an approach to compute the visual correspondence by coupling the advantages of mutual information and monogenic curvature phase. Experimental results demonstrate that the proposed approach can work robustly under radiometric variations.

© 2012 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. D. B. Russakoff, C. Tomasi, T. Rohlfing, and C. Mauere, in Proc. of the 8th Euprpeanl Conference on Computer Vision (2004), pp. 596–607.
  2. J. P. W. Pluim, J. A. Maintz, and M. A. Viergever, IEEE Trans. Med. Imaging 19, 809 (2000).
    [CrossRef] [PubMed]
  3. D. Zang and G. Sommer, in Proc. of the International Workshop on Combinatorial Image Analysis (2006), pp. 320–332.
  4. D. Zang and G. Sommer, J. Visual Commun. Image Represent 18, 81 (2007).
    [CrossRef]
  5. M. Felsberg and G. Sommer, IEEE Trans. Signal Process. 49, 3136 (2001).
    [CrossRef]
  6. M. Felsberg and G. Sommer, J. Math. Imaging Vision 21, 5 (2004).
    [CrossRef]
  7. F. Brackx, B. D. Knock, and H. D. Schepper, Int. j. math. math. sci. 1 (2006).
    [CrossRef]
  8. H. Hirschmuller and D. Scharstein, in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (2007), pp. 18–23.
  9. J. Kim, V. Kolmogorov, and R. Zabih, in Proc. of the International Conference on Computer Vision (2003), pp. 1033–1040.
  10. Y. Boykov, O. Veksler, and R. Zabih, IEEE Trans. Pattern Anal. Machine Intell. 23, 1222 (2001).
    [CrossRef]
  11. http://vision.middlebury.edu/stereo/.

2007

D. Zang and G. Sommer, J. Visual Commun. Image Represent 18, 81 (2007).
[CrossRef]

2006

F. Brackx, B. D. Knock, and H. D. Schepper, Int. j. math. math. sci. 1 (2006).
[CrossRef]

2004

M. Felsberg and G. Sommer, J. Math. Imaging Vision 21, 5 (2004).
[CrossRef]

2001

M. Felsberg and G. Sommer, IEEE Trans. Signal Process. 49, 3136 (2001).
[CrossRef]

Y. Boykov, O. Veksler, and R. Zabih, IEEE Trans. Pattern Anal. Machine Intell. 23, 1222 (2001).
[CrossRef]

2000

J. P. W. Pluim, J. A. Maintz, and M. A. Viergever, IEEE Trans. Med. Imaging 19, 809 (2000).
[CrossRef] [PubMed]

Boykov, Y.

Y. Boykov, O. Veksler, and R. Zabih, IEEE Trans. Pattern Anal. Machine Intell. 23, 1222 (2001).
[CrossRef]

Brackx, F.

F. Brackx, B. D. Knock, and H. D. Schepper, Int. j. math. math. sci. 1 (2006).
[CrossRef]

Felsberg, M.

M. Felsberg and G. Sommer, J. Math. Imaging Vision 21, 5 (2004).
[CrossRef]

M. Felsberg and G. Sommer, IEEE Trans. Signal Process. 49, 3136 (2001).
[CrossRef]

Hirschmuller, H.

H. Hirschmuller and D. Scharstein, in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (2007), pp. 18–23.

Kim, J.

J. Kim, V. Kolmogorov, and R. Zabih, in Proc. of the International Conference on Computer Vision (2003), pp. 1033–1040.

Knock, B. D.

F. Brackx, B. D. Knock, and H. D. Schepper, Int. j. math. math. sci. 1 (2006).
[CrossRef]

Kolmogorov, V.

J. Kim, V. Kolmogorov, and R. Zabih, in Proc. of the International Conference on Computer Vision (2003), pp. 1033–1040.

Maintz, J. A.

J. P. W. Pluim, J. A. Maintz, and M. A. Viergever, IEEE Trans. Med. Imaging 19, 809 (2000).
[CrossRef] [PubMed]

Mauere, C.

D. B. Russakoff, C. Tomasi, T. Rohlfing, and C. Mauere, in Proc. of the 8th Euprpeanl Conference on Computer Vision (2004), pp. 596–607.

Pluim, J. P. W.

J. P. W. Pluim, J. A. Maintz, and M. A. Viergever, IEEE Trans. Med. Imaging 19, 809 (2000).
[CrossRef] [PubMed]

Rohlfing, T.

D. B. Russakoff, C. Tomasi, T. Rohlfing, and C. Mauere, in Proc. of the 8th Euprpeanl Conference on Computer Vision (2004), pp. 596–607.

Russakoff, D. B.

D. B. Russakoff, C. Tomasi, T. Rohlfing, and C. Mauere, in Proc. of the 8th Euprpeanl Conference on Computer Vision (2004), pp. 596–607.

Scharstein, D.

H. Hirschmuller and D. Scharstein, in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (2007), pp. 18–23.

Schepper, H. D.

F. Brackx, B. D. Knock, and H. D. Schepper, Int. j. math. math. sci. 1 (2006).
[CrossRef]

Sommer, G.

D. Zang and G. Sommer, J. Visual Commun. Image Represent 18, 81 (2007).
[CrossRef]

M. Felsberg and G. Sommer, J. Math. Imaging Vision 21, 5 (2004).
[CrossRef]

M. Felsberg and G. Sommer, IEEE Trans. Signal Process. 49, 3136 (2001).
[CrossRef]

D. Zang and G. Sommer, in Proc. of the International Workshop on Combinatorial Image Analysis (2006), pp. 320–332.

Tomasi, C.

D. B. Russakoff, C. Tomasi, T. Rohlfing, and C. Mauere, in Proc. of the 8th Euprpeanl Conference on Computer Vision (2004), pp. 596–607.

Veksler, O.

Y. Boykov, O. Veksler, and R. Zabih, IEEE Trans. Pattern Anal. Machine Intell. 23, 1222 (2001).
[CrossRef]

Viergever, M. A.

J. P. W. Pluim, J. A. Maintz, and M. A. Viergever, IEEE Trans. Med. Imaging 19, 809 (2000).
[CrossRef] [PubMed]

Zabih, R.

Y. Boykov, O. Veksler, and R. Zabih, IEEE Trans. Pattern Anal. Machine Intell. 23, 1222 (2001).
[CrossRef]

J. Kim, V. Kolmogorov, and R. Zabih, in Proc. of the International Conference on Computer Vision (2003), pp. 1033–1040.

Zang, D.

D. Zang and G. Sommer, J. Visual Commun. Image Represent 18, 81 (2007).
[CrossRef]

D. Zang and G. Sommer, in Proc. of the International Workshop on Combinatorial Image Analysis (2006), pp. 320–332.

IEEE Trans. Med. Imaging

J. P. W. Pluim, J. A. Maintz, and M. A. Viergever, IEEE Trans. Med. Imaging 19, 809 (2000).
[CrossRef] [PubMed]

IEEE Trans. Pattern Anal. Machine Intell.

Y. Boykov, O. Veksler, and R. Zabih, IEEE Trans. Pattern Anal. Machine Intell. 23, 1222 (2001).
[CrossRef]

IEEE Trans. Signal Process.

M. Felsberg and G. Sommer, IEEE Trans. Signal Process. 49, 3136 (2001).
[CrossRef]

Int. j. math. math. sci.

F. Brackx, B. D. Knock, and H. D. Schepper, Int. j. math. math. sci. 1 (2006).
[CrossRef]

J. Math. Imaging Vision

M. Felsberg and G. Sommer, J. Math. Imaging Vision 21, 5 (2004).
[CrossRef]

J. Visual Commun. Image Represent

D. Zang and G. Sommer, J. Visual Commun. Image Represent 18, 81 (2007).
[CrossRef]

Other

D. B. Russakoff, C. Tomasi, T. Rohlfing, and C. Mauere, in Proc. of the 8th Euprpeanl Conference on Computer Vision (2004), pp. 596–607.

D. Zang and G. Sommer, in Proc. of the International Workshop on Combinatorial Image Analysis (2006), pp. 320–332.

H. Hirschmuller and D. Scharstein, in Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (2007), pp. 18–23.

J. Kim, V. Kolmogorov, and R. Zabih, in Proc. of the International Conference on Computer Vision (2003), pp. 1033–1040.

http://vision.middlebury.edu/stereo/.

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 (3)

Fig. 1
Fig. 1

Top row from left to right: test image and its monogenic curvature amplitude. Second row from left to right: estimated results of the monogenic curvature main orientation and phase.

Fig. 2
Fig. 2

Top row from left to right: two views of Moebius with different camera exposures and illuminations, disparity ground truth. Bottom row: estimated disparity maps from the normalized cross-correlation, intensity-based mutual information, and the proposed approach.

Fig. 3
Fig. 3

Top row from left to right: two views of dolls with different camera exposures and illuminations, disparity ground truth. Bottom row: estimated disparity maps from the normalized cross-correlation, intensity-based mutual information, and the proposed approach.

Tables (2)

Tables Icon

Table 1 Disparity Errors in Unoccluded Areas (%) for Moebius

Tables Icon

Table 2 Disparity Errors in Unoccluded Areas (%) for Dolls

Equations (16)

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

f m c = [ f 1 f 2 f 3 ] T ,
H = [ f x x f x y f x y f y y ] ,
f 1 = f x x f y y f x y 2 .
f 2 = F 1 { F 1 cos 2 α } ,
f 3 = F 1 { F 1 sin 2 α } ,
A = f 1 2 + f 2 2 + f 3 2 ,
θ = 1 2 atan 2 ( f 3 , f 2 ) , θ ( π 2 , π 2 ] ,
Φ = u | u | atan 2 ( | u | , f 1 ) , Φ ( π , π ] ,
E = E data + E smooth ,
PMI ( Φ l , Φ r ) = H ( Φ l ) + H ( Φ r ) H ( Φ l , Φ r ) ,
H ( Φ ) = E Φ [ log ( P ( Φ ) ) ] = ϕ i Ω ϕ log ( P ( Φ = ϕ i ) ) P ( Φ = ϕ i ) ,
H ( Φ l , Φ r ) = E Φ l [ E Φ r [ log ( P ( Φ l , Φ r ) ) ] ] ,
PMI ( Φ l , Φ r ) p p m i ( Φ l ( p ) , Φ r ( p + d p ) ) ,
E data = p p m i ( Φ l ( p ) , Φ r ( p + d p ) ) .
E smooth = p q N ( p ) V p q ( d p , d q ) ,
V p q ( d p , d q ) = λ min ( | d p d q | 2 , V max ) ,

Metrics