Abstract

A multiscale method based on local-color-phase congruency in the color monogenic signal framework is proposed to match feature points and estimate disparity maps for stereo images. As the monogenic signal is the extension of the analytic signal to gray-level images using the Dirac operator and the Laplace equation, the scale-space color monogenic signal is the extension of the monogenic signal to color images based on Clifford algebras. The local color phase, which is estimated by computing the geometric product between the color monogenic signal and a unit reference vector in red–green–blue color space, contains the color and geometric structure information and is robust against noise and brightness change. Experimental results on synthetic and natural stereo images show the performance of the proposed approach.

© 2010 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. J. Vince, in Geometric Algebra for Computer Graphics (Springer, 2008), pp. 79–124.
    [CrossRef]
  2. G. Demarcq, L. Mascarilla, and P. Courtellemont, in IEEE International Conference on Image Processing (ICIP) (2009), pp. 481–484.
    [CrossRef]
  3. M. Felsberg and G. Sommer, IEEE Trans. Signal Process. 49, 3136 (2001).
    [CrossRef]
  4. J. Li, H. Zhao, X. Zhou, and C. Shi, Opt. Lett. 34, 3514 (2009).
    [CrossRef] [PubMed]
  5. J. Li, H. Zhao, Q. Fu, and K. Jiang, Opt. Lett. 35, 1049 (2010).
    [CrossRef] [PubMed]
  6. H. Bay, A. Ess, T. Tuytelaars, and L. V. Gool, Comput. Vision Image Underst. 110, 346 (2008).
    [CrossRef]
  7. F. Yasutaka and P. Jean, in IEEE Conference on Computer Vision and Pattern Recognition (2007), pp. 2118–2125.

2010 (1)

2009 (2)

J. Li, H. Zhao, X. Zhou, and C. Shi, Opt. Lett. 34, 3514 (2009).
[CrossRef] [PubMed]

G. Demarcq, L. Mascarilla, and P. Courtellemont, in IEEE International Conference on Image Processing (ICIP) (2009), pp. 481–484.
[CrossRef]

2008 (2)

H. Bay, A. Ess, T. Tuytelaars, and L. V. Gool, Comput. Vision Image Underst. 110, 346 (2008).
[CrossRef]

J. Vince, in Geometric Algebra for Computer Graphics (Springer, 2008), pp. 79–124.
[CrossRef]

2007 (1)

F. Yasutaka and P. Jean, in IEEE Conference on Computer Vision and Pattern Recognition (2007), pp. 2118–2125.

2001 (1)

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

Bay, H.

H. Bay, A. Ess, T. Tuytelaars, and L. V. Gool, Comput. Vision Image Underst. 110, 346 (2008).
[CrossRef]

Courtellemont, P.

G. Demarcq, L. Mascarilla, and P. Courtellemont, in IEEE International Conference on Image Processing (ICIP) (2009), pp. 481–484.
[CrossRef]

Demarcq, G.

G. Demarcq, L. Mascarilla, and P. Courtellemont, in IEEE International Conference on Image Processing (ICIP) (2009), pp. 481–484.
[CrossRef]

Ess, A.

H. Bay, A. Ess, T. Tuytelaars, and L. V. Gool, Comput. Vision Image Underst. 110, 346 (2008).
[CrossRef]

Felsberg, M.

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

Fu, Q.

Gool, L. V.

H. Bay, A. Ess, T. Tuytelaars, and L. V. Gool, Comput. Vision Image Underst. 110, 346 (2008).
[CrossRef]

Jean, P.

F. Yasutaka and P. Jean, in IEEE Conference on Computer Vision and Pattern Recognition (2007), pp. 2118–2125.

Jiang, K.

Li, J.

Mascarilla, L.

G. Demarcq, L. Mascarilla, and P. Courtellemont, in IEEE International Conference on Image Processing (ICIP) (2009), pp. 481–484.
[CrossRef]

Shi, C.

Sommer, G.

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

Tuytelaars, T.

H. Bay, A. Ess, T. Tuytelaars, and L. V. Gool, Comput. Vision Image Underst. 110, 346 (2008).
[CrossRef]

Vince, J.

J. Vince, in Geometric Algebra for Computer Graphics (Springer, 2008), pp. 79–124.
[CrossRef]

Yasutaka, F.

F. Yasutaka and P. Jean, in IEEE Conference on Computer Vision and Pattern Recognition (2007), pp. 2118–2125.

Zhao, H.

Zhou, X.

Comput. Vision Image Underst. (1)

H. Bay, A. Ess, T. Tuytelaars, and L. V. Gool, Comput. Vision Image Underst. 110, 346 (2008).
[CrossRef]

IEEE Trans. Signal Process. (1)

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

Opt. Lett. (2)

Other (3)

F. Yasutaka and P. Jean, in IEEE Conference on Computer Vision and Pattern Recognition (2007), pp. 2118–2125.

J. Vince, in Geometric Algebra for Computer Graphics (Springer, 2008), pp. 79–124.
[CrossRef]

G. Demarcq, L. Mascarilla, and P. Courtellemont, in IEEE International Conference on Image Processing (ICIP) (2009), pp. 481–484.
[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 (3)

Fig. 1
Fig. 1

Local color phases in the scale-space color monogenic signal framework. Shown are (a) the left image and three local-color-phase maps at the (b) first, (c) second and (d) third scales, respectively.

Fig. 2
Fig. 2

Results for estimating disparity map. (a) Ground disparity map, (b) CMS, (c) MWT, and (d) SSD.

Fig. 3
Fig. 3

Results for reconstructing a set of 3D dense oriented points of the color coffee can. Shown are source images (a)–(d) and reconstructed image cells (e)–(h) at 1, 5, 9, and 13 frames, respectively.

Tables (2)

Tables Icon

Table 1 Experiment Results for Testing Robustness against Noise and Brightness Change

Tables Icon

Table 2 Experiment Results for Matching Features and Reconstructed Three-Dimensional Oriented Points

Equations (4)

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

f c = i = 1 5 A i e i = i = 3 5 h p i h R f i + i = 3 5 h p i f i e i ,
f c V = f c V 0 + f c V 2 = f c V 0 + f c V 2 | f c V 2 | | f c V 2 | ,
φ = arg ( f c V ) = arctan ( | f c V 2 | f c V 0 ) .
Cost ( X , d ) = matching error Δ X Ω | φ s , l ( X + Δ X ) φ s , r ( X + Δ X + d ) | + β smoothness error N 8 2 d + η discontinuity error N p | d d p | .

Metrics