© The Institution of Engineering and Technology
Video registration in the presence of several segments of non-texture frames remains a challenging issue, although a wide repertoire of image registration algorithms was developed over the last two decades. In this study, the authors proposed an effective causal scheme of video frames registration, and implemented it by the modified two frames intensity match algorithm. In order to achieve its real-time performance, the authors avoid handling a much more complex appearance model in this causal system by using registration parameters as measurement values, which are estimated directly from two consecutive frames via intensity matching. The simple linear and Gaussian system is thus derived and an efficient Kalman filter algorithm can be utilised. As the Kalman filter naturally incorporated the temporal information contained in a video into the estimation of registration parameters, the algorithm developed in this study is quite robust and has good performance even if the processed video contains several segments of non-texture frames.
References
-
-
1)
-
A.F. Bobick ,
S.S. Intille
.
Large occlusion stereo.
Int. J. Comput. Vis.
,
181 -
200
-
2)
-
S. Baker ,
I. Matthews
.
Lucas–Kanade 20 years on: a unifying framework.
Int. J. Comput. Vis.
,
221 -
255
-
3)
-
J.P.W. Pluim ,
J.B.A. Maintz ,
M.A. Viergever
.
Mutual information-based registration of medical images: a survey.
IEEE Trans. Med. Imaging
,
809 -
814
-
4)
-
B1. Caspi, Y., Irani, M.: `Alignment of non-overlapping sequences', Proc. Eighth Int. Conf. on Computer Vision, 2001, Vancouver, Canada, 2, p. 76–82.
-
5)
-
Baker, S., Sim, T., Kanade, T.: `A characterization of inherent stereo ambiguities', Proc. Eighth Int. Conf. on Computer Vision, 2001, Vancouver, Canada, 1, p. 428–435.
-
6)
-
Scharstein, D., Szeliski, R.: `Stereo matching with non-linear diffusion', Proc. Computer Vision and Pattern Recognition, 1996, San Francisco, CA, p. 343–350.
-
7)
-
Y. Boykov ,
O. Veksler ,
R. Zabih
.
Fast approximate energy minimization via graph cuts.
IEEE Trans. PAMI
,
1222 -
1239
-
8)
-
W.H. Press ,
S.A. Teukolsky ,
W.T. Vetterling ,
B.P. Flannery
.
(1994)
Numerical recipes in C: the art of scientific computing.
-
9)
-
K. Zhou ,
R. Chellappa ,
B. Moghaddam
.
Visual tracking and recognition using appearance adaptive models in particle filters.
IEEE Trans. Image Process.
,
530 -
544
-
10)
-
D. Nicholas ,
R. Bowden
.
Mutual Information for Lucas–Kanade tracking (MILK): an inverse compositional formulation.
IEEE Trans. PAMI
,
180 -
185
-
11)
-
Zheng, Q., Rama, C.: `Automatic registration of oblique aerial images', Proc. First Int. Conf. on Image Processing, 1994, Austin, TX, 1, p. 218–222.
-
12)
-
Jepson, A.D., Fleet, D.J., Maraghi, T.E.I.: `Robust online appearance model for visual tracking', IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2001, p. 415–422.
-
13)
-
Tao, H., Sawhney, H.S., Kumar, R.: `A global matching framework for stereo computation', Proc. Eighth Int. Conf. on Computer Vision, 2001, Vancouver, Canada, 1, p. 532–539.
-
14)
-
Rohith, M.V., Somanath, G., Chandra, K., Geiger, C.: `Towards estimation of dense disparities from stereo image containing large textureless regions', Proc. 19th Int. Conf. on Pattern Recognition, 2008, Tampa, FL, p. 1–5.
-
15)
-
Sundaram, H., Nayar, S.: `Are textureless scenes recoverable?', Proc. Computer Vision and Pattern Recognition, 1997, San Juan, Puerto Rico, p. 814–820.
-
16)
-
M.J. Black ,
P. Anandan
.
The robust estimation of multiple motions: parametric and piecewise-smooth flow fields.
Comput. Vis. Image Underst.
,
75 -
104
-
17)
-
P. Voila ,
W.M. wells
.
Alignment by maximization of mutual information.
Int. J. Comput. Vis.
,
137 -
154
-
18)
-
Bergen, J.R., Anandan, P., Hanna, K.J., Hingorani, R.: `Hierarchical model-based motion estimation', Proc. Second European Conf. on Computer Vision, May 1992, Italy, p. 237–253.
-
19)
-
Q.-S. Chen ,
M. Defrise ,
F. Deconinck
.
Symmetric phase-only matched filtering of Fourier–Mellin transforms for mage registration and recognition.
IEEE Trans. PAMI
,
1156 -
1168
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2008.0004
Related content
content/journals/10.1049/iet-cvi.2008.0004
pub_keyword,iet_inspecKeyword,pub_concept
6
6