In this paper, some image registration algorithms are investigated for the purpose of image fusion in a digital camera application. A hybrid scheme which uses both feature-based and intensity-based methods is proposed. In particular, an edge-based image registration approach is developed to guide the intensity-based registration which uses optical flow estimation. The idea of coarse-to-fine multi-scale iterative refinement is also utilized. The combination of these different methods tends to compensate for any deficiencies in the individual methods. Experiments show that our approach provides accurate registrations for the digital camera application. It is also demonstrated that the approach proves useful for registering some multi-spectral images. Keywords-Image fusion, registration, multi-scale, optical flow, feature-based.
|
1662
|
A computational approach to edge detection
– Canny
- 1986
|
|
1044
|
Determining Optical Flow
– Horn, Schunck
- 1981
|
|
461
|
Hierarchical modelbased motion estimation
– Bergen, Anandan, et al.
- 1992
|
|
442
|
A survey of image registration techniques
– Brown
- 1992
|
|
343
|
A computational framework and an algorithm for the measurement of
– Anandan
|
|
333
|
Computer and Robot Vision
– Haralick, Shapiro
- 1993
|
|
239
|
Computation of component image velocity from local phase information
– Fleet, Jepson
- 1990
|
|
153
|
Digital image processing
– Pratt
- 1991
|
|
120
|
On the computation of motion from sequences of images - a review
– Aggarwal, Nandhakumar
- 1988
|
|
114
|
On the estimation of optical flow: Relations between different approaches and some new results
– Nagel
- 1987
|
|
85
|
Investigations of multigrid algorithms for estimation of optical flow fields in image sequences
– Enkelmann
- 1988
|
|
84
|
Model for the extraction of image flow
– Heeger
- 1987
|
|
61
|
A computational vision approach to image registration
– Zheng, Chellappa
- 1993
|
|
44
|
A class of algorithms for fast digital image registration
– Barnea, Silverman
- 1972
|
|
44
|
Computing two motions from three frames
– Bergen, Burt, et al.
- 1990
|
|
42
|
Shape Matching Using Relaxation Techniques
– Davis
- 1979
|
|
35
|
Mechanisms for isolating component patterns in the sequential analysis of multiple motion
– Burt, Hingorani, et al.
- 1991
|
|
34
|
A dynamic model for image registration
– Burr
- 1981
|
|
34
|
A contour-based approach to multisensor image registration
– Li, Manjunath, et al.
- 1995
|
|
27
|
A fast subspace algorithm for recovering rigid motion
– Jepson, Heeger
- 1991
|
|
16
|
Correlation techniques of image registration
– Pratt
- 1974
|
|
16
|
Simple Method for Computing 3D Motion and Depth
– Heeger, Jepson
- 1990
|
|
16
|
computationally efficient motion estimation algorithm
– Hierarchical
- 1987
|
|
14
|
A unified perspective on computational techniques for the measurement of visual motion
– Anandan
- 1987
|
|
12
|
Model of human visual motion sensing
– Watson, Ahumada
- 1985
|
|
11
|
A region-based approach to digital image registration with subpixel accuracy
– Goshtasby, Stockman, et al.
- 1986
|
|
6
|
A categorization and study of multiscale-decomposition-based image fusion schemes
– Zhang, Blum
- 1999
|
|
5
|
Image registration by recognition of corresponding structures
– Ventura, Rampini, et al.
- 1990
|
|
5
|
Local motion estimation with the dynamic pyramid
– Dengler
- 1986
|
|
4
|
Contour registration by shape-specific points for shape matching
– Mitiche, Aggarwal
- 1983
|
|
2
|
Automated Multisensor Reg-istration: Requirements and Techniques
– Rignot, Kowk, et al.
- 1991
|
|
2
|
A Vector Space Approach to Models and Optimization
– Dorny
- 1983
|
|
1
|
A class of algorithms for fast digital image registration
– Stockman, Kopstein, et al.
- 1982
|
|
1
|
Subspace methods for recovering regid motion i: Algorithm and implementation
– Heeger, Jepson
- 1992
|
|
