Image registration is a process of transforming a data set from one coordinate system into another. There are two
typical approaches for image registration: Feature point match based and Area similarity comparison based. The
feature point match based approach, using points to establish the correspondence between two images, is relatively
fast, but it involves feature extractions and parameter selection to create feature points. Feature extractions involve
derivatives which are ill-posed problems and may lead to robustness issues. The area similarity comparison based
approach compares intensity patterns using a correlation metric such as normalized cross correlation (NCC). Since
it does not require feature extraction, is simple and not sensitive to noise. However its computational cost is high.
Even when some fast techniques like FFT are used to reduce the computational cost, the implementation is still time
consuming.
In this paper, we propose a diffusion equation and normalized cross correlation (NCC) combined method to perform
robust image registration with low computational cost. We first apply the diffusion equation to two images received
from two sensors (or the same sensor) and allow these two images to evolve by this diffusion equation. Based on
the characteristics of evolutions, we select a very small percentage of stable points in the first image and perform the
normalized cross correlation to the second image at each transformation point. The highest NCC point provides the
transformation parameters for registering these two images. This new method is resistant to noise since the
evolution of the diffusion equation reduces noise and it chooses only stable points for the NCC computation.
Furthermore, the new method is computationally efficient since only a small percentage of pixels involve in the
transformation estimation. Finally, the experiments for video motion estimation and image registration are provided
to demonstrate that the new method is able to estimate the registration transformation reliably in real time.
|