Multi-Parameter Simultaneous Estimation on Area-Based Matching

Area-based matching is a fundamental image processing method that obtains displacement between image regions. In addition, the similarity interpolation method to estimate sub-pixel displacement is commonly used to enhance resolution. This paper proposes a novel 2D sub-pixel displacement estimation method based on similarity interpolation. The method estimates the displacement as an intersection point of two lines, which are approximations of zero positions of the partial derivatives with respect to each motion parameter. The proposed method requires a non-iterative computation. Furthermore, the method engenders only slightly higher calculation costs than the conventional similarity interpolation method. Moreover, the method is suitable for hardware implementation. We show that the proposed method can be extended to obtain the N-parameter of image deformation with noniterative computation. Using similarity measures obtained at discrete positions in the parameter space, our method provides a highly accurate maximum position of the similarity in sub-sampling resolution; that position corresponds to the image deformation parameters. Experimental results using both synthetic and real images demonstrate that our method can estimate parameters more accurately than conventional methods.