Feature-based image alignment via coupled Hough transforms

We investigate the problem of feature based image alignment under vertical and horizontal translation and scaling. The problem of finding the two dimensional affine alignment without rotation can be separated into two coupled simpler problems. The resulting two model fitting problems are coupled through a consensuses set of points that fit both models. The proposed solution can be viewed as a coordinate-wise optimization that separates the two dimensional shift and stretch problem into two coupled one-dimensional problems. Each one dimensional alignment problem is solved through a Hough transform that allows fast and robust estimation of the two parameters of a one dimensional affine deformation model. Experimental results demonstrate the efficiency and accuracy of the proposed method in finding the spatial transform between two given video sequences.