Digital image stabilization using similarity transformation over constrained Differential-Radon warping vectors

• Differential-Radon by incorporating projection shape produces improved correlation.
• Resolution of 0.1 degree provides better inter-frame rotation estimation accuracy.
• Constrained warping of angular slice results improved processing time efficiency.
• Interest vector selection efficiently eliminates curve miswarping singularities.
• Least square solution on interest vector gives extended range of motion parameters.

In this paper an image-stabilizer based on novel Differential-Radon warping for combined camera motions, i.e., translation, rotation and zoom estimation has been presented. Motion estimation using intensity integrals in classical Radon transform (RT) does not consider projection shape for its correlation and leads to erroneous results under local intensity variations. As a solution, Differential-Radon (DRadon) matrix utilizing inherent curve variance as matching feature is proposed. The scheme provides peaked correlation curves, which gives better motion accuracy in comparison to the classical RT. DRadon projections of the test and target images computed at an intermediate angular-slice resolution of 0.1 degree are correlated to find relative image tilt, and the best matched projections are warped using Sakoe–Chiba constrained dynamic time warping. The estimated warping vectors are then processed using a new local-optima based interest vectors selection scheme to remove various one-to-many-matched warping singularities. A linear-motion model is applied over the extracted interest warping vectors and their least-square solution is used as inter-frame translation and zoom motions. Finally, a composite affine motion stabilizer framework is presented for shaky videos taken under different scene-capture conditions. Comparative stability performance evaluation using peak signal-to-noise ratio and mean structural similarity index is presented for various real-world sequences.