Image Stabilization for Feature Tracking and Generation of Stable Video Overlays

Abstract

We present the formulation and implementation of an image stabilization system capable of stabilizing video with very large displacements between frames. A coarse-to-fine technique is applied in resolution and in model spaces. The registration algorithm uses phase correlation to obtain an initial estimate for translation between images; then Levenberg-Marquardt method for non-linear optimization is applied to refine the solution. Registration is performed in color space, using a subset of the pixels selected by a gradient-based subsampling criteria. The algorithm was applied to feature tracking and to generate stable overlays on video sequences. Several techniques of motion compensation are presented. The current implementation has been tested with several video sequences. This software implementation runs at 5Hz on non-dedicated hardware (Silicon Graphics R10000 workstation).