Feature point selection for object-based motion estimation on a programmable device

摘要

Recently, we reported on a recursive algorithm enabling real-time object-based motion estimation (OME) for standard definition video on a digital signal processor (DSP). The algorithm approximates the motion of objects in the image with parametric motion models and creates a segmentation mask by assigning the best matching model to image parts on a block-by-block basis. A parameter estimation module determines the parameters of the motion models on a small fraction of the pictorial data called feature points. In this paper, we propose a new, computationally very efficient, feature point selection method that improves the convergence of the motion parameter estimation process.