This paper presents a motion estimation algorithm based on a new multiresolution representation, the quadtree spline. This representation describes the motion field as a collection of smoothly connected patches of varying size, where the patch size is automatically adapted to the complexity of the underlying motion. The topology of the patches is determined by a quadtree data structure, and both split and merge techniques are developed for estimating this spatial subdivision. The quadtree spline is implemented using another novel representation, the adaptive hierarchical basis spline, and combines the advantages of adaptively-sized correlation windows with the speedups obtained with hierarchical basis preconditioners. Results are presented on some standard motion sequences.<>
Motion estimation with quadtree splines
1995-01-01
884163 byte
Conference paper
Electronic Resource
English
Motion Estimation with Quadtree Splines
British Library Conference Proceedings | 1995
|Motion estimation and vector splines
IEEE | 1994
|Motion Estimation and Vector Splines
British Library Conference Proceedings | 1994
|British Library Online Contents | 1993
|Splines and Axial Motion Devices
Automotive engineering | 1979
|