This paper presents a new image analysis method, combining motion estimation and image segmentation. Whereas none of these methods, used on its own, delivers error free meta-information, an appropriate combination leads to an orthogonalization of these errors. This method is applied to improve the quality of motion vector fields.
No takes yet. Share an insight, caveat, or question.
Blume et al. (2002) studied this question.
Synapse has enriched 5 related papers. Consider them for comparative context: