Towards quantitative comparison of motion estimation algorithms

Motion estimation is a common component of machine vision systems. Given the number of motion estimation algorithms available, selection of an appropriate algorithm is a difficult process. A quantitative measurement of the performance of motion estimation algorithms on real unlabelled data allows for more realistic comparison of motion estimation algorithms than the current situation. At present the most common measure of a motion estimation algorithm involves comparing a measured to a known motion field. Szeliski suggested treating motion estimation as a registration process. The motion between two successive images is computed and used to warp one of the images onto the other. The registration error is then used as a quantitative measure of the motion estimation algorithm. An extension to the Szeliski metric is examined. Examples will be shown where algorithms are selected and the tunable parameters are optimised for some test sequences.