A Comparative Study of Block Matching Optical Flow Algorithms

The paper presents a study of existing Block Matching Optical Flow algorithms, which estimate the motion from an image sequence. The seven algorithms selected for our performance and comparative study (ES, TSS, SETSS, NTSS, FSS, DS and ARPS) are finding a minimum cost match between the current image reference block and one of the considered blocks in the next image. The benchmark used for the performance testing was the Middlebury Dataset, with the conclusions leading to a parameters and algorithm selection criteria.