ROBUST OPTIC FLOW COMPUTATION

This paper formulates the optic flow problem as a set of over-determin ed simultaneous linear equations. It then introduces and studies two n ew robust optic flow methods. The first technique is based on using th e Least Median of Squares (LMedS) to detect the outliers. Then, the in lier group is solved using the least square technique. The second meth od employs a new robust statistical method named the Least Median of S quares Orthogonal Distances (LMSOD) to identify the outliers and then uses total least squares to solve the optic flow problem. The performa nce of both methods are studied by experiments on synthetic and real i mage sequences. These methods outperform other published methods both in accuracy and robustness.