Performance Evaluation of Optical Ow Estimators: Assessment of a New Aane Ow Method

Over the years, computer vision researchers have developed a number of algorithms to solve a large number of problems. However, most of the existing algorithms are not characterized in terms of their performance, accuracy, cost, etc. Consequently, it is hardly ever possible to compare and choose between these various algorithms to tackle a speciic problem. One of the contributions of this paper is the introduction of a framework for evaluating the performance of optical ow estimators, which is based on classical estimation theory criteria, and on considerations about the computation cost. This framework is general, and may be applied to other estimation problems. The optic ow is widely used in many vision systems. It is a vector velocity eld deened on sequences of images. The AAne Optic Flow is formed by the optical ow together with its rst-order derivatives with respect to image coordinates. As a second contribution, we present two new estimators for the aane ow. We justify theoreticaly their design with hypotheses concerning the input images, which we show to be empirically valid. Finally, we use the performance analysis framework in order to compare the aane ow estimators with a more classical \diierential" method.