Space Variant Representations for Mobile Platform Vision Applications

Abstract. The log-polar space variant representation, motivated by biological vision, has been widely studied in the literature. Its data re-duction and invariance properties made it useful in many vision appli-cations. However, due to its nature, it fails in preserving features in the periphery. In the current work, as an attempt to overcome this prob-lem, we propose a novel space-variant representation. It is evaluated and proved to be better than the log-polar representation in preserving the peripheral information, crucial for on-board mobile vision applications. The evaluation is performed by comparing log-polar and the proposed representation once they are used for estimating dense optical flow