An improved MOBIL descriptor for markerless augmented reality

Abstract

In this paper, we present an improved version of MOBIL descriptor [1] (Improved MOments based BInary differences for Local description), which introduces two main contributions. The first one is the use of geometric information for the binary test instead of the classical intensity binary test, to get more precision in the description step. The second one is to attribute two bits for each test, to increase the distinctiveness level. This approach offers high distinctiveness against affine transformations and appearance changes. The experimental evaluation shows that MOBIL achieves a quite good performance in term of low computation complexity and high recognition rate compared to state-of-the-art real-time local descriptors.