Three-dimensional interest point detection and description using Speeded-Up Robust Features and histograms of oriented points

This article presents a novel systematic methodology for the detection of interest points in 3D point clouds and its corresponding descriptors by using the information of an RGB camera and a structured-light sensor. This is achieved by fusing Speeded-Up Robust Features (SURF) in the image space, and histograms that statistically represent the relationship of three dimensional geometric data around the interest points. The SURF algorithm is implemented over an image whose pixel coordinates have a direct corresponding 3D point, thus allowing the fusion of both approaches. By combining both methodologies, it is intent to define a set of interest points whose descriptors are able to maintain the intrinsic characteristics of its constituent parts such as repeatability, distinctiveness and robustness while remaining compact and fast to compute. The detected points will be use for both, localization and mapping of mobile robots in partially unknown environments.