Contour localization based on matching dense HexHoG descriptors

The ability to detect and localize an object of interest from a captured image containing a cluttered background is an essential function for an autonomous robot operating in an unconstrained environment. In this paper, we present a novel approach to refining the pose estimate of an object and directly labelling its contours by dense local feature matching. We perform this task using a new image descriptor we have developed called the HexHoG. Our key novel contribution is the formulation of HexHoG descriptors comprising hierarchical groupings of rotationally invariant (S)HoG fields, sampled on a hexagonal grid. These HexHoG groups are centred on detected edges and therefore sample the image relatively densely. This formulation allows arbitrary levels of rotation-invariant HexHoG grouped descriptors to be implemented efficiently by recursion. We present the results of an evaluation based on the ALOI image dataset which demonstrates that our proposed approach can significantly improve an initial pose estimation based on image matching using standard SIFT descriptors. In addition, this investigation presents promising contour labelling results based on processing 2892 images derived from the 1000 image ALOI dataset.