Title :
BRAND: A robust appearance and depth descriptor for RGB-D images
Author :
Nascimento, Erickson R. ; Oliveira, Gabriel L. ; Campos, Mario F M ; Vieira, Antônio W. ; Schwartz, William Robson
Author_Institution :
Comput. Sci. Dept., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil
Abstract :
This work introduces a novel descriptor called Binary Robust Appearance and Normals Descriptor (BRAND), that efficiently combines appearance and geometric shape information from RGB-D images, and is largely invariant to rotation and scale transform. The proposed approach encodes point information as a binary string providing a descriptor that is suitable for applications that demand speed performance and low memory consumption. Results of several experiments demonstrate that as far as precision and robustness are concerned, BRAND achieves improved results when compared to state of the art descriptors based on texture, geometry and combination of both information. We also demonstrate that our descriptor is robust and provides reliable results in a registration task even when a sparsely textured and poorly illuminated scene is used.
Keywords :
image registration; image texture; natural scenes; transforms; BRAND; RGB-D images; SIFT; SURF; binary robust appearance and normals descriptor; binary string; depth descriptor; geometric shape information; memory consumption; point information; rotation transform; scale invariant feature descriptor; scale transform; speed up robust descriptor; state of the art descriptors; Geometry; Legged locomotion; Noise; Robustness; Shape;
Conference_Titel :
Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on
Conference_Location :
Vilamoura
Print_ISBN :
978-1-4673-1737-5
DOI :
10.1109/IROS.2012.6385693