Using retinex for point selection in 3D shape registration

PATTERN RECOGNITION

卷:47

Article

Liu, Yonghuai¹  Martin, Ralph R.²  de Dominicis, Luigi³  Li, Baihua⁴ 

[1] Aberystwyth Univ, Dept Comp Sci, Ceredigion SY23 3DB, Dyfed, Wales

[2] Cardiff Univ, Sch Informat & Comp Sci, Cardiff CF24 3AA, S Glam, Wales

[3] ENEA, Diagnost & Metrol Lab UTAPRAD DIM, I-00044 Frascati, Italy

[4] Manchester Metropolitan Univ, Sch Comp Math & Digital Technol, Manchester M1 5GD, Lancs, England

关键词: Retinex;    Key point;    Freeform shape;    Adaptive smoothing;    Registration;   

DOI  :  10.1016/j.patcog.2013.12.015

来源: Elsevier

【 摘 要 】

Inspired by retinex theory, we propose a novel method for selecting key points from a depth map of a 3D freeform shape; we also use these key points as a basis for shape registration. To find key points, first, depths are transformed using the Hotelling method and normalized to reduce their dependence on a particular viewpoint. Adaptive smoothing is then applied using weights which decrease with spatial gradient and local inhomogeneity; this preserves local features such as edges and corners while ensuring smoothed depths are not reduced. Key points are those with locally maximal depths, faithfully capturing shape. We show how such key points can be used in an efficient registration process, using two state-of-the-art iterative closest point variants. A comparative study with leading alternatives, using real range images, shows that our approach provides informative, expressive, and repeatable points leading to the most accurate registration results. (C) 2014 Elsevier Ltd. All rights reserved.

【 授权许可】

Free