This paper presents a 3D object recognition method aimed to industrial applications. The proposed method compares any object represented as a set of 3D polygonal surfaces through their corresponding normal map, a bidimensional array which stores local curvature (mesh normals) as the pixels RGB components of a color image. The recognition approach, based on the computation of a difference map resulting from the comparison of normal maps, is simple yet fast and accurate. First results show the effectiveness of the method on a database of 3D models of sanitary equipments.
Fast and low cost 3d object recognition / C. Bornaghi, B. Ferrari, E. Damiani (STUDIES IN COMPUTATIONAL INTELLIGENCE). - In: New directions in intelligent interactive multimedia systems and services - 2 / [a cura di] E. Damiani ... [et al.]. - Berlin : Springer, 2009. - ISBN 9783642029363. - pp. 391-399 (( Intervento presentato al 2. convegno International Symposium on Intelligent Interactive Multimedia Systems and Services (KES-IIMSS) tenutosi a Mogliano Veneto (TV) nel 2009 [10.1007/978-3-642-02937-0].
Fast and low cost 3d object recognition
E. Damiani
2009
Abstract
This paper presents a 3D object recognition method aimed to industrial applications. The proposed method compares any object represented as a set of 3D polygonal surfaces through their corresponding normal map, a bidimensional array which stores local curvature (mesh normals) as the pixels RGB components of a color image. The recognition approach, based on the computation of a difference map resulting from the comparison of normal maps, is simple yet fast and accurate. First results show the effectiveness of the method on a database of 3D models of sanitary equipments.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.