The ability of recognizing object categories in 3D data is still an underdeveloped topic. This paper investigates on adopting Implicit Shape Models (ISMs) for 3D categorization, that, dierently from current approaches, include also information on the geometrical structure of each object category. ISMs have been originally proposed for recognition and localization of categories in cluttered images. Modications to allow for a correct deployment for 3D data are discussed. Moreover, we propose modications to three design points within the structure of a standard ISM to enhance its eectiveness for the categorization of databases entries, either 3D or 2D: namely, codebook size and composition, codeword activation strategy and vote weight strategy. Experimental results on two standard 3D datasets allow us to discuss the positive impact of the proposed modications as well as to show the performance in recognition accuracy yielded by our approach compared to the state of the art.

On the use of Implicit Shape Models for recognition of object categories in 3D data

SALTI, SAMUELE;TOMBARI, FEDERICO;DI STEFANO, LUIGI
2010

Abstract

The ability of recognizing object categories in 3D data is still an underdeveloped topic. This paper investigates on adopting Implicit Shape Models (ISMs) for 3D categorization, that, dierently from current approaches, include also information on the geometrical structure of each object category. ISMs have been originally proposed for recognition and localization of categories in cluttered images. Modications to allow for a correct deployment for 3D data are discussed. Moreover, we propose modications to three design points within the structure of a standard ISM to enhance its eectiveness for the categorization of databases entries, either 3D or 2D: namely, codebook size and composition, codeword activation strategy and vote weight strategy. Experimental results on two standard 3D datasets allow us to discuss the positive impact of the proposed modications as well as to show the performance in recognition accuracy yielded by our approach compared to the state of the art.
Proceedings of the 10th Asian Conference on Computer Vision
1952
1964
S. Salti; F. Tombari; L. Di Stefano
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11585/96903
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact