In this paper, we propose an optimization method for estimating the parameters that typically appear in graph-theoretical formulations of the matching problem for object detection. Although several methods have been proposed to optimize parameters for graph matching in a way to promote correct correspondences and to restrict wrong ones, our approach is novel in the sense that it aims at improving performance in the more general task of object detection. In our formulation, similarity functions are adjusted so as to increase the overall similarity among a reference model and the observed target, and at the same time reduce the similarity among reference and "non-target" objects. We evaluate the proposed method in two challenging scenarios, namely object detection using data captured with a Kinect sensor in a real environment, and intrinsic metric learning for deformable shapes, demonstrating substantial improvements in both settings.

Learning similarities for rigid and non-rigid object detection / Kanezaki, Asako; Rodolà, Emanuele; Cremers, Daniel; Harada, Tatsuya. - (2015), pp. 720-727. (Intervento presentato al convegno 2014 2nd International Conference on 3D Vision, 3DV 2014 tenutosi a Tokyo, Japan) [10.1109/3DV.2014.61].

Learning similarities for rigid and non-rigid object detection

Rodolà, Emanuele;
2015

Abstract

In this paper, we propose an optimization method for estimating the parameters that typically appear in graph-theoretical formulations of the matching problem for object detection. Although several methods have been proposed to optimize parameters for graph matching in a way to promote correct correspondences and to restrict wrong ones, our approach is novel in the sense that it aims at improving performance in the more general task of object detection. In our formulation, similarity functions are adjusted so as to increase the overall similarity among a reference model and the observed target, and at the same time reduce the similarity among reference and "non-target" objects. We evaluate the proposed method in two challenging scenarios, namely object detection using data captured with a Kinect sensor in a real environment, and intrinsic metric learning for deformable shapes, demonstrating substantial improvements in both settings.
2015
2014 2nd International Conference on 3D Vision, 3DV 2014
Graph theory; Object recognition; Object detection
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Learning similarities for rigid and non-rigid object detection / Kanezaki, Asako; Rodolà, Emanuele; Cremers, Daniel; Harada, Tatsuya. - (2015), pp. 720-727. (Intervento presentato al convegno 2014 2nd International Conference on 3D Vision, 3DV 2014 tenutosi a Tokyo, Japan) [10.1109/3DV.2014.61].
File allegati a questo prodotto
File Dimensione Formato  
Rodola_Learning_2015.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.07 MB
Formato Adobe PDF
1.07 MB Adobe PDF   Contatta l'autore

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: https://hdl.handle.net/11573/1227798
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? ND
social impact