This paper proposes an online tracking method which has been inspired by studying the effects of Scale Invariant Feature Transform (SIFT) when applied to objects assumed to be flat even though they are not. The consequent deviation from flatness induces nuisance factors that act on the feature representation in a manner for which no general local invariants can be computed, such as in the case of occlusion, sensor quantization and casting shadows. However, if features are over-represented, they can provide the necessary information to build online, a robust object/context discriminative classifier. This is achieved based on weakly aligned multiple instance local features in a sense that will be made clear in the rest of this paper. According to this observation, we present a non parametric online tracking by detection approach that yields state of the art performance. Specific tests on video sequences of faces show excellent long-term tracking performance in unconstrained videos. © 2012 Springer-Verlag.

FaceHugger: The ALIEN tracker applied to faces / Pernici, F.. - ELETTRONICO. - 7585 LNCS:(2012), pp. 597-601. (Intervento presentato al convegno 12th European Conference on Computer Vision, ECCV 2012; tenutosi a Florence; Italy; nel 7 October 2012 through 13 October 2012;) [10.1007/978-3-642-33885-4_61].

FaceHugger: The ALIEN tracker applied to faces

PERNICI, FEDERICO
2012

Abstract

This paper proposes an online tracking method which has been inspired by studying the effects of Scale Invariant Feature Transform (SIFT) when applied to objects assumed to be flat even though they are not. The consequent deviation from flatness induces nuisance factors that act on the feature representation in a manner for which no general local invariants can be computed, such as in the case of occlusion, sensor quantization and casting shadows. However, if features are over-represented, they can provide the necessary information to build online, a robust object/context discriminative classifier. This is achieved based on weakly aligned multiple instance local features in a sense that will be made clear in the rest of this paper. According to this observation, we present a non parametric online tracking by detection approach that yields state of the art performance. Specific tests on video sequences of faces show excellent long-term tracking performance in unconstrained videos. © 2012 Springer-Verlag.
2012
12th European Conference on Computer Vision, ECCV 2012; Florence; Italy; 7 October 2012 through 13 October 2012;
12th European Conference on Computer Vision, ECCV 2012;
Florence; Italy;
Pernici, F.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1056908
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 15
  • ???jsp.display-item.citation.isi??? 14
social impact