The recognition of people orientation in single images is still an open issue in several real cases, when the image resolution is poor, body parts cannot be distinguished and localized or motion cannot be exploited. However, the estimation of a person orientation, even an approximated one, could be very useful to improve people tracking and re-identification systems, or to provide a coarse alignment of body models on the input images. In these situations, holistic features seem to be more effective and faster than model based 3D reconstructions. In this paper we propose to describe the people appearance with multi-level HoG feature sets and to classify their orientation using an array of Extremely Randomized Trees classifiers trained on quantized directions. The outputs of the classifiers are then integrated into a global continuous probability density function using a Mixture of Approximated Wrapped Gaussian distributions. Experiments on the TUD Multiview Pedestrians, the Sarc3D, and the 3DPeS datasets confirm the efficacy of the method and the improvement with respect to state of the art approaches.

People Orientation Recognition by Mixtures of Wrapped Distributions on Random Trees / Baltieri, Davide; Vezzani, Roberto; Cucchiara, Rita. - STAMPA. - 7576:(2012), pp. 270-283. ((Intervento presentato al convegno 12th European Conference on Computer Vision tenutosi a Florence, Italy nel October 7-13, 2012 [10.1007/978-3-642-33715-4_20].

People Orientation Recognition by Mixtures of Wrapped Distributions on Random Trees

BALTIERI, DAVIDE;VEZZANI, Roberto;CUCCHIARA, Rita
2012-01-01

Abstract

The recognition of people orientation in single images is still an open issue in several real cases, when the image resolution is poor, body parts cannot be distinguished and localized or motion cannot be exploited. However, the estimation of a person orientation, even an approximated one, could be very useful to improve people tracking and re-identification systems, or to provide a coarse alignment of body models on the input images. In these situations, holistic features seem to be more effective and faster than model based 3D reconstructions. In this paper we propose to describe the people appearance with multi-level HoG feature sets and to classify their orientation using an array of Extremely Randomized Trees classifiers trained on quantized directions. The outputs of the classifiers are then integrated into a global continuous probability density function using a Mixture of Approximated Wrapped Gaussian distributions. Experiments on the TUD Multiview Pedestrians, the Sarc3D, and the 3DPeS datasets confirm the efficacy of the method and the improvement with respect to state of the art approaches.
12th European Conference on Computer Vision
Florence, Italy
October 7-13, 2012
7576
270
283
Baltieri, Davide; Vezzani, Roberto; Cucchiara, Rita
People Orientation Recognition by Mixtures of Wrapped Distributions on Random Trees / Baltieri, Davide; Vezzani, Roberto; Cucchiara, Rita. - STAMPA. - 7576:(2012), pp. 270-283. ((Intervento presentato al convegno 12th European Conference on Computer Vision tenutosi a Florence, Italy nel October 7-13, 2012 [10.1007/978-3-642-33715-4_20].
File in questo prodotto:
File Dimensione Formato  
eccv2012_orientation_camera_ready.pdf

non disponibili

Tipologia: Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione 1.22 MB
Formato Adobe PDF
1.22 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/815689
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 42
  • ???jsp.display-item.citation.isi??? 38
social impact