An image signal indicative of the head pose of a person in a scene, as provided, e.g. by a camera (W), is processed by: - estimating (102), as a function of the image signal received (100) by the image sensor (W), the head pose of the person, - generating (104) from the estimated head pose, a view frustum of the person, - generating (106) from the view frustum a visual frustum of attention or VFOA of the person, and - generating from the visual frustum of attention e.g.: - a predicted movement trajectory of the person, preferably by tracking the person as a function of a predicted movement trajectory, or - an estimated scene attention map as a function of the visual frustum of attention, preferably by identifying in the attention map at least one object (L) to be controlled (L). For instance, the method may be applied to controlling a smart lighting system (L) including plural lighting devices (L) controllable by one control device (C), by identifying in the attention map one lighting device (L) to be controlled, so that the control device (C) may be used to control the lighting device identified in the plurality of lighting devices in the attention map.

A method of view frustum detection, corresponding system and computer program product / Cristiani, Marco; DEL BUE, Alessio; Eschey, Michael; Galasso, Fabio; Hasan, Irtiza; Kaestle, Herbert; Setti, Francesco; Tsesmelis, Theodore. - (2016).

A method of view frustum detection, corresponding system and computer program product

GALASSO, Fabio;
2016

Abstract

An image signal indicative of the head pose of a person in a scene, as provided, e.g. by a camera (W), is processed by: - estimating (102), as a function of the image signal received (100) by the image sensor (W), the head pose of the person, - generating (104) from the estimated head pose, a view frustum of the person, - generating (106) from the view frustum a visual frustum of attention or VFOA of the person, and - generating from the visual frustum of attention e.g.: - a predicted movement trajectory of the person, preferably by tracking the person as a function of a predicted movement trajectory, or - an estimated scene attention map as a function of the visual frustum of attention, preferably by identifying in the attention map at least one object (L) to be controlled (L). For instance, the method may be applied to controlling a smart lighting system (L) including plural lighting devices (L) controllable by one control device (C), by identifying in the attention map one lighting device (L) to be controlled, so that the control device (C) may be used to control the lighting device identified in the plurality of lighting devices in the attention map.
2016
Scene understanding, gaze estimation, human pose estimation, smart lighting
05 Brevetto::05a Brevetto
A method of view frustum detection, corresponding system and computer program product / Cristiani, Marco; DEL BUE, Alessio; Eschey, Michael; Galasso, Fabio; Hasan, Irtiza; Kaestle, Herbert; Setti, Francesco; Tsesmelis, Theodore. - (2016).
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

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/11573/1342847
 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