Depth cameras allow to set up reliable solutions for people monitoring and behavior understanding, especially when unstable or poor illumination conditions make unusable common RGB sensors. Therefore, we propose a complete framework for the estimation of the head and shoulder pose based on depth images only. A head detection and localization module is also included, in order to develop a complete end-to-end system. The core element of the framework is a Convolutional Neural Network, called POSEidon+, that receives as input three types of images and provides the 3D angles of the pose as output. Moreover, a Face-from-Depth component based on a Deterministic Conditional GAN model is able to hallucinate a face from the corresponding depth image. We empirically demonstrate that this positively impacts the system performances. We test the proposed framework on two public datasets, namely Biwi Kinect Head Pose and ICT-3DHP, and on Pandora, a new challenging dataset mainly inspired by the automotive setup. Experimental results show that our method overcomes several recent state-of-art works based on both intensity and depth input data, running in real-time at more than 30 frames per second.

Face-from-Depth for Head Pose Estimation on Depth Images / Borghi, Guido; Fabbri, Matteo; Vezzani, Roberto; Calderara, Simone; Cucchiara, Rita. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - 42:3(2020), pp. 596-609. [10.1109/TPAMI.2018.2885472]

Face-from-Depth for Head Pose Estimation on Depth Images

Guido Borghi;Matteo Fabbri;Roberto Vezzani;Simone Calderara;Rita Cucchiara
2020

Abstract

Depth cameras allow to set up reliable solutions for people monitoring and behavior understanding, especially when unstable or poor illumination conditions make unusable common RGB sensors. Therefore, we propose a complete framework for the estimation of the head and shoulder pose based on depth images only. A head detection and localization module is also included, in order to develop a complete end-to-end system. The core element of the framework is a Convolutional Neural Network, called POSEidon+, that receives as input three types of images and provides the 3D angles of the pose as output. Moreover, a Face-from-Depth component based on a Deterministic Conditional GAN model is able to hallucinate a face from the corresponding depth image. We empirically demonstrate that this positively impacts the system performances. We test the proposed framework on two public datasets, namely Biwi Kinect Head Pose and ICT-3DHP, and on Pandora, a new challenging dataset mainly inspired by the automotive setup. Experimental results show that our method overcomes several recent state-of-art works based on both intensity and depth input data, running in real-time at more than 30 frames per second.
7-dic-2018
42
3
596
609
Face-from-Depth for Head Pose Estimation on Depth Images / Borghi, Guido; Fabbri, Matteo; Vezzani, Roberto; Calderara, Simone; Cucchiara, Rita. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - 42:3(2020), pp. 596-609. [10.1109/TPAMI.2018.2885472]
Borghi, Guido; Fabbri, Matteo; Vezzani, Roberto; Calderara, Simone; Cucchiara, Rita
File in questo prodotto:
File Dimensione Formato  
pre-printTPAMIVEZZANI.pdf

accesso aperto

Tipologia: Pre-print dell'autore (bozza pre referaggio)
Dimensione 3.73 MB
Formato Adobe PDF
3.73 MB Adobe PDF Visualizza/Apri
08567956.pdf

non disponibili

Tipologia: Versione dell'editore (versione pubblicata)
Dimensione 5.12 MB
Formato Adobe PDF
5.12 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento 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: http://hdl.handle.net/11380/1167738
Citazioni
  • ???jsp.display-item.citation.pmc??? 3
  • Scopus 32
  • ???jsp.display-item.citation.isi??? 25
social impact