Abstract

Social signals are observable behaviours which are displayed during an interaction. By observing these signals, it is possible to make predictions about the intent of that individual and other individuals within the vicinity. Measuring social signals has often proved challenging as they are often characterised by subtle movements which are difficult to detect. Head pose is one such social signal used to indicate where an individual’s attention is focused. This paper will discuss the problem of head pose estimation by defining the problem in terms of two fields of view, pan and tilt. The presented approach uses template matching and tested using a well-known dataset. The template matching approach is shown to be able to determine head pan to within one class ~51% of the time and head tilt to within one class ~71% of the time.
LanguageEnglish
Number of pages7
Publication statusAccepted/In press - 6 Jul 2018
EventIrish Machine Vision and Image Processing (IMVIP) - Dublin, Ireland
Duration: 26 Aug 2015 → …

Conference

ConferenceIrish Machine Vision and Image Processing (IMVIP)
Period26/08/15 → …

Fingerprint

Template matching

Keywords

  • Head pose estimation
  • template matching
  • social signal processing

Cite this

Reid, S., Coleman, S., Kerr, D., Vance, P., & O'Neill, S. (Accepted/In press). Template Matching for Head Pose Estimation. Paper presented at Irish Machine Vision and Image Processing (IMVIP), .
Reid, Shane ; Coleman, Sonya ; Kerr, Dermot ; Vance, Philip ; O'Neill, Siobhan. / Template Matching for Head Pose Estimation. Paper presented at Irish Machine Vision and Image Processing (IMVIP), .7 p.
@conference{ae65a41f4afb462982c941cd8eb71841,
title = "Template Matching for Head Pose Estimation",
abstract = "Social signals are observable behaviours which are displayed during an interaction. By observing these signals, it is possible to make predictions about the intent of that individual and other individuals within the vicinity. Measuring social signals has often proved challenging as they are often characterised by subtle movements which are difficult to detect. Head pose is one such social signal used to indicate where an individual’s attention is focused. This paper will discuss the problem of head pose estimation by defining the problem in terms of two fields of view, pan and tilt. The presented approach uses template matching and tested using a well-known dataset. The template matching approach is shown to be able to determine head pan to within one class ~51{\%} of the time and head tilt to within one class ~71{\%} of the time.",
keywords = "Head pose estimation, template matching, social signal processing",
author = "Shane Reid and Sonya Coleman and Dermot Kerr and Philip Vance and Siobhan O'Neill",
year = "2018",
month = "7",
day = "6",
language = "English",
note = "Irish Machine Vision and Image Processing (IMVIP) ; Conference date: 26-08-2015",

}

Reid, S, Coleman, S, Kerr, D, Vance, P & O'Neill, S 2018, 'Template Matching for Head Pose Estimation' Paper presented at Irish Machine Vision and Image Processing (IMVIP), 26/08/15, .

Template Matching for Head Pose Estimation. / Reid, Shane; Coleman, Sonya; Kerr, Dermot; Vance, Philip; O'Neill, Siobhan.

2018. Paper presented at Irish Machine Vision and Image Processing (IMVIP), .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Template Matching for Head Pose Estimation

AU - Reid, Shane

AU - Coleman, Sonya

AU - Kerr, Dermot

AU - Vance, Philip

AU - O'Neill, Siobhan

PY - 2018/7/6

Y1 - 2018/7/6

N2 - Social signals are observable behaviours which are displayed during an interaction. By observing these signals, it is possible to make predictions about the intent of that individual and other individuals within the vicinity. Measuring social signals has often proved challenging as they are often characterised by subtle movements which are difficult to detect. Head pose is one such social signal used to indicate where an individual’s attention is focused. This paper will discuss the problem of head pose estimation by defining the problem in terms of two fields of view, pan and tilt. The presented approach uses template matching and tested using a well-known dataset. The template matching approach is shown to be able to determine head pan to within one class ~51% of the time and head tilt to within one class ~71% of the time.

AB - Social signals are observable behaviours which are displayed during an interaction. By observing these signals, it is possible to make predictions about the intent of that individual and other individuals within the vicinity. Measuring social signals has often proved challenging as they are often characterised by subtle movements which are difficult to detect. Head pose is one such social signal used to indicate where an individual’s attention is focused. This paper will discuss the problem of head pose estimation by defining the problem in terms of two fields of view, pan and tilt. The presented approach uses template matching and tested using a well-known dataset. The template matching approach is shown to be able to determine head pan to within one class ~51% of the time and head tilt to within one class ~71% of the time.

KW - Head pose estimation

KW - template matching

KW - social signal processing

M3 - Paper

ER -

Reid S, Coleman S, Kerr D, Vance P, O'Neill S. Template Matching for Head Pose Estimation. 2018. Paper presented at Irish Machine Vision and Image Processing (IMVIP), .