Kafa duruşu kestirimlerinden bakiş yönünün türetilmesi

Translated title of the contribution: Derivation of gaze direction from head pose estimates

Zeynep Yucel, Albert Ali Salah, Çetin ̧ Meriçli, Tekin Meriçli

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Automatic estimation of gaze direction information is important for certain applications of human-robot and human-computer interaction. Depending on the properties of the specific application, it may be required to derive this information in real time from low resolution visual inputs, with as much precision as possible. In this paper we present an algorithm for transforming head pose estimates to gaze direction estimates. The main contribution of this study lies in the fact that it makes a clear distinction between head pose and gaze direction. Unlike some of the previous works in this field, we do not correct the head pose to correspond to a possible attention fixation point in accordance with the experiment scenario. Instead we propose using a concrete and environment-independent method for this purpose. To transform the head pose estimates into gaze direction, a Gaussian process regression model is proposed and the reasons validating this choice are discussed in detail.

Original languageTurkish
Title of host publicationSIU 2010 - IEEE 18th Signal Processing and Communications Applications Conference
Pages224-227
Number of pages4
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event18th IEEE Signal Processing and Communications Applications Conference, SIU 2010 - Diyarbakir, Turkey
Duration: Apr 22 2010Apr 24 2010

Other

Other
CountryTurkey
CityDiyarbakir
Period4/22/104/24/10

Fingerprint

Human computer interaction
Concretes
Robots
Experiments

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this

Yucel, Z., Salah, A. A., Meriçli, Ç. ., & Meriçli, T. (2010). Kafa duruşu kestirimlerinden bakiş yönünün türetilmesi. In SIU 2010 - IEEE 18th Signal Processing and Communications Applications Conference (pp. 224-227). [5652736] https://doi.org/10.1109/SIU.2010.5652736

Kafa duruşu kestirimlerinden bakiş yönünün türetilmesi. / Yucel, Zeynep; Salah, Albert Ali; Meriçli, Çetin ̧; Meriçli, Tekin.

SIU 2010 - IEEE 18th Signal Processing and Communications Applications Conference. 2010. p. 224-227 5652736.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yucel, Z, Salah, AA, Meriçli, Ç & Meriçli, T 2010, Kafa duruşu kestirimlerinden bakiş yönünün türetilmesi. in SIU 2010 - IEEE 18th Signal Processing and Communications Applications Conference., 5652736, pp. 224-227, Diyarbakir, Turkey, 4/22/10. https://doi.org/10.1109/SIU.2010.5652736
Yucel Z, Salah AA, Meriçli Ç, Meriçli T. Kafa duruşu kestirimlerinden bakiş yönünün türetilmesi. In SIU 2010 - IEEE 18th Signal Processing and Communications Applications Conference. 2010. p. 224-227. 5652736 https://doi.org/10.1109/SIU.2010.5652736
Yucel, Zeynep ; Salah, Albert Ali ; Meriçli, Çetin ̧ ; Meriçli, Tekin. / Kafa duruşu kestirimlerinden bakiş yönünün türetilmesi. SIU 2010 - IEEE 18th Signal Processing and Communications Applications Conference. 2010. pp. 224-227
@inproceedings{72f600166349417488fb0e4076bdd555,
title = "Kafa duruşu kestirimlerinden bakiş y{\"o}n{\"u}n{\"u}n t{\"u}retilmesi",
abstract = "Automatic estimation of gaze direction information is important for certain applications of human-robot and human-computer interaction. Depending on the properties of the specific application, it may be required to derive this information in real time from low resolution visual inputs, with as much precision as possible. In this paper we present an algorithm for transforming head pose estimates to gaze direction estimates. The main contribution of this study lies in the fact that it makes a clear distinction between head pose and gaze direction. Unlike some of the previous works in this field, we do not correct the head pose to correspond to a possible attention fixation point in accordance with the experiment scenario. Instead we propose using a concrete and environment-independent method for this purpose. To transform the head pose estimates into gaze direction, a Gaussian process regression model is proposed and the reasons validating this choice are discussed in detail.",
author = "Zeynep Yucel and Salah, {Albert Ali} and Meri{\cc}li, {{\cC}etin ̧} and Tekin Meri{\cc}li",
year = "2010",
doi = "10.1109/SIU.2010.5652736",
language = "Turkish",
isbn = "9781424496716",
pages = "224--227",
booktitle = "SIU 2010 - IEEE 18th Signal Processing and Communications Applications Conference",

}

TY - GEN

T1 - Kafa duruşu kestirimlerinden bakiş yönünün türetilmesi

AU - Yucel, Zeynep

AU - Salah, Albert Ali

AU - Meriçli, Çetin ̧

AU - Meriçli, Tekin

PY - 2010

Y1 - 2010

N2 - Automatic estimation of gaze direction information is important for certain applications of human-robot and human-computer interaction. Depending on the properties of the specific application, it may be required to derive this information in real time from low resolution visual inputs, with as much precision as possible. In this paper we present an algorithm for transforming head pose estimates to gaze direction estimates. The main contribution of this study lies in the fact that it makes a clear distinction between head pose and gaze direction. Unlike some of the previous works in this field, we do not correct the head pose to correspond to a possible attention fixation point in accordance with the experiment scenario. Instead we propose using a concrete and environment-independent method for this purpose. To transform the head pose estimates into gaze direction, a Gaussian process regression model is proposed and the reasons validating this choice are discussed in detail.

AB - Automatic estimation of gaze direction information is important for certain applications of human-robot and human-computer interaction. Depending on the properties of the specific application, it may be required to derive this information in real time from low resolution visual inputs, with as much precision as possible. In this paper we present an algorithm for transforming head pose estimates to gaze direction estimates. The main contribution of this study lies in the fact that it makes a clear distinction between head pose and gaze direction. Unlike some of the previous works in this field, we do not correct the head pose to correspond to a possible attention fixation point in accordance with the experiment scenario. Instead we propose using a concrete and environment-independent method for this purpose. To transform the head pose estimates into gaze direction, a Gaussian process regression model is proposed and the reasons validating this choice are discussed in detail.

UR - http://www.scopus.com/inward/record.url?scp=78651456584&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651456584&partnerID=8YFLogxK

U2 - 10.1109/SIU.2010.5652736

DO - 10.1109/SIU.2010.5652736

M3 - Conference contribution

SN - 9781424496716

SP - 224

EP - 227

BT - SIU 2010 - IEEE 18th Signal Processing and Communications Applications Conference

ER -