Comparing two eye-tracking databases : the effect of experimental setup and image presentation time on the creation of saliency maps

U. Engelke; H. Liu; H.-J. Zepernick; I.E.J. Heynderickx; A. Maeder

doi:10.1109/PCS.2010.5702487

Comparing two eye-tracking databases : the effect of experimental setup and image presentation time on the creation of saliency maps

U. Engelke, H. Liu, H.-J. Zepernick, I.E.J. Heynderickx, A. Maeder

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

5 Citations (Scopus)

Abstract

Visual attention models are typically designed based on human gaze patterns recorded through eye tracking. In this paper, two similar eye tracking experiments from independent laboratories are presented, in which humans observed natural images under task-free condition. The resulting saliency maps are analysed with respect to two criteria; the consistency between the experiments and the impact of the image presentation time. It is shown, that the saliency maps between the experiments are strongly correlated independent of presentation time. It is further revealed that the presentation time can be reduced without substantially sacrificing the accuracy of the convergent saliency map. The results provide valuable insight into the similarity of saliency maps from independent laboratories and are highly beneficial for the creation of converging saliency maps at reduced experimental time and cost. © 2010 IEEE.

Original language	English
Title of host publication	28th Picture Coding Symposium (PCS), 8-10 December 2010, Nagoya
Place of Publication	Nagoya
Pages	282-285
DOIs	https://doi.org/10.1109/PCS.2010.5702487
Publication status	Published - 2010

Access to Document

10.1109/PCS.2010.5702487

Cite this

@inproceedings{9cf9c59ed2244266a45aa22c00f43b99,

title = "Comparing two eye-tracking databases : the effect of experimental setup and image presentation time on the creation of saliency maps",

abstract = "Visual attention models are typically designed based on human gaze patterns recorded through eye tracking. In this paper, two similar eye tracking experiments from independent laboratories are presented, in which humans observed natural images under task-free condition. The resulting saliency maps are analysed with respect to two criteria; the consistency between the experiments and the impact of the image presentation time. It is shown, that the saliency maps between the experiments are strongly correlated independent of presentation time. It is further revealed that the presentation time can be reduced without substantially sacrificing the accuracy of the convergent saliency map. The results provide valuable insight into the similarity of saliency maps from independent laboratories and are highly beneficial for the creation of converging saliency maps at reduced experimental time and cost. {\textcopyright} 2010 IEEE.",

author = "U. Engelke and H. Liu and H.-J. Zepernick and I.E.J. Heynderickx and A. Maeder",

year = "2010",

doi = "10.1109/PCS.2010.5702487",

language = "English",

pages = "282--285",

booktitle = "28th Picture Coding Symposium (PCS), 8-10 December 2010, Nagoya",

}

Comparing two eye-tracking databases : the effect of experimental setup and image presentation time on the creation of saliency maps. / Engelke, U.; Liu, H.; Zepernick, H.-J. et al.
28th Picture Coding Symposium (PCS), 8-10 December 2010, Nagoya. Nagoya, 2010. p. 282-285.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Comparing two eye-tracking databases : the effect of experimental setup and image presentation time on the creation of saliency maps

AU - Engelke, U.

AU - Liu, H.

AU - Zepernick, H.-J.

AU - Heynderickx, I.E.J.

AU - Maeder, A.

PY - 2010

Y1 - 2010

N2 - Visual attention models are typically designed based on human gaze patterns recorded through eye tracking. In this paper, two similar eye tracking experiments from independent laboratories are presented, in which humans observed natural images under task-free condition. The resulting saliency maps are analysed with respect to two criteria; the consistency between the experiments and the impact of the image presentation time. It is shown, that the saliency maps between the experiments are strongly correlated independent of presentation time. It is further revealed that the presentation time can be reduced without substantially sacrificing the accuracy of the convergent saliency map. The results provide valuable insight into the similarity of saliency maps from independent laboratories and are highly beneficial for the creation of converging saliency maps at reduced experimental time and cost. © 2010 IEEE.

AB - Visual attention models are typically designed based on human gaze patterns recorded through eye tracking. In this paper, two similar eye tracking experiments from independent laboratories are presented, in which humans observed natural images under task-free condition. The resulting saliency maps are analysed with respect to two criteria; the consistency between the experiments and the impact of the image presentation time. It is shown, that the saliency maps between the experiments are strongly correlated independent of presentation time. It is further revealed that the presentation time can be reduced without substantially sacrificing the accuracy of the convergent saliency map. The results provide valuable insight into the similarity of saliency maps from independent laboratories and are highly beneficial for the creation of converging saliency maps at reduced experimental time and cost. © 2010 IEEE.

U2 - 10.1109/PCS.2010.5702487

DO - 10.1109/PCS.2010.5702487

M3 - Conference contribution

SP - 282

EP - 285

BT - 28th Picture Coding Symposium (PCS), 8-10 December 2010, Nagoya

CY - Nagoya

ER -

Comparing two eye-tracking databases : the effect of experimental setup and image presentation time on the creation of saliency maps

Abstract

Access to Document

Fingerprint

Cite this