Estimation for the eye movement using the spanning tree of transition probability-based graphs

Szilard Szilái, Z. Vidnyánszky, T. Szirányi

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

Abstract

In this paper, we present an algorithm for estimating the eye movement looking at a picture. Our solution is based on human data measured by a wearable eye tracker device which is able to record the user's eye movement during the record. From the same video streams, measuring the artificial salient points on the image by machine vision algorithms, the clusters of these points are assigned according to human measurement data in a learning procedure, and, as a result, transition probability tables are generated containing information on the behavior of a human subject. Using these data, we constructed an algorithm that estimates the movement of the eye on a picture taken in a similar place and during similar conditions. The algorithm generates graphs based on these probability tables and uses their spanning trees to calculate the position of the points that are likely to be visited by the gaze in human experiments. We compared the results with real human tests where subjects were expected to look at the pictures for a certain time.

Original languageEnglish
Title of host publication2011 2nd International Conference on Cognitive Infocommunications, CogInfoCom 2011
Publication statusPublished - 2011
Event2011 2nd International Conference on Cognitive Infocommunications, CogInfoCom 2011 - Budapest, Hungary
Duration: Jul 7 2011Jul 9 2011

Other

Other2011 2nd International Conference on Cognitive Infocommunications, CogInfoCom 2011
CountryHungary
CityBudapest
Period7/7/117/9/11

Fingerprint

Eye movements
Trees (mathematics)
Computer vision
Experiments

Keywords

  • clustering
  • eye tracker
  • eye tracking
  • graph
  • k-means
  • saliency
  • scene analysis
  • spanning tree
  • statistical summary
  • transition probability table

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications

Cite this

Szilái, S., Vidnyánszky, Z., & Szirányi, T. (2011). Estimation for the eye movement using the spanning tree of transition probability-based graphs. In 2011 2nd International Conference on Cognitive Infocommunications, CogInfoCom 2011 [5999454]

Estimation for the eye movement using the spanning tree of transition probability-based graphs. / Szilái, Szilard; Vidnyánszky, Z.; Szirányi, T.

2011 2nd International Conference on Cognitive Infocommunications, CogInfoCom 2011. 2011. 5999454.

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

Szilái, S, Vidnyánszky, Z & Szirányi, T 2011, Estimation for the eye movement using the spanning tree of transition probability-based graphs. in 2011 2nd International Conference on Cognitive Infocommunications, CogInfoCom 2011., 5999454, 2011 2nd International Conference on Cognitive Infocommunications, CogInfoCom 2011, Budapest, Hungary, 7/7/11.
Szilái S, Vidnyánszky Z, Szirányi T. Estimation for the eye movement using the spanning tree of transition probability-based graphs. In 2011 2nd International Conference on Cognitive Infocommunications, CogInfoCom 2011. 2011. 5999454
Szilái, Szilard ; Vidnyánszky, Z. ; Szirányi, T. / Estimation for the eye movement using the spanning tree of transition probability-based graphs. 2011 2nd International Conference on Cognitive Infocommunications, CogInfoCom 2011. 2011.
@inproceedings{6621aa73765243ffb9a63dbbf05df40b,
title = "Estimation for the eye movement using the spanning tree of transition probability-based graphs",
abstract = "In this paper, we present an algorithm for estimating the eye movement looking at a picture. Our solution is based on human data measured by a wearable eye tracker device which is able to record the user's eye movement during the record. From the same video streams, measuring the artificial salient points on the image by machine vision algorithms, the clusters of these points are assigned according to human measurement data in a learning procedure, and, as a result, transition probability tables are generated containing information on the behavior of a human subject. Using these data, we constructed an algorithm that estimates the movement of the eye on a picture taken in a similar place and during similar conditions. The algorithm generates graphs based on these probability tables and uses their spanning trees to calculate the position of the points that are likely to be visited by the gaze in human experiments. We compared the results with real human tests where subjects were expected to look at the pictures for a certain time.",
keywords = "clustering, eye tracker, eye tracking, graph, k-means, saliency, scene analysis, spanning tree, statistical summary, transition probability table",
author = "Szilard Szil{\'a}i and Z. Vidny{\'a}nszky and T. Szir{\'a}nyi",
year = "2011",
language = "English",
isbn = "9781457718069",
booktitle = "2011 2nd International Conference on Cognitive Infocommunications, CogInfoCom 2011",

}

TY - GEN

T1 - Estimation for the eye movement using the spanning tree of transition probability-based graphs

AU - Szilái, Szilard

AU - Vidnyánszky, Z.

AU - Szirányi, T.

PY - 2011

Y1 - 2011

N2 - In this paper, we present an algorithm for estimating the eye movement looking at a picture. Our solution is based on human data measured by a wearable eye tracker device which is able to record the user's eye movement during the record. From the same video streams, measuring the artificial salient points on the image by machine vision algorithms, the clusters of these points are assigned according to human measurement data in a learning procedure, and, as a result, transition probability tables are generated containing information on the behavior of a human subject. Using these data, we constructed an algorithm that estimates the movement of the eye on a picture taken in a similar place and during similar conditions. The algorithm generates graphs based on these probability tables and uses their spanning trees to calculate the position of the points that are likely to be visited by the gaze in human experiments. We compared the results with real human tests where subjects were expected to look at the pictures for a certain time.

AB - In this paper, we present an algorithm for estimating the eye movement looking at a picture. Our solution is based on human data measured by a wearable eye tracker device which is able to record the user's eye movement during the record. From the same video streams, measuring the artificial salient points on the image by machine vision algorithms, the clusters of these points are assigned according to human measurement data in a learning procedure, and, as a result, transition probability tables are generated containing information on the behavior of a human subject. Using these data, we constructed an algorithm that estimates the movement of the eye on a picture taken in a similar place and during similar conditions. The algorithm generates graphs based on these probability tables and uses their spanning trees to calculate the position of the points that are likely to be visited by the gaze in human experiments. We compared the results with real human tests where subjects were expected to look at the pictures for a certain time.

KW - clustering

KW - eye tracker

KW - eye tracking

KW - graph

KW - k-means

KW - saliency

KW - scene analysis

KW - spanning tree

KW - statistical summary

KW - transition probability table

UR - http://www.scopus.com/inward/record.url?scp=80052888785&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052888785&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:80052888785

SN - 9781457718069

BT - 2011 2nd International Conference on Cognitive Infocommunications, CogInfoCom 2011

ER -