A Validation of Automatically-Generated Areas-of-Interest in Videos of a Face for Eye-Tracking Research
When mapping eye-movement behavior to the visual information presented to an observer, Areas of Interest (AOIs) are commonly employed. For static stimuli (screen without moving elements), this requires that one AOI set is constructed for each stimulus, a possibility in most eye-tracker manufacturers...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2018-08-01
|
| Series: | Frontiers in Psychology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fpsyg.2018.01367/full |
| _version_ | 1819243310192001024 |
|---|---|
| author | Roy S. Hessels Roy S. Hessels Jeroen S. Benjamins Jeroen S. Benjamins Tim H. W. Cornelissen Ignace T. C. Hooge |
| author_facet | Roy S. Hessels Roy S. Hessels Jeroen S. Benjamins Jeroen S. Benjamins Tim H. W. Cornelissen Ignace T. C. Hooge |
| author_sort | Roy S. Hessels |
| collection | DOAJ |
| description | When mapping eye-movement behavior to the visual information presented to an observer, Areas of Interest (AOIs) are commonly employed. For static stimuli (screen without moving elements), this requires that one AOI set is constructed for each stimulus, a possibility in most eye-tracker manufacturers' software. For moving stimuli (screens with moving elements), however, it is often a time-consuming process, as AOIs have to be constructed for each video frame. A popular use-case for such moving AOIs is to study gaze behavior to moving faces. Although it is technically possible to construct AOIs automatically, the standard in this field is still manual AOI construction. This is likely due to the fact that automatic AOI-construction methods are (1) technically complex, or (2) not effective enough for empirical research. To aid researchers in this field, we present and validate a method that automatically achieves AOI construction for videos containing a face. The fully-automatic method uses an open-source toolbox for facial landmark detection, and a Voronoi-based AOI-construction method. We compared the position of AOIs obtained using our new method, and the eye-tracking measures derived from it, to a recently published semi-automatic method. The differences between the two methods were negligible. The presented method is therefore both effective (as effective as previous methods), and efficient; no researcher time is needed for AOI construction. The software is freely available from https://osf.io/zgmch/. |
| first_indexed | 2024-12-23T14:53:40Z |
| format | Article |
| id | doaj.art-cdb92485eb8141ca97ec78b330f5c06b |
| institution | Directory Open Access Journal |
| issn | 1664-1078 |
| language | English |
| last_indexed | 2024-12-23T14:53:40Z |
| publishDate | 2018-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychology |
| spelling | doaj.art-cdb92485eb8141ca97ec78b330f5c06b2022-12-21T17:42:52ZengFrontiers Media S.A.Frontiers in Psychology1664-10782018-08-01910.3389/fpsyg.2018.01367382113A Validation of Automatically-Generated Areas-of-Interest in Videos of a Face for Eye-Tracking ResearchRoy S. Hessels0Roy S. Hessels1Jeroen S. Benjamins2Jeroen S. Benjamins3Tim H. W. Cornelissen4Ignace T. C. Hooge5Experimental Psychology, Helmholtz Institute, Utrecht University, Utrecht, NetherlandsDevelopmental Psychology, Utrecht University, Utrecht, NetherlandsExperimental Psychology, Helmholtz Institute, Utrecht University, Utrecht, NetherlandsSocial, Health and Organisational Psychology, Utrecht University, Utrecht, NetherlandsScene Grammar Lab, Department of Cognitive Psychology, Goethe University Frankfurt, Frankfurt, GermanyExperimental Psychology, Helmholtz Institute, Utrecht University, Utrecht, NetherlandsWhen mapping eye-movement behavior to the visual information presented to an observer, Areas of Interest (AOIs) are commonly employed. For static stimuli (screen without moving elements), this requires that one AOI set is constructed for each stimulus, a possibility in most eye-tracker manufacturers' software. For moving stimuli (screens with moving elements), however, it is often a time-consuming process, as AOIs have to be constructed for each video frame. A popular use-case for such moving AOIs is to study gaze behavior to moving faces. Although it is technically possible to construct AOIs automatically, the standard in this field is still manual AOI construction. This is likely due to the fact that automatic AOI-construction methods are (1) technically complex, or (2) not effective enough for empirical research. To aid researchers in this field, we present and validate a method that automatically achieves AOI construction for videos containing a face. The fully-automatic method uses an open-source toolbox for facial landmark detection, and a Voronoi-based AOI-construction method. We compared the position of AOIs obtained using our new method, and the eye-tracking measures derived from it, to a recently published semi-automatic method. The differences between the two methods were negligible. The presented method is therefore both effective (as effective as previous methods), and efficient; no researcher time is needed for AOI construction. The software is freely available from https://osf.io/zgmch/.https://www.frontiersin.org/article/10.3389/fpsyg.2018.01367/fulleye trackingAreas of Interestfacesautomaticvideos |
| spellingShingle | Roy S. Hessels Roy S. Hessels Jeroen S. Benjamins Jeroen S. Benjamins Tim H. W. Cornelissen Ignace T. C. Hooge A Validation of Automatically-Generated Areas-of-Interest in Videos of a Face for Eye-Tracking Research Frontiers in Psychology eye tracking Areas of Interest faces automatic videos |
| title | A Validation of Automatically-Generated Areas-of-Interest in Videos of a Face for Eye-Tracking Research |
| title_full | A Validation of Automatically-Generated Areas-of-Interest in Videos of a Face for Eye-Tracking Research |
| title_fullStr | A Validation of Automatically-Generated Areas-of-Interest in Videos of a Face for Eye-Tracking Research |
| title_full_unstemmed | A Validation of Automatically-Generated Areas-of-Interest in Videos of a Face for Eye-Tracking Research |
| title_short | A Validation of Automatically-Generated Areas-of-Interest in Videos of a Face for Eye-Tracking Research |
| title_sort | validation of automatically generated areas of interest in videos of a face for eye tracking research |
| topic | eye tracking Areas of Interest faces automatic videos |
| url | https://www.frontiersin.org/article/10.3389/fpsyg.2018.01367/full |
| work_keys_str_mv | AT royshessels avalidationofautomaticallygeneratedareasofinterestinvideosofafaceforeyetrackingresearch AT royshessels avalidationofautomaticallygeneratedareasofinterestinvideosofafaceforeyetrackingresearch AT jeroensbenjamins avalidationofautomaticallygeneratedareasofinterestinvideosofafaceforeyetrackingresearch AT jeroensbenjamins avalidationofautomaticallygeneratedareasofinterestinvideosofafaceforeyetrackingresearch AT timhwcornelissen avalidationofautomaticallygeneratedareasofinterestinvideosofafaceforeyetrackingresearch AT ignacetchooge avalidationofautomaticallygeneratedareasofinterestinvideosofafaceforeyetrackingresearch AT royshessels validationofautomaticallygeneratedareasofinterestinvideosofafaceforeyetrackingresearch AT royshessels validationofautomaticallygeneratedareasofinterestinvideosofafaceforeyetrackingresearch AT jeroensbenjamins validationofautomaticallygeneratedareasofinterestinvideosofafaceforeyetrackingresearch AT jeroensbenjamins validationofautomaticallygeneratedareasofinterestinvideosofafaceforeyetrackingresearch AT timhwcornelissen validationofautomaticallygeneratedareasofinterestinvideosofafaceforeyetrackingresearch AT ignacetchooge validationofautomaticallygeneratedareasofinterestinvideosofafaceforeyetrackingresearch |