Error-aware gaze-based interfaces for robust mobile gaze interaction

Barz, Michael; Daiber, Florian; Sonntag, Daniel; Bulling, Andreas

doi:10.1145/3204493.3204536

Cited by 29 publications

(23 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The same group recently reported an average calibration accuracy of 3.9-4.34 • for this eye tracker (FOVE; [47]). The range of these values highlight the necessity of good eye tracking fdelity to achieve robust target selection, and newer approaches are already circumventing this limitation by adapting user interfaces (UIs) to the available gaze tracking performance, for example by dynamically changing the size of UI elements [2,14].…”

Section: Related Work and Background Eye Gaze For Selectionmentioning

confidence: 99%

An Explanation of Fitts' Law-like Performance in Gaze-Based Selection Tasks Using a Psychophysics Approach

Schütz

Murdison

MacKenzie

et al. 2019

Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Eye gaze as an input method has been studied since the 1990s, to varied results: some studies found gaze to be more efcient than traditional input methods like a mouse, others far behind. Comparisons are often backed up by Fitts' Law without explicitly acknowledging the ballistic nature of saccadic eye movements. Using a vision science-inspired model, we here show that a Fitts'-like distribution of movement times can arise due to the execution of secondary saccades, especially when targets are small. Study participants selected circular targets using gaze. Seven diferent target sizes and two saccade distances were used. We then determined performance across target sizes for diferent sampling windows ("dwell times") and predicted an optimal dwell time range. Best performance was achieved for large targets reachable by a single saccade. Our fndings highlight that Fitts' Law, while a suitable approximation in some cases, is an incomplete description of gaze interaction dynamics. CCS CONCEPTS • Human-centered computing → Pointing devices; Pointing; User models; User studies.

show abstract

Section: Related Work and Background Eye Gaze For Selectionmentioning

confidence: 99%

An Explanation of Fitts' Law-like Performance in Gaze-Based Selection Tasks Using a Psychophysics Approach

Schütz

Murdison

MacKenzie

et al. 2019

Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Gaze-tracking equipment has become robust, inexpensive and accurate, and gaze sensors may soon be included in computers, phones, tablets, and head-mounted displays (Barz et al, 2018;Hu & Lodewijks, 2020). The use of eyebased physiological signals derived from blinks (Martins & Carvalho, 2015;Stern et al, 1984), eye movements (Cazzoli et al, 2014;Hirvonen et al, 2010), and pupils (Marandi et al, 2019;Morad et al, 2000), recorded using eye-tracking (Hopstaken et al, 2015b;Itoh et al, 2000;Li, Chen et al, 2019;Maffei & Angrilli, 2018;Marandi et al, 2018) and electro-oculography (EOGHirvonen et al, 2010;Tag et al, 2019), have received increased scrutiny in the past years as a means of measuring fatigue (Dawson et al, 2014;Eckstein et al, 2017;Kramer, 1991;Martins & Carvalho, 2015).…”

Section: Introductionmentioning

confidence: 99%

Mental fatigue measurement using eye metrics: A systematic literature review

Bafna

Hansen

2021

Psychophysiology

View full text Add to dashboard Cite

Mental fatigue measurement techniques utilize one or a combination of the cognitive, affective, and behavioral responses of the body. Eye-tracking and electrooculography, which are used to compute eye-based features, have gained momentum with increases in accuracy and robustness of the lightweight equipment emerging in the markets and can be used for objective and continuous assessment of mental fatigue. The main goal of this systematic review was to summarize the various eye-based features that have been used to measure mental fatigue and explore the relation of eye-based features to mental fatigue. The review process, following the preferred reporting items for systematic reviews and meta-analyses, used the electronic databases Web of Science, Scopus, ACM digital library, IEEE Xplore, and PubMed. Of the 1,385 retrieved documents, 34 studies met the inclusion criteria, resulting in 21 useful eye-based features. Categorizing these into eight groups revealed saccades as the most promising category, with saccade mean and peak velocity providing quick access to the cognitive states within 30 min of fatiguing activity. Complex brain networks involving sympathetic and parasympathetic nervous systems control the relation of mental fatigue to tonic pupil size and have the potential to indicate mental fatigue in controlled experimental conditions. Other categories, like blinks, are derived from the field of sleep research and should be used with caution. Several limitations emerged in the analysis, including varied experimental methods, use of dim lighting during the experiment (that could possibly also induce sleepiness), and use of unclear data analysis techniques, thereby complicating comparisons between studies.

show abstract

“…However, fixation-wise annotation does not remedy the need to annotate AOIs in every recording of every participant. A solution can be found in attaching fiducial markers to, e.g., a target stimulus in 2D [ 3 ] and 3D [ 4 ], an interactive area [ 5 ], or tangible objects [ 6 ]. In this research, we aim at circumventing the requirement to instrument the environment with obtrusive markers.…”

Section: Introductionmentioning

confidence: 99%

Automatic Visual Attention Detection for Mobile Eye Tracking Using Pre-Trained Computer Vision Models and Human Gaze

Barz

Sonntag

2021

Sensors

Self Cite

View full text Add to dashboard Cite

Processing visual stimuli in a scene is essential for the human brain to make situation-aware decisions. These stimuli, which are prevalent subjects of diagnostic eye tracking studies, are commonly encoded as rectangular areas of interest (AOIs) per frame. Because it is a tedious manual annotation task, the automatic detection and annotation of visual attention to AOIs can accelerate and objectify eye tracking research, in particular for mobile eye tracking with egocentric video feeds. In this work, we implement two methods to automatically detect visual attention to AOIs using pre-trained deep learning models for image classification and object detection. Furthermore, we develop an evaluation framework based on the VISUS dataset and well-known performance metrics from the field of activity recognition. We systematically evaluate our methods within this framework, discuss potentials and limitations, and propose ways to improve the performance of future automatic visual attention detection methods.

show abstract

Error-aware gaze-based interfaces for robust mobile gaze interaction

Cited by 29 publications

References 40 publications

An Explanation of Fitts' Law-like Performance in Gaze-Based Selection Tasks Using a Psychophysics Approach

An Explanation of Fitts' Law-like Performance in Gaze-Based Selection Tasks Using a Psychophysics Approach

Mental fatigue measurement using eye metrics: A systematic literature review

Automatic Visual Attention Detection for Mobile Eye Tracking Using Pre-Trained Computer Vision Models and Human Gaze

Contact Info

Product

Resources

About