Gaze-based Interface Research Articles

The impact of visual and motor space size on gaze-based target selection

ABSTRACT Objective Previous studies have demonstrated that making a target larger is sufficient to compensate for the inaccuracy of gaze-based target selection. However, few studies systemically examined the individual contribution of the target’s motor and visual space size in gaze selection. We investigated how the motor and visual space size affect gaze-based target selection. Method Experiment 1 was used to examine the effect of the invisible expanded motor space in a 2D target selection task under hand-based and gaze-based control modes. Experiment 2 was used to examine the impact of the invisible expanded motor space on gaze-based target selection performance with different visual-space sizes. Results As the motor-space size increased, participants selected targets more efficiently and experienced less frustration and temporal demand; these effects were more pronounced in the gaze-based control mode. The selection was faster in the group with a larger visual-space size. Moreover, there were significant interactions between visual-space size and motor-space size on the throughput of gaze-based selection, which refers to the efficiency of input method that containing the accuracy and speed. These interactions also significantly affected endpoint distance variation and effort demand. Conclusions The motor-space size, even invisible, is the determining factor in facilitating the gaze selection performance. Additionally, the size of the visual space has a feedforward effect on selection speed and modulates the effect of motor space. These findings provide insights into the contribution of these two spaces and a new perspective to optimize the gaze-based interface.

Wheelchair driving strategies: A comparison between standard joystick and gaze-based control

ABSTRACT This paper aims to evaluate and compare the driving performances achieved with a power wheelchair using a standard joystick versus a novel gaze-based technology. The gaze-based interface, called RoboEYE, involves a novel paradigm of computer interaction that handles the receipt of information from an eye tracker, using it as a continuous input for wheelchair navigation. A pool of 36 subjects has tested both technologies in a circuit designed considering the Wheelchair Skill Test. The experimental analysis involved evaluations of specific metrics of motion and the submission of questionnaires to collect required information about perceived feelings and mental workload. The joystick proved to be the best driving interface. It turned out to be more accurate and efficient than the gaze-based solution. However, the latter achieved only small differences in driving kinematics. These differences can be considered negligible from an operational point of view, offering a driving experience similar to that achievable with the joystick. Testers reported no particular stress, fatigue, or frustration when switching from one interface to another. These elements suggest that the proposed gaze-based solution is an appropriate alternative for a technology transition driven by a pathological change in the user’s condition.

MEG-Based Detection of Voluntary Eye Fixations Used to Control a Computer.

Gaze-based input is an efficient way of hand-free human-computer interaction. However, it suffers from the inability of gaze-based interfaces to discriminate voluntary and spontaneous gaze behaviors, which are overtly similar. Here, we demonstrate that voluntary eye fixations can be discriminated from spontaneous ones using short segments of magnetoencephalography (MEG) data measured immediately after the fixation onset. Recently proposed convolutional neural networks (CNNs), linear finite impulse response filters CNN (LF-CNN) and vector autoregressive CNN (VAR-CNN), were applied for binary classification of the MEG signals related to spontaneous and voluntary eye fixations collected in healthy participants (n = 25) who performed a game-like task by fixating on targets voluntarily for 500 ms or longer. Voluntary fixations were identified as those followed by a fixation in a special confirmatory area. Spontaneous vs. voluntary fixation-related single-trial 700 ms MEG segments were non-randomly classified in the majority of participants, with the group average cross-validated ROC AUC of 0.66 ± 0.07 for LF-CNN and 0.67 ± 0.07 for VAR-CNN (M ± SD). When the time interval, from which the MEG data were taken, was extended beyond the onset of the visual feedback, the group average classification performance increased up to 0.91. Analysis of spatial patterns contributing to classification did not reveal signs of significant eye movement impact on the classification results. We conclude that the classification of MEG signals has a certain potential to support gaze-based interfaces by avoiding false responses to spontaneous eye fixations on a single-trial basis. Current results for intention detection prior to gaze-based interface’s feedback, however, are not sufficient for online single-trial eye fixation classification using MEG data alone, and further work is needed to find out if it could be used in practical applications.

Calibration-Free Gaze Interfaces Based on Linear Smooth Pursuit.

Since smooth pursuit eye movements can be used without calibration in spontaneous gaze interaction, the intuitiveness of the gaze interface design has been a topic of great interest in the human-computer interaction field. However, since most related research focuses on curved smooth-pursuit trajectories, the design issues of linear trajectories are poorly understood. Hence, this study evaluated the user performance of gaze interfaces based on linear smooth pursuit eye movements. We conducted an experiment to investigate how the number of objects (6, 8, 10, 12, or 15) and object moving speed (7.73 ˚/s vs. 12.89 ˚/s) affect the user performance in a gaze-based interface. Results show that the number and speed of the displayed objects influence users’ performance with the interface. The number of objects significantly affected the correct and false detection rates when selecting objects in the display. Participants’ performance was highest on interfaces containing 6 and 8 objects and decreased for interfaces with 10, 12, and 15 objects. Detection rates and orientation error were significantly influenced by the moving speed of displayed objects. Faster moving speed (12.89 ˚/s) resulted in higher detection rates and smaller orientation error compared to slower moving speeds (7.73 ˚/s). Our findings can help to enable a calibration-free accessible interaction with gaze interfaces.

Gaze-based Kinaesthetic Interaction for Virtual Reality

AbstractKinaesthetic interaction using force-feedback devices is promising in virtual reality. However, the devices are currently not suitable for interactions within large virtual spaces because of their limited workspace. We developed a novel gaze-based kinaesthetic interface that employs the user’s gaze to relocate the device workspace. The workspace switches to a new location when the user pulls the mechanical arm of the device to its reset position and gazes at the new target. This design enables the robust relocating of device workspace, thus achieving an infinite interaction space, and simultaneously maintains a flexible hand-based kinaesthetic exploration. We compared the new interface with the scaling-based traditional interface in an experiment involving softness and smoothness discrimination. Our results showed that the gaze-based interface performs better than the traditional interface, in terms of efficiency and kinaesthetic perception. It improves the user experience for kinaesthetic interaction in virtual reality without increasing eye strain.

Evaluating gaze-based interface tools to facilitate point-and-select tasks with small targets

Gaze interaction affords hands-free control of computers. Pointing to and selecting small targets using gaze alone is difficult because of the limited accuracy of gaze pointing. This is the first experimental comparison of gaze-based interface tools for small-target (e.g. <12 × 12 pixels) point-and-select tasks. We conducted two experiments comparing the performance of dwell, magnification and zoom methods in point-and-select tasks with small targets in single- and multiple-target layouts. Both magnification and zoom showed higher hit rates than dwell. Hit rates were higher when using magnification than when using zoom, but total pointing times were shorter using zoom. Furthermore, participants perceived magnification as more fatiguing than zoom. The higher accuracy of magnification makes it preferable when interacting with small targets. Our findings may guide the development of interface tools to facilitate access to mainstream interfaces for people with motor disabilities and other users in need of hands-free interaction.

Investigating shared attention with a virtual agent using a gaze-based interface

This paper investigates the use of a gaze-based interface for testing simple shared attention behaviours during an interaction scenario with a virtual agent. The interface is non-intrusive, operating in real-time using a standard web-camera for input, monitoring users’ head directions and processing them in real-time for resolution to screen coordinates. We use the interface to investigate user perception of the agent’s behaviour during a shared attention scenario. Our aim is to elaborate important factors to be considered when constructing engagement models that must account not only for behaviour in isolation, but also for the context of the interaction, as is the case during shared attention situations.