Jump to content

Eye tracking

From VR & AR Wiki
Revision as of 16:47, 24 April 2025 by Xinreality (talk | contribs) (→Standards and Regulations)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
See also: Terms and Technical Terms

Eye tracking is a sensor technology that measures eye positions and eye movement. In the context of virtual reality (VR) and augmented reality (AR), it refers to the integration of sensors within VR headsets or AR headsets to determine precisely where the user is looking (gaze) in real-time within the virtual environment or overlaid digital interface. By accurately monitoring characteristics like pupil position, corneal reflections, and eye movements such as saccades and fixations, this technology enables more immersive, efficient, and intuitive user experiences. It has become an increasingly critical feature in modern head-mounted displays (HMDs), driving advancements in rendering, interaction, analytics, and social presence.[1]

History

While its integration into consumer VR/AR is relatively recent, the systematic study of eye movements dates back to the 19th century. Louis Émile Javal noted in 1879 that reading involved discrete stops (fixations) and rapid movements (saccades).[2] Early tracking devices included Edmund Huey's contact lens-based tracker (~1908)[3] and Guy Thomas Buswell's film-based systems in the 1930s. Alfred L. Yarbus's work in the 1960s highlighted how viewing patterns are task-dependent.[4] These foundational efforts paved the way for modern video-based and integrated tracking systems.

Technical Principles

Tracking Method

Most eye tracking systems in contemporary VR and AR headsets employ one of several core technologies:

  • Pupil Center Corneal Reflection (PCCR): This is the predominant method. It involves:[5][6]
  • Illumination: Infrared (IR) light-emitting diodes (LEDs) safely illuminate the eye. IR light is used because it is invisible to the human eye, preventing distraction, and provides high contrast for cameras.
  • Imaging: Small, high-frame rate infrared cameras capture images of the eye, specifically tracking the center of the pupil and the reflection(s) of the IR light off the surface of the cornea (known as glints).
  • Algorithmic Processing: Sophisticated computer vision and image processing algorithms analyze the captured images. By calculating the vector between the pupil center and the corneal reflection(s), the system determines the eye's orientation and calculates the user's gaze point with high accuracy.
  • Calibration: A per-user calibration process is usually required upon first use, and sometimes periodically, to account for individual differences in eye physiology (e.g., corneal shape, pupil size range) and the precise fit of the headset. This typically involves the user looking at specific points displayed within the headset.
  • Video-based eye tracking (Shape/Feature Tracking): Uses cameras aimed at the eyes to capture images, which are then analyzed using computer vision algorithms to identify eye features (pupil outline, iris texture, blood vessels) to determine gaze direction without necessarily relying on corneal reflections.[7] PCCR is often considered a subset of this broader category.
  • Electrooculography (EOG): Measures the electrical potential difference between electrodes placed on the skin around the eyes. This potential changes predictably as the eye rotates. While less common for high-accuracy gaze pointing in consumer VR/AR due to lower precision and susceptibility to muscle noise, it can be used for detecting larger eye movements or in specialized applications.[8]
  • Scleral search coil: Involves wearing a special contact lens containing a wire coil. The user sits within a magnetic field, and eye movements induce currents in the coil, providing extremely precise measurements. This is highly invasive and primarily used in laboratory research, not consumer VR/AR.[9]

Key Components (PCCR-based)

A typical PCCR eye tracking system integrated into a VR/AR headset consists of:

  • Illuminators: Infrared LEDs providing consistent, non-visible lighting.
  • Cameras: Specialized high-speed infrared cameras positioned to capture clear images of both eyes.
  • Processing Unit: Either onboard SoC resources or dedicated hardware to run the detection and gaze calculation algorithms in real-time.
  • Calibration Software: Software routines guiding the user through calibration and storing individual profiles.[10]

Eye Movement Types Measured

Eye tracking systems in VR/AR can detect and analyze various types of eye movements and states:

  • Fixations: Periods when the gaze remains relatively stable on a specific area (typically > 100-200 ms), indicating visual attention.
  • Saccades: Rapid, ballistic movements shifting the gaze between fixation points (typically 30-120 ms).
  • Smooth pursuit: Movements allowing the eyes to smoothly follow a moving object.
  • Vergence: The simultaneous movement of both eyes in opposite directions to obtain or maintain single binocular vision, critical for focusing on objects at different depths.
  • Pupil Size / Dilation: Changes in pupil diameter (pupillometry), which can correlate with changes in light levels, cognitive load, emotional arousal, or interest.[11]
  • Blinks: Detection of eyelid closures.

Applications in VR and AR

Eye tracking unlocks numerous capabilities enhancing VR and AR experiences:

  • Foveated rendering: Arguably the most impactful application for performance. By knowing precisely where the user is looking, the system renders the scene at maximum resolution only in the small, central area of the user's gaze (corresponding to the eye's high-acuity fovea), while rendering the peripheral areas at progressively lower resolutions. This mimics human vision and can drastically reduce the computational load on the graphics processing unit (GPU) – potentially by 30% to over 70% – allowing for higher fidelity graphics, increased frame rates, reduced latency, or lower power consumption, all without a noticeable loss in perceived visual quality.[12][13][14]
  • Natural Interaction / Gaze-Based Interaction: Eye tracking enables more intuitive control schemes:
    • Gaze Selection/Pointing: Allows users to select objects, menu items, or targets simply by looking at them. This is often combined with a confirmation action like a button press on a controller, a hand tracking gesture (e.g., pinch), or a short dwell time.[15]
    • Intent Prediction: Systems can anticipate user actions or needs based on gaze patterns (e.g., highlighting an object the user looks at intently).
    • Gaze-directed Locomotion: Steering movement within the virtual world based on gaze direction.
  • Enhanced Social Presence / Avatar Realism: Realistic eye movements, including subtle saccades, blinks, and responsive gaze shifts, can be mirrored onto a user's avatar in social VR applications. This significantly enhances non-verbal communication and the feeling of social presence and connection when interacting with others.[16]
  • User Analytics and Research: Eye tracking provides invaluable objective data for:
    • Usability testing & User Experience (UX) Research: Understanding how users visually explore and interact with interfaces or environments.
    • Attention mapping: Creating heatmaps and gaze plots to visualize areas of interest and attention duration.
    • Cognitive Load Assessment: Measuring mental workload through metrics like pupil dilation, blink rate, and fixation patterns.[17]
    • Training and Simulation Analysis: Assessing trainee attention, situational awareness, and decision-making processes in professional simulations (e.g., medical, aviation).
  • Automatic IPD Adjustment: Some headsets utilize the eye tracking cameras to automatically measure the user's interpupillary distance (the distance between the centers of the pupils) and mechanically adjust the lens spacing for optimal visual clarity, stereo depth perception, and user comfort.
  • Accessibility: Eye tracking offers a powerful hands-free input modality for users with limited physical mobility, enabling them to navigate interfaces, communicate (e.g., gaze typing), and control applications within VR/AR.
  • Adaptive Optics / Varifocal displays: Eye tracking is essential for dynamic varifocal displays, which adjust their focal plane based on where the user is looking in virtual depth. This helps address the vergence-accommodation conflict, potentially reducing eye strain and improving visual realism.[18]
  • Dynamic Distortion Compensation: Real-time adjustments to lens distortion correction based on precise eye position relative to the lens center can improve perceived sharpness across the field of view.[13]

Current Implementations

Several commercially available VR and AR headsets incorporate integrated eye tracking:

VR Headsets with Eye Tracking

  • Apple Vision Pro: Uses high-precision eye tracking as a primary input method (combined with hand gestures and voice), enabling UI navigation, selection, and foveated rendering.[19]
  • Meta Quest Pro: Features inward-facing sensors for eye and face tracking, primarily used for foveated rendering and driving realistic avatar expressions in social applications.[16]
  • PlayStation VR2: Integrates Tobii eye tracking technology for foveated rendering, gaze-based interactions in games, and enhanced immersion.[20]
  • HTC VIVE Pro Eye: An earlier enterprise-focused headset integrating Tobii eye tracking (accuracy ~0.5-1.1 degrees, 120Hz). Newer VIVE models may offer eye tracking via add-ons (e.g., VIVE Focus 3 Eye Tracker).[21]
  • Varjo XR-4, XR-3, VR-3, Aero: High-end professional headsets featuring industrial-grade eye tracking (sub-degree accuracy, 200Hz) for demanding simulation, research, and design applications.[22][23]
  • Pimax Crystal: Consumer-focused high-resolution headset incorporating eye tracking for features like foveated rendering and automatic IPD adjustment.[24]
  • Pico 4 Enterprise (previously Pico Neo 3 Pro Eye): Enterprise headsets integrating Tobii eye tracking for business applications.[25]
  • HP Reverb G2 Omnicept Edition: Featured integrated eye tracking (along with other biometric sensors) for enterprise use cases.[26]

AR Headsets with Eye Tracking

Eye tracking is also crucial for interaction and performance in AR:

  • Microsoft HoloLens 2: Uses eye tracking for user calibration, interaction (gaze targeting), and potentially performance optimization. Reported accuracy around 1.5 degrees.[27]
  • Magic Leap 2: Incorporates eye tracking for input (gaze, dwell), foveated rendering (on segmented dimmer), user calibration, and analytics.[28]

Technical Specifications and Performance Metrics

Key Performance Indicators

The quality and usability of eye tracking systems are measured using several critical metrics:

  • Accuracy: The average difference between the true gaze point and the system's reported gaze point, typically measured in degrees of visual angle. Good systems achieve 0.5° to 1.5° accuracy within the central field of view.
  • Precision: The consistency or reproducibility of measurements for the same gaze point (RMS of successive samples). Often between 0.1° and 0.5°.
  • Sampling Rate: The frequency at which eye position is measured, expressed in Hertz (Hz). Consumer systems range from 30Hz to 120Hz or more, while research systems can exceed 1000Hz. Higher rates capture more detail about rapid movements like saccades.
  • Latency: The time delay between an actual eye movement and when it is detected and reported by the system. Crucial for real-time applications like foveated rendering and interaction, ideally below 20ms, though system latency can sometimes be higher (e.g., 45-81 ms reported in some studies).[29]
  • Robustness / Tracking Ratio: The percentage of time the system successfully tracks the eyes under various conditions (e.g., different users, lighting, eyewear).
  • Field of View / Freedom of Head Movement: The range of eye rotation and head position within which the system maintains tracking.

[30]

Calibration Methods

Achieving specified accuracy typically requires individual user calibration:

  • Point Calibration: The most common method. The user looks sequentially at several points displayed on the screen while the system records corresponding eye data to build a mapping model.
  • Smooth Pursuit Calibration: The user follows one or more moving targets across the screen.
  • Implicit/Adjustment Calibration: Systems that attempt to calibrate or refine calibration based on natural viewing behavior during normal use, potentially reducing user friction.
  • Calibration Drift: Accuracy can degrade over time due to headset slippage or physiological changes, potentially requiring recalibration. Some studies note significant drift (e.g., 30% accuracy loss) within minutes under certain conditions.[29]

[31]

Challenges and Limitations

Despite significant progress, eye tracking in VR/AR still faces hurdles:

Technical Challenges

  • Individual Variations: Differences in eye physiology (e.g., corneal curvature, pupil size, eyelid shape, ethnicity-related features, "droopy" eyelids) can impact tracking accuracy and robustness.
  • Eyewear Compatibility: Prescription glasses (especially with thick lenses, bifocals, or certain coatings) and some types of contact lenses can interfere with IR illumination and camera imaging, degrading performance.
  • Processing Requirements: Real-time, high-frequency eye tracking requires significant computational resources, impacting overall system performance and battery life, especially on standalone mobile headsets.
  • Power Consumption: The cameras and illuminators continuously consume power, contributing to battery drain in untethered devices.
  • Accuracy/Latency Trade-offs: Achieving both high accuracy and very low latency simultaneously remains challenging.

[32]

User Experience Concerns

  • Calibration Process: The need for calibration can be perceived as inconvenient, especially if required frequently.
  • Privacy Implications: Eye tracking data is highly sensitive biometric data. It can potentially reveal information about identity, attention focus, cognitive state, emotional responses, interests, and even certain health conditions (e.g., fatigue, intoxication, neurological disorders), raising significant privacy concerns if collected, stored, or shared improperly.[33][34]
  • The "Uncanny Valley" Effect: Imperfectly synchronized or unnatural avatar eye movements can appear disturbing rather than enhance social presence.

Accessibility Issues

  • Compatibility with Eye Conditions: Certain ophthalmological conditions (e.g., strabismus, nystagmus, ptosis, corneal scarring) can significantly impair or prevent accurate eye tracking for affected individuals.
  • Make-up Interference: Certain types of mascara or eyeliner can sometimes interfere with tracking.

[35]

Future Developments

The field continues to evolve rapidly:

Emerging Technologies

  • Lower Power, Smaller Sensors: Miniaturization and improved power efficiency for better integration into lighter HMDs.
  • AI/ML-Enhanced Tracking: Using neural networks to improve robustness across diverse users, reduce calibration needs, and potentially infer more complex states from eye data.[36]
  • Advanced Optical Designs: Novel lens and camera configurations to improve tracking quality, especially for users with eyewear.
  • Sensor Fusion: Combining eye tracking data with other sensor inputs (e.g., electroencephalography (EEG), head tracking, facial expression tracking) for richer interaction and analysis.

Research Directions

  • Predictive Tracking: Algorithms that anticipate eye movements to compensate for system latency, enabling smoother foveated rendering and interaction.
  • Emotion and Cognitive State Recognition: Refining models to reliably infer affective states or cognitive load from eye metrics for adaptive interfaces or mental health applications.
  • Standardization: Developing common metrics, APIs, and data formats to facilitate cross-platform development and research comparison.
  • Longitudinal Tracking: Understanding how gaze patterns change over extended use and adapting systems accordingly.

[37]

Software Development and APIs

Integrating eye tracking into applications requires specific software support:

Development Frameworks and APIs

  • Unity: Provides APIs through its XR Interaction Toolkit and potential vendor-specific SDKs (e.g., Tobii XR SDK).
  • Unreal Engine: Offers native interfaces and plugins for accessing eye tracking data.
  • OpenXR: The cross-platform standard includes an `XR_EXT_eye_gaze_interaction` extension, allowing developers to write more portable code.
  • Vendor SDKs: Companies like Tobii provide dedicated Software Development Kits offering fine-grained control and optimized features for their hardware.[38]

Data Access Levels

Developers typically access eye tracking data at different levels of abstraction:

  • Raw Data: Direct coordinates of pupil centers, glints, eye openness, etc. Requires significant processing by the application.
  • Gaze Data: Processed output providing calibrated gaze origin and direction vectors, or intersection points on virtual surfaces.
  • Eye Movement Events: Classified data identifying fixations, saccades, and blinks.
  • Semantic Data: Higher-level interpretations, such as the specific object being looked at (gaze target) or estimated attention levels.

[39]

Ethical and Privacy Considerations

The collection and use of eye tracking data necessitate careful ethical consideration:

  • Biometric Data Privacy: Gaze patterns can be unique identifiers. This data requires strong data security measures and compliance with regulations like GDPR (which may classify it as sensitive biometric data).
  • Inference and Profiling: The potential to infer sensitive information (health, emotions, interests) without explicit consent raises ethical questions.
  • Attention Monitoring: Concerns about workplace surveillance or manipulative advertising based on attention analytics.
  • Informed Consent: Users must be clearly informed about what eye data is collected, how it is processed, stored, and shared, and for what purposes. Opt-in mechanisms are crucial.
  • Data Minimization and Anonymization: Collect only necessary data, anonymize or aggregate whenever possible, and define clear data retention policies.

[33]

Standards and Regulations

Efforts are underway to standardize aspects of eye tracking technology and address its implications:

  • Khronos Group / OpenXR: Defines standard APIs for accessing eye tracking data (e.g., XR_EXT_eye_gaze_interaction).
  • IEEE: Working groups like IEEE P2048.5 focus on standards for immersive learning, potentially including eye tracking metrics.
  • Virtual Reality Industry Forum (VRIF): Develops guidelines for VR implementation, potentially covering eye tracking best practices.
  • Data Protection Regulations: GDPR (Europe), CCPA/CPRA (California), and similar laws globally impose requirements on handling personal and biometric data, including eye tracking data.
  • ISO/IEC JTC 1/SC 24: Committee working on international standards for computer graphics, image processing, and environmental data representation, relevant to VR/AR interfaces.[40]

See Also

References

  1. ↑ Duchowski, A. T. (2017). *Eye Tracking Methodology: Theory and Practice*. Springer.
  2. ↑ Rayner, K. (1998). Eye movements in reading and information processing: 20 years of research. *Psychological Bulletin, 124*(3), 372–422.
  3. ↑ Huey, E.B. (1908). *The Psychology and Pedagogy of Reading*. Macmillan.
  4. ↑ Yarbus, A.L. (1967). *Eye Movements and Vision*. Plenum Press.
  5. ↑ Holmqvist, K., Nyström, M., Andersson, R., Dewhurst, R., Jarodzka, H., & Van de Weijer, J. (2011). *Eye tracking: A comprehensive guide to methods and measures*. Oxford University Press.
  6. ↑ Lang, B. (2021, July 21). *Casual Explainer: What is Eye-tracking & How Does it Work?* Road to VR. https://www.roadtovr.com/casual-explainer-what-is-eye-tracking-how-does-it-work/
  7. ↑ Hansen, D. W., & Ji, Q. (2010). In the eye of the beholder: A survey of models for eyes and gaze. *IEEE Transactions on Pattern Analysis and Machine Intelligence, 32*(3), 478-500.
  8. ↑ Bulling, A., Ward, J. A., Gellersen, H., & Tröster, G. (2011). Eye movement analysis for activity recognition using electrooculography. *IEEE Transactions on Pattern Analysis and Machine Intelligence, 33*(4), 741-753.
  9. ↑ Robinson, D.A. (1963). A method of measuring eye movement using a scleral search coil in a magnetic field. *IEEE Transactions on Biomedical Engineering, BME-10*(4), 137–145.
  10. ↑ Kar, A., & Corcoran, P. (2017). A review and analysis of eye-gaze estimation systems, algorithms and performance evaluation methods in consumer platforms. *IEEE Access, 5*, 16495-16519.
  11. ↑ Leigh, R. J., & Zee, D. S. (2015). *The neurology of eye movements*. Oxford University Press.
  12. ↑ Patney, A., Salvi, M., Kim, J., Kaplanyan, A., Wyman, C., Benty, N., Luebke, D., & Lefohn, A. (2016). Towards foveated rendering for gaze-tracked virtual reality. *ACM Transactions on Graphics, 35*(6), 179.
  13. ↑ 13.0 13.1 Tobii Blog: Eye Tracking in VR — A Vital Component. Retrieved Nov 17, 2023.
  14. ↑ NVIDIA Corporation. (n.d.). *Maximize VR Performance with Foveated Rendering*. NVIDIA Developer. Retrieved November 16, 2023, from https://developer.nvidia.com/vrworks/graphics/foveatedrendering
  15. ↑ Piumsomboon, T., Lee, G., Lindeman, R. W., & Billinghurst, M. (2017). Exploring natural eye-gaze-based interaction for immersive virtual reality. *IEEE Symposium on 3D User Interfaces*, 36-39.
  16. ↑ 16.0 16.1 Meta Platforms, Inc. (2022, October 11). *Meta Quest Pro: A New Way to Work, Create and Collaborate*. Meta Quest Blog. https://www.meta.com/blog/quest/meta-quest-pro-vr-headset-features-price-release-date/
  17. ↑ Clay, V., König, P., & König, S. (2019). Eye tracking in virtual reality. *Journal of Eye Movement Research, 12*(1).
  18. ↑ Akeley, K., Watt, S.J., Girshick, A.R., & Banks, M.S. (2004). A stereo display prototype with multiple focal distances. *ACM Transactions on Graphics, 23*(3), 804–813.
  19. ↑ Apple Inc. (n.d.). *Apple Vision Pro*. Apple. Retrieved November 16, 2023, from https://www.apple.com/apple-vision-pro/
  20. ↑ Sony Interactive Entertainment. (2023). *PS VR2 Features*. PlayStation.com. https://www.playstation.com/en-us/ps-vr2/features/
  21. ↑ HTC Corporation. (n.d.). *VIVE Pro Eye*. VIVE. Retrieved November 16, 2023, from https://www.vive.com/us/product/vive-pro-eye/overview/
  22. ↑ Varjo Technologies Oy. (n.d.). *Varjo Aero*. Varjo. Retrieved November 16, 2023, from https://varjo.com/products/aero/
  23. ↑ Varjo Technologies. (2021). *Varjo XR-3 Technical Specifications*. Varjo.com.
  24. ↑ Pimax Technology (Shanghai) Co., Ltd. (n.d.). *Pimax Crystal*. Pimax. Retrieved November 16, 2023, from https://pimax.com/crystal/
  25. ↑ Pico Interactive. (2021). *Pico Neo 3 Pro Eye Specifications*. Pico-interactive.com.
  26. ↑ HP Development Company, L.P. (n.d.). *HP Reverb G2 Omnicept Edition VR Headset*. HP.com. Retrieved November 16, 2023, from https://www.hp.com/us-en/vr/reverb-g2-vr-headset-omnicept-edition.html
  27. ↑ Microsoft Corporation. (2019). *HoloLens 2 Hardware Details*. Microsoft.com.
  28. ↑ Magic Leap, Inc. (2022). *Magic Leap 2 Technical Overview*. MagicLeap.com.
  29. ↑ 29.0 29.1 Mack, S., et al. (2022). A survey on eye tracking in virtual and augmented reality. *Virtual Reality*, 27, 1597–1625. https://link.springer.com/article/10.1007/s10055-022-00738-z
  30. ↑ Blignaut, P. (2018). Using eye tracking to assess user experience: A case of a mobile banking application. In *ACM International Conference Proceeding Series*, 219-228.
  31. ↑ Santini, T., Fuhl, W., & Kasneci, E. (2018). CalibMe: Fast and unsupervised eye tracker calibration for gaze-based pervasive human-computer interaction. *CHI Conference on Human Factors in Computing Systems*, 1-6.
  32. ↑ Majaranta, P., & Bulling, A. (2014). Eye tracking and eye-based human-computer interaction. In *Advances in physiological computing*, 39-65. Springer.
  33. ↑ 33.0 33.1 Kröger, J. L., Lutz, O. H. M., & Müller, F. (2020). What does your gaze reveal about you? On the privacy implications of eye tracking. *Privacy and Identity Management*, 226-241.
  34. ↑ Crockford, K., & Electronic Frontier Foundation. (2020, November 19). *The Privacy Bird Isn't Real: Your VR/AR Data Is*. Electronic Frontier Foundation. https://www.eff.org/deeplinks/2020/11/privacy-bird-isnt-real-your-vrar-data
  35. ↑ Titz, J., Scholz, A., & Sedlmeier, P. (2018). Comparing eye trackers by correlating their eye-metric data. *Behavior Research Methods, 50*(5), 1853-1863.
  36. ↑ Fuhl, W., Santini, T., Kasneci, G., & Kasneci, E. (2016). PupilNet: Convolutional neural networks for robust pupil detection. *CoRR, abs/1601.04902*.
  37. ↑ Duchowski, A. T., Krejtz, K., Krejtz, I., Biele, C., Niedzielska, A., Kiefer, P., Raubal, M., & Giannopoulos, I. (2018). The index of pupillary activity: Measuring cognitive load vis-à-vis task difficulty with pupil oscillation. *CHI Conference on Human Factors in Computing Systems*, 1-13.
  38. ↑ Tobii Technology. (2023). *Tobii XR SDK Documentation*. Tobii.com.
  39. ↑ Kumar, D., Dutta, A., Das, A., & Lahiri, U. (2016). SmartEye: Developing a novel eye tracking system for quantitative assessment of oculomotor abnormalities. *IEEE Transactions on Neural Systems and Rehabilitation Engineering, 24*(10), 1051-1059.
  40. ↑ International Organization for Standardization. (2023). *ISO/IEC JTC 1/SC 24 - Computer graphics, image processing and environmental data representation*. ISO.org.
Retrieved from "https://vrarwiki.com/index.php?title=Eye_tracking&oldid=34465"