Predictive tracking: Difference between revisions - VR & AR Wiki - Virtual Reality & Augmented Reality Wiki

Line 10:

==History and Development==

The concept of predictive tracking has roots in early [[computer vision]] and [[human-computer interaction]] research dating back to the 1990s. However, its critical importance for immersive technologies became apparent with the resurgence of consumer VR in the early 2010s~~<ref name="Oculus2013"></ref>~~. Early VR prototypes suffered from significant motion-to-photon latency issues, making predictive algorithms essential for creating viable consumer products.

The concept of predictive tracking has roots in early [[computer vision]] and [[human-computer interaction]] research dating back to the 1990s. However, its critical importance for immersive technologies became apparent with the resurgence of consumer VR in the early 2010s. Early VR prototypes suffered from significant motion-to-photon latency issues, making predictive algorithms essential for creating viable consumer products.

[[John Carmack]], while working as CTO at Oculus, popularized the implementation of predictive tracking algorithms in consumer VR and emphasized their importance in reducing perceived latency. His work on "timewarp," a rendering technique that incorporates prediction to update images just before display, became fundamental to modern VR systems<ref name="Carmack2013"></ref>.

Line 67:

*'''Double Exponential Smoothing''' - This statistical technique gives more weight to recent observations while still considering historical data. It's particularly effective for tracking movements with gradual acceleration or deceleration patterns, such as head rotations that naturally speed up and slow down<ref name="LaViola2003"></ref>.

*'''Artificial Neural Networks''' - Modern AR and VR systems increasingly incorporate machine learning approaches to prediction. Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks can learn complex patterns in human movement, potentially outperforming traditional algorithms for users with consistent movement styles. These approaches require training data but can adapt to individual users over time~~<ref name="Orozco2019"></ref>~~.

*'''Artificial Neural Networks''' - Modern AR and VR systems increasingly incorporate machine learning approaches to prediction. Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks can learn complex patterns in human movement, potentially outperforming traditional algorithms for users with consistent movement styles. These approaches require training data but can adapt to individual users over time.

*'''Hybrid Approaches''' - State-of-the-art predictive tracking often combines multiple algorithms, using fast methods for immediate response and more sophisticated algorithms to refine predictions. For example, a system might use dead reckoning for immediate feedback while a Kalman filter computes a more accurate prediction in parallel<ref name="Greer2020"></ref>.

Line 163:

<ref name="Abrash2014">Abrash, M. (2014). "What VR Could, Should, and Almost Certainly Will Be Within Two Years." Steam Dev Days, Seattle.</ref>

<ref name="Azuma1997">Azuma, R. T. (1997). "A Survey of Augmented Reality." Presence: Teleoperators and Virtual Environments, 6(4), pp. 355-385.</ref>

~~<ref name="Oculus2013">Oculus VR (2013). "Measuring Latency in Virtual Reality Systems." Oculus Developer Documentation.</ref>~~

<ref name="Carmack2013">Carmack, J. (2013). "Latency Mitigation Strategies." Oculus Connect Keynote.</ref>

<ref name="Yao2014">Yao, R., Heath, T., Davies, A., Forsyth, T., Mitchell, N., & Hoberman, P. (2014). "Oculus VR Best Practices Guide." Oculus VR.</ref>

Line 183:

Line 182:

<ref name="Isard1998">Isard, M., & Blake, A. (1998). "CONDENSATION—Conditional Density Propagation for Visual Tracking." International Journal of Computer Vision, 29(1), pp. 5-28.</ref>

<ref name="LaViola2003">LaViola, J. J. (2003). "Double Exponential Smoothing: An Alternative to Kalman Filter-Based Predictive Tracking." Proceedings of the Workshop on Virtual Environments, pp. 199-206.</ref>

~~<ref name="Orozco2019">Orozco Gómez, D., & Malkani, A. (2019). "Deep Learning for Movement Prediction in Mixed Reality." Microsoft Research Technical Report.</ref>~~

<ref name="Greer2020">Greer, J., & Johnson, K. (2020). "Multi-modal Prediction for XR Tracking." IEEE Conference on Virtual Reality and 3D User Interfaces (VR), pp. 161-170.</ref>

<ref name="Olsson2011">Olsson, T., & Salo, M. (2011). "Narratives of Satisfying and Unsatisfying Experiences of Current Mobile Augmented Reality Applications." Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 2779-2788.</ref>