3D Eye Tracking Smoothing During Temporary Signal Loss
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye tracking techniques fail to adequately handle periods of data unavailability, leading to sudden jumps in eye position tracking that cause visual anomalies in content display.
Innovation Solution
Implementing temporal smoothing of the 3D position of the eye, using a confidence level-based transition rate and hysteresis to stabilize eye tracking during interruptions, such as blinking, by updating the position based on previous and current sensor data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If eye tracking data is updated continuously based on sensor data, then tracking precision is improved, but during temporary sensor data loss (e.g., blinking, fast eye motion), sudden jumps in tracked position occur causing visual anomalies
Solution Approach 1:
The system performs preliminary actions by detecting eye tracking loss conditions (blinking, fast eye motion) before they cause sudden jumps. When loss is detected, the system proactively switches to using the last known good eye position instead of waiting for the jump to occur, thereby preventing visual anomalies while maintaining tracking precision during normal operation
Solution Approach 2:
The patent introduces an intermediary mechanism that detects sensor data quality and mediates between raw sensor data and the final tracked position. When sensor data is deemed unreliable (during blinking or fast motion), the intermediary switches to using the last known good position as a fallback, smoothing the transition and preventing sudden jumps while maintaining measurement precision during stable periods
2Reliability
If the system uses the last known good eye position during sensor data loss, then tracking stability is improved, but the tracked position lags behind the actual eye position causing delayed response
Solution Approach 1:
The system dynamically adjusts its behavior based on real-time sensor data quality. During normal operation, it uses continuous sensor data for immediate response. When loss is detected, it dynamically switches to the last known good position strategy, and when recovery is detected, it switches back to continuous tracking. This dynamic adaptation resolves the contradiction by optimizing for stability during loss and for responsiveness during normal operation
Solution Approach 2:
The patent changes the parameter of position update strategy based on the detected state. When sensor data is reliable, the system uses real-time sensor-derived positions. When loss is detected, it changes the parameter to use the last known good position. When recovery is detected, it changes back to real-time tracking. This parameter switching resolves the contradiction between stability and responsiveness by adapting to current conditions
Data Source
AI summary
Various implementations disclosed herein include devices, systems, and methods that mitigate eye tracking loss. For example, a process may capture sensor data of a 3D region. The process may further generate eye tracking data comprising a 3D position of an eye based on tracking the 3D position of the eye. The 3D position may be updated over time based on the captured sensor data. The process may further detect a condition interfering with updating the 3D position of the eye based on the captured sensor data. The process may further update the eye tracking data using a smoothed 3D position of the eye. The smoothed 3D position may be determined based on previously-tracked 3D positions of the portion of the eye and a current 3D position of the portion of the eye determined based on current sensor data.