Investigation of camera-free eye tracking glasses compared to a video-based system
Bibliographic record
Abstract
Eye movements provide insight into human cognitive and sensorimotor control. However, most research has been constrained to traditional laboratories. Recent advances in eye tracking technology could facilitate research and application in ecological settings such as aviation training or sideline assessment. It is important to confirm the accuracy of the emerging systems. Here we compare a system consisting of camera-free eye tracking glasses with a research grade video-based system. Eleven healthy participants (22.6±2.8 years) were tested using a saccade task (target range 3-25°). Eye movements were recorded simultaneously using a video-based system (EyeLink-2, SR Research) and a portable eye/gaze tracking system (Mindlink, AdHawk Microsystems) at 250 Hz. Calibration for each system was performed separately following guidelines (accuracy error was <1deg). The head was stabilized in a chinrest throughout the experiment. Results showed a mean amplitude difference between the systems of 0.05°±2.05 and mean peak velocity difference of 28.98°/sec ±65.33. Analyses of the results revealed two important factors associated with larger errors between the systems. First, greater error was found in individuals wearing contact lenses (n=4) compared to non-contact lens wearers (n=7) (amplitude: 0.24°±2.13 vs -0.05°±2.00; peak velocity: 45.96°/sec ±66.6 vs 20.32°/sec ±62.94). Second, linear regression analysis revealed Mindlink calibration precision explained 50% of variance in amplitude difference, and 0.3% variance in peak velocity difference between the systems. The Mindlink system offers unprecedented advantage for recording of eye and gaze movements in ecological settings. Our study provides important insight regarding two factors that could contribute to significant errors in saccade amplitude and peak velocity: 1) errors may be higher in individuals wearing contact lenses; 2) in addition to accuracy, Mindlink’s precision calibration variable has a significant impact on the quality of the recording. These results should be considered when adopting the Mindlink for research applications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".