Metrics in a Dynamic Gaze Environment

The development of algorithms for Areas of Interest (AOIs) segmentation represents a significant leap in dynamic gaze data analysis. These algorithms enable the transformation of two-dimensional raw data into meaningful one-dimensional metrics to unlock insights into human attention. Unlike traditional methods that focus on static gaze points in controlled environments, this research introduces novel algorithms for interpreting eye-tracking data in dynamic settings. The proposed techniques specifically address the challenge of processing gaze information in scenarios with changing frames of reference, such as driving, where understanding visual attention is critical for safety and to improve performance. This paper presents two innovative metrics designed to quantify the focus areas, duration, and scanning patterns of users in dynamic driving conditions. By employing advanced transfer learning for improved multiclass image segmentation methods, a percentage time AOI metric can be created. This metric gives insight into the amount of time a driver spends fixating on a given area. An enhancement in gaze pattern determination, achieved through class segmentation, provides a clearer depiction of drivers' true gaze patterns. This nuanced approach suggests that comprehensive attention assessment cannot rely solely on AOI metrics but requires the integration of gaze pattern derived metrics for a more accurate determination of attention-related scores. The introduction of these innovative gaze analysis methods marks a pivotal advancement in cognitive research and has practical applications. These metrics promise significant contribution to driver safety and attentiveness assessment methodologies.