Eye tracking systems have recently experienced a diversity of novel calibration procedures, including smooth pursuit and vestibulo-ocular reflex based calibrations. These approaches allowed collecting more data compared to the standard 9-point calibration. However, the computation of the mapping function which provides planar gaze positions from pupil features given as input is mostly based on polynomial regressions, and little work has investigated alternative approaches. This paper fills this gap by providing a new calibration computation method based on symbolic regression. Instead of making prior assumptions on the polynomial transfer function between input and output records, symbolic regression seeks an optimal model among different types of functions and their combinations. This approach offers an interesting perspective in terms of flexibility and accuracy. Therefore, we designed two experiments in which we collected ground truth data to compare vestibulo-ocular and smooth pursuit calibrations based on symbolic regression, both using a marker or a finger as a target, resulting in four different calibrations. As a result, we improved calibration accuracy by more than 30%, with reasonable extra computation time.

中文翻译：

---

使用符号回归提高眼动追踪校准精度。

眼动追踪系统最近经历了多种新颖的校准程序，包括平滑追踪和基于前庭眼反射的校准。与标准 9 点校准相比，这些方法可以收集更多数据。然而，根据作为输入给出的瞳孔特征提供平面凝视位置的映射函数的计算主要基于多项式回归，并且很少有工作研究替代方法。本文通过提供一种新的基于符号回归的校准计算方法填补了这一空白。符号回归不是对输入和输出记录之间的多项式传递函数进行事先假设，而是在不同类型的函数及其组合之间寻求最佳模型。这种方法在灵活性和准确性方面提供了有趣的视角。因此，我们设计了两个实验，收集地面实况数据来比较基于符号回归的前庭视觉校准和平滑追踪校准，均使用标记或手指作为目标，从而产生四种不同的校准。结果，我们将校准精度提高了 30% 以上，并节省了合理的额外计算时间。