CoCAtt

CoCAtt数据集是由伊利诺伊大学厄巴纳-香槟分校的研究团队创建，专注于驾驶员注意力的认知条件化研究。该数据集通过使用网络摄像头进行眼动追踪，收集了驾驶员在驾驶过程中的注意力数据，特别关注了由于佩戴口罩和肤色差异导致的面部标志检测失败的情况。数据集的创建过程中，研究者提出了一种从粗到细的校准程序来处理数据噪声问题。CoCAtt数据集的应用领域主要集中在自动驾驶和驾驶员行为分析，旨在通过分析驾驶员的注意力模式来提高道路安全。

The CoCAtt dataset was developed by a research team from the University of Illinois Urbana-Champaign, focusing on cognitive conditioning research of driver attention. This dataset collects driver attention data during driving via eye tracking using webcams, with particular focus on cases of facial landmark detection failures caused by wearing face masks and skin tone disparities. During the development of the CoCAtt dataset, the researchers proposed a coarse-to-fine calibration procedure to address data noise issues. The main application fields of the CoCAtt dataset are autonomous driving and driver behavior analysis, aiming to improve road safety by analyzing driver attention patterns.