YawDD: Yawning Detection Dataset

A dataset of videos, recorded by an in-car camera, of drivers in an actual car with various facial characteristics (male and female, with and without glasses/sunglasses, different ethnicities) talking, singing, being silent, and yawning. It can be used primarily to develop and test algorithms and models for yawning detection, but also recognition and tracking of face and mouth. The videos are taken in natural and varying illumination conditions. The videos come in two sets, as described next: In the first set, a camera is installed under the front mirror of the car. This set provides 322 videos in 3 different situations: 1- normal driving (no talking), 2- talking or singing while driving, and 3- yawning while driving. Each subject has 3 or 4 videos.In the second set, the camera is installed on the driver’s dash. This set provides 29 videos, one for each subject, and each video containing scenes with driving silently, driving while talking, and driving while yawning.

本数据集为车载摄像头采集的真实车内驾驶场景视频集，受试者涵盖具备多样化面部特征的群体：包括男性与女性、佩戴或未佩戴眼镜/太阳镜者，以及不同种族人群；视频中受试者呈现交谈、歌唱、静默与打哈欠等多种行为状态。该数据集主要用于开发与测试打哈欠检测相关的算法及模型，同时也可应用于人脸、嘴部的识别与跟踪任务。所有视频均采集于自然且光照条件多变的场景中。本次数据集包含两组视频，详情如下：第一组视频的摄像头安装于车辆前后视镜下方，共包含322段视频，对应3种驾驶场景：1. 常规驾驶（无交谈）；2. 驾驶过程中交谈或歌唱；3. 驾驶过程中打哈欠。每位受试者对应3至4段视频。第二组视频的摄像头安装于驾驶员仪表盘上，共包含29段视频，每位受试者对应1段，每段视频均涵盖静默驾驶、交谈驾驶与打哈欠驾驶三种场景。