LPW

This is a novel dataset of 66 high-quality, high-speed eye region videos for the development and evaluation of pupil detection algorithms. The videos in our dataset were recorded from 22 participants in everyday locations at about 95 FPS using a state-of-the-art dark-pupil head-mounted eye tracker. They cover people with different ethnicities, a diverse set of everyday indoor and outdoor illumination environments, as well as natural gaze direction distributions. The dataset also includes participants wearing glasses, contact lenses, as well as make-up. We benchmark five state-of-the-art pupil detection algorithms on our dataset with respect to robustness and accuracy. We further study the influence of image resolution, vision aids, as well as recording location (indoor, outdoor) on pupil detection performance. Our evaluations provide valuable insights into the general pupil detection problem and allow us to identify key challenges for robust pupil detection on head-mounted eye trackers. Detailed information about our participants can be found in Table 2. We recruited 22 participants including 9 female through university mailing lists and personal communication. Among them are five different ethnicities: 11 Indian, 6 German, 2 Pakistani, 2 Iranian, and 1 Egyptian. In total we had five different eye colors: 12 brown, 5 black, 3 blue-gray, 1 blue-green, 1 green. Also 5 people had impaired vision, 2 wore glasses and 1 wore contact lenses. Strong eye make-up was worn by 1 person (with participant ID 22). The eye tracker used for the recording was a high-speed Pupil Pro head-mounted eye tracker that record eye videos with 120 Hz [Kass- ner et al. 2014]. In order to capture high frame rate scene videos, we replaced the original scene camera with a PointGrey Chameleon3 USB3.0 camera recording at up to 149 Hz. The hardware set up is shown in Figure 2a and Figure 2b. It allowed us to record all videos with 95 FPS, which is a speed at which even fast eye movements last through several frames. As shown in the right image below, the participants were instructed to look at a moving red ball as a fixation target during the data collection. The position of the red ball in the visual field of the participant is shown in middle image below with an image captured by the scene camera. In order to cover as many different conditions as possible, we randomly picked the recording locations in and around of several buildings. Each location was not chosen more than once during the whole recording of all participants. 34.3% of the recordings were done outdoors, in 84.7% natural light was present and in 33.6% artificial light was present. Besides locations, we have also tweaked the angle of the eye cameras such that the dataset contains a wide range of camera angles from frontal views to highly off-axis angles. This is done by either asking the participant to take the tracker off and put it back on, or manually moving the camera. With each of the 22 participant we recorded three videos with around 20 seconds length, yielding 130,856 images overall.Participants could keep their glasses and contact lenses on during the recording.

本数据集为一款全新构建的高质量高速眼部区域视频数据集，旨在用于瞳孔检测算法的开发与评估。本数据集内的视频由22名受试者在日常场景下录制，帧率约为95 FPS，录制设备采用当前顶尖的暗瞳式头戴式眼动仪（dark-pupil head-mounted eye tracker）。数据集涵盖了不同种族的受试者，覆盖了丰富的日常室内、室外光照环境，同时包含多样化的自然视线方向分布。此外，数据集纳入了佩戴眼镜、隐形眼镜以及化眼妆的受试者。我们基于本数据集，针对鲁棒性与精度两大指标，对五款当前顶尖的瞳孔检测算法进行了基准测试。此外，我们还研究了图像分辨率、视力辅助器具以及录制场景（室内/室外）对瞳孔检测性能的影响。本次评估为通用瞳孔检测问题提供了极具价值的研究视角，并帮助我们明确了头戴式眼动仪上实现鲁棒性瞳孔检测的核心挑战。受试者的详细信息见表2。我们通过高校邮件列表与私人联络招募了22名受试者，其中9名为女性。受试者涵盖5个不同种族：11名印度裔、6名德国裔、2名巴基斯坦裔、2名伊朗裔以及1名埃及裔。受试者的虹膜颜色共计5种：12人为棕色、5人为黑色、3人为蓝灰色、1人为蓝绿色、1人为绿色。另有5名受试者存在视力障碍，其中2人佩戴框架眼镜，1人佩戴隐形眼镜。受试者ID为22的1名受试者化了浓眼妆。本次录制使用的眼动仪为高速Pupil Pro头戴式眼动仪，其眼部视频录制帧率为120 Hz [Kassner等人，2014]。为了录制高帧率场景视频，我们将原有的场景摄像头替换为最高支持149 Hz录制的PointGrey Chameleon3 USB3.0摄像头。硬件搭建方案如图2a与图2b所示。该配置使我们能够以95 FPS的帧率录制所有视频，该帧率足以让快速眼球运动覆盖多个视频帧。如下方右图所示，在数据采集过程中，我们要求受试者以一个移动的红色小球作为注视目标。下方中间的场景摄像头实拍图展示了红色小球在受试者视野中的位置。为了覆盖尽可能多样的采集条件，我们在多栋建筑及其周边随机选取录制地点，且在所有受试者的完整录制过程中，每个地点仅被使用一次。其中34.3%的录制工作在室外完成，84.7%的录制场景存在自然光，33.6%的场景存在人工照明。除录制地点外，我们还调整了眼部摄像头的角度，使数据集涵盖从正视角到大幅离轴视角的多种摄像头拍摄角度。调整方式包括让受试者取下并重新佩戴眼动仪，或是手动调整摄像头位置。我们为22名受试者各录制了三段时长约20秒的视频，最终总计得到130856帧图像。受试者在录制过程中可自行佩戴框架眼镜与隐形眼镜。

搜集汇总

背景与挑战

背景概述

LPW数据集是一个专注于瞳孔检测算法开发与评估的高质量眼区视频数据集，包含22名不同种族参与者的66段视频，覆盖多种光照条件和视觉辅助工具使用情况，视频记录速度为95 FPS，总图像数达130,856张。