T.N. Bhaskar, Foo Tun Keat, S. Ranganath, Y.V. Venkatesh
{"title":"Blink detection and eye tracking for eye localization","authors":"T.N. Bhaskar, Foo Tun Keat, S. Ranganath, Y.V. Venkatesh","doi":"10.1109/TENCON.2003.1273293","DOIUrl":null,"url":null,"abstract":"A method of using frame differencing coupled with optical flow computation for eye blink detection is proposed. Frame differencing allows quick determination of possible motion regions. If they are detected, optical flow is computed within these regions. The direction and magnitude of the flow field are then used to determine whether a blink has occurred. The eyes are then tracked using the Kanade Lucas Tomasi (KLT) tracker. We obtained a success rate of 97.0% in blink detection using the proposed method, and localised the eyes automatically at an average rate of 22 frames per second.","PeriodicalId":405847,"journal":{"name":"TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region","volume":"20 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2003-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"68","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TENCON.2003.1273293","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 68
Abstract
A method of using frame differencing coupled with optical flow computation for eye blink detection is proposed. Frame differencing allows quick determination of possible motion regions. If they are detected, optical flow is computed within these regions. The direction and magnitude of the flow field are then used to determine whether a blink has occurred. The eyes are then tracked using the Kanade Lucas Tomasi (KLT) tracker. We obtained a success rate of 97.0% in blink detection using the proposed method, and localised the eyes automatically at an average rate of 22 frames per second.
提出了一种结合帧差光流计算的眨眼检测方法。帧差允许快速确定可能的运动区域。如果检测到这些区域，则计算这些区域内的光流。然后使用流场的方向和大小来确定是否发生了闪烁。然后使用Kanade Lucas Tomasi (KLT)跟踪器跟踪眼睛。该方法的眨眼检测成功率为97.0%，并能以平均22帧/秒的速度自动定位眼睛。
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
