[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-328049-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-328049-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","binocular-gaze-estimation-with-single-camera-and-single-light-source-abstract","Binocular Gaze Estimation with Single Camera and Single Light Source - Abstract","","A gaze estimation approach reduces hardware complexity by using one camera and one light source instead of the commonly required one camera and two light sources for free head movements. The method introduces a geometrically symmetric “virtual light source” to generate a “virtual glint” and estimates it from relationships between inter-pupil distance and inter-glint distance. Polynomial regression is then applied using the virtual glint-derived features and a verified normalization factor suited for one-glint systems. Results show acceptable performance with degradation compared to two actual light sources.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/binocular-gaze-estimation-with-single-camera-and-single-light-source-abstract/328049/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/binocular-gaze-estimation-with-single-camera-and-single-light-source-abstract/328049.png","ImageObject",300,407,{"name":42,"@type":43},"Quinn","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-10","2026-09-21",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why does the paper aim to use fewer hardware components for gaze estimation?","Question",{"text":63,"@type":64},"The paper targets scenarios such as eye tracking on mobile devices where using fewer components, especially fewer light sources, is preferable while maintaining practical usability.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How is the “virtual light source” used in the proposed method?",{"text":68,"@type":64},"A virtual light source is placed symmetrically to the real light source with respect to the camera to produce a “virtual glint” in the acquired image.",{"name":70,"@type":61,"acceptedAnswer":71},"How does the method estimate gaze after obtaining the virtual glint?",{"text":72,"@type":64},"The virtual glint is estimated using relationships involving inter-pupil distance and inter-glint distance, and gaze is then derived via polynomial regression using normalized features designed for a one-glint system.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},328049,1791174782,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":111,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":97,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":144,"preview_page_count":4},962075114765,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Binocular Gaze Estimation with Single Camera and  \nSingle Light Source  \nTongbing Huang 7Invensun Technology Co. Ltd.  \nBeijing,China [huangtb@7invensun.com](huangtb@7invensun.com)  \nYang Fu TnB Galaxy Beijing,China  \n[624933405@qq.com](624933405@qq.com)  \nYunfei Wang  \n7Invensun Technology Co. Ltd. Beijing,China  \n[wangyf@7invensun.com](wangyf@7invensun.com)  \nZhaocan Wang  \nUniversity of Science and Technology Beijing  \nBeijing,China  \n[wzc1ws2@163.com](wzc1ws2@163.com)  \nABSTRACT  \nAccording to commonly consented theories, the minimum hardware requirement for gaze tracker is one camera and two light sources to realize gaze estimation with free head movements [2] . However, in some scenarios such as eye tracking on mobile devices, it is preferable to use less components, especially light sources. We propose a gaze estimation method with one camera and one light source. A “virtual light source” is introduced, which is geometrically placed symmetrically to the real light source with respect to the camera, and generates a “virtual glint” in the acquired image. We estimate the “virtual glint” by exploiting the relationship between the distance between two pupils and two glints in the captured image, and estimate the gaze with polynomial regression assuming two light sources are available. A new normalization factor for regression method is verified, which turns out to be practical for one-glint system. The performance is proved to be acceptable, while degradation is noticed compared to system with two actual light sources.  \nCCS Concepts  \n• Computing methodologies~Model verification and validation Keywords  \nGaze estimation, Polynomial regression, Binocular, Video oculography  \n1. INTRODUCTION  \nGaze estimation is a technique to tell where the user is looking, the estimated gaze is represented by either a gaze point or gaze direction. Existing methods include scleral coil method [11], electrooculography (EOG) [12], and video oculography [2-10] . Gaze estimation with video oculography has been proved to be the most practical approach for commercial and academical purposes [1] . Two common methods are geometric method [2, 3] and regression method [4, 5], both of which require a minimum of one camera and two light sources to enable head movement [2, 4] .  \nGeometric method, which relies on 3D model of eye, estimates the line of sight by solving parameters of eye model. With one camera and two light sources, there are enough equations to solve the unknown parameters without knowing distance information of the user [2] . Regarding regression method, with one off-axis light source, noticeable mean error exists. Such drawback caused by asymmetry glint could be eliminated by using two light sources and define the pupil-cornea reflection (􀜲􀜥􀜴) vector as the midpoint of the two glints [4] . It also points out that it is susceptible to perpendicular head movement simply using 􀜲􀜥􀜴 as regression input, but more robust with normalized 􀜲􀜥􀜴 vector. Experiments indicate that the best normalization factor is inter-glint distance. A study on mobile phone eye tracking [6] is based on one camera and two light sources embedded on the phone. The two light sources are place apart from each other diagonal to the screen because the glint in the image might adjoin each other if they are placed too close, making feature extraction erroneous. However, such design is not quite practical since it is very difficult to have both glints available due to the obstruction of eyelids.  \nFor commercial applications, it is preferable to use fewer light sources. Take eye tracking on mobile phone for example, the manufactures prefer to save the space for front-facing components to accommodate bigger screen. According to our observations and mobile platform visibility study [7, 8], for consideration on glint(s) visibility, the light sources should not be place too far from the camera. And the most practical solution is too use only one light source.  \n[4] made an attemp","cbCaigNV0N2Jxh1U","https://ap.wps.com/l/cbCaigNV0N2Jxh1U","pdf",358036,"English","# Abstract\n# Introduction","[{\"question\":\"Why does the paper aim to use fewer hardware components for gaze estimation?\",\"answer\":\"The paper targets scenarios such as eye tracking on mobile devices where using fewer components, especially fewer light sources, is preferable while maintaining practical usability.\"},{\"question\":\"How is the “virtual light source” used in the proposed method?\",\"answer\":\"A virtual light source is placed symmetrically to the real light source with respect to the camera to produce a “virtual glint” in the acquired image.\"},{\"question\":\"How does the method estimate gaze after obtaining the virtual glint?\",\"answer\":\"The virtual glint is estimated using relationships involving inter-pupil distance and inter-glint distance, and gaze is then derived via polynomial regression using normalized features designed for a one-glint system.\"}]","Binocular Gaze Estimation with Single Camera and Single Light Source - Abstract | PDF",1789978574,13]