SET: a pupil detection method using sinusoidal approximation. Javadi, A., Hakimi, Z., Barati, M., Walsh, V., & Tcheang, L. Frontiers in neuroengineering, 8:4, 2015. Paper abstract bibtex Mobile eye-tracking in external environments remains challenging, despite recent advances in eye-tracking software and hardware engineering. Many current methods fail to deal with the vast range of outdoor lighting conditions and the speed at which these can change. This con-fines experiments to artificial environments where conditions must be tightly controlled. Ad-ditionally, the emergence of low-cost eye tracking devices calls for the development of analy-sis tools that enable non-technical researchers to process the output of their images. We have developed a fast and accurate method (known as ‘SET’) that is suitable even for natural envi-ronments with uncontrolled, dynamic and even extreme lighting conditions. We compared the performance of SET with that of two open-source alternatives by processing two collec-tions of eye images: images of natural outdoor scenes with extreme lighting variations (‘Natu-ral’); and images of less challenging indoor scenes (‘CASIA-Iris-Thousand’). We show that SET excelled in outdoor conditions and was faster, without significant loss of accuracy, in-doors. SET offers a low cost eye-tracking solution, delivering high performance even in chal-lenging outdoor environments. It is offered through an open-source MATLAB toolkit as well as a dynamic-link library (‘DLL’), which can be imported into many programming languages including C# and Visual Basic in Windows OS (www.eyegoeyetracker.co.uk).
@article{
title = {SET: a pupil detection method using sinusoidal approximation},
type = {article},
year = {2015},
identifiers = {[object Object]},
keywords = {Dark Pupil,Ellipse Fitting,Eye Tracking,Head Mounted Device,Pupil Detection,dark pupil,eye tracking,head mo,pupil detection},
pages = {4},
volume = {8},
id = {5e7e7b9d-bea1-3ab9-ba8b-3a2fc080a826},
created = {2015-04-09T10:24:18.000Z},
file_attached = {true},
profile_id = {69574ccf-a202-3c13-b9e9-b6e77dadc9f9},
last_modified = {2015-04-09T15:58:52.000Z},
read = {true},
starred = {false},
authored = {true},
confirmed = {true},
hidden = {false},
abstract = {Mobile eye-tracking in external environments remains challenging, despite recent advances in eye-tracking software and hardware engineering. Many current methods fail to deal with the vast range of outdoor lighting conditions and the speed at which these can change. This con-fines experiments to artificial environments where conditions must be tightly controlled. Ad-ditionally, the emergence of low-cost eye tracking devices calls for the development of analy-sis tools that enable non-technical researchers to process the output of their images. We have developed a fast and accurate method (known as ‘SET’) that is suitable even for natural envi-ronments with uncontrolled, dynamic and even extreme lighting conditions. We compared the performance of SET with that of two open-source alternatives by processing two collec-tions of eye images: images of natural outdoor scenes with extreme lighting variations (‘Natu-ral’); and images of less challenging indoor scenes (‘CASIA-Iris-Thousand’). We show that SET excelled in outdoor conditions and was faster, without significant loss of accuracy, in-doors. SET offers a low cost eye-tracking solution, delivering high performance even in chal-lenging outdoor environments. It is offered through an open-source MATLAB toolkit as well as a dynamic-link library (‘DLL’), which can be imported into many programming languages including C# and Visual Basic in Windows OS (www.eyegoeyetracker.co.uk).},
bibtype = {article},
author = {Javadi, Amir-homayoun and Hakimi, Zahra and Barati, Morteza and Walsh, Vincent and Tcheang, Lili},
journal = {Frontiers in neuroengineering}
}
Downloads: 0
{"_id":"C9wXFdjY6NnCjHW4o","bibbaseid":"javadi-hakimi-barati-walsh-tcheang-setapupildetectionmethodusingsinusoidalapproximation-2015","downloads":0,"creationDate":"2016-12-01T18:34:56.087Z","title":"SET: a pupil detection method using sinusoidal approximation","author_short":["Javadi, A.","Hakimi, Z.","Barati, M.","Walsh, V.","Tcheang, L."],"year":2015,"bibtype":"article","biburl":null,"bibdata":{"title":"SET: a pupil detection method using sinusoidal approximation","type":"article","year":"2015","identifiers":"[object Object]","keywords":"Dark Pupil,Ellipse Fitting,Eye Tracking,Head Mounted Device,Pupil Detection,dark pupil,eye tracking,head mo,pupil detection","pages":"4","volume":"8","id":"5e7e7b9d-bea1-3ab9-ba8b-3a2fc080a826","created":"2015-04-09T10:24:18.000Z","file_attached":"true","profile_id":"69574ccf-a202-3c13-b9e9-b6e77dadc9f9","last_modified":"2015-04-09T15:58:52.000Z","read":"true","starred":false,"authored":"true","confirmed":"true","hidden":false,"abstract":"Mobile eye-tracking in external environments remains challenging, despite recent advances in eye-tracking software and hardware engineering. Many current methods fail to deal with the vast range of outdoor lighting conditions and the speed at which these can change. This con-fines experiments to artificial environments where conditions must be tightly controlled. Ad-ditionally, the emergence of low-cost eye tracking devices calls for the development of analy-sis tools that enable non-technical researchers to process the output of their images. We have developed a fast and accurate method (known as ‘SET’) that is suitable even for natural envi-ronments with uncontrolled, dynamic and even extreme lighting conditions. We compared the performance of SET with that of two open-source alternatives by processing two collec-tions of eye images: images of natural outdoor scenes with extreme lighting variations (‘Natu-ral’); and images of less challenging indoor scenes (‘CASIA-Iris-Thousand’). We show that SET excelled in outdoor conditions and was faster, without significant loss of accuracy, in-doors. SET offers a low cost eye-tracking solution, delivering high performance even in chal-lenging outdoor environments. It is offered through an open-source MATLAB toolkit as well as a dynamic-link library (‘DLL’), which can be imported into many programming languages including C# and Visual Basic in Windows OS (www.eyegoeyetracker.co.uk).","bibtype":"article","author":"Javadi, Amir-homayoun and Hakimi, Zahra and Barati, Morteza and Walsh, Vincent and Tcheang, Lili","journal":"Frontiers in neuroengineering","bibtex":"@article{\n title = {SET: a pupil detection method using sinusoidal approximation},\n type = {article},\n year = {2015},\n identifiers = {[object Object]},\n keywords = {Dark Pupil,Ellipse Fitting,Eye Tracking,Head Mounted Device,Pupil Detection,dark pupil,eye tracking,head mo,pupil detection},\n pages = {4},\n volume = {8},\n id = {5e7e7b9d-bea1-3ab9-ba8b-3a2fc080a826},\n created = {2015-04-09T10:24:18.000Z},\n file_attached = {true},\n profile_id = {69574ccf-a202-3c13-b9e9-b6e77dadc9f9},\n last_modified = {2015-04-09T15:58:52.000Z},\n read = {true},\n starred = {false},\n authored = {true},\n confirmed = {true},\n hidden = {false},\n abstract = {Mobile eye-tracking in external environments remains challenging, despite recent advances in eye-tracking software and hardware engineering. Many current methods fail to deal with the vast range of outdoor lighting conditions and the speed at which these can change. This con-fines experiments to artificial environments where conditions must be tightly controlled. Ad-ditionally, the emergence of low-cost eye tracking devices calls for the development of analy-sis tools that enable non-technical researchers to process the output of their images. We have developed a fast and accurate method (known as ‘SET’) that is suitable even for natural envi-ronments with uncontrolled, dynamic and even extreme lighting conditions. We compared the performance of SET with that of two open-source alternatives by processing two collec-tions of eye images: images of natural outdoor scenes with extreme lighting variations (‘Natu-ral’); and images of less challenging indoor scenes (‘CASIA-Iris-Thousand’). We show that SET excelled in outdoor conditions and was faster, without significant loss of accuracy, in-doors. SET offers a low cost eye-tracking solution, delivering high performance even in chal-lenging outdoor environments. It is offered through an open-source MATLAB toolkit as well as a dynamic-link library (‘DLL’), which can be imported into many programming languages including C# and Visual Basic in Windows OS (www.eyegoeyetracker.co.uk).},\n bibtype = {article},\n author = {Javadi, Amir-homayoun and Hakimi, Zahra and Barati, Morteza and Walsh, Vincent and Tcheang, Lili},\n journal = {Frontiers in neuroengineering}\n}","author_short":["Javadi, A.","Hakimi, Z.","Barati, M.","Walsh, V.","Tcheang, L."],"urls":{"Paper":"http://bibbase.org/service/mendeley/69574ccf-a202-3c13-b9e9-b6e77dadc9f9/file/08ba96fc-877f-9a2d-256a-0fec2e4500c1/2015-SET_a_pupil_detection_method_using_sinusoidal_approximation.pdf.pdf"},"bibbaseid":"javadi-hakimi-barati-walsh-tcheang-setapupildetectionmethodusingsinusoidalapproximation-2015","role":"author","keyword":["Dark Pupil","Ellipse Fitting","Eye Tracking","Head Mounted Device","Pupil Detection","dark pupil","eye tracking","head mo","pupil detection"],"downloads":0},"search_terms":["set","pupil","detection","method","using","sinusoidal","approximation","javadi","hakimi","barati","walsh","tcheang"],"keywords":["dark pupil","ellipse fitting","eye tracking","head mounted device","pupil detection","dark pupil","eye tracking","head mo","pupil detection"],"authorIDs":[]}