Precise Eye Gaze Tracking in Video Frames via Combining Particle Filters Method with Genetic Algorithm

Document Type : Original Article

Abstract

Gaze tracking is a key process in human-computer interactions. A basic approach in this field is to predict the position of the pupil in sequential video frames. Particle filter, the most important method which is based on aforementioned approach, has a low precision in predicting the pupil position though guaranteeing expected speed. To solve this problem, in this paper, genetic algorithm (GA) is used in the sampling step of the particle filter method. As a result, in each frame, diversity of the particles required for predicting the pupil position in the next video frame is preserved and at the same time the monotony of them is reduced. To evaluate performance, corresponding to different particle populations, speed and precision of the proposed method and the basic particle filter method in predicting pupil positions in video frames of eye were computed and compared.  Results show that the proposed method, compared to the basic particle filter method, tracks the gaze more precisely in a lower time.

Keywords

References

[1]T.Kocejko, A.Bujnowskiand J.Wtorek, “Eye mouse for disa-bled”, in Proc. IEEE Conf.Human Syst. Interact., pp. 199-202, May 2008.
[2]R. Khushaba, Ch. Wise, S. Kodagoda, J. Louviere, B. E. Kahn and C. Townsend, “Consumer neuroscience: Assessing the brain re-sponse to marketing stimuli using electroencephalogram (EEG) and eye tracking”, Elsevier, Expert Systems with Applications, vol. 40, Issue. 9, pp. 3803-3812, July 2013.
[3]R. C. Coetzer and G. P. Hancke, “Eye detection for a real-time vehicle driver fatigue monitoring system”, in Proc. IEEE Intell. Veh. Symp,pp. 66-71,Jun. 2011.
[4]C. Corcoran, F. Nanu, S. Petrescuand P. Bigioi ,“Real-time eye gaze tracking for gaming design and consumer electronics sys-tems”, IEEE Transactions Consumer Electronics, vol.58, Issue.2, pp. 347 –355, 2012.
[5]A.T. Duchowski,Eye Tracking Methodology, Verlag London Limited, Springer, 2007.
[6]Z. ZhuandJ. Qiang, “Robust real-time eye detection and tracking under variable lighting conditions and various face orientations”, Elsevier,Computer Vision and Image Understanding, 2005.
[7]D. W. Hansen andJ. Qiang, “Inthe eye of the beholder: a survey of models for eyes and gazes”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 3, 2010.
[8]G. Daunys, et al., D5.2 Report on New Approaches to Eye Track-ing. Communication by Gaze interaction (COGAIN), IST-2003-511598: Deliverable 5.2., 2006http://www.cogain.org/results/re-ports/ COGAIN D5.2.pdf.
[9]R. M. Sundaram, B. C. Dhara andB. Chanda, “A fast method for iris Localization” in Proc. 2nd Int. Conf. EAIT, pp. 89-92, 2011.
[10]A. PranithandC. R. Srikanth, “Iris recognition using corner de-tection” in Proc. 2nd ICISE, pp. 2151-2154, 2010.
[11]R. Valenti andT. Gevers, “Accurate eye center location and track-ing using isophote curvature” Proc. IEEE Conf. Computer Vision and Pattern Recognition,2008.
[12]B. Fu andR. Yang, “Display control based on eye gaze estima-tion” in Proc. 4th Int. CISP, vol. 1, pp. 399-403, 2011.
[13]H. Liu andQ. Liu, “Robust real-time eye detection and tracking for rotated facial images under complex conditions” in Proc. 6th ICNC, vol. 4, pp. 2028-2034, 2010.
[14]J. Tang andJ. Zhang, “Eye tracking based on grey prediction” in Proc. 1stInt. Workshop Educ. Technol. Comput.Sci., pp. 861-864, 2009.
[15]S. Kawato and N. Tetsutani, “Detection and tracking of eyes for gaze-camera control” Proc. 15th Int’l Conf. Vision Interface, 2002.
[16]S. Sirohey,A. Rosenfeld and Z. Duric, “A method of detecting and tracking irises and eyelids in video” Pattern Recognition, vol. 35, no. 6, pp. 1389-1401, June 2002.
[17]S.A. Sirohey, A. Rosenfeld, “Eye detection in a face image using linear and nonlinear filters” Pattern Recognition, vol. 34, pp. 1367-1391, 2001.
[18]C. Morimoto andM. Nimica,“Eye gaze tracking techniques for interactive applications”, Elsevier, Computer Visiontechniques for interactive applications, vol. 98, Issue. 1, pp. 4-24, April 2005.
[19]Z. ZhuandJ. Qiang,“Eye and gaze tracking for interactive graphic display”, Springer,Machine Vision and applications, vol. 15, Issue. 3, pp. 139-148, July 2004.
[20]Y. Matsumoto,T. Ogasawaraand A. Zelinsky,“Behavior recog-nition based on head pose and gaze direction measurement”, IEEE, Intelligent Robots and Systems, vol. 3, pp. 2127-2132, NOV 2000.
[21]K. Choi, S. Baek, Ch. Ma, S. Park and S. Ko, “Improved pupil center localization method for eye-gaze tracking-based human-de-vice interaction”, IEEE International Conference on Consumer Electronics (ICCE), pp. 514-515, 2014.
[22]H. Qin, X. Wang, M. Liang and W. Yan, “A novel pupil detection algorithm for infrared eye image”, Signal Processing, Communi-cation and Computing (ICSPCC), IEEE International Conference, pp. 1-5, 2013.
[23]Th. Charoenpong, P. Pattrapisetwong, Th. Chanwimalueang andM. Mahasithiwat, “Accurate pupil extraction algorithm by using integrated method”, Knowledge and Smart Technology (KST), 2013 5th International Conference on IEEE, pp. 32 –37, 2013.
[24]K.Choi, S. Baek, Ch. Ma, S. Park and S. Ko, “Improved pupil center localization method for eye-gaze tracking-based human-de-vice interaction”, IEEE International Conference on Consumer Electronics (ICCE), pp. 514-515, 2014.
[25]A. Liaghatdar, k. Kangarloo and F.Farokhi, “Pupil localizing in video images the first step toward eye monitoring”, IEEE, Multi-media Technology(ICMT), pp. 3163-3166, 2011.
[26]M. Sadri, k. Kangarloo and F. Farokhi, “Particle filtering in the design of an accurate pupil tracking system”, International Journal of Computer Applications (0975 –8887), vol. 51, no.8, pp. 6-11, August 2012.
[27]H. Qin, X.Wang, M. Liang and W. Yan, “A novel pupil detection algorithm for infrared eye image”,IEEE International Conference,Signal Processing, Communication and Computing (ICSPCC),pp. 1-5, 2013.
[28]Th. Charoenpong, P. Pattrapisetwong, Th. Chanwimalueang and M.Mahasithiwat, “Accurate pupil extraction algorithm by using integrated method”, IEEE, knowledge and smart Technology (KST), pp. 32 –37, 2013.
[29]A. AL-rahayfeh and M. Faezipour, “Eye tracking and head move-ment detection: a state-of-art survey”, Rehabilitation Devices and Systems, vol. 1, 2013.
[30]    رمضان هاونگی . محمد تشنه لب . محمدعلی نکویی و حمیدرضا تقی راد "بررسی مسئله تخمین از دیدگاه بهینه سازی مقید و طراحی تخمین گر تکاملی " مجله مکانیک هوافضا (دینامیک . ارتعاشات و کنترل) جلد7 شماره 27 . 40-1 . 1390
 
 [31]    سید فرید موسوی پور . نادعلی زارعی "فیلتر کالمن و ذره ای در ردیابی اهداف چالش ها و رهیافت ها" پنجمین کنفرانس ملی فرماندهی و کنترل ایران دانشگاه تهران . 1-7 آذر  1390
[32]M. Shakir Hussain, Real-Coded Genetic Algorithm Particle Fil-ters for High-Dimensional State Spaces,Ph.D. Thesis, Depart-ment of Computer Science University College London, pp.11, 2014.
[33]J. H. Holland, “Adaptation in natural and artificial systems”, Uni-versity of Michigan Press, Ann Arbor, MI, 1975.
[34]    مجتبی جعفری . تشخیص تومور در تصاویر سی تی مغزی با استفاده از الگوریتم بهینه سازی اجتماع ذرات چند جمعیتی همراه با جستجوی محلی . پایاننامه کارشناسی ارشد . دانشگاه علوم و تحقیقات تهران . 48 . 1393
[35]    امیر حسین تمجید . انتخاب استخراج و تطبیق ویژگی در  Visual SLAM   سمینار کارشناسی ارشد دانشگاه طوسی . 30 .1386
[36]A. Slama, A. Machraoui and M. Sayadi, “Pupil tracking using ac-tive contour model for Videonystagmography applications”, IEEE IPAS’14: International Image Processing Applications and Sys-tems Conference, pp.1 –5, 2014.
[37]S. Park, J. Hwang, E. Kim, and H. Kang, “Anew evolutionary particle filter for the preventionof sample impoverishment” IEEE Trans. Onevolutionary Computation, vol. 13, no. 4, 2009.
[38]D.Simon, “Optimal state estimation kalman, H∞and non-linear approaches”, John Wiley and Sons, New Jersey, 2006
 
Advanced Signal Processing
Volume 1, Issue 1 - Serial Number 1
December 2016
Pages 1-14

Files

Share

How to cite

Statistics