Abstract
The ability to monitor eye closures and blink patterns has long been known to enable accurate assessment of fatigue and drowsiness in individuals. Many measures of the eye are known to be correlated with fatigue including coarse-grained measures like the rate of blinks as well as fine-grained measures like the duration of blinks and the extent of eye closures. Despite a plethora of research validating these measures, we lack wearable devices that can continually and reliably monitor them in the natural environment. In this work, we present a low-power system, iLid, that can continually sense fine-grained measures such as blink duration and Percentage of Eye Closures (PERCLOS) at high frame rates of 100fps. We present a complete solution including design of the sensing, signal processing, and machine learning pipeline; implementation on a prototype computational eyeglass platform; and extensive evaluation under many conditions including illumination changes, eyeglass shifts, and mobility. Our results are very encouraging, showing that we can detect blinks, blink duration, eyelid location, and fatigue-related metrics such as PERCLOS with less than a few percent error.
Supplemental Material
Available for Download
Supplemental movie, appendix, image and software files for, iLid: Low-power Sensing of Fatigue and Drowsiness Measures on a Computational Eyeglass
- 2007. SensoMotoric Instruments (SMI): Eye and gaze tracking systems. (28 Nov. 2007). http://www.smivision.com/en.html.Google Scholar
- 2014. Current Centeye Vision Chips. http://www.centeye.com/. (22 Feb. 2014).Google Scholar
- 2014. OmniVision: CMOS VGA (640x480) Image Sensor. (27 Feb. 2014). http://www.ovt.com/products/sensor.php?id=146.Google Scholar
- 2015. JINS MEME Eyewear. (14 Oct. 2015). https://jins-meme.com/en/.Google Scholar
- 2015. STM3232-bitARMCortex MCUs - STMicroelectronics. (24 Mar. 2015). Retrieved September 10, 2016 from http://www.st.com/stm32.Google Scholar
- 2015. Tobii Glasses: Mobile Eye Tracker for real world research. (15 Oct. 2015). http://www.tobii.com.Google Scholar
- 2016. Research on Drowsy Driving. (23 Jan. 2016). http://www.nhtsa.gov/Driving+Safety/Drowsy+Driving/scope-of-the-problem.Google Scholar
- 2016. SMI Eye Tracking Glasses. (2016). http://www.eyetracking-glasses.com/products/eye-tracking-glasses-2-wireless/technology/.Google Scholar
- 2017. Center of Excellence for Mobile Sensor Data-to-Knowledge. (2017). https://md2k.org.Google Scholar
- Saeed Abdullah, Elizabeth L Murnane, Mark Matthews, Matthew Kay, Julie A Kientz, Geri Gay, and Tanzeem Choudhury. 2016. Cognitive rhythms: unobtrusive and continuous sensing of alertness using a mobile phone. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. ACM, 178--189. Google ScholarDigital Library
- Christer Ahlstrom, Marcus Nyström, Kenneth Holmqvist, Carina Fors, David Sandberg, Anna Anund, Göran Kecklund, and Torbjörn Åkerstedt. 2013. Fit-for-duty test for estimation of drivers? sleepiness level: eye movements improve the sleep/wake predictor. Transportation research part C: emerging technologies 26 (2013), 20--32.Google Scholar
- Rizwan Ahmad. 2016. Understanding the Language of the Eye: Detecting and Identifying Eye Events in Real Time via Electrooculography. (2016). http://www.escholarship.org/uc/item/53n1p2z5Google Scholar
- Tobias Appel, Thiago Santini, and Enkelejda Kasneci. 2016. Brightness-and motion-based blink detection for head-mounted eye trackers. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct. ACM, 1726--1735. Google ScholarDigital Library
- Ioana Bacivarov, Mircea Ionita, and Peter Corcoran. 2008. Statistical models of appearance for eye tracking and eye-blink detection and measurement. IEEE transactions on consumer electronics 54, 3 (2008). Google ScholarDigital Library
- P. L. Benitez, G. H. Kamimori, T. J. Balkin, A. Greene, and M. L. Johnson. 2009. Modeling fatigue over sleep deprivation, circadian rhythm, and caffeine with a minimal performance inhibitor model. Meth. Enzymol. 454 (2009), 405--421.Google ScholarCross Ref
- Luis Miguel Bergasa, Jesús Nuevo, Miguel A Sotelo, Rafael Barea, and María Elena Lopez. 2006. Real-time system for monitoring driver vigilance. IEEE Transactions on Intelligent Transportation Systems 7, 1 (2006), 63--77. Google ScholarDigital Library
- Serge Boverie and Alain Giralt. 2008. Driver vigilance diagnostic based on eyelid movement observation. IFAC Proceedings Volumes 41, 2 (2008), 12831--12836.Google ScholarCross Ref
- J. E. Bower. 2014. Cancer-related fatigue--mechanisms, risk factors, and treatments. Nat Rev Clin Oncol 11, 10 (Oct 2014), 597--609.Google ScholarCross Ref
- Andreas Bulling, Daniel Roggen, and Gerhard Tröster. 2008. It's in your eyes: towards context-awareness and mobile HCI using wearable EOG goggles. In Proceedings of the 10th international conference on Ubiquitous computing. ACM, 84--93. Google ScholarDigital Library
- Andreas Bulling, Daniel Roggen, and Gerhard Tröster. 2009. Wearable EOG goggles: Seamless sensing and context-awareness in everyday environments. Journal of Ambient Intelligence and Smart Environments 1, 2 (2009), 157--171. Google ScholarDigital Library
- Andreas Bulling, Jamie A Ward, Hans Gellersen, and Gerhard Troster. 2011. Eye movement analysis for activity recognition using electrooculography. IEEE transactions on pattern analysis and machine intelligence 33, 4 (2011), 741--753. Google ScholarDigital Library
- Michael Chau and Margrit Betke. 2005. Real time eye tracking and blink detection with usb cameras. Technical Report. Boston University Computer Science Department.Google Scholar
- Elizabeth J. Corwin, Laura Cousino Klein, and Kristin Rickelman. 2002. Predictors of Fatigue in Healthy Young Adults: Moderating Effects of Cigarette Smoking and Gender. Biological Research For Nursing 3, 4 (2002), 222--233, PMID: 12184665.Google ScholarCross Ref
- Anirban Dasgupta, Anjith George, SL Happy, and Aurobinda Routray. 2013. A Vision-Based System for Monitoring the Loss of Attention in Automotive Drivers. IEEE Trans. Intelligent Transportation Systems 14, 4 (2013), 1825--1838. Google ScholarDigital Library
- Tomas Drutarovsky and Andrej Fogelton. 2014. Eye blink detection using variance of motion vectors. In European Conference on Computer Vision. Springer, 436--448.Google Scholar
- John D. Fisk, Amanda Pontefract, Paul G. Ritvo, Catherine J. Archibald, and T.J. Murray. 1994. The Impact of Fatigue on Patients with Multiple Sclerosis. Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques 21, 1 (001 002 1994), 9--14.Google ScholarCross Ref
- J. Friedman, T. Hastie, and R. Tibshirani. 2001. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer Series in Statistics, Vol. 1.Google Scholar
- Wolfgang Fuhl, Thiago Santini, David Geisler, Thomas Kübler, Wolfgang Rosenstiel, and Enkelejda Kasneci. 2016. Eyes wide open? eyelid location and eye aperture estimation for pervasive eye tracking in real-world scenarios. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct. ACM, 1656--1665. Google ScholarDigital Library
- Kyosuke Fukuda, John A Stern, Timothy B Brown, and Michael B Russo. 2005. Cognition, blinks, eye-movements, and pupillary movements during performance of a running memory task. Aviation, space, and environmental medicine 76, 7 (2005), C75--C85.Google Scholar
- X. Y. Gao, Y. F. Zhang, W. L. Zheng, and B. L. Lu. 2015. Evaluating driving fatigue detection algorithms using eye tracking glasses. In 2015 7th International IEEE/EMBS Conference on Neural Engineering (NER). 767--770.Google Scholar
- I Garcia, Sebastian Bronte, Luis Miguel Bergasa, Javier Almazán, and J Yebes. 2012. Vision-based drowsiness detector for real driving conditions. In Intelligent Vehicles Symposium (IV), 2012 IEEE. IEEE, 618--623.Google ScholarCross Ref
- N. Goel, M. Basner, H. Rao, and D. F. Dinges. 2013. Circadian rhythms, sleep deprivation, and human performance. Prog Mol Biol Transl Sci 119 (2013), 155--190.Google ScholarCross Ref
- Kristen Grauman, Margrit Betke, James Gips, and Gary R Bradski. 2001. Communication via eye blinks-detection and duration analysis in real time. In Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, Vol. 1. IEEE, I--I.Google ScholarCross Ref
- Martijn Haak, Steven Bos, Sacha Panic, and LJM Rothkrantz. 2009. Detecting stress using eye blinks and brain activity from EEG signals. Proceeding of the 1st driver car interaction and interface (DCII 2008) (2009), 35--60.Google Scholar
- E. Havlikova, J. Rosenberger, I. Nagyova, B. Middel, T. Dubayova, Z. Gdovinova, J. P. Van Dijk, and J. W. Groothoff. 2008. Impact of fatigue on quality of life in patients with Parkinsonfis disease. European Journal of Neurology 15, 5 (2008), 475--480.Google ScholarCross Ref
- Tianyi Hong and Huabiao Qin. 2007. Drivers drowsiness detection in embedded system. In Vehicular Electronics and Safety, 2007. ICVES. IEEE International Conference on. IEEE, 1--5.Google ScholarCross Ref
- Chin-Shun Hsieh and Cheng-Chi Tai. 2013. An improved and portable eye-blink duration detection system to warn of driver fatigue. Instrumentation Science 8 Technology 41, 5 (2013), 429--444.Google Scholar
- Michael Ingre, Torbjörn Ákerstedt, Björn Peters, Anna Anund, and Göran Kecklund. 2006. Subjective sleepiness, simulated driving performance and blink duration: examining individual differences. Journal of Sleep Research 15, 1 (2006), 47--53.Google ScholarCross Ref
- Amir-Homayoun Javadi, Zahra Hakimi, Morteza Barati, Vincent Walsh, and Lili Tcheang. 2015. SET: a pupil detection method using sinusoidal approximation. Frontiers in neuroengineering 8 (2015).Google Scholar
- Xianta Jiang, Geoffrey Tien, Da Huang, Bin Zheng, and M Stella Atkins. 2013. Capturing and evaluating blinks from video-based eyetrackers. Behavior research methods 45, 3 (2013), 656--663.Google Scholar
- Hughes JR and Hatsukami D. 1986. Signs and symptoms of tobacco withdrawal. Archives of General Psychiatry 43, 3 (1986), 289--294.Google ScholarCross Ref
- Hughes JR, Higgins ST, Bickel WK, and et al. 1991. Caffeine self-administration, withdrawal, and adverse effects among coffee drinkers. Archives of General Psychiatry 48, 7 (1991), 611--617.Google ScholarCross Ref
- Won Oh Lee, Eui Chul Lee, and Kang Ryoung Park. 2010. Blink detection robust to various facial poses. Journal of neuroscience methods 193, 2 (2010), 356--372.Google ScholarCross Ref
- I. S. Lobentanz, S. Asenbaum, K. Vass, C. Sauter, G. Klsch, H. Kollegger, W. Kristoferitsch, and J. Zeitlhofer. 2004. Factors influencing quality of life in multiple sclerosis patients: disability, depressive mood, fatigue and sleep quality. Acta Neurologica Scandinavica 110, 1 (2004), 6--13.Google ScholarCross Ref
- Amol M Malla, Paul R Davidson, Philip J Bones, Richard Green, and Richard D Jones. 2010. Automated video-based measurement of eye closure for detecting behavioral microsleep. In Engineering in Medicine and Biology Society (EMBC), 2010 Annual International Conference of the IEEE. IEEE, 6741--6744.Google ScholarCross Ref
- R Martins and JM Carvalho. 2015. Eye blinking as an indicator of fatigue and mental load-a systematic review. Occupational Safety and Hygiene III (2015), 231--235.Google Scholar
- Addison Mayberry, Pan Hu, Benjamin Marlin, Christopher Salthouse, and Deepak Ganesan. 2014. iShadow: Design of a Wearable, Real-time Mobile Gaze Tracker. In Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys ‘14). ACM, New York, NY, USA, 82--94. Google ScholarDigital Library
- Addison Mayberry, Yamin Tun, Pan Hu, Duncan Smith-Freedman, Deepak Ganesan, Benjamin M. Marlin, and Christopher Salthouse. 2015. CIDER: Enabling Robustness-Power Tradeoffs on a Computational Eyeglass. In Proceedings of the 21st Annual International Conference on Mobile Computing and Networking (MobiCom ‘15). ACM, New York, NY, USA, 400--412. Google ScholarDigital Library
- Lindsey K McIntire, John P McIntire, R Andy McKinley, and Chuck Goodyear. 2014. Detection of vigilance performance with pupillometry. In Proceedings of the Symposium on Eye Tracking Research and Applications. ACM, 167--174. Google ScholarDigital Library
- T. R. Mendoza, X. S. Wang, C. S. Cleeland, M. Morrissey, B. A. Johnson, J. K. Wendt, and S. L. Huber. 1999. The rapid assessment of fatigue severity in cancer patients: use of the Brief Fatigue Inventory. Cancer 85, 5 (Mar 1999), 1186--1196.Google ScholarCross Ref
- Inga Meyhöfer, Veena Kumari, Antje Hill, Nadine Petrovsky, and Ulrich Ettinger. 2016. Sleep deprivation as an experimental model system for psychosis: Effects on smooth pursuit, prosaccades, and antisaccades. Journal of Psychopharmacology (2016), 0269881116675511.Google Scholar
- Tim Morris, Paul Blenkhorn, and Farhan Zaidi. 2002. Blink detection for real-time eye tracking. Journal of Network and Computer Applications 25, 2 (2002), 129--143. Google ScholarDigital Library
- TL Morris and James C Miller. 1996. Electrooculographic and performance indices of fatigue during simulated flight. Biological psychology 42, 3 (1996), 343--360.Google Scholar
- M Patel, SKL Lal, Diarmuid Kavanagh, and Peter Rossiter. 2011. Applying neural network analysis on heart rate variability data to assess driver fatigue. Expert systems with Applications 38, 6 (2011), 7235--7242. Google ScholarDigital Library
- Leo Pauly and Deepa Sankar. 2015. Detection of drowsiness based on hog features and svm classifiers. In Research in Computational Intelligence and Communication Networks (ICRCICN), 2015 IEEE International Conference on. IEEE, 181--186.Google ScholarCross Ref
- Marco Pedrotti, Shengguang Lei, Jeronimo Dzaack, and Matthias Rötting. 2011. A data-driven algorithm for offline pupil signal preprocessing and eyeblink detection in low-speed eye-tracking protocols. Behavior Research Methods 43, 2 (2011), 372--383.Google ScholarCross Ref
- A. Picot, A. Caplier, and S. Charbonnier. 2009. Comparison between EOG and high frame rate camera for drowsiness detection. In Applications of Computer Vision (WACV), 2009 Workshop on. 1--6.Google Scholar
- Antoine Picot, Alice Caplier, and Sylvie Charbonnier. 2009. Comparison between EOG and high frame rate camera for drowsiness detection. In Applications of Computer Vision (WACV), 2009 Workshop on. IEEE, 1--6.Google ScholarCross Ref
- R. Schleicher, N. Galley, S. Briest, and L. Galley. 2008. Blinks and saccades as indicators of fatigue in sleepiness warnings: looking tired? Ergonomics 51, 7 (2008), 982--1010, PMID: 18568959.Google ScholarCross Ref
- Robert Schleicher, Niels Galley, Susanne Briest, and Lars Galley. 2008. Blinks and saccades as indicators of fatigue in sleepiness warnings: looking tired? Ergonomics 51, 7 (2008), 982--1010.Google ScholarCross Ref
- Paul Smith, Mubarak Shah, and Niels da Vitoria Lobo. 2003. Determining driver visual attention with one camera. IEEE transactions on intelligent transportation systems 4, 4 (2003), 205--218. Google ScholarDigital Library
- M. D. Stein and P. D. Friedmann. 2005. Disturbed sleep and its relationship to alcohol use. Subst Abus 26, 1 (Mar 2005), 1--13.Google ScholarCross Ref
- J. A. Stern, D. Boyer, David J. Schroeder, United States., and Civil Aeromedical Institute. 1994. Blink rate as a measure of fatigue {microform}: a review / J.A. Stern, D. Boyer, D.J. Schroeder. U.S. Dept. of Transportation, Federal Aviation Administration, Office of Aviation Medicine; Available to the public through the National Technical Information Service Washington, D.C.: Springfield, Va. i, 12 p.; pages. http://purl.access.gpo.gov/GPO/LPS84339Google Scholar
- Federico M Sukno, Sri-Kaushik Pavani, Constantine Butakoff, and Alejandro F Frangi. 2009. Automatic assessment of eye blinking patterns through statistical shape models. In International Conference on Computer Vision Systems. Springer, 33--42. Google ScholarDigital Library
- Louis Tijernia, Stoltzfus Duane Gleckler, Mark nad, Scott Johnston, Michael J. Goodman, and Walter W. Wierwille. 1999. A Preliminary Assessment of Algorithms for Drowsy and Inattentive Driver Detection on the Road. Technical Report. Springfield VA.Google Scholar
- Marc Tonsen, Xucong Zhang, Yusuke Sugano, and Andreas Bulling. 2016. Labelled pupils in the wild: a dataset for studying pupil detection in unconstrained environments. In Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research 8 Applications. ACM, 139--142. Google ScholarDigital Library
- W. W. Wierwille, S. S. Wreggit, C. L. Kirn, L. A. Ellsworth, and R. J. Fairbanks. 1994. Research on Vehicle-Based Driver Status/Performance Monitoring; Development, Validation, and Refinement of Algorithms For Detection of Driver Drowsiness. Technical Report. Springfield VA.Google Scholar
- Ann Williamson. 2007. Predictors of Psychostimulant Use by Long-Distance Truck Drivers. American Journal of Epidemiology 166, 11 (2007), 1320.Google ScholarCross Ref
- Junwen Wu and Mohan M Trivedi. 2007. Simultaneous eye tracking and blink detection with interactive particle filters. EURASIP Journal on Advances in Signal Processing 2008, 1 (2007), 823695. Google ScholarDigital Library
- Cui Xu, Ying Zheng, and Zengfu Wang. 2008. Efficient eye states detection in real-time for drowsy driving monitoring system. In Information and Automation, 2008. ICIA 2008. International Conference on. IEEE, 170--174.Google Scholar
- Chuang-Wen You, Nicholas D Lane, Fanglin Chen, Rui Wang, Zhenyu Chen, Thomas J Bao, Martha Montes-de Oca, Yuting Cheng, Mu Lin, Lorenzo Torresani, and others. 2013. Carsafe app: Alerting drowsy and distracted drivers using dual cameras on smartphones. In Proceeding of the 11th annual international conference on Mobile systems, applications, and services. ACM, 13--26. Google ScholarDigital Library
Index Terms
- iLid: Low-power Sensing of Fatigue and Drowsiness Measures on a Computational Eyeglass
Recommendations
iLid: eyewear solution for low-power fatigue and drowsiness monitoring
ETRA '19: Proceedings of the 11th ACM Symposium on Eye Tracking Research & ApplicationsThe ability to monitor eye closures and blink patterns has long been known to enable accurate assessment of fatigue and drowsiness in individuals. Many measures of the eye are known to be correlated with fatigue including coarse-grained measures like ...
An eye detection method robust to eyeglasses for mobile iris recognition
An eye detection method that is robust to eyeglass interference is proposed for mobile iris recognition system.Multi-scale window mask consisting of 2ź ź3 subblocks is used to generate eye candidates.Eye validation is applied to select the true eye ...
Rendering refraction and reflection of eyeglasses for synthetic eye tracker images
ETRA '16: Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & ApplicationsWhile for the evaluation of robustness of eye tracking algorithms the use of real-world data is essential, there are many applications where simulated, synthetic eye images are of advantage. They can generate labelled ground-truth data for appearance ...
Comments