Abstract
We analyze the feasibility of a cheap eye-tracker where the hardware consists of a single webcam and a Raspberry Pi device. Our aim is to discover the limits of such a system and to see whether it provides an acceptable performance. We base our work on the open source Opengazer (Zielinski, 2013) and we propose several improvements to create a robust, real-time system which can work on a computer with 30Hz sampling rate. After assessing the accuracy of our eye-tracker in elaborated experiments involving 12 subjects under 4 different system setups, we install it on a Raspberry Pi to create a portable stand-alone eye-tracker which achieves 1.42° horizontal accuracy with 3Hz refresh rate for a building cost of 70 Euros.
Highlights
Recent advancements in eye-tracking hardware research have resulted in an increased number of available models that have improved performance and that provide easier setup procedures
2. [2-EYE] Previous case + average estimate of 2 eyes 3. [TRACK] Previous case + tracking changes 4. [BLINK] Previous case + excluding blinks during calibration 5. [CORR] Previous case + training error correction 6. [Neural network (NN)] Previous case + neural network estimator In all versions, the facial feature points are selected automatically by the method described in previous sections and gaze is not estimated during blinks
The black baseline shows the best results of the system without any normalization (1.37° horizontal, 1.48° vertical errors)
Summary
Recent advancements in eye-tracking hardware research have resulted in an increased number of available models that have improved performance and that provide easier setup procedures. The main problem with these devices continues to be the scalability since their price and the required expertise for operation make them infeasible at the large scale. These latest commercial models provide great accuracies (between 0.1 and 1°) at high frequencies (over 100Hz); in situations where such accuracies are not necessary and such frequencies are irrelevant, their high prices make them unsuitable. In the case of online advertisement, eye-tracking is used to analyze which parts of webpages draw more attention and how the page layout directs user gaze. We believe that a system that provides comparable performance at an acceptable frequency will enable many applications on devices ranging from computers to tablets and smartphones
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
