An Embedded and Real-Time Pupil Detection Pipeline
This work addresses the need for smaller and more efficient wearable eye-tracking systems, though it is incremental as it builds on existing methods with specific hardware integration.
The paper tackles the problem of wearable pupil detection by proposing a hardware-software co-design that enables real-time processing on an embedded platform, achieving a runtime of 54ms at 480x640 resolution and an average cumulative error of 5.3368px on the LPW dataset with a 51.9% detection rate.
Wearable pupil detection systems often separate the analysis of the captured wearer's eye images for wirelessly-tethered back-end systems. We argue in this paper that investigating hardware-software co-designs would bring along opportunities to make such systems smaller and more efficient. We introduce an open-source embedded system for wearable, non-invasive pupil detection in real-time, on the wearable, embedded platform itself. Our system consists of a head-mounted eye tracker prototype, which combines two miniature camera systems with Raspberry Pi-based embedded system. Apart from the hardware design, we also contribute a pupil detection pipeline that operates using edge analysis, natively on the embedded system at 30fps and run-time of 54ms at 480x640 and 23ms at 240x320. Average cumulative error of 5.3368px is found on the LPW dataset for a detection rate of 51.9\% with our detection pipeline. For evaluation on our hardware-specific camera frames, we also contribute a dataset of 35000 images, from 20 participants.