A Fast and Accurate Eye Tracker Using Stroboscopic Differential Lighting

Abstract

The use of video-based eye trackers (VETs) for gaze interaction have allowed people with severe motor disabilities to communicate more effectively. Nonetheless, current low cost VETs present limited accuracy and precision that impose several design constraints for gaze-based computer applications. In this paper we present an extension of the differential lighting (DL) technique for pupil detection and tracking using active light sources. The original technique was developed for analog interlaced cameras with external sync signal to synchronize the light sources with the video signal. In this paper we introduce the Stroboscopic DL technique that can be used with any rolling shutter camera, even those with no external sync. We have developed a computer vision technique to adjust the firing of the stroboscopic lights. Our new algorithm also exploits characteristics of pupil images to improve the accuracy of the tracking algorithm. Another advantage of the method is that using flashed pulses of light creates a virtual exposure time, reducing motion blur and temporal shear in the video volume. A real-time 187 fps prototype of the system was implemented using a low cost PS3 camera. Experimental results comparing the performance of our algorithm with Starburst show significant accuracy and speed improvement.

Recognizing Edge-Based Diseases of Vocal Cords by Using Convolutional Neural Networks

“…Borsato et al marked the edge of eyeballs by object color and shape to enable the evaluation of user focus through the tracking of eyeball positions [8]. Eyeball tracking is tractable because eyeball images can be stored directly and an invasive test is not required.…”

“…During a clinical examination, a doctor uses a stroboscope to access the glottis and examine VC tissue. Stroboscopes are widely used in various domains to observe real tissue images [8]. Figs.…”

“…6) The EVC-DD disease model could be derived after training model. 7) The testing images were used to evaluate the performance of the derived model 8). The derived model outputted the potential disease for each given testing image.…”

Motion-Blur-Free High-Speed Video Shooting Using a Resonant Mirror

“…However, these systems are not suitable for capturing non-blurred input images because they cannot address existing motion blur in the captured images. Since its origination in [ 60 ], many high-speed photography methods and systems with strobe lights [ 61 , 62 , 63 , 64 ] have been developed. They can shoot videos of fast-moving objects without motion blur with very short strobe pulses, whereas they cannot shoot videos of fast-moving objects at distant places under daylight conditions because ambient light becomes dominant.…”