Fuzzy-based estimation of continuous Z-distances and discrete directions of home appliances for NIR camera-based gaze tracking system

Abstract

With the development of eye gaze tracking technology, much research has been performed to adopt this technology for interfacing with home appliances by severely disabled and wheelchair-bound users. For this purpose, two cameras are usually required, one for calculating the gaze position of the user, and the other for detecting and recognizing the home appliance. In order to accurately calculate the gaze position on the home appliance that the user looks at, the Z-distance and direction of the home appliance from the user should be correctly measured. Therefore, stereo cameras or depth-measuring devices such as Kinect are necessary, but they have limitations such as the need for additional camera calibration, and low acquisition speed for two cameras or a large-size of Kinect device. To overcome this problem, we propose a new method for estimating the continuous Z-distances and discrete directions of home appliances using one (small-sized) near-infrared (NIR) web camera and a fuzzy system. Experimental results show that the proposed method can accurately estimate the Z-distances and directions to home appliances.