Telfor Journal, Vol. 9, No. 1, 2017. 49 Abstract — In this paper, an eye tracking methodology is presented. It represents a commercial camera based system for detection of eye pupil and its trajectory and classification of eye movements that led to the formation of assessed eye path. Methodology was examined on 10 subjects, who performed specified series of eye movements in two recording conditions: with and without simultaneous head motions. Image segmentation was performed and coordinates of eye pupil were found for each consecutive video frame. Modified velocity threshold method for eye movement classification was performed. Classification accuracy was evaluated with two parameters: Sensitivity (S) and Positive predictive value (PP), and compared for both recording conditions. In the absence of head motions, a high accuracy result was obtained (S=96.25%; PP=100%). A less accurate result was obtained in the second case (S=87.50%; PP=88.61%). However, it was shown that proposed methodology can provide good results for commercial eye tracking regardless of the recording conditions. Keywords — eye tracking, image gradient, pupil detection, velocity threshold. I. INTRODUCTION YE tracking represents detection of an eye position and its movements and has found the application in many academic and commercial research areas, including diagnosis of patients in ophthalmology, neurology and psychology, as well as market, usability, and gaming research, human computer interaction, etc. Because of that, it is of high importance to provide a system that will allow accurate monitoring of the eye and provide information about its trajectory, but also about the movements that led to the formation of such an eye path. The eye movements, which are commonly used for assessing subjects’ attention and abilities and that are considered in this paper, are fixations and saccades. Fixation represents the ability of eye to inhibit ocular shift by focusing to one point, i.e. the target. Gathering of visual information about the external environment is possible only during a stable fixation [1]. Saccade is a rapid change between two fixations within the field of view [2]. It represents a fast movement that allows eye to change a fixation from one point to another. They are characterized with a large initial acceleration and final slowdown. The amplitude of saccadic movements is usually expressed in degrees of visual angle [3]. A visual angle is formed between two lines connecting the center of the eye and two consecutive eye targets. In general, this eye movement has an amplitude within the range of 1 - 40°, whereby the tracking of moving targets exceeding 30° must include corresponding head movements. The duration of saccade may vary from 10 to 120ms [4]. Velocity of saccadic movement is characterized by the peak whose maximum value depends on the amplitude of saccades and it can reach values up to 400-600°/s. The absence of fixation can indicate some diseases, primarily the occurrence of autism [5]. Babies at the age of 2-6 months, disabled to perform fixation were later diagnosed with autism [6]. Some studies have shown that patients with an atypical form of Parkinsonism have reduced velocity of saccades [7]. Additionally, eye tracking is used in the diagnosis of several other diseases such as: traumatic brain injury [8], schizophrenia [9], Alzheimer's disease [10], a functional loss associated with macular degeneration [11], and Meniere's disease [12]. Because of that, monitoring of eye condition can be very useful in the diagnostics of the most common and most problematic neurological or psychological disorders nowadays. Until now, several systems have been created for eye tracking in clinical settings. The simplest of them is certainly a visual inspection by the physician. More sophisticated methods are also applied, such as video nystamography [13], electrooculography [14] and computerized eye tracking devices that work in the infrared or visible part of the spectrum [15], [16]. All clinical systems are characterized by a high sampling frequency and high image resolution as well as by the use of specific stimulating systems. Therefore, they are unavailable for home assessment (primarily because of their price). In order to improve their visual marketing and make it more effective, companies want to track and obtain information about consumers’ partiality, and affection. Because of that, eye tracking has become a significant part of visual marketing in USA and Europe where obtained spatiotemporal measures indicate attention processes of prime interest [17]. Gaming, as one of the fastest growing industries, has effectively included eye tracking as one of Simple and Precise Commercial Camera based Eye Tracking Methodology Vladislava Bobić and Stevica Graovac E Paper received May 7, 2017; revised June 27, 2107; accepted July 25, 2017. Date of publication July 31, 2017. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Branimir Reljin. This paper is a revised and expanded version of the paper presented at the 24th Telecommunications Forum TELFOR 2016 [29]. This work was supported in part by the Serbian Ministry of Education, Science and Technological Development under Grant No. 175016. Vladislava Bobić is PhD student with the School of Electrical Engineering, University of Belgrade, Bul. kralja Aleksandra 73, 11120 Belgrade, Serbia, and Innovation Center of School of Electrical Engineering, University of Belgrade, Bul. kralja Aleksandra 73, 11120 Belgrade, Serbia, (e-mail: vladislava.bobic@yahoo.com). Stevica Graovac is with the School of Electrical Engineering, University of Belgrade, Bul. kralja Aleksandra 73, 11120 Belgrade, Serbia (e-mail: graovac@etf.rs).