Eye Tracking Technology
Studies show that you can't simply observe and directly detect what people are looking at. Without eye tracking technology, many studies simply ask questions and observe the person's behavior. However eye tracking technology can generate reliable data. Typical eye tracking technology uses a camera and an infrared light source. The light source is directed to one or both eyes while the camera follows and records the reflection of the light as well as the eye or visual features. While there are other ways of tracking eye movements, the use of video cameras sensing reflected light from the eye is not invasive and generally inexpensive.
Typically, an eye tracking project will first involve the relationship between the eye positioning of the participants, and the scenes are measured and calibrated. Each person has to be calibrated via a valid eye movement prior to using the eye tracker. The participant must look at a number of calibration spots. Eye-tracking will then generate data. Finally the eye tracking data is analyzed and subsequently presented in meaningful framework. Eye trackers are primarily looking at the pupils of the eyes, and corneal reflection.
Many times the camera is remotely positioned to collect the data, such as mounted on a retail shelf or wall. Other methods include a head-mounted eye tracker apparatus. Regardless of the eye tracking method the data is collected and analyzed by a computer. This data is used to identify the direction of gaze, pupil diameter, eye rotation, the motion of the eye related to the head, and blink frequency. Eye tracking will measure the point of gaze (where one is looking) or the motion of an eye relative to the head, eye positions and eye movement. There are a number other of methods for measuring eye movement.
The most widely used current designs are video-based eye trackers. A camera focuses on one or both eyes and records their movement as the viewer looks at some kind of stimulus. Most modern eye-trackers use the center of the pupil and infrared light to create corneal reflections (CR). The vector between the pupil center and the corneal reflections can be used to compute the point of regard on a surface or the gaze direction.
Software interprets the data that is recorded by the various types of eye trackers, and animates or visually represents it, so that the visual behavior of a person can be graphically displayed. Graphical presentation and quantitative measures of the eye movement events and their parameters can be used in the analysis. The main measurements used in eye-tracking projects are fixations and saccades. A fixation is when the user's gaze is relatively motionless on a specific area. A saccade is a quick movement between fixations to another element. There are other eye movement events that stem from these basic measures, such as smooth pursuit which allow the eyes to closely follow a moving object and blink rate measurements.
Heat maps are the most common visualizations of eye tracking. Heat maps are static representations, which can identify where users focused their gaze. Heat maps reveal exactly where people look. The results often point to useful insights.
Eye tracking generates data regarding what a person views and how long their gaze is. This is part of big data where data is obtained, mined and
Figure 10.1 Eye tracking equipment.
analyzed. The heat maps show the distribution of attention with a color coded map superimposed on the stimulus with an intensity indicator.
The resulting data can be statistically analyzed and graphically rendered to provide evidence of specific visual patterns. By examining fixations, sac- cades, pupil dilation, blinks, and a variety of other behaviors researchers can determine a great deal about the effectiveness of a given medium or product.
The most common use of eye tracking is with web sites. Traditionally web sites have developed data on clicking and scrolling patterns. Eye tracking provides data on what is eye catching on the web site. Eye tracking can be used to measure search efficiency, navigation, and usability.
Eye tracking is commonly utilized in a variety of different advertising media. Commercials, print ads, online ads, and sponsored programs are all conducive to analysis with current eye tracking technology. For instance in newspapers, eye tracking studies can be used to find out in what way advertisements should be mixed with the news in order to catch the subject's eyes.
One of the most promising applications in eye tracking research is in the field of automotive design. Research is currently underway to integrate eye tracking cameras into automobiles. The goal is to provide the vehicle with the capacity to assess the visual behavior of the driver in real-time. The USA National Highway Traffic Safety Administration (NHTSA) estimates that drowsiness is the primary causal factor in 100,000 police-reported accidents per year. Another NHTSA study suggests that 80% of collisions occur within three seconds of a distraction. By equipping automobiles with the ability to monitor drowsiness, inattention, and cognitive engagement driving safety could be dramatically enhanced. For example, the Driver Monitoring System, also known as Driver Attention Monitor, is a vehicle safety system first introduced by Toyota in 2006 in its Lexus models providing a warning if the driver takes his or her eye off the road.
Since 2005, eye-tracking has been used in communication systems for disabled persons: allowing the user to speak, send e-mail, browse the Internet and perform other such activities, using only their eyes. Eye control works even when the user has involuntary movement as a result of Cerebral palsy or other disabilities, and for those who have glasses or other physical interference.
Examples of Museums
New York's Solomon R. Guggenheim Museum recently deployed an indoor positioning system and an eye tracking system. The devices will enable the museum to send messages about artworks to visitors via their smartphones while at the same time collect details about the visitors. The museum then filters the data to better understand guests' behavior, such as how often they visit, which shows they flock to, and what art they ignore.
Understanding audience behavior enables museums to target marketing for future exhibits or personalize messages to visitors based on their past viewing history. From an educational standpoint, this data can help museums find the most effective tools for teaching their audiences about the art on the walls.