Download - Gaze Tracking

8/2/2019 Gaze Tracking

1/12

1

INTRODUCTION

If the eyes are the windows to the soul as to quote William Shakespeare,

then the one of the logical steps to understanding the human behavior and

motivation should involve the study of eye gaze tracking. When someones eye

movements are tracked, the path where attention is deployed can be determined.

Human vision and acuity is one of the most complex systems of the human body

and is important to human survival. We move our eyes to shift our attention from

one portion of the visible field to another. In doing so, we can obtain a higher

resolution where ever direction we direct the central point of our gaze. If we track

some ones eye movement we can follow the path of their attention.

The other appropriate words to describe the meaning of the word gaze are

look, glare, stare, glimpse etc. Thus gaze tracking is detecting and analyzing the

position that a user is looking at. A wide variety of disciplines has its application,

including cognitive science, psychology (notably psycholinguistics, the visual

world paradigm), human-computer interaction (HCI), video conferences

marketing research and medical research (neurological diagnosis). Using eye gaze

trackers as a selection tool is necessary too for people with disabilities where eye

movements may be the only body movement over which the person has control.

Marketing and commercial uses could provide information on what sort of

packaging may attract more attention or what aspects of commercials or

marketing strategies are successful. More recently, there has been growth in using

eye tracking to study how users interact with different computer interfaces.

Specific questions researchers ask are related to the how easy different interfaces

are for users. The results of the eye tracking research can lead to changes in design

of the interface. Yet another recent area of research focuses on Web development.This can include how users react to drop-down menus or where they focus their

attention on a Website so the developer knows where to place an advertisement.


2/12

2

HISTORY

In the 1800s, the study of the eye movement was made using direct

observation. In 1879 in Paris, Louis mile Javal observed that reading does not

involve a smooth sweeping of the eyes along the text, as previously assumed, buta series of short stops (called fixations) and quick saccades. This observation

raised important questions about reading, which were explored during the 1900s:

On which words do the eyes stop? For how long? When does it regress back to

already seen words?

Fig.1. An example of fixations and saccades over text. This is the typical pattern

of eye movement during reading. The eyes never move smoothly over still text.


3/12

3

Edmund Huey built an early eye tracker, using a sort of contact lens with a hole

for the pupil. The lens was connected to an aluminum pointer that moved in

response to the movement of the eye.

In the 1950s, Alfred L. Yarbus did important eye tracking research and his

1967 book is very highly quoted. He showed the task given to a subject has a very

large influence on the subject's eye movement.

He also wrote about the relation between fixations and interest: "All the

records ... show conclusively that the character of the eye movement is either

completely independent of or only very slightly dependent on the material of the

picture and how it was made, provided that it is flat or nearly flat."

Fig.2. This study by Yarbus (1967) is often referred to as evidence on how the

task given to person influences his or her eye movement.


4/12

4

The cyclical pattern in the examination of pictures "is dependent not only

on what is shown on the picture, but also on the problem facing the observer and

the information that he hopes to gain from the picture."

The 1980s also saw the birth of using eye tracking to answer questions

related to human-computer interaction. Specifically, researchers investigated how

users search for commands in computer menus. Additionally, computers allowed

researchers to use eye-tracking results in real time, primarily to help disabled

users.

According to Hoffman, current consensus is that visual attention is always

slightly (100 to 250 ms) ahead of the eye. But as soon as attention moves to a new

position, the eyes will want to follow. We still cannot infer specific cognitive

processes directly from a fixation on a particular object in a scene. For instance, a

fixation on a face in a picture may indicate recognition, liking, dislike, puzzlement

etc. Therefore eye tracking is often coupled with other methodologies, such as

introspective verbal protocols.

GAZE TRACKER TYPES

Camera-vision-based gaze-tracking methods can be categorized into two

types: the wearable-camera- based method and the remote-camera-based

method. The former method is called the head-mounted gaze-tracking method

and requires the user to wear a device consisting of a camera to capture the eye

image of the user at a close distance.

Light, typically infrared, is reflected from the eye and sensed by a video

camera or some other specially designed optical sensor. The information is then

analyzed to extract eye rotation from changes in reflections. Video based eyetrackers typically use the corneal reflection (the first Purkinje image) and the

center of the pupil as features to track over time. A more sensitive type of eye

tracker, the dual-Purkinje eye tracker, uses reflections from the front of the cornea

(first Purkinje image) and the back of the lens (fourth Purkinje image) as features

to track. A still more sensitive method of tracking is to image features from inside

the eye, such as the retinal blood vessels, and follow these features as the eye


5/12

5

rotates. Optical methods, particularly those based on video recording, are widely

used for gaze tracking and are favored for being non-invasive and inexpensive.

In the Head-mounted-display (HMD)-based eye tracking devices light

illuminators at the corners of the monitor and the helmet-type device consisting of

the camera for capturing an eye image. The Head-mounted-display (HMD)-based

eye tracking devices in which, it is not necessary to consider the facial movement

since the HMD moves according to the facial movement of the user. However, if

the HMD is moved or slipped down from its initial wearing status of the user-

dependent calibration, the error of gaze estimation increases.

Next, in the remote-camera-based method, the camera with a zoom lens

captures the users eye. It is even more convenient for the users because they do

not need to wear any devices.

Each method of gaze tracking has advantages and disadvantages, and the

choice of an eye tracking system depends on considerations of cost and

application. There are offline methods and online procedures like Attention

Tracking. There is a trade-off between cost and sensitivity, with the most sensitive

systems costing many tens of thousands of Eye tracking 6 dollars and requiring

considerable expertise to operate properly. Advances in computer and videotechnology have led to the development of relatively low cost systems that are

useful for many applications and fairly easy to use. Interpretation of the results

still requires some level of expertise, however, because a misaligned or poorly

calibrated system can produce wildly erroneous data.

With the increase in the number of gaze-tracking applications, various

researches on gaze tracking have been carried out in order to improve accuracy

and user convenience, reducing processing time and simplifying the complicated

stage of calibration.

DATA REPRESENTATION

To allow interpretation of the data that is recorded by the various types of

eye trackers exist various software that animates or visually represents it, so that

the visual behavior of one or more users can be graphically resumed. The

following ones are the most commonly used:


6/12

6

Animated representations of a point on the interface: This method is used

when the visual behavior is examined individually indicating where did the user

focus his/her gaze in each moment, complemented with a small path that indicates

the previous saccade movements, as seen in the image.

Static representations of the saccade path: This is fairly similar to the one

described above with the difference that this is static method. A higher level of

expertise than with the animated ones is required to interpret this.

Heat maps: An alternative static representation, mainly used for the agglomerated

analysis of the visual exploration patterns in a group of users, differing from both

methods explained before. In these representations, the hot zones or zones with

higher density designate where the users focused their gazes with a higher

frequency.

Blind zones maps: This method is a simplified version of the Heat maps where

the visually less attended zones by the users are displayed clearly, thus allowing

for an easier understanding of the most relevant information, that is to say, we are

informed about which zones were not seen by the users.

The four methods described above are extremely useful and easy to understand in

a later analysis. With them we can easily show the client with a single image that

the users dont explore the interface in an orderly way as it is commonly believed.

CASE STUDIES ON GAZE TRACKING

i. GAZE TRACKING WHILE DRIVINNG A CAR IN A DIFFICULT

SITUATION:

The eye movements of two groups of drivers have been filmed with a special head

camera by a team of the Swiss Federal Institute of Technology: Novice and

experienced drivers had their eye-movement recorded while approaching a bend

of a narrow road. The series of images has been condensed from the original film

frames to show 2 eye fixations per image for better comprehension. Each of these

stills correspond approximately to 0.5 seconds in real-time.


7/12

7

Fig.3. Frames from narrow road eye tracking described in this section

Comparison of the top images shows that the experienced driver checks

the curve and even has Fixation No. 9 left to look aside while the novice driver

needs to check the road and estimate his distance to the parked car. In the middle

images the experienced driver is now fully concentrating on the location where an

oncoming car could be seen. The novice driver concentrates his view on the

parked car. In the bottom image the novice is busy estimating the distance

between the left wall and the parked car, while the experienced driver can use his

peripheral vision for that and still concentrates his view on the dangerous point of


8/12

8

the curve: If a car appears there he has to give way, i. e. stop to the right instead of

passing the parked car.

ii. GAZE TRACKING OF YOUNGER AND ELDRELY PEOPLE IN

WALKING:

Elderly subjects depend more on foveal vision than younger subjects

during walking. Their walking speed is decreased by a limited visual field,

probably caused by a deteriorated peripheral vision.

Younger subjects make use of both their central and peripheral vision

while walking. Their peripheral vision allows faster control over the process of

walking.

iii. GAZE VS. MOUSE: AN EVALUATION OF USER EXPERIENCE AND

PLANNING IN PROBLEM SOLVING GAMES

The aim of ths thesis was to investigate whether gaze-based interaction is a

suitable means of input for problem solving games. Where a player has to use

his/her eyes not only to select objects, but also to visually perceive the puzzle and

plan his/her next move in order to solve the puzzle.

Two common problem solving puzzles were implemented, the Sudoku and

the Tile Slide puzzle (or 15 puzzle). Each puzzle can be played with eye gaze or

with the mouse. Although test subjects found gaze interesting, the mouse was still

the preferred mode of interaction. We found that gaze selection is more erroneous

than mouse selection and that these errors can cause a player to lose concentration

from the task at hand. We also found that the user interface and the interaction

sequence influences both the planning strategy that the player would use and theamount of time it takes him/her to complete the task.

Human computer interaction (HCI) can be defined as a discipline that is

concerned with the design, evaluation and implementation of interactive computer

systems for human use [Acmsigchi, nd].

Traditionally, computer user interfaces have used command-based

principles to facilitate the communication between humans and computers.


9/12

9

Command-based user interfaces require a user to explicitly issue a command to

the system.

Commands come in different forms depending upon the generation of the

computer, user interface, selection technique and the purpose or use of the system.

Nielsen (1993) singles out two types of command-based user interfaces: function

orientated interfaces and object orientated interfaces.

Function orientated interfaces make use of verb-noun syntaxes, where

the user issues a command by first specifying the function (operation) to be

executed and then identifying the item that the operation should be executed on.

Nielsen gives an example of deleting a file named Foo. The typical syntax for

deleting the Foo file in a (line- based) function orientated system would be del

Foo. In contrast,object orientated interfaces make use of noun-verb syntaxes,

where the user first identifies the object and then specifies the operation to be

executed. In a modern graphical object orientated system, the Foo file would be

deleted by first selecting the file and then issuing a delete command, for example,

dragging the Foo file to trash can.

In recent years, researchers have been moving away from command orientated

interfaces, in search for faster, more natural, and more convenient [Jacob, 1993]

ways of communicating between people and computers. One such approach is

non-command based interfaces. In non-command based interfaces, the system

passively monitors the user as s/he performs a task and provides the appropriate

responses during the task, without the user explicitly giving a command. These

new interfaces are often not even dialogues (commands issued by the user and

carried out by the computer) in the traditional meaning of the word, even though

they obviously can be analyzed as having some dialogue content at some level

since they do involve the exchange of information between a user and acomputer[Nielsen, 1993].

Nielsen identifies eye gaze tracking, computer music, interface agents, and

embedded help as means of achieving non-command based interaction. In this

study we focus primarily on eye tracking. Eye tracking (as will be shown later)

involves measuring the movement of the eyes.

According to Ware and Mikaelian (1987) object selection is one of the

most frequent actions performed by a person sitting in front of a computer. One


10/12

10

can therefore infer that, by tracking a users eye positions as s/he interacts with an

interface, it is possible to obtain information about what a person is selecting. This

information is important because it not only give us an indication of where the

users interests lie, but it also gives us a clue about where the user will go to next

for information.

The use of eye gaze data during human computer interaction has some obvious

benefits when compared to manual input: a user looks at the object which she/he

wants to select even before activating a manual selection device; moving the

mouse or pressing a key on the keyboard. Using eye gaze to select targets on the

screen is therefore faster than any manual selection device. Gaze input reduces

fatigue as the user does

not have to engage in physical movement, like moving the mouse around, to

achieve selection. Gaze input also provides a natural means of pointing, and is

therefore easy to use and learn. Finally, depending on how the interaction is

designed, eye gaze interaction also provides a means of non-command based

interaction.

APPLICATIONS

A wide variety of disciplines use eye tracking techniques, including

cognitive science, psychology (notably psycholinguistics, the visual world

paradigm), human-computer interaction (HCI), marketing research and medical

research (neurological diagnosis). Specific applications include the tracking eye

movement in language reading, music reading, human activity recognition, the

perception of advertising, and the playing of sport.

COMMERCIAL USEIn recent years, the increased sophistication and accessibility of eye tracking

technologies have generated a great deal of interest in the commercial sector.

Applications include web usability, advertising, sponsorship, package design and

automotive engineering. In general, commercial eye tracking studies function by

presenting a target stimulus to a sample of consumers while an eye tracker is used

to record the activity of the eye. Examples of target stimuli may include websites,

television programs, sporting events, films, commercials, magazines, newspapers,


11/12

11

packages, shelf Displays, consumer systems (ATMs, checkout systems, kiosks),

and software. The resulting data can be statistically analyzed and graphically

rendered to provide evidence of specific visual patterns. By examining fixations,

saccades, pupil dilation, blinks and a variety of other behaviors researchers can

determine a great deal about the effectiveness of a given medium or product.

While some companies complete this type of research internally, there are many

private companies that offer eye tracking services and analysis.

The most prominent field of commercial eye tracking research is web

usability. While traditional usability techniques are often quite powerful in

providing information on clicking and scrolling patterns, eye tracking offers the

ability to analyze user interaction between the clicks. This provides valuable

insight into which features are the most eye-catching, which features cause

confusion and which ones are ignored altogether. Specifically, eye tracking can be

used to assess search efficiency, branding, online advertisements, navigation

usability, overall design and many other site components. Analyses may target a

prototype or competitor site in addition to the main client site.

Eye tracking is commonly used 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. Analyses focus on visibility of a

target product or logo in the context of a magazine, newspaper, website, or

televised event. This allows researchers to assess in great detail how often a

sample of consumers fixates on the target logo, product or ad. In this way, an

advertiser can quantify the success of a given campaign in terms of actual visual

attention.

Eye tracking provides package designers with the opportunity to examine the

visual behavior of a consumer while interacting with a target package. This maybe used to analyze distinctiveness, attractiveness and the tendency of the package

to be chosen for purchase. Eye tracking is often utilized while the target product is

in the prototype stage.

Prototypes are tested against each other and competitors to examine which

specific elements are associated with high visibility and appeal.

I


12/12

12

CONCLUSION

The method of eye tracking systems which once started with the

basic application of direct observation of the eye movements for just general study

of the cognitive linguistics in the past has now reached a point where highly

calibrated systems of gaze tracking are being used for human machine interactions

and just the human eye gaze is being used as an input to process and complete

tasks. Though this is just in the nascent stage where more research is upcoming

each day there is wide scope of using gaze tracking for communication of

disabled people just by looking and in HCI(human computer interfacing). A very

through and deep look should be taken into consideration into gaze tracking

because it can be a step ahead in communication.

In conclusion, there is a potential for using gaze-based interaction techniques in

problem solving games, however in order for gaze-based interaction to replace the

mouse (in problem solving games), a lot of research still needs to be conducted

and gaze related problems such as accuracy and Midas touch have to be solved

and more attention should be given to the layout of gaze-based user interfaces .