GSET Somi: A Game-Specific Eye Tracking Dataset for Somi Hamed - - PowerPoint PPT Presentation

▶
gset somi a game specific eye tracking dataset for somi
SMART_READER_LITE
LIVE PREVIEW

GSET Somi: A Game-Specific Eye Tracking Dataset for Somi Hamed - - PowerPoint PPT Presentation

Mar 07, 2024 289 likes •445 views

GSET Somi: A Game-Specific Eye Tracking Dataset for Somi Hamed Ahmadi 1 Saman Zadtootaghaj 1 Sajad Mowlaei 1 Mahmoud Reza Hashemi 1 Shervin Shirmohammadi 1,2 University ofTehran 1 Multimedia Processing Laboratory (MPL), School of Electrical and

slide-1
SLIDE 1

GSET Somi: A Game-Specific Eye Tracking Dataset for Somi

Hamed Ahmadi1 Saman Zadtootaghaj1 Sajad Mowlaei1 Mahmoud Reza Hashemi1 Shervin Shirmohammadi1,2

University ofTehran

1 Multimedia Processing Laboratory (MPL), School

  • f Electrical and Computer Engineering, College of

Engineering, University of Tehran

2 DISCOVER Lab, School of Electrical Engineering

and Computer Science, University of Ottawa

slide-2
SLIDE 2

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

2

GAMING INDUSTRY

  • Wide range of gaming devices
  • Gaming will hit $91.5 billion this year1

1 http://www.gamesindustry.biz/articles/2015-04-22-gaming-will-hit-usd91-5-billion-this-year-newzoo

slide-3
SLIDE 3

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

3

CLOUD GAMING

Game Engine Video Encoder Video Decoder Display System Game Input Device Cloud Client

Bandwidth!

slide-4
SLIDE 4

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

4

BANDWIDTH CHALLENGE

  • Currently requires ~5Mbps per player
  • Perceptual video coding is used to reduce bit

rate while preserving perceived quality!

  • Specific eye-tracking datasets are required to

build specific perceptual models for gaming applications.

slide-5
SLIDE 5

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

5

COMPARISON OF THE GAME-RELATED EYE-TRACKING DATASETS

GSET PETERS BORJI CRCNS DIEM Collected while playing

  • ○

○

Collected while watching

○ ○ ○

  • Game video
  • ○

Game video trailer

○ ○ ○ ○

  • #Subjects*

84 5 21 8

  • #Videos*

135 24 27

  • 4

Resolution

720p 680x480 680x480 680x480 Varying

Video format

Raw Raw

H.264/AVC

MPEG-1

  • Eyes

Both Right

  • Eye-tracker

Remote Chin rest

Chin rest + Head mount

Chin rest

slide-6
SLIDE 6

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

6

VIDEO GAME

  • Title: “Somi, My Beautiful Doll”
  • Game Genre: Side-scrolling
  • Built by: GameMakerStudio
  • Resolution: 720p
slide-7
SLIDE 7

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

7

SOMI’S GAME OBJECTS

  • Categorized into eight groups
slide-8
SLIDE 8

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

8

DATA COLLECTION PROCEDURE

Introduction Training Calibration Playing Verification

slide-9
SLIDE 9

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

9

EYE-TRACKING DEVICE

  • Tobii X2-30 Compact

▫ Remote eye-tracker ▫ Sampling rate of 30 Hz ▫ Accuracy of 0.4°

slide-10
SLIDE 10

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

10

SAMPLE RESULTS 1

  • Attention patterns are different among players of

different skill levels

SKILL LEVEL SCORERANGE Beginner score <= 1000 Intermediate 1000 < score <= 6000 Expert 6000 < score

10 20 30 40 50 60 70

Percentage

Beginner Intermediate Expert

Average attention per category

slide-11
SLIDE 11

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

11

SAMPLE RESULTS 2

  • Attention patterns are different during different game

states

10 20 30 40 50 60 70

Percentage

Beginner Intermediate Expert 10 20 30 40 50 60 70

Percentage

Beginner Intermediate Expert

Average attention per category in Jumping state Average attention per category in Running state

slide-12
SLIDE 12

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

12

Dataset Structure

  • Each session contains

▫ Gaze records ▫ Keyboard strikes ▫ Mouse info ▫ Game objects’ info

– Size – Location

▫ Gameplay video

– In a lossless format http://www.site.uottawa.ca/~shervin/gaze/

slide-13
SLIDE 13

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

13

CONCLUSION

  • Compared to existing datasets, ours has the

following features at once:

▫ HD resolution ▫ Collection during gameplay instead of watching ▫ Recording of mouse and keyboard inputs ▫ Recording of game objects’ locations ▫ A large number of subjects

  • Can be used to recognize the different attention

patterns among players

slide-14
SLIDE 14

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

14

FUTURE WORK

  • Adding more video games of the side-scrolling

genre

  • Adding video games of the other game genres
slide-15
SLIDE 15

7th ACM Multimedia Systems Conference (ACM MMSys), Klagenfurt am Wörthersee, Austria, May 2016

15