Final Year Project 20042005 LYU0402 Augmented Reality Table for Interactive Card Games

1
Final Year Project 2004/2005LYU0402Augmented
Reality Table for Interactive Card Games

• Supervisor Prof Michael Lyu
• Presented by Kevin Chow, Albert Lam

2
Overview

• Introduction
• Objective
• Trading Card Game
• Architecture of ART
• Implementation in Second Term
• Experiment
• Conclusion
• Future Work

3
Introduction

• What is Augmented Reality?
• Mixed Reality combines the content from the real
  world with virtual imaginary
• Augmented Reality is a subset of this where
  virtual content is overlaid into real objects of
  the world

4
Introduction (Cont)

• Paul Milgram characterized Mixed Reality
  interfaces on his Reality-Virtuality Continuum
  in 1994

5
Introduction (Cont)

• An AR system has the following three main
  characteristics
• Combines real and virtual objects in a real
  environment
• Runs interactively, and in real time
• Registers virtual objects onto the real world

6
Introduction (Cont)

• ART stands for Augmented Reality Table
• User can play Card Games on the ART.
• ART can enhance the visual effect during the
  playing of the card game.

7
Objective

• Develop a generic Interactive ART Trading Card
  Game application.
• Enhance the traditional card games
• Visual effect
• Sound effect
• Complex calculation

8
Trading Card Game

• Trading Card Games
• Two players play a match.
• Players play cards to fight with each other. It
  includes summoning monster, casting magic, or
  setting traps, etc.
• We choose YU-GI-OH as our implementation

9
Trading Card Game (Cont)

• Trading card game includes five kinds of actions
• Restore
• Draw cards
• Play cards
• Attack/Challenge
• Discard cards

10
An Example - YU-GI-OH

• In YU-GI-OH, Different information are stored on
  the card.

11
An Example - YU-GI-OH (Cont)

• Game Mat of YU-GI-OH
• Different kinds of card must be put inside
  particular card zones

12
An Example - YU-GI-OH (Cont)
1200 500 700
-700
ATK 500
ATK 1200
LP 2000
LP 2000
LP 1300
13
An Example - YU-GI-OH (Cont)
1300 1200 100
-100
DEF 1300
ATK 1200
LP 1300
LP 2000
LP 1900
14
Architecture

• Hardware Setup
• Plasma monitor
• Overhead camera
• System architecture
• Augmented Reality Perception
• Game Core
• Database
• Game Enhancement

15
Hardware Setup
16
Hardware Setup (Cont)

• Computer
• processes perceiving image
• generates visual and audio enhancement
• controls game flow
• Plasma Monitor.
• acts as the Game Table
• displays computer-generated scene
• Overhead mounted camera
• captures the cards and the screen of the plasma.
• only input of the system

17
System Architecture

• Game Core Module
• Perception Module
• Database Module
• Game Enhancement Module

18
System Architecture (Cont)
19
Implementation

• Database Module
• Access card information
• Access game rules and card rules
• Identify cards
• GameCore Module
• Control game flow
• Store game state
• Rulebase game engine

20
Database Module

• Contains all game information
• Card Database
• Contain all card information
• Simple editor
• Rule Database
• Contain all game rule and card rule
• Simple editor

21
Image Database

• Image Database
• Query with a card image
• Retrieve card id
• Use improved block matching algorithm

?
22
Block Matching Algorithm

• Select the best matched card from the candidates
  
• Split the captured image into 4 channels
• Compare only inner image
• Compare the different channels to the database
  separately

23
Block Matching Algorithm

• Find the pixel difference by
• Reject the image if the pixel difference is
  larger than the threshold
• Accept the image with minimum pixel difference

24
Improved Block Matching Algorithm

• However, the Block Matching Algorithm cause some
  error in real time game
• Solution, we use an improved Block Matching
  Algorithm
• Divide the image into 9 squares
• Apply Block Matching Algorithm to each squares

25
GameCore

• Core Part of ArtTable
• Contains
• Input Manager handles input
• Output Manager handles output
• Rule Manager stores rules and inference rules
• Game Manager stores game states
• Control how these managers interact and flow of
  the game.

26
GameCore
1. Receive input
7. Display output to player
Output Manager
Input Manager
GameCore
2. Pass to game manager
6. Generate output if any
Rule Manager
Game Manager
5. Perform actions if any
3. Update game states
4. Inference rules
27
Rulebase

• Why rulebase?
• Flexible Card games are very flexible and some
  card effect are unpredictable.
• Extensible New cards can be extended by adding
  new rules.
• Generic New card games can be implemented by
  new rule models.

28
Rulebase

• Load game rules
• Forward checking for predicate
• While conclusion reached
• Perform the action of the rule
• further forward checking

P.S. Action may be load another rule, remove a
rule, reset a rule, update game states, or show
some outputs, etc.
29
Rulebase
30
Experiment

• We have used 90 cards to do the recognition
  experiment. The result is as follow

31
Experimental Result Discussion

• Reasons decrease the accuracy
• Image are captured in low resolution. The small
  error in cards position detection will lead to
  inaccuracy in recognition process.
• Reference images are recorded from camera. Errors
  in recording will lead to errors in recognition
  process.

32
Conclusion

• We have designed and implemented the prototype of
  ART system
• We have improved the card recognition algorithm
  with increased accuracy and efficiency
• We have developed a rulebase game engine which is
  generic and extensible for card games

33
Future Work

• Color Calibration
• Improve in card recognition algorithm
• Game Enhancement

34
End of Presentation

• Thank you very much

35
Q A Session